BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Meng, Fanbo
Liu, Jinsuo
Zhu, Weiji
Zhang, Yongzhe
Feng, Tian
Abstract
A video processing method and apparatus, a medium, and a program product. The method includes acquiring a first video clip, the first video clip corresponding to a template text in a first text, and the first video comprising a video subclip with a speech pause, the video subclip being at a boundary position between the template text and a variable text in the first text; generating a second video clip corresponding to the variable text; and stitching the first video clip with the second video clip to obtain a video corresponding to the first text.
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
H04N 21/845 - Structuring of content, e.g. decomposing content into time segments
2.
VIRTUAL KEYBOARD SETTING METHOD AND APPARATUS, AND STORAGE MEDIUM
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Feng, Lei
Lu, Jian
Cao, Jin
Hu, Miaoli
Hu, Wei
Yang, Yihang
Song, Xiaoxue
Li, Haixin
Abstract
A virtual keyboard setting method includes: determining an operation region and a trigger region, the operation region being a region operated in a screen for using an input method, and the trigger region being a region covered by an external entity when touching the screen; determining a display region of a virtual keyboard according to the operation region; determining an area of a virtual key in the virtual keyboard according to the trigger region; and setting the virtual keyboard according to the display region of the virtual keyboard and the area of the virtual key.
G06F 3/04886 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
3.
THREE-DIMENSIONAL ROAD NETWORK CONSTRUCTION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xu, Ran
Abstract
This application provides a three-dimensional road network construction method performed by an electronic device. The method includes: obtaining a two-dimensional road network, the two-dimensional road network comprising a plurality of paths, each path being formed by connecting a plurality of nodes; determining a relative elevation for a node of a current path overlapping the current path and/or another path among the nodes of the current path, the relative elevation representing a height of the current path at the node from a reference plane; determining relative elevations of nodes constituting a center line of the current path according to the relative elevations of the nodes of the current path and a width of the current path; and constructing a three-dimensional road corresponding to the current path according to the width and the relative elevations of the nodes of the center line of the current path to obtain a three-dimensional road network.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Tian, Kai
Chen, Wei
Su, Xuefeng
Abstract
A method and apparatus for processing an action of a virtual object, and a storage medium are provided. The method specifically includes: receiving an action instruction, the action instruction including: an action identifier and time-dependent information of performing an action associated with the action identifier; determining an action video frame sequence corresponding to the action identifier; determining, from the action video frame sequence, an action state image corresponding to a preset state image of the virtual object at a target time, the target time being determined according to the time-dependent information; generating a connection video frame sequence according to the action state image, the connection video frame sequence connecting the preset state image with the action video frame sequence; and splicing the connection video frame sequence with the action video frame sequence, to obtain an action video. Embodiments of this application can improve action processing efficiency of a virtual object.
G06V 10/24 - Aligning, centring, orientation detection or correction of the image
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
G06V 10/54 - Extraction of image or video features relating to texture
G06V 10/74 - Image or video pattern matching; Proximity measures in feature spaces
5.
SPEECH SYNTHESIS METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD (China)
Inventor
Fang, Peng
Liu, Kai
Chen, Wei
Abstract
Embodiments of this application provide a speech synthesis method performed by an electronic device. The method includes: acquiring a target text to be synthesized into a speech; generating hidden layer features and prosodic features of the target text, and predicting pronunciation duration of characters in the target text using an acoustic model corresponding to the target text; generating acoustic features corresponding to the target text based on the hidden layer features, the prosodic features and the pronunciation duration; and synthesizing a target speech corresponding to the target text according to the acoustic features. Using the solution provided by the embodiments of this application is beneficial to reducing the difficulty of speech synthesis.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhao, Ang
Yu, Jian
Abstract
A speech recognition text processing method includes acquiring an original text obtained by speech recognition, and performing at least one of punctuation addition processing and numerical normalization processing on the original text to obtain an intermediate result. The method further includes performing word removal processing on the original text through an attention interaction layer based on the intermediate result to obtain a processed text of the original text.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Congtao
Yang, Jiajun
Wei, Yuanming
Chen, Wei
Wei, Tao
Wu, Jun
Gong, Li
Zhu, Weiji
Abstract
The present disclosure discloses a picture recognition method performed by a computing device. The method includes: obtaining a recognized current string and a hash value of the current string during text recognition for an acquired image through an optical character recognition model, and storing the current string and the hash value of the current string into a first preset tree structure and a second preset tree structure; predicting a new probability value of the current string at a next moment, to obtain an extended string set; obtaining N strings with the highest probability value according to the hash value stored in the second preset tree structure and retaining the N strings; and using the N strings as the current strings, repeating the foregoing steps until recognition of all acquired images is completed, and obtaining a string with the highest probability value as a final recognition result.
H04L 9/32 - Arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system
G06F 40/154 - Tree transformation for tree-structured or markup documents, e.g. XSLT, XSL-FO or stylesheets
8.
DATA PROCESSING METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Duan, Wenjun
Bi, Jingrong
Li, Mei
Meng, Fanbo
Peng, Yun
Liu, Kai
Abstract
Provided herein are a data processing method and apparatus, a computer device, and a storage medium for sign language translation. Sign language is translated to text by: obtaining sign language action data; determining a sign language tagging sequence corresponding to the sign language action data by element analysis, and performing operation processing on the sign language action data based on the sign language tagging sequence. Text is translated to sign language by: performing word segmentation processing on a text sequence to obtain a natural word sequence; determining a basic sign language element and an element type corresponding to each natural word in the natural word sequence; sorting the basic sign language element and the element type to generate a sign language element sequence; determining a sign language tagging sequence; and performing sign language translation processing on the text sequence based on the sign language tagging sequence.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Congtao
Yang, Jiajun
Wei, Yuanming
Chen, Wei
Wei, Tao
Wu, Jun
Gong, Li
Zhu, Weiji
Abstract
Some aspects of the disclosure provide a method for image processing. The method includes receiving one or more first images corresponding to first portions in a section of characters for recognition, splicing the one or more first images into a first intermediate spliced image and performing a first intermediate character recognition on the first intermediate spliced image based on a first optical character recognition model. The first intermediate character recognition generates a first intermediate recognition result for display. The method further includes performing a final character recognition on a final spliced image corresponding to the section of characters for recognition based on a second optical character recognition model that is different from the first optical character recognition model. The final character recognition generates a final recognition result of the section of characters. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xin, Xiaozhe
Qin, Bo
Zhao, Zhiyong
Wang, Yingjun
Wang, Jie
Su, Xuefeng
Chen, Wei
Abstract
A handwriting recognition method is provided, which includes: obtaining handwritten original trajectory data in real-time; compressing the handwritten original trajectory data, to obtain compressed handwritten trajectory data; and inputting the compressed handwritten trajectory data into a compressed handwriting recognition model for recognition, to obtain a text recognition result corresponding to the handwritten original trajectory data. A handwriting recognition model is obtained by training with handwritten trajectory data of each piece of training data in a training data set, and the compressed handwriting recognition model is obtained by performing model compression on the handwriting recognition model. The handwriting recognition method can address the problem in the related art that the handwriting recognition accuracy is low caused by incorrect segmentation, thereby effectively improving the handwriting recognition accuracy.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
He, Junqing
Abstract
Embodiments of this application provide an inquiry information processing method performed at a computing device. The method specifically includes: determining user disease features according to at least one user input; performing disease prediction on the user disease features to obtain corresponding candidate diseases; acquiring question entities from a knowledge graph according to disease feature entities corresponding to the candidate diseases, the question entities being used for representing questions related to the disease feature entities; and generating target questions according to the question entities, the target questions being used for performing an inquiry on a user. By means of the embodiments of this application, the accuracy of target questions for an inquiry can be improved, thereby improving the inquiry efficiency.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Guo, Baokui
Kang, Qi
Abstract
A method for poetry generation includes receiving generation information indicative of a theme for the poetry generation, and determining at least a candidate piece of poetry corresponding to the generation information according to an autoregressive language model that is configured to generate elements in the candidate piece of poetry in an autoregressive manner with a plurality of regression rounds. An element in the elements is a character or a word. The autoregressive language model is configured for generating poetry in a plurality of formats, the autoregressive language model includes a plurality of processing layers connected sequentially, a processing layer in the plurality of processing layers is configured to determine attention levels for potential elements in a potential element list according to generated elements prior to a current regression round, and predict one or more additional element for the current regression round using a neural network according to the attention levels.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Lin, Jiansu
Liu, Fang
Meng, Yuqing
Huang, Xiaofeng
Chen, Weipeng
Gong, Zhaohan
Zong, Ming
Chen, Liwei
Wang, Dandan
Ning, Yanan
Abstract
This application discloses a data processing method performed by a computing device. The method includes: acquiring a search keyword of a user, and determining a plurality of target keywords related to the search keyword. After the plurality of keywords are determined, the search keyword and the plurality of target keywords may further be displayed. When the search keyword and the plurality of target keywords are displayed, the plurality of target keywords are distributed on a periphery of a circle with the search keyword as a center in a dispersed manner to achieve a more convenient and intuitive effect. By using this solution, the plurality of target keywords related to the search keyword can be displayed for the user instead of directly providing the user with search results corresponding to the search keyword, and the user obtains the plurality of target keywords through analysis according to the search results.
Beijing Sogou Technology Development Co., Ltd. (China)
Inventor
Wang, Jie
Wang, Yingjun
Qin, Bo
Xin, Xiaozhe
Abstract
A formula recognition method and apparatus, a computer-readable medium, and an electronic device. The formula recognition method includes acquiring a target image including a formula, processing the target image to obtain a global image feature and a local image feature, and processing the global image feature and the local image feature to obtain the formula included in the target image.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/42 - Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
15.
SPEECH PROCESSING METHOD AND SPEECH PROCESSING APPARATUS
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Liu, Yun
Abstract
The embodiments of this application disclose a speech processing method and a speech processing apparatus. The speech processing method includes obtaining a first spectrum of a noisy speech in a complex number domain; performing subband division on the first spectrum to obtain a first subband spectrum in the complex number domain; processing the first subband spectrum based on a pre-trained noise reduction model to obtain a second subband spectrum of a target speech in the noisy speech in the complex number domain; performing subband restoration on the second subband spectrum to obtain a second spectrum in the complex number domain; and synthesizing the target speech based on the second spectrum.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wei, Tao
Rao, Xudong
Abstract
The present disclosure relates to a search method and apparatus. The method includes: obtaining network construction information corresponding to a target task, the network construction information including: search space information, sample data, and a search indicator; constructing a supernetwork based on the search space information and training the supernetwork based on the sample data, the supernetwork including a plurality of sub-networks; and searching a sub-network from the trained supernetwork based on the search indicator, to obtain a target network for performing the target task.
Beijing Sogou Technology Development Co., Ltd. (China)
Inventor
Cui, Guohui
Abstract
An embodiment of this application provides a speech processing method and apparatus, and an apparatus for speech processing, applied to a terminal device, where the terminal device is equipped with at least two microphones. The method includes: performing summation on signals received by the at least two microphones to obtain a first signal, and performing subtraction on the signals received by the at least two microphones to obtain a second signal; performing blind separation on the first signal and the second signal to obtain a speech signal and a noise signal; and performing adaptive noise cancellation on the speech signal based on the noise signal to obtain a target speech signal. The embodiments of this application can optimize a speech denoising effect, and further improve the speech recognition accuracy of the terminal device in a complex and changeable environment with large noise or strong interference.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Yao, Bohuai
Cui, Xin
Abstract
Some aspects of the disclosure provide a method for sentence conversion. The method includes receiving a first sentence that is inputted by a user, inputting the first sentence into a first sentence based rewrite model to obtain a second sentence having a same semantic as the first sentence but a different style from the first sentence. The first sentence based rewrite model converts the first sentence into the second sentence without partitioning the first sentence into smaller portions. The method also includes displaying the second sentence. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhao, Hang
Abstract
An apparatus and method for data processing includes determining a search keyword according to a search statement input by a user; determining a first graph entity library corresponding to a category to which the search keyword belongs; determining, according to an association relationship between graph entity libraries of a plurality of categories, a category of a graph entity library associated with the first graph entity library, and constructing a first set, the first set including at least one graph entity library which has an association relationship with the first graph entity library, and the association relationship between the graph entity libraries is established according to a search demand of a user; and displaying, after the first set is constructed, each graph entity library included in the first set by using the search keyword as a center.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
He, Fulin
Abstract
An input method and apparatus are provided. The input method includes: detecting in real time a touch point position during a handwriting input process on a user device; determining a display point position based on the touch point position and user-related information, the display point position being deviated from the touch point position; and presenting a touch point movement trajectory based on the display point position.
G06F 3/04883 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
G06F 3/041 - Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Li, Xin
Abstract
An apparatus and method for entry recommendation includes: recalling a plurality of vocabularies based on a multi-path recall policy, entries in each of the vocabularies having original scores; normalizing the original scores for the vocabulary to obtain target scores of the entries in the vocabulary; respectively determining weights of the entries in the vocabulary; selecting target entries from the plurality of vocabularies based on the target scores and the weights; and pushing the target entries to a target client.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xu, Ran
Abstract
Provided in the present application are a three-dimensional road network construction method and apparatus, and an electronic device and a storage medium, the method being executed by the electronic device. The method comprises: acquiring a two-dimensional road network, and in all nodes of a path, setting a corresponding relative elevation for a node which overlaps with the current path and/or other paths; reducing the relative elevation of a target node having the largest relative elevation in the path, and increasing the relative elevations of the other nodes in the path; determining a center line of the path, and according to the relative elevations of the nodes of the path, determining the relative elevations of nodes that constitute the center line, and setting the width of the path; and according to the width of the path and the relative elevations of the nodes of the center line, constructing a three-dimensional road which corresponds to the path, so as to obtain a three-dimensional road network.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Meng, Fanbo
Liu, Jinsuo
Zhu, Weiji
Zhang, Yongzhe
Feng, Tian
Abstract
A video processing method and apparatus, and a medium and a program product. The method specifically comprises: acquiring a first video clip, wherein the first video clip corresponds to template text in first text of a video to be generated, the first video clip comprises a video sub-clip of which voice is paused, and the position of the video sub-clip corresponds to a demarcation position between the template text and variable text to be processed in the first text (101); generating a second video clip corresponding to the variable text to be processed (102); and splicing the first video clip and the second video clip, so as to obtain a video corresponding to the first text (103). By means of the embodiments of the present application, the processing efficiency of a video can be improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fan, Ziwei
Zhan, Jiqing
Yu, Jian
Wang, Yanfeng
Zhu, Yun
Zhao, Ang
Abstract
The present application discloses a data processing method applied in fields such as artificial intelligence and natural language processing. Inputting into a pre-trained model and an initial service model on the basis of acquired service data, to obtain a first fully connected layer output of the pre-trained model and a second fully connected layer output of the initial service model. Because the pre-trained model and the initial service model construct modeling units using different granularities, a first modeling unit of the pre-trained model is matched with a second modeling unit of the initial service model, fully connected layer output of a second modeling unit and fully connected layer output of a matching target first modeling unit have the same sequence length, and knowledge distillation is carried out on this basis, a target service model can be obtained by means of the initial service model with the assistance of the pre-trained model, and knowledge distillation is carried out on a model comprising modeling units of different granularities, thereby expanding an application range for knowledge distillation, and effectively improving service performance of the service model.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fan, Bo
Xu, Zhen
Chen, Xi
Chen, Wei
Meng, Fanbo
Liu, Kai
Zhang, Kening
Duan, Wenjun
Abstract
The present disclosure discloses a method and an apparatus for driving a digital human, and an electronic device. The method includes obtaining a target action corresponding to a target text; obtaining a reference action to be executed before the digital human executes the target action when the digital human is driven to output speech based on the target text; modifying a target action parameter of the target action according to a reference action parameter of the reference action; and driving the digital human to execute the target action according to a modified target action parameter when driving the digital human to output the speech based on the target text.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Duan, Wenjun
Bi, Jingrong
Li, Mei
Meng, Fanbo
Peng, Yun
Liu, Kai
Abstract
A data processing method and apparatus, and a computer device and a storage medium. The method comprises: acquiring sign language action data to be processed (101); on the basis of a preconstructed sign language annotation system, performing element analysis on the sign language action data, so as to determine a sign language annotation sequence, which corresponds to the sign language action data, wherein the sign language annotation sequence contains annotation information of each basic sign language element, which corresponds to the sign language action data (102); and according to the sign language annotation sequence, performing operation processing on the sign language action data (103).
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Tian, Kai
Chen, Wei
Su, Xuefeng
Abstract
An action processing method and apparatus for a virtual object, and a storage medium. The method specifically comprises: receiving an action instruction, wherein the action instruction may comprise: an action identifier and time-related information (101); determining an action video frame sequence corresponding to the action identifier (102); according to a preset state image of a virtual object at a target time, determining, from the action video frame sequence, an action state image corresponding to the preset state image, wherein the target time can be determined according to the time-related information (103); according to the preset state image and the action state image, generating a connecting video frame sequence, wherein the connecting video frame sequence is used for connecting the preset state image and the action video frame sequence (104); and splicing the connecting video frame sequence and the action video frame sequence to obtain an action video (105). By means of the method, the action processing efficiency for a virtual object is improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fang, Peng
Liu, Kai
Chen, Wei
Abstract
A speech synthesis method, an apparatus, a device, and a storage medium. The method comprises: acquiring a text to be synthesized (101); generating a hidden layer feature and a prosodic feature of the text to be synthesized, and predicting the pronunciation duration of a character in the text to be synthesized (102); on the basis of the hidden layer feature, the prosodic feature, and the pronunciation duration, generating an acoustic feature corresponding to the text to be synthesized (103); and according to the acoustic feature, generating text speech corresponding to the text to be synthesized (104). The described method is helpful to reduce the difficulty of speech synthesis.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Cui, Guohui
Abstract
Embodiments of the present application provide a speech processing method and apparatus, and an apparatus for speech processing, applied to a terminal device. The terminal device is provided with at least two microphones. The method comprises: performing summation processing on signals received by the at least two microphones to obtain a first signal, and performing subtraction processing on the signals received by the at least two microphones to obtain a second signal; performing blind separation processing on the first signal and the second signal to obtain a speech signal and a noise signal; and performing adaptive noise cancellation processing on the speech signal on the basis of the noise signal to obtain a target speech signal. According to the embodiments of the present application, a speech denoising effect can be optimized, so that the accuracy of speech recognition of the terminal device is improved under the condition that the environment is complex and changeable and noise or interference is large.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Jie
Wang, Yingjun
Qin, Bo
Xin, Xiaozhe
Abstract
Disclosed in the present application is a formula recognition method. In one example, the method may be executed by a first device. The first device may obtain an image to be recognized that comprises a formula, and then process said image to obtain a global image feature and a local image feature. Furthermore, the global image feature and the local image feature may be processed to obtain the formula comprised in said image. Therefore, in embodiments of the present application, during recognition of the formula in said image, the local image feature of said image is combined. Hence, even if characters comprised in the formula in said image are small, the formula in said image can also be accurately recognized using the solutions of the embodiments of the present application. Therefore, the formula in said image can be accurately recognized using this solution.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Han, Qin
Yu, Tianzhao
Wang, Yu
Sheng, Yue
Zhuo, Xingzhong
Abstract
Embodiments of the present application provide a request processing method and apparatus, and a medium. The method specifically comprises: presenting a candidate item, and timing the presentation time; and sending a request when the timing value is within a time range, wherein the request is used for requesting a cloud candidate; the time range is obtained according to historical behavior data corresponding to the candidate item; the historical behavior data comprises: on-screen behavior data when presenting the candidate item, and/or trigger behavior data for a preset control when presenting the candidate item; and the preset control is used for triggering presentation of more candidate items. The embodiments of the present application can improve the speed of presenting a cloud candidate while reducing the burden on a server.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Guo, Baokui
Kang, Qi
Abstract
Embodiments of the present application provide a poem generation method and apparatus, and a medium. The method specifically comprises: receiving generated information; and according to an auto-regressive language model, determining at least one candidate poem corresponding to the generated information, wherein the language model is trained and obtained by means of a poem corpus, and is used to predict unknown information of a poem in the unit of words according to known information of the poem. The language model comprises a plurality of processing layers that are sequentially connected. The processing layers comprise a self-attention module and a neural network module, wherein the self-attention module is used to determine information of attention from known words in a sentence of a poem to words in a word list, so as to predict unknown words in the sentence of the poem according to the information of attention. By means of the embodiments of the present application, a candidate poem which is in compliance with rules of poems can be generated, and the coherence of the generated candidate poem can be improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
He, Junqing
Abstract
Embodiments of the present application provide an inquiry information processing method and apparatus, and a medium. The method specifically comprises: determining disease features of a user according to at least one user input; performing disease prediction processing on the disease features of the user, so as to obtain corresponding candidate diseases; acquiring corresponding question entities from a knowledge graph according to disease feature entities corresponding to the disease features of the candidate diseases, wherein the question entities are used for representing questions related to the disease feature entities; and generating target questions according to questions corresponding to the question entities, wherein the target questions are used for performing an inquiry on the user. By means of the embodiments of the present application, the accuracy of target questions for an inquiry can be improved, such that the inquiry efficiency is improved.
G16H 80/00 - ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
34.
METHOD AND APPARATUS FOR SETTING APPLICATION PROGRAM
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhang, Yijun
Abstract
A method and an application for setting an application program, specifically: in order to enable a user to clearly view target content in a page corresponding to an application program, acquiring the background colour of the target content; and then determining the page content colour of the application program on the basis of the acquired background colour, wherein the contrast between the determined page content colour and the background colour is greater than or equal to a first threshold. In other words, the contrast between the page content colour and the background colour is greater. After determining the page content colour of the application program, implementing colour setting of the target content according to the page content colour, such that the colour of the target content is the determined page content colour.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xin, Xiaozhe
Qin, Bo
Zhao, Zhiyong
Wang, Yingjun
Wang, Jie
Su, Xuefeng
Chen, Wei
Abstract
A handwriting recognition method, comprising: acquiring handwritten original trajectory data in real time (S101); compressing the handwritten original trajectory data to obtain compressed handwritten trajectory data (S102); and inputting the compressed handwritten trajectory data into a compressed handwriting recognition model for recognition to obtain a text recognition result corresponding to the handwritten original trajectory data, the handwriting recognition model being obtained by training handwritten trajectory data of each piece of training data in a training data set, and the compressed handwriting recognition model being obtained by performing model compression on the handwriting recognition model (S103). The method can effectively improve accuracy of handwriting recognition.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
He, Fulin
Abstract
The embodiments of the present application disclose an input method and device, and a device for input. The embodiment of said method comprises: detecting, in real time, a contact position during handwriting input of a user; on the basis of the contact position and information related to the user, determining a display point position, the display point position being offset from the contact position; and on the basis of the display point position, presenting a contact movement trace. The embodiment improves the efficiency and accuracy of handwriting input.
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
37.
SEARCH METHOD AND APPARATUS, AND ELECTRONIC DEVICE
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wei, Tao
Rao, Xudong
Abstract
A search method and apparatus, and an electronic device. The method comprises: acquiring network construction information corresponding to a target task, wherein the network construction information comprises: search space information, sample data and a search index (102); constructing a super-network on the basis of the search space information, and training the super-network on the basis of the sample data, wherein the super-network comprises a plurality of sub-networks (104); and searching the trained super-network for a sub-network on the basis of the search index, so as to obtain a target network for executing the target task (106). Compared with the fact that it is necessary to manually design a network in the prior art, the present application can be adapted to tasks, such that a network can be quickly constructed.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhao, Hang
Abstract
A data processing method and device. The method comprises: determining a search keyword according to a search statement inputted by a user (S101), and determining a first graph entity library corresponding to a category to which the search keyword belongs (S102); according to an association relationship among multiple categories of graph entity libraries, determining the category of a graph entity library associated with the first graph entity library, and constructing a first set, the first set comprising at least one graph entity library having an association relationship with the first graph entity library, and the association relationship among the graph entity libraries being constructed according to search requirements of the user (S103); and after the first set is constructed, using the search keyword as a center to display the graph entity libraries comprised in the first set (S104). The first set can reflect the search requirements of the search statement and guide the user to further trigger a search behavior on the basis of the search requirements of the user; and the method allows for providing a search result meeting the user requirements to the user.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Congtao
Yang, Jiajun
Wei, Yuanming
Chen, Wei
Wei, Tao
Wu, Jun
Gong, Li
Zhu, Weiji
Abstract
An image processing method, comprising: when an image recognition apparatus collects images in real time, storing the collected real-time images into an image splicing module by means of a first thread (S101); performing real-time splicing on the images in the image splicing module by means of a second thread to obtain an intermediate spliced image (S102); performing character recognition on the intermediate spliced image by means of a lightweight optical character recognition model to obtain an intermediate recognition result, and displaying same (S103); and when it is detected that a state of the image recognition apparatus is changed, obtaining an image set consisting of all images in the image splicing module, performing character recognition on the image set by means of a universal optical character recognition model to obtain a final recognition result, and displaying same (S104). According to the image processing method, the image recognition apparatus, an electronic device, and a medium, recognition real-time performance of character recognition for the intermediate spliced image can be improved, and a response duration of on-screen display of a first character is shortened.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Congtao
Yang, Jiajun
Wei, Yuanming
Chen, Wei
Wei, Tao
Wu, Jun
Gong, Li
Zhu, Weiji
Abstract
A picture recognition method and apparatus, an electronic device, and a medium. The method comprises: in the process of performing text recognition on an acquired image by means of an optical character recognition model, obtaining the current recognized character string and a hash value thereof, and storing the current character string and the hash value thereof into a first preset tree-like structure and a second preset tree-like structure; predicting a new probability value of the current character string at a next moment; obtaining an extended character string set; obtaining, according to the hash value stored in the second preset tree-like structure, N character strings having highest probability values, retaining the N character strings, and using the N character strings as the current character strings; and repeating the foregoing steps until the recognition of all acquired images is completed, and obtaining a character string having the highest probability value as a final recognition result. The calculation amount required for storing an intermediate character string in the process of performing text recognition on an image can be effectively reduced, and the efficiency of storing the intermediate character string can be effectively improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Li, Xin
Abstract
An entry recommendation method and apparatus, and an apparatus for recommending entries. The method comprises: recalling a plurality of word lists on the basis of a multi-path recall policy, wherein entries in each word list have original scores; for each word list, respectively performing normalization processing on the original scores so as to obtain target scores of the entries in each word list, and respectively determining the weights of the entries in each word list; and on the basis of the target scores and the weights, selecting a target entry from the plurality of word lists, and pushing the target entry to a target client. By the means of the method, entries recommended to a user can satisfy input requirements of the user to a greater extent, and the accuracy of the entries recommended to the user is improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Liu, Yun
Abstract
Disclosed are a speech processing method and apparatus, and an apparatus for processing speech. An embodiment of the method comprises: acquiring a first spectrum of noisy speech in a complex number field; performing sub-band decomposition on the first spectrum to obtain a first sub-band spectrum in the complex number field; processing the first sub-band spectrum on the basis of a pre-trained noise reduction model, so as to obtain a second sub-band spectrum, in the complex number field, of target speech in the noisy speech; performing sub-band restoration on the second sub-band spectrum to obtain a second spectrum in the complex number field; and synthesizing the target speech on the basis of the second spectrum. By means of the embodiment, the problem of high-frequency and low-frequency information being imbalanced is effectively solved, and the clarity of speech after noise reduction is thus improved.
G10L 25/30 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the analysis technique using neural networks
43.
INPUT METHOD AND APPARATUS, AND APPARATUS FOR INPUTTING
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Yao, Bohuai
Cui, Xin
Abstract
Disclosed in the embodiments of the present application are an input method and apparatus, and an apparatus for inputting. The embodiment of the method comprise: acquiring a first statement inputted by a user; inputting the first statement into a pre-trained rewriting model to obtain a second statement which has the same semantic but a different style with the first statement; and displaying the second statement. The embodiment of the present application can improve the generalization of a statement rewriting function and the fluency of a rewritten statement.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fang, Fei
Abstract
A word processing method and apparatus, and an apparatus for word processing. Said method specifically comprises: splitting a word inputted by a user, the obtained splitting result comprising at least one sub-word and at least one affix (201); and using a tree structure to display the word and the splitting result hierarchically (202). Said method can improve word learning efficiency, and can reduce word learning difficulty.
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Lin, Jiansu
Liu, Fang
Meng, Yuqing
Huang, Xiaofeng
Chen, Weipeng
Gong, Zhaohan
Zong, Ming
Chen, Liwei
Wang, Dandan
Ning, Yanan
Abstract
A data processing method and device. The method comprises: obtaining a search keyword of a user (S101), determining a plurality of target keywords related to the search keyword (S102), and after determining a plurality of keywords, further displaying the search keyword and the plurality of target keywords, wherein when displaying the search keyword and the plurality of target keywords, the plurality of target keywords are dispersedly distributed on the periphery of a circle taking the search keyword as the center (S103).
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Ying
Li, Jiantao
Zhang, Dan
Liu, Bao
Zhang, Shuo
Yang, Tianfu
Liang, Xiao
Rong, Hejiang
Li, Pengchong
Abstract
A translation method and apparatus, and a headset, with the method being applied to the headset. The method comprises: a headset acquiring source speech data (102); and the headset translating the source speech data to generate target speech data (104). Therefore, a user only needs to use a headset device to be able to realize translation, without using a specialized translation device.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhao, Nan
Cui, Wenhua
Abstract
Provided in the embodiments of the present application are a process execution method, a device, and a readable medium. The method comprises: detecting a work state of a pair of headphones, identifying a movement state of a user via an accelerometer built in the headphones, determining a target process associated to the movement state in the work state, and executing the target process, thus implementing the triggering of various target processes by the headphones on the basis of the movement state of the user, obviating the need for the user to trigger via a hand movement or speaking, and increasing the degree of convenience of triggering various target processes; moreover, target processes corresponding to same movement state of the user may be different in different work states of the headphones, implemented on the headphones is the triggering of more target processes, thus solving the problem in which it is difficult for the user to trigger a target process by means of a hand movement or speaking in some scenarios.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Chen, Wei
Fan, Bo
Meng, Fanbo
Abstract
A method for driving a virtual human in real time, comprising: obtaining data to be processed used for driving a virtual human, said data comprising at least one of text data and voice data (S201); using an end-to-end model to process said data, so as to determine a gesture feature sequence corresponding to said data (S202); and inputting the gesture feature sequence into a trained muscle model to drive the virtual human by means of the muscle model (S203). Since the end-to-end model can obtain the gesture feature sequence in a shorter period of time, and the gesture feature sequence is input into the muscle model to directly drive the virtual human, the amount of computation and the amount of data transmission are greatly reduced, and the computational efficiency is further improved, so that the real time nature of virtual human driving is greatly improved, thereby achieving real time driving of the virtual human to perform sign language output.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Song, Yingshuang
Xie, Shuo
Zhou, Zheng
Xie, Zhuo
Song, Jinchang
Abstract
A scanning and shadow reading processing method and apparatus, a dictionary pen, and a machine-readable medium. The method comprises: in response to a scanning operation of a dictionary pen on text, obtaining a query result of the text and displaying same on a display interface of the dictionary pen (201); in response to a shadow reading speech input operation of a user on the display interface of the query result, obtaining shadow reading speech of the user (202); and obtaining a shadow reading evaluation result of the shadow reading speech on the basis of the shadow reading speech and standard reading speech corresponding to the shadow reading speech, and displaying the shadow reading evaluation result on the display interface of the dictionary pen (203). In this way, by means of a dictionary pen, shadow reading speech of a user can be acquired and evaluated, thereby better assisting the user in learning a query result of text.
G10L 25/51 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination
G06K 9/32 - Aligning or centering of the image pick-up or image-field
G06F 3/0487 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fan, Bo
Abstract
A method and apparatus for driving a digital person, and an electronic device. The method comprises: acquiring a target action corresponding to target text (S20); obtaining, when driving a digital person to output a voice on the basis of the target text, a reference action needing to be performed by the digital person before performing the target action (S22); modifying a target action parameter of the target action according to a reference action parameter of the reference action (S24); and in the process of driving the digital person to output the voice on the basis of the target text, driving the digital person to perform the target action according to the modified target action parameter (S26). In the technical solution, a corresponding action is obtained on the basis of text, and an action parameter of a target action corresponding to the text is modified according to a reference action of a digital person, so that the process of the digital person switching from the reference action to the target action is natural and delicate, the technical problem in the prior art that the action of the digital person changes suddenly is solved, and the delicacy of change of the action of the digital person is improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fan, Bo
Chen, Wei
Chen, Xi
Meng, Fanbo
Liu, Kai
Zhang, Kening
Duan, Wenjun
Abstract
Disclosed is a method for driving a virtual human in real time. The method comprises: acquiring data to be processed that is used for driving a virtual human, wherein said data comprises at least one of text data and speech data (S201); processing said data by means of an end-to-end model, so as to determine an acoustic feature sequence, a facial feature sequence and a limb feature sequence corresponding to said data (S202); and inputting the acoustic feature sequence, the facial feature sequence and the limb feature sequence into a trained muscle model, and driving the virtual human by means of the muscle model (S203). In this way, the computing efficiency is improved, and the real-time performance of driving a virtual human is greatly improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Fan, Bo
Xu, Zhen
Chen, Xi
Abstract
The present disclosure discloses a virtual anchor face swapping method and apparatus, an electronic device, and a storage medium. The method comprises: using an end-to-end sequence learning model to process a historical video material of a target virtual anchor so as to acquire face feature parameters of the target virtual anchor; using a candidate virtual face to perform face swapping on the target virtual anchor so as to acquire an image material corresponding to the face-swapped virtual anchor; using the end-to-end sequence learning model to process the face feature parameters and the image material of the target virtual anchor so as to acquire face feature parameters of the face-swapped virtual anchor; and merging the candidate virtual face into the historical video material according to the face feature parameters of the face-swapped virtual anchor so as to acquire a video material resulting from the face swapping. The invention improves the utilization rate of the historical video material, and ensures that an image of the face-swapped virtual anchor is realistic and natural, and that facial features are natural and coordinated.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Li, Dongliang
Liu, Kai
Zhou, Ming
Chen, Wei
Abstract
Disclosed are a speech processing method and apparatus, and an electronic device (800). The method comprises: acquiring text information to be converted (102), and determining a source language corresponding to the text information and a target user for whom conversion is to be carried out (104); and according to the text information and a target conversion model corresponding to said target user, converting the text information into target speech data, which is pronounced in the source language by said target user, wherein the target conversion model performs adaptive training on a trained universal conversion model according to monolingual speech data pronounced by said target user, the universal conversion model is trained according to speech data in N languages, the source language is one of the N languages, and N is an integer greater than 1 (106). Thus, when there is only speech data, in a single language, of a target user, multilingual text can be converted into target speech data, in corresponding languages, of the target user, thereby achieving multilingual speech conversion.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Hao, Qianqian
Mansuer, Maerhufu
Cui, Xin
Zhang, Yang
Abstract
An information processing method and device for simplifying the operation process. The method comprises: in a process of performing interaction via a pre-configured messaging mode, acquiring interaction information sent by an opposite end; determining a preset triggering condition that matches the interaction information through analysis, and acquiring corresponding display information; and recommending the display information corresponding to the matched preset triggering condition. The information that the user may be interested in during the interaction process is directly recommended and displayed, such that the operation process is simplified, and the efficiency is improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zheng, Hong
Abstract
A speech recognition method and a device (800) for speech recognition. The method specifically comprises: receiving speech information inputted by a user (101); obtaining a personalized vocabulary of the user, wherein the personalized vocabulary is established according to historical input content generated according to a process during which the user uses an input method (102); according to the personalized vocabulary, determining a decoding path weight corresponding to the speech information (103); and according to the decoding path weight, determining a speech recognition result corresponding to the speech information (104). The described method and device (800) may improve the accuracy of speech recognition.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Chen, Xiaomin
Zhang, Jingjing
Chen, Wei
Zhao, Chao
Wang, Xiaochuan
Abstract
A speech recognition method and apparatus, and an apparatus for speech recognition. The method specifically comprises: receiving speech data to be subjected to recognition, and determining a first keyword related to the speech data to be subjected to recognition (201); determining a second keyword related to the first keyword according to a knowledge graph (202); and decoding the speech data to be subjected to recognition, adjusting, according to the first keyword and the second keyword, a score of a decoding path corresponding to the speech data to be subjected to recognition, and determining, according to the adjusted score of the decoding path, a speech recognition result corresponding to the speech data to be subjected to recognition (203). According to the method, the accuracy of speech recognition corresponding to keywords relating to an application scenario can thus be improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Luo, Dawei
Abstract
An audio data processing method and apparatus, and an electronic device (600, 700) and a storage medium (730). The method comprises: acquiring first multi-channel audio data, wherein the first multi-channel audio data is composed of audio data collected by one or more microphone arrays (101); performing de-reverberation processing on the first multi-channel audio data to obtain second multi-channel audio data (102); generating a time-frequency mask for the second multi-channel audio data (103); performing beamforming processing on the second multi-channel audio data according to the time-frequency mask to obtain first single-channel audio data (104); and outputting an audio signal by using the first single-channel audio data (105). The method realizes audio processing of a plurality of microphone arrays used for non-synchronous collection, thereby preventing the high cost caused by the fact that only unified arrays used for synchronous collection can be used for audio processing, enlarging the pickup range, and improving the robustness.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Yao, Guangchao
Abstract
In present disclosure, a data processing method, a data processing device, and an apparatus for data processing are provided. The method specifically includes: receiving a source language speech input by a target user; determining, based on the source language speech, a target acoustic model from a preset acoustic model library, the acoustic model library including at least two acoustic models corresponding to different timbre characteristics; converting, based on the target acoustic model, the source language speech into a target language speech; and outputting the target language speech. According to the embodiments of the present disclosure, the recognition degree of the speaker corresponding to the target language speech output by the translation device can be increased, and the effect of user communication can be improved.
G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
G10L 17/00 - Speaker identification or verification
G10L 17/02 - Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
G10L 17/06 - Decision making techniques; Pattern matching strategies
59.
DATA PROCESSING METHOD AND APPARATUS, AND APPARATUS USED FOR DATA PROCESSING
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Yao, Guangchao
Abstract
A data processing method and an apparatus (800) used for data processing. The method specifically comprises: receiving a source language speech input by a target user (101); determining a target acoustic model from a preset acoustic model library according to the source language speech, wherein the preset acoustic model library comprises at least two acoustic models corresponding to different timbre features (102); converting the source language speech to target language speech according to the target acoustic model (103); and outputting the target language speech (104). The method can improve the degree of differentiation of a speaker corresponding to the target language speech output by a translation device, and can enhance the effect of communications of users.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Luo, Dawei
Abstract
Disclosed in embodiments of the present application are a sound collection method and apparatus. Specifically, a microphone array first acquires position information of a user collected in real time from a visual sensor system so as to determine according to the position information of the user a collection direction corresponding to the user. Directional radio sound reception is then performed on the collection direction corresponding to the user. If a target sound signal is received in the collection direction corresponding to the user, then the collection direction in which the target sound signal is received is determined to be a target sound source direction, and then sound collection is performed in the target sound source direction, thereby obtaining a required sound signal. That is, in the embodiments of the present application, a plurality of possible collection directions may be determined and a final target sound source direction may be determined with the aid of the visual sensor system, so that sound collection is performed according to the known sound source direction, which prevents scanning and collection in all directions in space, and improves the accuracy and efficiency of collection.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Ma, Hailei
Abstract
The present disclosure provides an information switching method. The method includes: obtaining tilting information after an tilt direction of a device changes; searching a pre-set tilt direction matching the tilting information and determining pre-set information corresponding to the matched pre-set tilt direction; and switching first input information of the device to second input information, where the second input information is determined based on the pre-set information matching the pre-set tilt direction.
G01C 9/06 - Electric or photoelectric indication or reading means
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06F 3/0346 - Pointing devices displaced or positioned by the user; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
63.
INFORMATION SWITCHING METHOD AND APPARATUS, AND ELECTRONIC DEVICE
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Ma, Hailei
Abstract
Provided in embodiments of the present invention are an information switching method and apparatus, and an electronic device, wherein the method comprises: acquiring tilt information after the tilt direction of a device is shifted; searching for a preset tilt direction that matches the tilt information, and determining preset information corresponding to the matching preset tilt direction; and switching first input information of the device to second input information, the second input information being determined according to preset information of the matching preset tilt direction. Compared to the prior art requiring manual switching, the embodiments of the present invention may automatically switch the input information according to the tilt direction of the device, which improves the efficiency of information switching.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Sun, Zhiyu
Wailibieke, Walayiding
Zhang, Peng
Abstract
The present disclosure provides a voice collection device, comprising: a housing; a microphone assembly disposed inside the housing and including a microphone main body and a microphone circuit board; and a sealing structure disposed between the microphone assembly and an inner side of the housing and including a dust filter and a first adhesive layer. One side of the microphone circuit board is connected to the dust filter. The other side of the microphone circuit board is connected to the microphone main body. The microphone circuit board and the dust filter are bonded to the inner side of the housing. A sound hole is configured on the microphone main body. A first through-hole is configured at a position on the microphone circuit board corresponding to the sound hole. A second through-hole is configured at a position on the housing corresponding to the first through-hole.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Sun, Zhiyu
Walayiding, Wailibieke
Zhang, Peng
Abstract
Embodiments of the present application provide a speech acquisition device, comprising a housing, a microphone assembly placed in the housing, and a seal structure located between the microphone assembly and the inner side of the housing. The microphone assembly comprises a microphone body and a microphone circuit board; the seal structure comprises a dust screen and a first adhesive layer; one side of the microphone circuit board is connected to the dust screen; the microphone circuit board and the dust screen are both adhered to the inner side of the housing by means of the first adhesive layer; the other side of the microphone circuit board is connected to the microphone body; the microphone body is provided with a sound hole; the microphone circuit board is provided with a first through hole corresponding to the sound hole; the housing is provided with a second through hole corresponding to the first through hole; the dust screen is disposed between the first through hole and the second through hole; the first through hole, the second through hole, and the sound hole form a sound pickup main channel, and the region outside the sound pickup main channel is sealed. The sealing effect is good.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Liu, Wenwen
Li, Lin
Pan, Muye
Abstract
Provided in the embodiments of the present application are a method and device for data processing and a device for use in data processing. The method specifically comprises: determining information to be replied from clipboard information; the information to be replied corresponding to the entirety or a portion of the clipboard information; determining a reply candidate corresponding to the information to be replied; and displaying the reply candidate. The embodiments of the present application increase reply efficiency and implement smart replying in a scenario of replying across communication windows.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Chen, Lin
Wang, Lu
Liu, Yezhou
Abstract
A data processing method and device, and a device for processing data. Said method comprises: according to a trigger text from a user in a trigger interface, determining a paragraph text corresponding to the trigger text, the trigger interface comprising: a target language translation result display interface corresponding to a source language text (101); and displaying, in the trigger interface, a target text corresponding to the paragraph text, the paragraph text and the target text having a translation relationship (102). Said method can improve the efficiency of a user viewing a source language text and a target language text by contrast.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Maerhufu, Mansuer
Cui, Xin
Zhang, Yang
Abstract
Embodiments of the present disclosure provide a text editing method, device, and electronic apparatus. The method comprises: acquiring a text-to-be-edited; after receiving a trigger operation, generating an edit region; segmenting the text-to-be-edited into N number of text segments, and separately displaying the N number of text segments in the edit region, where N is a positive integer greater than 1; and after receiving an editing operation with respect to the N number of text segments, editing the N number of text segments based on the editing operation. The method and device provided in the embodiments of the present disclosure are used to solve technical problems such as complicated operations and low editing efficiency in current text editing technologies. The embodiments of the present disclosure may reduce complexity of text editing operations and improve technical effects of text editing efficiency.
G06F 3/0482 - Interaction with lists of selectable items, e.g. menus
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
69.
DATA PROCESSING METHOD, APPARATUS, AND APPARATUS USED FOR DATA PROCESSING
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Jiang, Liyang
Wang, Yuguang
Yang, Jiajun
Shi, Liangliang
Wei, Linyu
Chen, Wei
Abstract
Provided in the embodiments of the present application are a data processing method and apparatus, and an apparatus used for data processing. The method specifically comprises: receiving a speech signal of a first language inputted by a user; determining a speech translation result corresponding to the speech signal and quality information corresponding to the speech translation result, the speech translation result corresponding to a second language; and outputting the speech translation result and the quality information corresponding to the speech translation result. The embodiments of the present application can provide the degree of confidence of a speech translation result to the user, such that the user can objectively understand the accuracy of the speech translation result.
G10L 25/60 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
G10L 25/48 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Han, Qin
Abstract
Provided are an input method and apparatus, and an electronic device, wherein the method comprises: an input method acquiring information of a track drawn in a keyboard region thereof, and displaying the corresponding drawn image according to the information of the track drawn (102); recognizing at least one associated image corresponding to the drawn image (104); and displaying the associated image (106). According to the method, when a user is not satisfied with the drawn image, an image complying with the intention may be selected from the image associated with the drawn image for input without redrawing, and the efficiency of inputting an image is improved.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Liu, Yezhou
Abstract
Disclosed are a content processing method and device. The processing method comprises: in response to the selection operation of a text, displaying a function option control, wherein the function option control comprises at least one operation option; in response to the triggering of any one operation option, generating a multimedia file that comprises the text; and according to a triggered operation option, transmitting the multimedia file to a target object and/or saving the multimedia file. Therefore, when a user cannot copy, share or save the text, the present invention realizes the sharing or saving of the text by converting the text that needs to be shared or saved into the multimedia file, then sharing the multimedia file to the target object, and/or saving in a local terminal.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Chen, Xiaoshuai
Zang, Jiaojiao
Zhang, Yang
Abstract
An input prediction method and device. The method comprises: acquiring a first input content and a second input content (S101); determining a scenario category corresponding to the first input content (S102); and predicting and acquiring, according to the first input content, the scenario category, and the second input content, a third input content that meets a preset condition concerning a partial order relationship with the first input content, wherein the partial order relationship is used to describe a sequence in which each input content appears (S103). The invention improves accuracy of input prediction, and effectively improves input efficiency.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
73.
Input method, input device and apparatus for input
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhang, Yang
Jiao, Haofeng
E, Yanli
Abstract
An input method, an input device, and an apparatus for input are provided in the embodiments of the present application. The method specifically includes: receiving an input string having a fast input intent, wherein the fast input intent is used to indicate, according to a shorthand information of a word or a phrase corresponding to the input string, the word or the phrase; obtaining word candidates and/or phrase candidates corresponding to the input string according to a language model, wherein the word candidates and the phrase candidates are respectively complete words and complete phrases corresponding to the input string; presenting word candidates and/or phrase candidates to a user. The embodiments of the present application can not only improve the flexibility and application range of the fast input, but also improve the quality of word candidates and/or phrase candidates, thereby improving input efficiency.
G06F 40/274 - Converting codes to words; Guess-ahead of partial word inputs
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 40/44 - Statistical methods, e.g. probability models
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
74.
DATA PROCESSING METHOD, APPARATUS AND ELECTRONIC DEVICE
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Tu, Chang
Zhou, Weihao
Abstract
Provided are a data processing method, an apparatus and an electronic device. The method comprises: obtaining input information, extracting multiple types of keywords corresponding to the input information (102), wherein the type of the keywords corresponds to the type of multimedia attribute information; matching different types of the keywords, and obtaining corresponding multimedia data according to a result of the matching (104); and recommending the multimedia data (106). Therefore, the input information whose intention cannot be identified can be matched with the corresponding multimedia data and be recommended, and the accuracy of the recommendation information is improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Chen, Xiaoshuai
Maerhufu, Mansuer
Zhang, Yang
Abstract
An input method, an input device, and an electronic apparatus are disclosed by embodiments of the present disclosure. The input method comprises: obtaining an input operation; determining an input content corresponding to the input operation; determining input candidates matching the input content based at least on one or more keywords included in an adaptive lexicon. The one or more keywords included in the adaptive lexicon are determined according to a current page content of the electronic apparatus. The embodiments of the present disclosure achieve the technical effect of being able to provide more accurate input candidates.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 16/00 - Information retrieval; Database structures therefor; File system structures therefor
G06F 40/274 - Converting codes to words; Guess-ahead of partial word inputs
76.
Cellphone display screen with graphical user interface
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Gao, Shuang
Yu, Hao
Zhang, Tingting
Feng, Ke
Zhao, Bo
Zhang, Long
Liu, Hu
Wang, Xun
Abstract
The present application provides a searching method and related device. The method comprises: turning on a camera device to shoot a real-world scene and generating a virtual object; displaying the real-world scene and the virtual object in a user interface using AR technology; acquiring voice data input by a user and converting the voice data into corresponding text data; sending the text data to a searching server and receiving a searching result corresponding to the text data returned from the searching server; and in the user interface which displays the real-world scene and the virtual object, displaying text data corresponding to the searching result using the AR technology, and/or outputting voice data converted from the searching result. Thus, according to the embodiment of the present invention, a plurality of searching results can be more intuitively obtained for viewing, thereby improving searching efficiency; besides, the sense of the real-world scene is enhanced by means of voice interaction with the virtual object and the user experience is thus improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Liu, Shiwen
Abstract
Disclosed in embodiments of the present application are an expression input method and apparatus. The method specifically comprises: displaying M candidate words on the basis of the input operation of a user, M being a positive integer; and displaying, on the basis of the trigger operation of the user, expressions corresponding to all or some of the M candidate words. The present application can solve the technical problem in the prior art of inconvenience in expression input, can improve the convenience of expression input, and can increase the input speed of a user.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
Provided is a translation pen, including a rear sleeve, a front sleeve, a top cover assembly, a bottom cover assembly and a main body assembly. The rear sleeve and the front sleeve are hollow cylindrical structure, and the hollow portions of the rear sleeve and the front sleeve are connected as a receiving chamber after the rear sleeve is embedded into the front sleeve. The main body assembly is received in the receiving chamber. The end of the main body assembly adjacent to the top cover assembly is threadedly connected to the top cover assembly, the end of the main body assembly adjacent to the bottom cover assembly is threadedly connected to the bottom cover assembly, and the front and rear sleeves can be tightly locked by threaded connection of the top cover assembly and the bottom cover assembly to the main body assembly. The present invention solves the problem of the insufficient structural strength caused by the connection between the front sleeve and the rear sleeve through cartridge modes such as buckles, guarantees the structural strength of the translation pen, and effectively protects the main body assembly inside the front sleeve and the rear sleeve.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xu, Jingfang
Zhang, Jiacheng
Zhai, Feifei
Dai, Lei
Liu, Qi
Fang, Fei
Ding, Yanzhuo
Abstract
Provided are a cross-language search method and apparatus, and an apparatus for a cross-language search. The method specifically comprises: translating a source language search term into a target language search term; with respect to the target language search term, acquiring a target language search result and a source language translation result, corresponding thereto, wherein the source language translation result is obtained by translating the target language search result; acquiring a keyword matching the target language search term from the source language translation result; and marking and displaying the keyword in the source language translation result. The embodiments of the present application can improve a coverage ratio of content marked in red in a source language translation result corresponding to a target language search term, and thus can improve the efficiency of acquiring information from the source language translation result corresponding to the target language search term.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
TSINGHUA UNIVERSITY (China)
Inventor
Xu, Jingfang
Liu, Yang
Zhang, Jiacheng
Zhai, Feifei
Dai, Lei
Liu, Qi
Fang, Fei
Ding, Yanzhuo
Abstract
Provided are a cross-language search method and apparatus, and an apparatus for a cross-language search. The method specifically comprises: translating a source language search term into a target language search term; with respect to the target language search term, acquiring a target language search result and a translation search result, corresponding thereto, wherein the translation search result is obtained by translating the target language search result; acquiring a keyword matching the target language search term from the translation search result; and replacing the keyword in the translation search result with the source language search term. The embodiments of the present application can improve the accuracy of a translation search result and the consistency between the translation search result and a target language search result, and can also improve the attraction of the translation search result for a user, so that the click rate of the translation search result can be further improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
Provided is a translation machine, comprising a housing, a microphone assembly, a speaker, and a switch button; the housing comprises a bottom and a frame; the bottom and the frame constitute an accommodating chamber; one frame of two adjacent frames is provided with the switch button, and the other frame is provided with a first sound-pickup hole of the microphone assembly and a first sound outlet hole of the speaker; the microphone component and the speaker are located in the accommodating chamber, and are arranged facing the first sound-pickup hole and the first sound outlet hole; the microphone assembly consists of two microphones, and the speaker is located between the two microphones. The two microphones and the speaker are located at the same end of the translation machine and during translation, the microphone and speakers operate alternatingly; therefore, the speaker and the microphones do not affect one another; at the same time, two microphones are arranged, such that the directivity of sound pickup is enhanced and sensitivity is high, improving the accuracy of speech translation results; furthermore, it easy to align the speaker and microphone to both parties to a conversation and operability is very good.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
A translation machine, comprising a housing (100), a display screen (200), and switch buttons (300). The display screen (200) is arranged on the housing (100). The housing (100) and a first edge frame (10) adjacent to the top of the translation machine are provided with a protruding part (11) protruding towards the exterior of the first edge frame (10). The protruding part (11) is provided in proximity to the top of the translation machine. The switch buttons (300) are arranged on the protruding part (11). Because the switch buttons (300) are arranged at positions on the edge frame of the translation machine in proximity to the top of the translation machine, when the translation machine is held by hand, the protruding part (11) is located precisely at the position of the thumb of the person holding, and, with the protruding part (11) in proximity to the position of the thumb, switching between translation languages can be performed quickly and conveniently with the thumb, thus making the operation of the translation machine to further comply with habits of the human body, increasing translation efficiency, and providing great operability.
G06F 15/02 - Digital computers in general; Data processing equipment in general manually operated with input through keyboard and computation using a built-in program, e.g. pocket calculators
G06F 17/28 - Processing or translating of natural language
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
A mainboard and a translation machine. The mainboard comprises a body, and a shielding area and a non-shielding area on the front surface of the body; the shielding area and the non-shielding area are provided with devices connected to the body, wherein the height of a device of the maximum height in the shielding area is smaller than the height of a device of the maximum height in the non-shielding area; since the device of a relatively large height is disposed in the non-shielding area, the height of the device in the shielding area is relatively small, and after a shielding cover is fixed in the shielding area, the height of the shielding cover can be effectively reduced, thereby reducing the height of the entire mainboard, reducing the thickness of the translation machine, and facilitating the lightening and thinning development of the translation machine.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Tu, Chang
Zhang, Yang
Wang, Yanfeng
Abstract
Disclosed in embodiments of the present application are a candidate word prediction method and device. In the method, according to content most recently input on the screen, on-screen content requiring word prediction can be determined; since a word prediction intention can reflect, to a large extent, a user's actual input intention for the on-screen content, if the word prediction intention of the on-screen content can be determined, content that may be continuously input on the screen by the user after the on-screen content can be determined according to the word prediction intention. Therefore, when data corresponding to the word prediction intention is obtained according to a keyword in the on-screen content, and a candidate corresponding to the on-screen content is predicted according to the data, the candidate determined according to the data is more likely to meet the user's input intention. Thus, the input convenience for the user is improved. Moreover, the determined candidate does not need to be generated on the basis of the past input data of the user, and thus, the likelihood and accuracy of the predicted candidate are improved.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 17/30 - Information retrieval; Database structures therefor
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Zhang, Jie
Bu, Hailiang
Jin, Yixiao
Xing, Zhenzhen
Jiang, Pin
Feng, Xinqiang
Abstract
The embodiments of the present application provide a video processing method and device, and a device for video processing, the method particularly comprising: recognizing a video stream and/or an audio stream corresponding to a video, to obtain a corresponding recognition result; acquiring, from a preset item database, a target item matching the recognition result; and adding target information corresponding to the target item into a video frame corresponding to the video stream and/or the audio stream. The embodiments of the present application can shorten video processing time and improve video processing efficiency, and can improve video coverage of target information.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Lin, Changqing
Abstract
The present disclosure provides a key processing method and apparatus, and an apparatus for key processing. The key processing method specifically includes processing a non-triggered key in response to a triggering operation by a user on a current key in a current interface where the non-triggered key is a key in the current interface other than the current key, and outputting a processing result of the non-triggered key. The embodiments of the present disclosure not only enrich the current interface, but also enhance the feedback effectiveness and user experience during the use of the interface. Thus, the accuracy of the key operation may be improved.
G06F 3/02 - Input arrangements using manually operated switches, e.g. using keyboards or dials
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xu, Meng
Han, Qin
Li, Lin
Cai, Pengli
Chen, Zhangqin
Abstract
Embodiments of the present application provide an input method, device, and machine-readable medium. The input method specifically comprises: obtaining the data of movement inputted by a user on an input interface; identifying the movement data so as to obtain the target character and/or target image corresponding to the movement data; displaying the target character and/or target image as a candidate. The embodiments of the present application effectively reduces user operation path and enhances user input efficiency.
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
A watch clasp and a wearable apparatus, the watch clasp specifically having: a clasp frame (1), wherein, the clasp frame (1) has a semicircular or circular, and a reinforcement shaft (2) is provided between two opposing edges of the clasp frame (1). The present application can, by means of the reinforcement shaft (2), increase the strength of the watch clasp, and so can to a certain extent avoid deformation of the watch clasp when in use.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Li, Liping
Wang, Suhang
Yan, Congxian
Yang, Lei
Liu, Min
Zhao, Hong
Yao, Jia
Abstract
An audio input method includes: in an audio-input mode, receiving a first audio input by a user, recognizing the first audio to generate a first recognition result, and displaying corresponding verbal content to the user based on the first recognition result; and in an editing mode, receiving a second audio input by the user and recognizing and generating a second recognition result, converting the second recognition result to an editing instruction, and executing a corresponding operation based on the editing operation. The audio-input mode and the editing mode are switchable.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Li, Mingxiu
Yin, Lei
Bu, Hailiang
Abstract
A voice-based data processing method and apparatus, and an electronic device, used for completely recording a diagnostic inquiry process. The method comprises: acquiring diagnostic inquiry process data, the diagnostic inquiry process data being determined according to voice data collected in a diagnostic inquiry process (102); performing recognition according to the diagnostic inquiry process data to acquire corresponding first text data and second text data, wherein the first text data belongs to a target user, and the second text data belongs to another user other than the target user (104); and obtaining diagnostic inquiry information according to the first text data and the second text data (106). By means of the method, the apparatus and the electronic device, the statements of a doctor and a patient in a diagnostic inquiry process can be automatically distinguished, the diagnostic inquiry process is completely recorded, and same is automatically organised to obtain content such as a medical record, thus saving on time for organising diagnostic inquiry records.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Tu, Chang
Zhang, Yang
Wang, Yanfeng
Abstract
The present disclosure provides a recommendation method and device, and a device for formulating recommendations. The recommendation method specifically includes obtaining a current context of an input method program after the input method program is triggered, analyzing data of past input actions by a current user under past contexts to obtain a target entry matching the current context in the data of the past input actions, and displaying the target entry. The present disclosure provides candidate entries to the user without any input operation by the user, thereby substantially improving the user's input efficiency.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Xiao, Ziqiu
Zhang, Jie
Sun, Peining
Abstract
A watch body comprising: a primary watch body (2) and a secondary watch body (2), where the left lateral surface or the right lateral surface of the secondary watch body (1) is fused and connected with the primary watch body (2), and the secondary watch body (1) is provided with a first camera (3) and a second camera (4). The watch body allows a user to implement the demand for photographing anytime and anywhere via a wearable device. This allows the stacking of the watch body corresponding to a movement to be of an increased degree of rationality and the spatial arrangement to be of increased compactness; therefore, the size of the watch body corresponding to the movement can be reduced as much as possible. Also provided is the wearable device comprising the watch body.
G04G 21/00 - Input or output devices integrated in time-pieces
G03B 29/00 - Combinations of cameras, projectors or photographic printing apparatus with non-photographic non-optical apparatus, e.g. clocks or weapons; Cameras having the shape of other objects
G04B 47/00 - Time-pieces combined with other articles which do not interfere with the running or the time-keeping of the time-piece
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
38 - Telecommunications services
41 - Education, entertainment, sporting and cultural services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Computer software, recorded; computer operating programs,
recorded; electronic publications, downloadable; mouse pads;
mouse [computer peripheral]; floppy disks; wires, electric;
animated cartoons. Advertising; shop window dressing; on-line advertising on a
computer network; advertising design; advertising planning;
organization of trade fairs for commercial or advertising
purposes; market studies; organization of exhibition for
advertising and commercial purpose; sales promotion for
others; personnel management consultancy. Television broadcasting; providing internet chatrooms;
message sending; email service; providing telecommunications
connections to a global computer network; rental of access
time to global computer networks; providing user access to
global computer networks; information about
telecommunication; communications by computer terminals;
voice mail services. Organization of competitions [education or entertainment];
mobile library services; production of radio and television
programmes; entertainment information; game services
provided on-line from a computer network; entertainer
services; health club services [health and fitness
training]. Technical research; packaging design; dress designing;
computer programming; computer software design; conversion
of data or documents from physical to electronic media;
providing search engines for the internet; hosting computer
sites [web sites]; rental of web servers; creating and
maintaining web sites for others.
97.
SEARCH METHOD AND APPARATUS, AND APPARATUS FOR SEARCHING
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Wang, Junhao
Lin, Jiansu
Abstract
Provided are a search method and apparatus, and an apparatus for searching, wherein the method specifically comprises: acquiring a search word with a meaningless target corresponding to the current search word input by a user; acquiring a relevant search result corresponding to the search word with a meaningless target; and displaying the relevant search result as a first search result item corresponding to the search word. In the embodiments of the present application, pre-set information related to a search word with a meaningless target can be carried by means of a relevant search result, so that the search experience of a user can be improved.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Mansuer, Maerhufu
Cui, Xin
Zhang, Yang
Abstract
Provided are a text editing method and device, and an electronic apparatus. The method comprises: acquiring a text to be edited (S101); upon receiving a trigger operation, generating an edit region (S102); segmenting the text into N text segments, and separately displaying the N text segments in the edit region, where N is a positive integer greater than 1 (S103); and upon receiving an edit operation with respect to the N text segments, editing the N text segments according to the edit operation (S104). The method and device solve a technical problem in which a text editing process requires complex operations and has low editing efficiency, thereby improving text editing efficiency.
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO., LTD. (China)
Inventor
Lin, Changqing
Abstract
The present disclosure provides an input method and device. The method specifically comprises: displaying an input interface, where the input interface includes at least one key; in response to a touch operation of a key by a user in an input process, playing an audio corresponding to the key and matching the characteristics of the input interface. Based on keystroke by the user in the input process, the disclosed embodiments provide feedback to the user with animation effect and dynamic audio matching a theme of the current input interface, and enhance key tones in the input process.
G06F 3/023 - Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
G06F 3/0488 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
G06F 3/02 - Input arrangements using manually operated switches, e.g. using keyboards or dials
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range