A visual-based classification model influenced by text features as a result of the outputs of a text-based classification model is disclosed. A system receives one or more documents to be classified based on one or more visual features and provides the one or more documents to a student classification model, which is a visual-based classification model. The system also classifies, by the student classification model, the one or more documents into one or more document types based on one or more visual features. The one or more visual features are generated by the student classification model that is trained based on important text identified by a teacher classification model for the one or more document types, with the teacher classification model being a text-based classification model. Generating training data and training the student classification model based on the training data are also described.
G06F 16/583 - Recherche caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
G06V 10/70 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique
Systems and methods for throttling requests to web services are disclosed. A system is configured to receive, at a host, one or more requests during a first time period. Each request is for a web service hosted on a backend. The host is one of a plurality of hosts of an application programming interface (API) gateway to receive a plurality of requests for the web services. The system is further configured to: process at least a portion of the one or more requests for the one or more web services; count, by a local counter in a local cache of the host, the one or more requests received at the host during the first time period; compare a local count of the local counter to a local bucket size associated with the host; and provide an instruction to update a remote count of a remote counter based on the comparison.
H04L 67/60 - Ordonnancement ou organisation du service des demandes d'application, p.ex. demandes de transmission de données d'application en utilisant l'analyse et l'optimisation des ressources réseau requises
H04L 67/1021 - Sélection du serveur pour la répartition de charge basée sur la localisation du client ou du serveur
G06F 8/656 - Mises à jour pendant le fonctionnement
A method may include generating a vector from unstructured data included in an untransformed transaction, and determining, for the vector, a cluster ID of cluster IDs by matching the vector with a matching cluster vector of cluster vectors. The method may further include generating a query using the cluster ID and the untransformed transaction, and transforming, using the cluster IDs, untransformed transactions to transformed transactions. The transformed transactions may each include a cluster ID. The method may further include generating, using the query, a query result from features of the transformed transactions, generating a fraud score using the query result, and presenting the fraud score and the cluster ID.
G06Q 20/40 - Autorisation, p.ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasin; Examen et approbation des payeurs, p.ex. contrôle des lignes de crédit ou des listes négatives
A method implements a customer recognition system. A request with an identifier of an unidentified user is received. Sparse data is generated from string information corresponding to the identifier. Preexisting identifiers are filtered to generate a list of candidate identifiers using the sparse data. The plurality of preexisting identifiers correspond to a plurality of preexisting users. A core identifier is selected by determining a match between the identifier and a preexisting identifier from the preexisting identifiers using distance information generated using the list of candidate identifiers. The core identifier is matched to the identifier using the match to identify the unidentified user as a preexisting user from the plurality of preexisting users.
A method including receiving, at a platform and from a first user using a first user device, selection of a uniform resource indicator (URI) unique to a second user using a second user device. The method also includes generating, automatically by the platform in response to receiving the URI, a conference session unique to the first user and the second user. The method also includes transmitting, automatically by the platform, a message to the second user, the message indicating that the conference session is initiated. The method also includes receiving, by the platform, an indication from the second user device that the second user joins the conference session. The method also includes joining, automatically by the platform, the first user device and the second user device in the conference session.
A computing system receives, from a client device, an image of a content item uploaded by a user of the client devices. The computing system divides the image into one or more overlapping patches. The computing system identifies, via a first machine learning model, one or more distortions present in the image based on the image and the one or more overlapping patches. The computing system determines that the image meets a threshold level of quality. Responsive to the determining, the computing system corrects, via a second machine learning model, the one or more distortions present in the image based on the image and the one or more overlapping patches. Each patch of the one or more overlapping patches are corrected. The computing system reconstructs the image of the content item based on the one or more corrected overlapping patches.
A computing system generates a plurality of training data sets for generating the NLP model. The computing system trains a teacher network to extract and classify tokens from a document. The training includes a pre-training stage where the teacher network is trained to classify generic data in the plurality of training data sets and a fine-tuning stage where the teacher network is trained to classify targeted data in the plurality of training data sets. The computing system trains a student network to extract and classify tokens from a document by distilling knowledge learned by the teacher network during the fine-tuning stage from the teacher network to the student network. The computing system outputs the NLP model based on the training. The computing system causes the NLP model to be deployed in a remote computing environment.
A method secures hash chains via hybrid consensus. A proximate payload for a proximate chain block for a proximate chain is obtained. A first identifier of the proximate chain and the proximate payload are hashed with a hash function to generate a second identifier of the proximate chain. The proximate chain block is added to the proximate chain. The proximate chain block includes the first identifier, the second identifier, and the proximate payload. A request to add the second identifier to a reporting chain is transmitted. A response indicating that the second identifier is incorporated into the reporting chain using the consensus mechanism is received.
H04L 9/32 - Dispositions pour les communications secrètes ou protégées; Protocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
9.
DYNAMIC SCHEDULING SYSTEM WITH PERFORMANCE-BASED ACCESS
This disclosure provides systems, methods and apparatuses for scheduling tasks in an electronic system. In some implementations, a dynamic scheduling system allows performance-based access to a task schedule. In distributing tasks to be completed, the dynamic scheduling system prioritizes resources that are more proficient at completing the tasks over resources that are less proficient. For example, resources that are more proficient may receive higher-priority access to the task schedule than resources that are less proficient. Each resource may be assigned a proficiency score based on quantitative or qualitative performance indicators associated with tasks previously completed by the resource. Each resource is dynamically provided access to the task schedule based on its proficiency score. For example, resources having the highest performance scores may be first to receive access to a set of timeslots, whereas resources having the lowest performance scores may be last to receive access to the set of timeslots.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
Aspects of the present disclosure provide techniques for expert matching though workload intelligence. Embodiments include receiving a request for a support engagement. Embodiments include receiving workload data of a plurality of experts. Embodiments include determining a workload capacity of each respective expert based on the respective workload data for the respective expert. Embodiments include determining a respective estimated completion time for the support, engagement for each of the plurality of experts using a machine learning model. Embodiments include determining match scores for the support engagement and each of the plurality of experts based on the estimated completion times and the workload capacities. Embodiments include selecting a given expert of the plurality of experts to handle the support engagement based on the match scores.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
11.
FORECASTING BASED ON BERNOULLI UNCERTAINTY CHARACTERIZATION
This disclosure relates to predictions based on a Bernoulli uncertainty characterization used in selecting between different prediction models. An example system is configured to perform operations including determining a prediction by a first prediction model. The first prediction model is associated with a loss function. The system is also configured to determine whether the prediction is associated with the first prediction model or a second prediction model based on a joint loss function. The second prediction model is associated with a likelihood function, and the joint loss function is based on the loss function and the likelihood function. The system is further configured to indicate the prediction to the user in response to determining that the prediction is associated with the first prediction model. If the prediction is associated with the second prediction model, the system may prevent indicating the prediction to the user.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
G06Q 40/06 - Gestion de biens; Planification ou analyse financières
G06Q 40/00 - Finance; Assurance; Stratégies fiscales; Traitement des impôts sur les sociétés ou sur le revenu
A computer-implemented system and method for generating heterogeneous graph feature embeddings for feature learning and prediction. An application server may receive and process a plurality of feature datasets to generate a graph data structure comprising a plurality of interconnected transaction pairs. The application server processes the graph data structure to determine a first-order transaction pair corresponding to a maximum transaction frequency based on a user identifier; executes a jumping probability algorithm to process the graph data structure to determine a second-order transaction pair jumping from a first-order transaction pair; and generates a transaction sequence associated with the user identifier.
Systems and methods for providing contextual information for computerized document understanding. The systems and methods can be used to assist users in filling out documents by providing contextual information based on anomalies identified in a provided document. The methods and systems may identify the deficiency in the document and automatically generate a query related to the anomaly. The query can be fed as an input to a question-answering (QA) model that can provide an answer as the contextual information.
This disclosure relates to systems and methods for processing electronic payments for customer purchases. In some implementations, a system receives a payment request from a merchant, and transmits payment information to a mobile computing device associated with the merchant. The payment information includes a transaction ID to identify the purchase, a purchase amount, and instructions that cause the mobile computing device to activate a card reader, present a notification of the purchase amount to the customer, receive an acceptance of the purchase amount from the customer, and authorize the card reader to process an electronic payment for the purchase amount. The system receives payment confirmation from the mobile computing device, and provides the parameter confirmation to the merchant.
G06Q 20/34 - Architectures, schémas ou protocoles de paiement caractérisés par l'emploi de dispositifs spécifiques utilisant des cartes, p.ex. cartes à puces ou cartes magnétiques
G06Q 20/20 - Systèmes de réseaux présents sur les points de vente
G06Q 20/32 - Architectures, schémas ou protocoles de paiement caractérisés par l'emploi de dispositifs spécifiques utilisant des dispositifs sans fil
15.
CARD READER BASED PAYMENT TRANSACTIONS FROM A WEB BROWSER
This disclosure relates to systems and methods for processing electronic payments for customer purchases. In some implementations, a mobile computing device receives a payment request identifying a sales transaction between a merchant and a customer. The payment request indicates a purchase amount owed by the customer to the merchant, and carries a set of instructions. The mobile computing device activates a card reader based at least in part on the set of instructions, receives customer authorization for electronic payment of the purchase amount, instructs the card reader to process a credit card for the purchase amount based on receiving the customer authorization, and receives confirmation of payment of the purchase amount from the card reader.
G06Q 20/34 - Architectures, schémas ou protocoles de paiement caractérisés par l'emploi de dispositifs spécifiques utilisant des cartes, p.ex. cartes à puces ou cartes magnétiques
G06Q 20/20 - Systèmes de réseaux présents sur les points de vente
G06Q 20/32 - Architectures, schémas ou protocoles de paiement caractérisés par l'emploi de dispositifs spécifiques utilisant des dispositifs sans fil
After a host client establishes a multimedia stream with a guest client, host data is received from a host application. A state machine is updated using the host data. The host application executes on the host client. Guest data is received from a guest application. The state machine is updated using the guest data. The guest application executes on the guest client. Transaction data is propagated between the host application and the guest application. The transaction data is presented with the multimedia stream. The transaction data includes the host data and the guest data. Provider data is generated responsive to updating the state machine with the host data and the guest data. The provider data is sent to the guest client. The provider data is presented with the multimedia stream by the guest application on the guest client.
H04N 21/478 - Services additionnels, p.ex. affichage de l'identification d'un appelant téléphonique ou application d'achat
H04N 21/262 - Ordonnancement de la distribution de contenus ou de données additionnelles, p.ex. envoi de données additionnelles en dehors des périodes de pointe, mise à jour de modules de logiciel, calcul de la fréquence de transmission de carrousel, retardement d
H04N 21/458 - Ordonnancement de contenu pour créer un flux personnalisé, p.ex. en combinant une publicité stockée localement avec un flux d'entrée; Opérations de mise à jour, p.ex. pour modules de système d'exploitation
H04N 21/254 - Gestion au sein du serveur de données additionnelles, p.ex. serveur d'achat ou serveur de gestion de droits
17.
COMBINING RULES-BASED KNOWLEDGE ENGINEERING WITH MACHINE LEARNING PREDICTION
Systems and methods for predicting one or more field values using machine learning in a knowledge engineering (KE) data model are disclosed. An example method may include identifying a first field in the KE data model which lacks a value and for which one or more machine learning models are defined, the first field being associated with one or more dependent field, determining that each dependent field of the first field has a corresponding value in the KE data model, executing each of the one or more machine learning models to predict one or more values for the first field, selecting one of the one or more predicted values as the representative value of the first field, identifying one or more further fields in the KE data model for which the first field is a dependent field, none of the one or more further fields defining any machine learning models, and calculating values for one or more further fields based at least in part on the representative value of the first field.
A method may include clustering form elements into line objects and columns of a table of a structured representation by applying a trained multi -dimensional clustering model to spatial coordinates of the form elements, and assigning a table header line type to a table header line object of the line objects based on a spatial coordinate of the table header line object relative to a spatial coordinate of a topmost table data line object of the line objects, and a determination that a number of columns of the table header line object is within a threshold of a number of columns of the topmost table data line object. The topmost table data line object may be assigned a table data line type. The method may further include presenting the stmctured representation to a user.
Systems and models are disclosed for determining a value over replacement feature (VORF) for one or more features of a machine learning model. An example method includes selecting one or more features used in the machine learning model, determining a comparison set of unused features not used in the machine learning model, for each unused feature in the comparison set, determining a difference in a specified metric when the selected one or more features are replaced by a corresponding unused feature from the comparison set, and determining the VORF to be the smallest difference in the specified metric.
This disclosure relates to systems and methods for constructing a customized debt reduction plan for a user. In some implementations, a customized debt reduction system obtains a plurality of financial attributes of the user and a plurality of other users, where the plurality of financial attributes are indicative of credit card debt, and identifies users from the plurality of other users who successfully repaid their credit card debt based on their respective financial attributes and one or more repayment techniques that resulted in successful repayment of their credit card debt. The customized debt reduction system correlates the plurality of financial attributes of the user with the plurality of financial attributes of a number of the identified users and determines a personalized score for the user, using a trained machine learning model, based on the correlation to determine a customized debt reduction plan for the user based on the personalized score.
Aspects of the present disclosure provide techniques for training a machine learning model. Embodiments include receiving a historical support record comprising time-stamped actions, a support initiation time, and an account indication. Embodiments include determining features of the historical support record based at least on differences between times of the time- stamped actions and the support initiation time. Embodiments include determining a label for the features based on the account indication. Embodiments include training an ensemble model, using training data comprising the features and the label, to determine an indication of an account in response to input features, wherein the ensemble model comprises a plurality of tree-based models and a ranking model.
Aspects of the present disclosure provide techniques for training a machine learning model. Embodiments include determining a set of unlabeled user transaction records associated with a user. Embodiments include selecting a first unlabeled user transaction record associated with a first vendor from the set of unlabeled user transaction records based on a transaction record prioritization scheme. Embodiments include presenting the first unlabeled user transaction record to the user in a label query. Embodiments include receiving, from the user in response to the label query, a label of a first account for the first unlabeled user transaction record. Embodiments include selecting a second unlabeled user transaction record associated with a second vendor from the set of unlabeled user transaction records based on: the transaction record prioritization scheme, and a determination that the second vendor is least likely to be categorized by the user in the first account.
Systems and methods that may be used to provide personalized financial nudges to users of a financial service that may be used to further the users' savings intentions (e.g., a savings goal, an emergency fund, etc.). The disclosed systems and methods may increase user interactivity with the financial service and the services it offers by providing personalized nudges that are based on, among other things, an evaluation of various behavioral economics principles. A machine learning recommendation system may be used to fit and output different nudges to users in a personalized way to maximize their savings' intentions.
An encrypted database system includes a memory storing a database comprising a plurality of logical structural elements each respectively including an unencrypted fuzzed value and encrypted sensitive data formed by encrypting a sensitive data value. The system also includes a processor in communication with the memory and configured to form the plurality of logical structural elements and store the plurality of logical structural elements in the memory. Forming a logical structural element comprises generating the unencrypted fuzzed value for the sensitive data value, encrypting the sensitive data value, and storing the encrypted sensitive data value and the unencrypted fuzzed value in the same logical structural element in the database. The unencrypted fuzzed value is within a predetermined value range and is different from the sensitive data value.
A processor may receive user interaction data of a user for a plurality of electronically-presented offers. The processor may generate a plurality of labels, the generating comprising generating a label for each respective offer according to a comparison of the quality of the user interactions of the respective offer to the frequency of the user interactions of the respective offer. Each label may be a positive label or a negative label. The processor may determine whether the generating produced both positive and negative labels. The processor may select one of a plurality of available ML models, wherein a two-class ML model is chosen in response to determining that the generating produced both positive and negative labels and a one-class ML model is chosen in response to determining that the generating did not produce both positive and negative labels. The selected ML model may be trained and/or may be used to process user profile data and provide recommendations.
A computer-implemented method and system are provided to perform a machine learning pipeline process to produce an explainable machine learning model. A computing device may be configured to train a plurality of machine learning models with a set of respective feature datasets to generate an accuracy and explainability property for each trained model. The computing device may evaluate a plurality of the trained machine learning models and select a model as an explainable machine learning model based on at least one of the accuracy and the explainability property.
Certain aspects of the present disclosure provide techniques for processing natural language utterances in a knowledge graph. An example method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application. Operands and operators are extracted from the natural language utterance using a natural language model. Operands may be mapped to nodes in a knowledge graph, the nodes representing values calculated from data input into the application, and operators may be mapped to operations to be performed on data extracted from the knowledge graph. The functions associated with the operators are executed using data extracted from the nodes in the knowledge graph associated with the operands to generate a query result. The query result is returned as a response to the received long -tail query.
Certain aspects of the present disclosure provide techniques for generating an application programming interface (API) for a plurality of associated services. The method generally includes retrieving a declarative schema for a service of a plurality of services in an application programming interface (API). A language object for the sendee is generated from a data object definition in the declarative schema associated with the service. Generally, the language object is configured to handle data events generated by the service. A service controller for the service is generated from a sen-ice definition in the declarative schema associated with the respective service. Generally, the service controller is fronted by a gateway for external sources to invoke one or more functions implemented by the sendee. An application programming interface (API) is exposed for the service independently of details of APIs for the associated services to one or more external services.
Disclosed herein are systems and methods for replicating data across deployments in a routing constrained environment. To replicate data, a processor may detect a modification that changes data for a source entity within a source environment hosting a source deployment of an application. The processor may then update a target environment hosting a target deployment of the application to mirror the modification within the source environment. To update the target environment, the processor may generate a mapping artifact that identifies the source entity having changed data and the target entity within the target environment receiving the changed data. The processor may then create a mapping infrastructure including one or more compute instances that replicate the changed data for the source entity in the target entity. To replicate data, the one or more compute instances may execute a mapping script that replicates the changed data from the source entity in the target entity by copying changed data from the source environment and writing it to a database in the target environment.
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p.ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
G06F 11/20 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel en utilisant un masquage actif du défaut, p.ex. en déconnectant les éléments défaillants ou en insérant des éléments de rechange
A method for using piecewise forecasts involves obtaining, by a model discovery service, a plurality of models and generating, by a demand prediction service, a plurality of values for a time series variable. The plurality of values corresponding to a plurality of days to be predicted. The method further involves inputting the plurality of values for the time series variable as part of a piecewise forecast to a headcount estimation service and generating, by the headcount estimation service with the piecewise forecast, an estimated headcount from the time series variable.
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
Aspects of the present disclosure provide techniques for dynamic location tracking. Embodiments include receiving a plurality of location records associated with a site, wherein each respective location record of the plurality of location records comprises respective location coordinates of a respective device associated with the respective location record. Embodiments include determining respective distances from a center point of the site to the respective location coordinates in each respective location record of the plurality' of location records. Embodiments include determining a radius of a region definition for the site based on the respective distances. Embodiments include receiving a device location from a device associated with a user. Embodiments include performing, based on the device location and the region definition, one or more location -based operations.
G06Q 30/02 - Marketing; Estimation ou détermination des prix; Collecte de fonds
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
33.
ORACLE-AIDED PROTOCOL FOR COMPACT DATA STORAGE FOR APPLICATIONS USING COMPUTATIONS OVER FULLY HOMOMORPHIC ENCRYPTED DATA
Systems and methods that may implement an Oracle-aided protocol for producing and using FHE encrypted data. The systems and methods may initially encrypt and store input data in one encrypted form that is not performed using FHE, which does not substantially increase the size of the data and storage resources required to store the encrypted data. In accordance with the Oracle-aided protocol, the encrypted data is re-encrypted as FHE encrypted data when FHE encrypted data is required.
Aspects of the present disclosure provide techniques for providing a graphical user interface. Embodiments include displaying a text input field. Embodiments include receiving an input of at least a portion of a tag via the text input field. Embodiments include displaying, in response to the input and proximate to the text input field, a graphical representation of an existing tag that relates to the input. The graphical representation includes a type of the existing tag, the existing tag, and a colored section on a right side or a left side of the graphical representation having a color that is associated with the type of the existing tag in the computing application. Embodiments include receiving a selection of the graphical representation and displaying an instance of the graphical representation inside of the text input field.
G06F 3/0488 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] utilisant des caractéristiques spécifiques fournies par le périphérique d’entrée, p.ex. des fonctions commandées par la rotation d’une souris à deux capteurs, ou par la nature du périphérique d’entrée, p.ex. des gestes en fonction de la pression exer utilisant un écran tactile ou une tablette numérique, p.ex. entrée de commandes par des tracés gestuels
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p.ex. des menus
35.
METHOD FOR SERVING PARAMETER EFFICIENT NLP MODELS THROUGH ADAPTIVE ARCHITECTURES
A machine learning system executed by a processor may generate predictions for a variety of natural language processing (NLP) tasks. The machine learning system may include a single deployment implementing a parameter efficient transfer learning architecture. The machine learning system may use adapter layers to dynamically modify a base model to generate a plurality of fine-tuned models. Each fine-tuned model may generate predictions for a specific NLP task. By transferring knowledge from the base model to each fine-tuned model, the ML system achieves a significant reduction in the number of tunable parameters required to generate a fine- tuned NLP model and decreases the fine-tuned model artifact size. Additionally, the ML system reduces training times for fine-tuned NLP models, promotes transfer learning across NLP tasks with lower labeled data volumes, and enables easier and more computationally efficient deployments for multi-task NLP.
A method for using shareable and nested transaction on hash chains includes storing transaction data of a transaction of a hash chain. A lock block is appended to the hash chain. Appending the lock block includes setting a tail block identifier of the hash chain from a preceding tail block of a preceding transaction to the lock block. A data block is appended to the hash chain. Appending the data block includes setting the tail block identifier of the hash chain to the data block. The method further includes removing the transaction data from the transaction without invalidating the hash chain. The method further includes appending an updated data block to the hash chain to update the transaction with updated transaction data.
H04L 9/32 - Dispositions pour les communications secrètes ou protégées; Protocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
Ad hoc contact data capture includes establishing a connection to a software application. A browser renders a source page from a source server. An extension of the browser receives a page event from the browser after rendering the page, the page event identifying a selected location of the source page. Ad hoc contact data capture further includes identifying source data from the source page after receiving the page event, calculating a distance between a contact element of the source page and the selected location to identify the source data, and populating the source data into the software application.
Certain aspects of the present disclosure provide techniques for node matching with accuracy by combining statistical methods with a knowledge graph to assist in responding (e.g., providing content) to a user query in a user support system. In order to provide content, a keyword matching algorithm, statistical method (e.g., a trained BERT model), and data retrieval are each implemented to identify node(s) in a knowledge graph with encoded content relevant to the user's query. The implementation of the keyword matching algorithm, statistical method, and data retrieval results in a matching metric score, semantic score, and graph metric data, respectively. Each score associated with a node is combined to generate an overall score that can he used to rank nodes. Once the nodes are ranked, the top ranking nodes are displayed to the user for selection. Based on the selection, content encoded in the node is displayed to the user.
A method for generating a synthetic dataset involves generating discretized synthetic data based on driving a model of a cumulative distribution function (CDF) with random numbers. The CDF is based on a source dataset. The method further includes generating the synthetic dataset from the discretized synthetic data by selecting, for inclusion into the synthetic dataset, values from a multitude of entries of the source dataset, based on the discretized synthetic data, and providing the synthetic dataset to a downstream application that is configured to operate on the source dataset.
Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.
G06Q 40/02 - Opérations bancaires, p.ex. calcul d'intérêts ou tenue de compte
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
41.
MODEL SELECTION IN A FORECASTING PIPELINE TO OPTIMIZE TRADEOFF BETWEEN FORECAST ACCURACY AND COMPUTATIONAL COST
Systems and methods for forecasting future values of data streams are disclosed. One example method may include receiving information characterizing each of a plurality of forecasting models, retrieving historical data for each of a plurality of data streams, determining one or more constraints, dynamically selecting one of the plurality of forecasting models for each of the data streams based on accuracy metrics for the forecasting models, estimating cost metrics associated with each forecasting model, dynamically selecting the forecasting model based at least in part on the accuracy metrics, the cost metrics, and the determined constraints, and forecasting a first subsequent value of each data stream using the corresponding selected forecasting model.
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
42.
ENHANCED INTENT MATCHING USING KEYWORD-BASED WORD MOVER'S DISTANCE
Aspects of the present disclosure provide techniques for intent matching. Embodiments include receiving input of text by a user via a user interface. Embodiments include determining weights for portions of the text based on a plurality of keywords. Embodiment include generating an embedding of the text. Embodiments include determining an intent of the text by weighting, based on the weights, word mover's distances from the embedding of the text to a known embedding of known text associated with the intent in order to determine a similarity measure between the text and the known text. Embodiments include providing content to the user via the user interface based on the intent.
At least one processor may obtain a document comprising text tokens. The at least one processor may determine, based on a pre-trained language model, word embeddings corresponding to the text tokens. The at least one processor may determine, based on the word embeddings, named entities corresponding to the text tokens; and one or more accuracy predictions corresponding to the named entities. The at least one processor may compare the one or more accuracy predictions with at least one threshold. The at least one processor may associate, based on the comparing, the named entities with one or more confidence levels. The at last one processor may deliver the named entities and the one or more confidence levels.
Aspects of the present disclosure provide techniques for explainable payroll calculations. Embodiments include receiving a request from a client for a rule-based calculation. Embodiments include receiving one or more user values related to the request. Embodiments include using a calculation graph to determine the rule-based calculation based on the one or more user values. The calculation graph may comprise at least one node that performs an operation using the one or more user values. Embodiments include identifying an explanation template associated with the at least one node. Embodiments include generating an explanation of the rule-based calculation based on the explanation template and the one or more user values. Embodiments include providing the rule-based calculation and the explanation of the rule-based calculation to the client in response to the request.
Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.
A document extraction system executed by a processor, may process documents using manual and automated systems. The document extraction system may efficiently route tasks to the manual and automated systems based on a predicted probability that the results generated by the automated system meet some baseline level of accuracy. To increase document processing speed, documents having a high likelihood of accurate automated processing may be routed to an automated system. To ensure a baseline level of accuracy, documents having a smaller likelihood of accurate automated processing may be routed to a manual system.
G06F 16/30 - Recherche d’informations; Structures de bases de données à cet effet; Structures de systèmes de fichiers à cet effet de données textuelles non structurées
G06F 40/00 - Maniement de données en langage naturel
Certain aspects of the present disclosure provide techniques for providing assistance to users by integrating social computing system with conversational user interface. In some cases, a user interacting with a virtual assistant of a conversational user interface provides input that the virtual assistant is not able identify a matching intent. As a result, the virtual assistant can leverage the social computing system to generate a new question based on the user input and post the question to the social computing system. Users of the social computing system can provide an answer, which the virtual assistant provides to the user in the conversational user interface. The social computing system can also generate a new intent for the virtual assistant to increase efficiency of the virtual assistant.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
G06Q 30/02 - Marketing; Estimation ou détermination des prix; Collecte de fonds
G06Q 30/06 - Transactions d’achat, de vente ou de crédit-bail
G06Q 50/00 - Systèmes ou procédés spécialement adaptés à un secteur particulier d’activité économique, p.ex. aux services d’utilité publique ou au tourisme
48.
SYSTEM AND METHOD FOR APPROXIMATING BRANCHING OPERATIONS FOR USE WITH DATA ENCRYPTED BY FULLY HOMOMORPHIC ENCRYPTION (FHE)
Systems and methods that approximate and use branching operations on data encrypted by fully homomorphic encryption (FHE). The systems and methods may use polynomial approximation to convert "if" statements into "soft if" statements that may be applied to the FHE encrypted data in a manner that preserves the security of the systems and methods.
In one embodiment a finite rank deep kernel learning method includes: receiving a training dataset; forming a plurality of training data subsets from the training dataset; for each respective training data subset of the plurality of training data subsets: calculating a subset- specific loss based on a loss function and the respective training data subset; and optimizing a model based on the subset-specific loss; determining a set of embeddings based on the optimized model; determining, based on the set of embeddings, a plurality of dot kernels; combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.
Certain aspects of the present disclosure provide techniques for performing finite rank deep kernel learning. In one example, a method for performing finite rank deep kernel learning includes receiving a training dataset; forming a set of embeddings by subjecting the training dataset to a deep neural network; forming, from the set of embeddings, a plurality of dot kernels; linearly combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.
A method and system automatically and dynamically creates routes between message dropboxes in separate data center infrastructures. The method and system determines that a first message dropbox in a first data center infrastructure is routable to a second message dropbox in a second data center infrastructure based on the names or policies of the first and second message dropboxes. After routability is determined, the method and system automatically creates and implements a route between the first and second message dropboxes in real time.
Known fraudulent invoice data, including defined and known fraudulent invoice feature data, is used to train a machine learning-based fraudulent invoice detection model to generate a fraudulent invoice score for invoices indicating a determined probability that a given invoice is fraudulent. The machine learning-based fraudulent invoice detection model is then used to generate a fraudulent invoice score for subsequent invoices before those invoices are paid by, and in some cases before the invoices are provided to, the parties being asked to pay the invoices. The fraudulent invoice score for the subsequent invoice is then used to determine if the subsequent invoice should be passed on to the parties being asked to pay the invoices for payment, or if one or more protective actions should be taken.
G06F 40/40 - Traitement ou traduction du langage naturel
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
Arbitrary image data may be transformed into data suitable for optical character recognition (OCR) processing. A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate at least one text proposal using a region proposal network (RPN). The at least one text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may merge the text proposals with one another to form a patch of the image that is predicted to contain text. The processor may determine outer coordinates of the patch. The outer coordinates may comprise at least leftmost, rightmost, topmost, and bottommost coordinates. The processor may generate a quadrilateral of the image that is a smallest quadrilateral including the leftmost, rightmost, topmost, and bottommost coordinates.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
G06K 9/32 - Alignement ou centrage du capteur d'image ou de la zone image
G06K 9/34 - Découpage des formes se touchant ou se chevauchant dans la zone image
G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
54.
ANOMALY DETECTION AND CLUSTERING IN FINANCIAL DATA CHANNEL MIGRATION
A method and system determines whether or not a new data acquisition process is working for individual financial accounts of users of a data management system. The method and system trains an analysis model with a machine learning process. The trained analysis model then analyzes financial data obtained by both an old data acquisition process and the new data acquisition process. The trained analysis model identifies whether the new data acquisition process is working properly based on the analysis.
A method and system trains, with a machine learning process, an analysis model to detect anomalous behavior of tax professionals affiliated with a tax return preparation system. The analysis model is trained with a training set that includes contextual and behavioral data for a plurality of historical tax professionals. The trained analysis model then analyzes and generates risk scores for current tax professionals based on current behavioral and contextual data associated with the current tax professionals.
Customer transaction data is processed to determine transaction locations for transactions, including transactions whose locations are not initially known. The transaction location data is then utilized to identify merchants that are mobile merchants, and the mobile merchant locations are periodically recalculated and tracked. Customer transaction data is further utilized to identify relationships between mobile merchants and customers of those mobile merchants. Merchant and customer data is also analyzed to identify potential customers of mobile merchants, and data related to the mobile merchants is provided to current and potential customers of those mobile merchants.
Certain aspects of the present disclosure provide techniques for entering user credentials through a proxy. One example method generally includes receiving, at a user device, a push request for user data from a cloud server and receiving a request file from an aggregation system. The method further includes injecting user credentials stored on the user device into the request file, wherein when injected the user credentials replace at least one dummy entry of the request file, and transmitting the request file to a data source associated with the request file. The method further includes receiving user data from the data source and transmitting the user data to the aggregation system.
Certain aspects of the present disclosure provide techniques for providing a diagnostics framework for large scale hierarchical time series forecasting models. In one embodiment, a method includes providing a plurality of hierarchical time-series, each of the plurality of hierarchical time-series comprising node data; concurrently providing node data from the plurality of hierarchical time-series to a forecasting model; using the forecasting model, concurrently calculating a plurality of forecasting data corresponding to each one of the node data of the plurality of hierarchical time-series; concurrently calculating a plurality of performance metrics of the forecasting model using the plurality of forecasting data; and generate an updated forecasting model by modifying the forecasting model based upon the plurality of performance metrics; concurrently calculating a plurality of updated forecasting data corresponding to each one of the node data using tire updated forecasting model; and provide the updated forecasting data to a user.
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
A computer-implemented method is provided to perform text classification with a neural network system. The method includes providing a computing device to receive input datasets including user input question text and feed the datasets to the neural network system. The neural network system includes one or more neural networks configured to extract and concatenate character-based features, word-based features from the question datasets and clickstream embeddings of clickstream data to form a representation vector indicative of the question text and user behavior. A representation vector is fed into fully connected layers of a feed-forward network. The feed-forward network is configured to predict a first class and a second class associated with respective user input questions based on the representation vector.
A processor may generate a plurality of intermediate feature layers of an image using convolutional neural network (CNN) processing. For each intermediate feature layer, the processor may generate a plurality of text proposals using a region proposal network (RPN). Each text proposal may comprise a portion of the intermediate feature layer that is predicted to contain text. The processor may perform OCR processing on image data within a plurality of regions of the image to generate a text result for each region. Each region may comprise at least one of the text proposals. The processor may assemble the text results into a text string comprising the text results ordered according to a spatial order in which the plurality of regions appear within the image.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
G06K 9/32 - Alignement ou centrage du capteur d'image ou de la zone image
G06K 9/34 - Découpage des formes se touchant ou se chevauchant dans la zone image
G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
61.
METHOD AND SYSTEM FOR USING TEST DEPOSITS TO DETECT UNLISTED ACCOUNTS ASSOCIATED WITH USERS OF A DATA MANAGEMENT SYSTEM
Test deposit mechanisms used by financial institutions to link accounts are used to identify undisclosed accounts associated with users of a data management system. The potential existence of undisclosed accounts is determined based on the assumption that the presence of test deposit transactions in user account data is a strong indication that an undisclosed user account exists. Using this assumption, transaction data from user accounts disclosed to a user data management system is scanned to identify test deposit transactions listed in the transaction data. If test deposit transactions are identified, the user of the data management system is queried regarding the existence of the undisclosed user account. If the user confirms the existence of the undisclosed account, the formally undisclosed account is added to a set of disclosed user accounts with the data management system.
Machine learning-based anomaly detection methods are used to identify a change in a users streaming transaction data. If a threshold level of change in the user's transaction data is detected, the user is then identified as potentially having experienced a life event. Then, after a user is identified has having potentially experienced a life event, individual user transactions are processed and analyzed to determine the specific life event the user has most likely experienced. The user is then identified as having experienced the identified specific life event. This information is then used to customize the interactions between the user and the data management system such as questions asked of the user, forms or displays provided to the user, or offers made to the user.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
A transceiver of a mobile device may receive a beacon transmitted by a mesh network member mobile device. A processor of the mobile device may extract a crew ID from the beacon. The processor may determine that the crew ID matches a crew ID of a user logged into the mobile device. In response to determining that the crew ID matches the crew ID of the user, the processor may generate a reply beacon. The transceiver may transmit the reply beacon. The transceiver may receive a response to the reply beacon. The response may include a job ID enabling the user to clock into a job. The processor may clock the user into the job. As a result of clocking the user into the job, the mobile device may become a member of the mesh network.
At least one processor of a central authority separate from a computing process may establish a first trust relationship between the computing process and a central authority separate from the computing process. The establishing may include authenticating the computing process, which may include providing a signed token to the computing process, receiving a request for the certificate from the computing process including the signed token and policy ID data, determining that the computing process is eligible for the certificate according to a policy that associates the certificate with the policy ID data, and validating the signed token. In response to the establishing, the at least one processor may obtain the certificate. The certificate may be signed by a third party certificate authority with which the central authority has a second trust relationship separate from the first trust relationship. The at least one processor may provide the certificate to the computing process.
A processor may obtain financial data for a user. The processor may process the financial data to generate feature data indicative of at least one feature. The processor may compare the at least one feature to at least one threshold value to determine that the user has a cognitive bias affecting a financial preference of the user and associated with the at least one threshold value. The at least one threshold value may denote a threshold for membership in a cluster of unlabeled users having the cognitive bias. In response to the comparing, the processor may identify a change applicable to a financial account of the user. The change may be associated with the cognitive bias. The processor may automatically cause the change to be implemented by a network-accessible financial service.
Certain aspects of the present disclosure provide techniques for automatically guiding transaction performance. Embodiments include receiving first input from a first user identifying a term of a transaction between the first user and a second user. Embodiments include receiving second input from the second user confirming the term. Embodiments include deploying a smart contract that corresponds to the term on a hash chain. The smart contract may comprise a program that guides performance of the term, and the hash chain may be resistant to modification. Embodiments include receiving, from a management component of the hash chain, a notification that the smart contract has verified through a trusted authority that the term is satisfied.
G06Q 20/38 - Architectures, schémas ou protocoles de paiement - leurs détails
G06Q 20/06 - Circuits privés de paiement, p.ex. impliquant de la monnaie électronique utilisée uniquement entre les participants à un programme commun de paiement
G06Q 20/40 - Autorisation, p.ex. identification du payeur ou du bénéficiaire, vérification des références du client ou du magasin; Examen et approbation des payeurs, p.ex. contrôle des lignes de crédit ou des listes négatives
H04L 9/32 - Dispositions pour les communications secrètes ou protégées; Protocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
Certain aspects of the present disclosure provide techniques for performing computations on encrypted data. One example method generally includes obtaining, at a computing device, encrypted data, wherein the encrypted data is encrypted using fully homomorphic encryption and performing at least one computation on the encrypted data while the encrypted data remains encrypted. The method further includes identifying a clear data operation to perform on the encrypted data and transmitting, from the computing device to a server, a request to perform the clear data operation on the encrypted data, wherein the request includes the encrypted data. The method further includes receiving, at the computing device in response to the request, encrypted output from the server, wherein the encrypted output is of the same size and the same format for all encrypted data transmitted to the server.
A method for loading objects from hash chains. A version chain of a class for a serialized object is located in an instance block of an instance chain. A class version of the serialized object is compared to a current version of the class. When the class version of the serialized object matches the current version of the class, a runtime object is loaded by deserializing the serialized object. When the class version of the serialized object does not match the current version of the class: one or more field values are extracted from the serialized object; a converter function is applied to the one or more field values to generate one or more converted field values; and a runtime object that matches the current version is loaded with the one or more converted field values.
A method for hash chain migration includes detecting a version update of an object that includes a hash chain that stores fields of the object. Sub chains are identified from the hash chain. Migration sub chains are generated from the plurality of sub chains using a plurality of processes. Container blocks are generated from the plurality of migration sub chains. A migration chain is generated from the plurality of container blocks. The object is accessed using the migration chain.
A system and method for providing and maintaining irrefutable proof of the building, testing, deployment and release of a software product. The system and method provide a secure, immutable electronic ledger to be accessed by various services and systems during the software product's development and release cycle. The ledger may be implemented using electronic blocks linked together via cryptography.
Certain aspects of the present disclosure provide techniques for interacting with a graph database structure. In one embodiment, a method includes receiving, at an application, information regarding a first entity; transmitting, to a graph database, a query regarding the first entity; receiving, at the application, query results based on one or more relationships between the first entity and other entities in the graph database; making, by the application, an inference based on the query results; modifying, by the application, a user interface of the application based on the inference by displaying at least one user interface element suggesting a selection of an application option; and receiving, by the application, a user selection of the suggested application option.
G06Q 20/02 - Architectures, schémas ou protocoles de paiement impliquant un tiers neutre, p.ex. une autorité de certification, un notaire ou un tiers de confiance
Certain aspects of the present disclosure provide techniques for generating a unified knowledge graph. In one example, a method includes receiving entity data from a data source comprising a plurality of entities; forming a plurality of type-specific groups of entity data based on the received entity data; for each respective type-specific group of entity data of the plurality of type-specific groups of entity data: disambiguating the entity data within the respective type- specific group of entity data; creating a plurality of entity relationships based on the disambiguated entity data; and exporting the plurality of entity relationships to a type-specific subgraph; and forming a unified knowledge graph based on a plurality of type-specific subgraphs, wherein each type-specific subgraph of the plurality of type-specific subgraphs is associated with a single type-specific group of entity data of the plurality of type-specific groups of entity data.
Certain aspects provide techniques for disambiguating graph data. In one example, a method includes receiving entity data from a data source in a first format; converting the entity data in the first format to a second format, wherein the second format is a standardized input format for a disambiguation pipeline; determining a blocked data set from the entity data in the second format based on a blocking parameter, wherein: the blocked data set comprises data regarding a first plurality of entities, and the first plurality of entities is a subset of a second plurality of entities represented in the entity data from the data source; matching at least two entities in the first plurality of entities in the blocked data set; merging the at least two entities into a single entity; generating a unique ID for the single entity; and importing the single entity into a graph database.
A system and method for extracting data from a piece of content using spatial information about the piece of content. The system and method may use a conditional random fields process or a bidirectional long short term memory and conditional random fields process to extract structured data using the spatial information.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
75.
SUPERVISED MACHINE LEARNING ALGORITHM APPLICATION FOR IMAGE CROPPING AND SKEW RECTIFICATION
Systems and methods here may be used for pre-processing images, including using a computer for receiving a pixelated image of a paper document of an original size, downscaling the received pixelated image, employing a neural network algorithm to the downscaled image to identify four comers of the paper document in the received pixelated image, re-enlarging the downscaled image to the original size, identifying each of four comers of the paper document in the pixelated image, determining a quadrilateral composed of lines that intersect at four angles at the four comers of the paper document in the pixelated image, defining a projective plane of the pixelated image, and determining an inverse transformation of the pixelated image to transform the projective plane quadrilateral into a right angled rectangle.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
G06K 9/32 - Alignement ou centrage du capteur d'image ou de la zone image
76.
SYSTEM AND METHOD FOR INFORMATION EXTRACTION WITH CHARACTER LEVEL FEATURES
A system and method for information extraction character level features. The system and method may be used for data extraction for various types of content including a receipt or a tax form.
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
Forecasts are provided based on dynamic model selection for different sets of time series. A model comprises a transformation and a prediction algorithm. Given a time series, a transformation is selected for the time series and a prediction algorithm is selected to make a forecast based on the transformed time series. Sets of time series are distinguished from each other based on diverse sparsities, temporal scales and other time series attributes. A model is dynamically selected based on time series attributes to increase forecasting accuracy and decrease forecasting computation time. The dynamic model selection is based on the creation of a meta-model from historical sets of historical time series.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
Aspects of the present disclosure provide techniques for efficient location tracking. Embodiments include receiving a device location from a mobile device. Embodiments include identifying a plurality of region definitions and selecting a set of region definitions from the plurality of region definitions based on a proximity of a location of each region definition of the plurality of region definitions to the device location. Embodiments include generating a provisional region definition based on a location of a region definition of the set of region definitions that is farthest from the device location and including the provisional region definition m the set of region definitions. Embodiments include providing the set of region definitions to the mobile device for provisioning and refraining from requesting device locations from the mobile device until receiving a notification from the mobile device that the mobile device has exited a provisional region defined by the provisional region definition.
A method to predict a delay involves receiving an open invoice sent by a company to a customer, extracting, using a programmable interface, a set of company data, a set of customer data, and a set of invoice data from a management application (MA) and the open invoice; refining, using a set of algorithms, the set of company data, the set of customer data, and the set of invoice data into a set of invoice attributes, a set of company features, and a set of customer features; predicting a delay in processing the open invoice using a trained model analyzing the set of company features and the set of customer features: updating, at an expiration of a predetermined timespan, the MA to add the delay to a due date of the open invoice by including the set of company features: and updating, at the expiration of the predetermined timespan, the MA to add the delay in processing the open invoice by including the set of customer features.
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
A method for storing object state on hash chains. A block of a hash chain is located with an accessor function. The block includes a field value of a field of an object. Version data is located using the block. The version data identifies a block version of the block. The block version is compared to a function version of the accessor function. The field value from the block is returned when the block version matches the function version. A version matched accessor function is called to return the field value when the block version does not match the function version.
A method for storing object state on hash chains. A read request that includes a received field name is received by an object with a plurality of fields. A field value that corresponds to the received field name is retrieved from a hash chain of the object by traversing the hash chain. A block is found that includes the field value from the plurality of field values that corresponds to the received field name. A response to the read request that includes the field value is generated and transmitted·
Detect duplicated questions using reverse gradient adversarial domain adaptation includes applying a general network to multiple general question pairs to obtain a first set of losses, A target domain network is applied to multiple domain specific network pairs to obtain a second set of losses. Further, a domain distinguishing network is applied to a set of domain specific questions and a set of general questions to obtain a third set of losses. A set of accumulated gradients is calculated from the first set of losses, the second set of losses, and the third set of losses. Multiple features are updated according to the set of accumulated gradients to train the target domain network.
Certain aspects of the present disclosure provide techniques for displaying sentiment of a user text comment. One example method generally includes receiving a text comment comprising a sequence of words, providing a vector sequence representing the sequence of words to a sentiment model configured to output a sequence of sentiment scores for the vector sequence and providing cleaned text to a topic module configured to output relevance scores. The method further includes receiving, from the sentiment model, the sequence of sentiment scores for the vector sequence and receiving, from the topic module, the relevance scores for the cleaned text. The method further includes determining, final sentiment scores for each word of the sequence of words and generating a sentiment visualization for the sequence of words showing the final sentiment scores corresponding to each word of the sequence of words.
One or more embodiments are directed to identifying documents with topic vectors by training a machine learning model with a training documents generated from text collections, receiving, after generating a list of topic vectors for the plurality of text collections, an additional text collection, and generating an additional topic vector for the additional text collection without training the machine learning model on the additional text collection. One or more embodiments further include updating the list of topic vectors with additional topic vectors that includes the additional topic vector, receiving a first topic vector based on a first text collection generated in response to user interaction, and matching the first topic vector to the additional topic vector. One or more embodiments further include presenting a link corresponding to the additional text collection in response to matching the first topic vector to the additional topic vector.
A processor of a central authority separate from a client and a service provider may receive an access request from the client. The access request may identify at least one of a client user and a client process. The processor may evaluate the access request to determine that the at least one of the client user and the client process complies with an access policy for the service provider. In response to determining that the at least one of the client user and the client process complies with the access policy, the processor may generate a credential including a key. The processor may send the credential to the client. The processor may receive the credential from the service provider. The processor may validate the key included in the credential. In response to the validating, the processor may cause the service provider to provide the client with access to the service.
Certain aspects of the present disclosure provide techniques for performing finite rank deep kernel learning. In one example, a method for performing finite rank deep kernel learning includes receiving a training dataset; forming a set of embeddings by subjecting the training data set to a deep neural network, forming, from the set of embeddings, a plurality of dot kernels; combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.
A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.
G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
G06F 16/338 - Présentation des résultats des requêtes
G06F 16/38 - Recherche caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
A processor of a remote crypto cluster (RCC) may obtain an encrypted specific key from at least one data source through at least one network. The processor of the RCC may derive intermediate data in blind based on the encrypted specific key. The intermediate data may include information from which a derived key is derived. The processor of the RCC may send the intermediate data in blind to a client device.
A method may include generating a source transaction description, encoding, by an encoder model of a machine translation model executing on a computer processor, the source transaction description to create a context vector, decoding, by a decoder model of the machine translation model, the context vector to predict a target entity description, generating a transaction including the target entity description, detecting an acceptance, by a user, of an action performed on the transaction, in response to detecting the acceptance, updating a translation accuracy metric for the target entity description, determining that the updated translation accuracy metric satisfies a translation accuracy criterion, and in response to determining that the updated translation accuracy metric satisfies the translation accuracy criterion, adding the target entity description to golden entity descriptions.
G06Q 20/38 - Architectures, schémas ou protocoles de paiement - leurs détails
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projets; Planification d’entreprise ou d’organisation; Modélisation d’entreprise ou d’organisation
90.
METHOD AND SYSTEM FOR USER DATA DRIVEN FINANCIAL TRANSACTION DESCRIPTION DICTIONARY CONSTRUCTION
A method and system identify characteristics of financial transaction description strings. The method and system trains a dictionary generation model with a machine learning process to classify financial transaction description strings. The dictionary generation model generates a dictionary that indicates key substrings from the financial transaction description strings that were most predictive in classifying the financial transaction description strings.
A method that involves receiving budget information of a containerized application deployed with a set of containers to a first cloud provider service of a set of cloud provider services; receiving pricing information from each cloud provider service of the set of cloud provider services, wherein the set of cloud provider services includes the first cloud provider service and a second cloud provider service; receiving performance information of the containerized application from the first cloud provider service; generating an output vector from a machine learning model, wherein the machine learning model uses the pricing information and the performance information to generate the output vector; determining a first cloud provider service cost and a second cloud provider service cost based on the output vector and the pricing information; migrating the containerized application from the first cloud provider service to the second cloud provider service.
A method is disclosed. The method includes: obtaining, from a management application, a login history including timestamps and internet protocol (IP) addresses corresponding to logins by a user; obtaining coordinates for the IP addresses; determining clusters for the coordinates based on distances between the coordinates; and determining primary locations for the user based on the clusters and the timestamps.
An invisible light sensing device senses invisible light from a plurality of invisible light emitting or reflecting objects in which each of the invisible light emitting or reflecting objects emits or reflects invisible light in an identification pattern that is distinct from other identification patterns. An identification pattern is based on a sequenced pulsing pattern of invisible light that is emitted by an invisible light emitting object to form the identification pattern. An identification pattern is also based on an invisible light reflective coating that is applied to an invisible light reflecting object.
G06K 7/10 - Méthodes ou dispositions pour la lecture de supports d'enregistrement par radiation corpusculaire
G06K 19/06 - Supports d'enregistrement pour utilisation avec des machines et avec au moins une partie prévue pour supporter des marques numériques caractérisés par le genre de marque numérique, p.ex. forme, nature, code
94.
SYSTEM AND METHOD FOR PROVIDING CUSTOMER SPECIFIED WEBPAGE CONFIGURATION
A method and system provide reduced and personalized versions of webpages to users lacking sufficient computing resources to load the full versions of the webpages in a satisfactorily short amount of time. The method and system receives a request from a user to access a webpage, analyze the computing resources of the user, and determine whether the user is able to load the full version of the webpage quickly. If the user is able to load the full version of the webpage quickly, then the method and system outputs the full version of the webpage to the user. If the user is unlikely able to load the full version of the webpage quickly, then the method and system outputs a reduced version of the webpage retaining the portions most likely to be relevant to the user based on an analysis of user data related to the user.
A method that involves receiving budget information of a containerized application deployed with a set of containers to a set of machine instances; receiving pricing information of a list of machine instance types; receiving performance information of the set of containers; receiving an alert generated based on the performance information by comparing the performance information to a set of thresholds; generating, after receiving the alert, an output vector from a machine learning model, wherein the machine learning model uses the performance information; and adjusting a resource of the set of containers by updating a parameter based on the output vector in response to the alert, wherein the resource is controlled by the parameter, and wherein the parameter is identified in the alert.
An invisible light sensing device senses invisible light from a plurality of invisible light emitting objects in which each of the invisible light emitting objects emits invisible light in an identification pattern that is distinct from other identification patterns. An identification pattern is based on one or more apertures through which invisible light is emitted to form the identification pattern. An identification pattern is also based on a plurality of invisible light emitters in which at least a portion of the invisible light emitters are positioned and activated to form the identification pattern.
G06K 7/10 - Méthodes ou dispositions pour la lecture de supports d'enregistrement par radiation corpusculaire
G06K 19/06 - Supports d'enregistrement pour utilisation avec des machines et avec au moins une partie prévue pour supporter des marques numériques caractérisés par le genre de marque numérique, p.ex. forme, nature, code
A method including receiving a source file containing a plurality of documents which, to a computer, initially are indistinguishable from each other. A first classification stage is applied to the source file using a convolutional neural network image classification to identify source documents in the multitude of documents and to produce a partially parsed file having a multitude of identified source documents. The partially parsed file includes sub-images corresponding to the plurality of identified source documents. A second classification stage, including a natural language processing artificial intelligence, is applied to sets of text in bounding boxes of the sub-images, to classify each of the multitude of identified source documents as a corresponding sub-type of document. Each of the sets of text corresponding to one of the sub-images. A parsed file having a multitude of identified sub-types of documents is produced. The parsed file is further computer processed.
G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
Certain aspects of the present disclosure provide techniques for determining an identity of a user requesting access to a resource. An example technique for determining the identity of the user includes, upon receiving a request for a resource, determining the identity assurance strength of the user. The determination of the identity assurance strength of the user is based on personal identifying information, risk signals, user history, and the like. If the user does not have the requisite identity assurance strength to access a resource, based on policy criteria, an identity proofing operation may be determined for the user to complete in order to access the resource, where the operation is determined based on policy criteria, risk signals, and the like. Upon completion of the identity assurance operation, if the user has adequate identity assurance strength, then the user may access the resource.
G06F 21/50 - Contrôle des usagers, programmes ou dispositifs de préservation de l’intégrité des plates-formes, p.ex. des processeurs, des micrologiciels ou des systèmes d’exploitation
The invention relates to a method for documenting subjects using hash chains. The method includes receiving a subject data write request including one or more subject attribute values, generating a fingerprint from a current last block of a hash chain, and generating a payload from the subject data, the payload including the one or more subject attribute values and one or more keys identifying the one or more subject attribute values. The method further includes appending a block to the hash chain. The appended block includes the payload and the fingerprint.
Aspects of the present disclosure provide techniques for displaying reduced data sets based on pre-classification of a larger data set. Embodiments include receiving a plurality of activity records describing a plurality of activities associated with the user. Embodiments further include grouping the plurality of activities into one or more pre-classified data sets based on the plurality of activity records. Embodiments further include providing the user with a summary of a pre-classified data set of tire one or more pre-classified data sets via a user interface. Embodiments further include providing the user, via the user interface, with a user interface element that allows the user to categorize all activities in the pre-classified data set together based on the summary. Embodiments further include receiving input from the user via the user interface, the input assigning a category to all activities in the pre-classified data set together based on the summary.