A computer-implemented method comprises obtaining an electronic claim record comprising claim data describing damage to a vehicle; selecting one or more of an obtained plurality of electronic vehicle diagnostic records by applying the records and claim data as inputs to a trained machine learning model, wherein responsive to the inference input the trained machine learning model selects one or more of the records; obtaining a vehicle repair estimate data structure having a plurality of fields; populating the fields of the vehicle repair estimate data structure with at least one of the claim data and the vehicle data from the selected one or more electronic vehicle diagnostic records; and generating a user interface for presentation to a user on a user device, wherein the user interface includes display elements that represent the populated fields of the generated vehicle repair estimate data structure.
A computer-implemented method comprises receiving an image of a vehicle having damage to a first exterior body panel; providing the image to one or more trained machine learning models that are configured to identify a first region of the first exterior body panel to be repaired and a second region to be paint-blended, when the second region contains a second exterior body panel of the vehicle other than the first exterior body panel, generating an exterior body panel repainting list that includes the identification of the first exterior body panel of the vehicle and the identification of the second exterior body panel of the vehicle; querying a repainting cost database using the exterior body panel repainting list; and receiving a repainting cost estimate from the repainting cost database responsive to the querying.
A computer-implemented method comprises obtaining an image of a first damaged vehicle; selecting a set of images of second damaged vehicles that are similar to the first damaged vehicle; finding a set of images of the second vehicles showing damage similar to the damage to the first vehicle; obtaining a set of vehicle repair claims corresponding to the set of one or more images of the second vehicles; adding a selected subset to a repair estimate data structure; presenting a user interface that represents the selected subset of line items; receiving first user input that represents line items chosen by the user; generating a vector that represents the chosen line items; and applying the vector to a trained machine learning model, wherein the trained machine learning model outputs a refined subset of line items.
A computer-implemented method comprises: generating a user interface operable by a user to generate one or more vehicle repair estimate lines for repairing a damaged vehicle and/or request an automated review of the line(s); generating one or more first vehicle repair estimate lines, adding the one or more first vehicle repair estimate lines to a vehicle repair estimate data structure, and presenting a first view of the data structure in the user interface; obtaining images of the damaged vehicle, providing the images to one or more trained machine learning (ML) models, which provide first output comprising second vehicle repair estimate lines for the vehicle repair estimate, adding second vehicle repair estimate lines to the data structure, and presenting a second view of the data structure in the user interface; and generating a vehicle repair estimation document based on the vehicle repair estimate data structure.
Systems and methods are provided for a dynamic and iterative process for determining a weighted decision using a combination of weighted output from multiple, trained machine learning (ML) models. Key data can be identified and efficient decision-based processing can be achieved. In some examples, the system calculates a weighted decision of a repair or total loss determination for a motor vehicle, yet any industry or data set may be implemented with the use of the dynamic and iterative decision process.
Vehicle insurance claim data is categorized into a plurality of strata. The categorized vehicle insurance claim data is mapped to corresponding geographic regions and aggregated. When the number of samples in the aggregated data meets a sampling threshold size, the aggregated data is clustered into clusters based on certain criteria and sampled to generate component synthetic peer data sets. A synthetic peer data set is generated by applying a bootstrap aggregation machine learning algorithm on the plurality of component synthetic peer data sets. The performance of a target vehicle insurance company is analyzed by comparing target vehicle insurance claim data of the target vehicle insurance company with the synthetic peer data set. The results of the comparison between the target vehicle insurance claim data and the synthetic peer are presented in a graphical representation.
A method and computing apparatus for determining comprehensive vehicle information using an intelligent Vehicle Identification Number ("VIN") decoder process is described. The method and computing apparatus obtains OEM marketing data, OEM engineering data, parts catalog data, uses a machine learning algorithm to determine relational dependencies between the obtained OEM data and standard comprehensive vehicle configuration data to generate complete vehicle data using VIN.
Systems, non-transitory machine-readable storage media, and computer- implemented methods are provided for automated scheduling of vehicle repair reinspections. In general, one aspect disclosed features a computer- implemented method comprising: obtaining an appraisal schedule that includes a plurality of appraisal appointments for appraisers, wherein each appointment identifies one of the appraisers, a vehicle repair to be appraised; receiving a reinspection notification that identifies a vehicle repair to be reinspected, a vehicle repair facility, and a duration for the reinspection; identifying availabilities in the appraisal schedule; selecting one of the availabilities in the appraisal schedule according to a predetermined assignment profile; modifying the appraisal schedule to schedule the reinspection during the selected availability, and sending an electronic message to an electronic device associated with the corresponding vehicle repair facility, wherein the electronic message identifies the vehicle repair to be reinspected, and the time of selected availability for the reinspection.
9.
AUTOMATED SELECTION OF VEHICLE REPAIRS FOR REINSPECTION
Systems, non-transitory machine-readable storage media, and computer- implemented methods are provided for automated selection of vehicle repairs for reinspection. In general, one aspect disclosed features a computer-implemented method comprising: receiving a notification that a vehicle repair estimate for a vehicle has been submitted by a vehicle repair facility; responsive to receiving the notification, determining whether the vehicle repair facility has satisfied a quantitative vehicle repair re-inspection benchmark; responsive to determining the vehicle repair facility has not satisfied the vehicle repair re-inspection benchmark, determining whether the vehicle repair facility has satisfied a temporal vehicle repair benchmark for repair of the vehicle; and responsive to determining the vehicle repair facility has satisfied the temporal vehicle repair benchmark for repair of the vehicle, initiating a re-inspection of the vehicle.
Systems and methods are provided for integrating damage evidence with appraisal management system to create a unified user experience for improving a virtual damage appraisal process. The system may display a curated collection of evidence providing an overview of the vehicle and sections of a vehicle damaged during an adverse incident. A user may select a damaged section from a plurality of damaged sections to view damage evidence determined by machine learning algorithms to best reflect the selected damaged section may be displayed. The damage evidence may be displayed concurrently with vehicle part selection and repair line editing functionality in a configurable graphical user interface (GUI) of a virtual appraisal application. Additionally, the system may generate set of recommendations for repairing or replacing the damaged parts in the selected section. The user may add the recommendations to a repair estimate as repair estimate lines.
Systems and methods are provided for automating the process of cataloging repair documents published by Original Equipment Manufacturers (OEMs). The method determines a corresponding service repair vehicle for the OEM vehicle associated with eh repair documents. Further, the OEM repair instructions are associated with the one or more vehicle parts of a service repair vehicle identified in a repair estimate record. The method of cataloging repair procedures from various OEMs utilizes standardized naming conventions a database structure for uploading individual documents.
Systems and methods are provided for automating the process of determining non- reusable parts associated with replacement or repair of a primary part of a vehicle involved in a collision event. The primary parts to be repaired may be indicated in repair estimate record. Notably, replacement of some primary parts may require replacement of certain non-reusable parts (NRPs) that were not damaged during the collision event and are not identified as such. The method determines which NRPs are required to be replaced when repairing the primary damaged part by using repair documents specifying repair instructions for repairing the primary part. Further, the repair estimate record is updated to include the information related to the primary pars and their associated NRPs.
Vehicle repair workflow automation with natural language processing is disclosed. One computer-implemented method comprises: providing images of a damaged vehicle as first input to a computer vision machine learning model, wherein the computer vision machine learning model has been trained with images of other damaged vehicles and corresponding vehicle repair operations; receiving first output of the computer vision machine learning model responsive to the first input, wherein the first output represents a plurality of the vehicle repair operations; providing the first output of the computer vision machine learning model to a natural language processing (NLP) machine learning model, wherein the NLP machine learning model has been trained with vehicle repair content comprising a plurality of vehicle repair procedures; and receiving second output of the NLP machine learning model responsive to the second input, wherein the second output comprises a recommended one of the plurality of the vehicle repair procedures.
Systems and methods are provided for automating the process of mapping repair documents, published by Original Equipment Manufacturers (OEMs), to repair information provided in a repair estimate record. A baseline set of repair estimate records specifying one or more parts of a baseline vehicle and an associated set of repair documents specifying instructions for repairing the one or more parts of the baseline vehicle may be saved using a data categorization model in a mapping dataset. The repair documents associated with baseline set of repair estimate records which have been saved in the mapping dataset may then be used to automatically determine associations between another set of repair estimate records and corresponding repair documents.
Systems and methods for managing predictions for vehicle repair estimates are provided. A method includes providing one or more images of a damaged vehicle as input to a machine learning model, wherein the machine learning model has been trained with images of other damaged vehicles and corresponding vehicle operations, wherein each of the vehicle operations represents the repair or replacement of a vehicle component; receiving output of the machine learning model responsive to the input, wherein the output comprises a plurality of values each corresponding to one of a plurality of the vehicle operations; determining a confidence metric based on the values; making a comparison between the confidence metric and a confidence threshold value; and selecting the one of the plurality of the vehicle operations corresponding to the highest value as a predicted operation based on the comparison.
A vehicle repair estimating tool with near-real-time compliance is provided, In general, one aspect disclosed features a method comprising: providing a near- real-time view of a repair estimate record to a client device, the repair estimate record having one or more fields, receiving, from the client device, a data entry input to be applied to one of the fields of the repair estimate record, selecting, in near real time, one or more compliance rules related to the one of the fields responsive to receiving the data entry input, determining, in near real time, whether the data entry input is valid based on the selected one or more compliance rules, and when the data entry input is determined not to be valid, notifying the client device, in near real time, that the data entry input is not valid for the one of the fields.
A near-real-time collaborative vehicle repair estimating tool is provided. In general, one aspect disclosed features a system, comprising: a hardware processor; and a non- transitory machine-readable storage medium encoded with instructions executable by the hardware processor to perform a method comprising: providing at least one view of a repair estimate record to a plurality of client devices; receiving a revision of the repair estimate record from one of the client devices; generating a revised repair estimate record by revising the repair estimate record according to the received revision responsive to receiving the revision of the repair estimate record; and providing at least one view of the revised repair estimate record to the plurality of client devices in near real time with receiving the revision of the repair estimate record.
18.
METHODS FOR AUTOMATING CUSTOMER AND VEHICLE DATA INTAKE USING WEARABLE COMPUTING DEVICES
Systems and methods are provided for automating information intake process by generating intake instructions for display on a client computing device. A user may be directed to capture data that includes vehicle and owner information using a wearable computing device. Insurance claim information, including damage information, may be obtained based on the captured vehicle information. The damage information may be used to determine intake instructions for capturing the images or videos of the damage. The user may use the system in a handsfree manner by viewing intake instructions via a display of the wearable computing device which allows the user to view the intake instructions while capturing the intake information. Additionally, the user may use voice commands or gestures to control the display of intake instructions.
Automated vehicle repair estimation by preferential ensembling of multiple artificial intelligence functions is provided. A method comprises receiving, from each source of a plurality of the sources, a respective vehicle repair recommendation set for a damaged vehicle, wherein each vehicle repair recommendation set identifies a recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle; determining a respective source rank of each source from a plurality of the source ranks; generating a composite vehicle repair recommendation set that identifies the recommended vehicle repair operations in an order determined according to the source ranks of the respective sources; and providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems.
A computer-implemented method comprising: obtaining repair estimate data that describes a repair estimate for a damaged vehicle; extracting, from an oem repair procedure database according to the received repair estimate data, repair procedure data that describes repair procedures for the damaged vehicle; transmitting the extracted repair procedure data to at least one technician computing device; obtaining repair log data generated by the at least one technician computing device, wherein the repair log data describes one or more repairs performed upon the damaged vehicle; determining whether the repair procedures for the damaged vehicle have been satisfactorily performed based on the received repair log data and the extracted repair procedure data; sending an electronic approval message responsive to determining the repair procedures for the damaged vehicle have been satisfactorily performed; and sending an electronic disapproval message responsive to determining the repair procedures for the damaged vehicle have not been satisfactorily performed.
Automated vehicle repair estimation by adaptive ensembling of multiple artificial intelligence functions is provided. A method comprises receiving, from a plurality of sources, vehicle repair recommendation sets identifying recommended vehicle repair operations for damaged vehicle components; selecting, by a trained artificial intelligence function, one of the operations for each component based on a plurality of learned states; generating a composite vehicle repair recommendation set identifying the selected operation; providing the composite vehicle repair recommendation set to one or more claims management systems; and repeatedly retraining the trained artificial intelligence function by adjusting the learned states according to the vehicle damage objects received, and the corresponding composite vehicle repair recommendation generated, since the last retraining of the trained artificial intelligence function.
Automated vehicle repair estimation by voting ensembling of multiple artificial intelligence functions is provided. A method comprises receiving a plurality of vehicle repair recommendation sets, each identifying (i) at least one component of a damaged vehicle, (ii) a recommended vehicle repair operation for each identified component, and (iii) a score and/or confidence percentage for each operation; when a plurality of the sets identify recommended operations for one of the components, selecting the operation having the highest score, and unselecting the other operations for the component; generating a composite vehicle repair recommendation set, wherein the composite vehicle repair recommendation set identifies the selected recommended vehicle repair operation, and wherein the composite vehicle repair recommendation set does not identify the unselected recommended vehicle repair operation; and providing the composite vehicle repair recommendation set to one or more claims management systems.
Systems and methods are provided for generating repair procedures, which are displayed on a client computing device as a series of repair steps based on a determined order. A user may be directed to capture an image that includes vehicle identifying information or license plate number using a computer wearable device. The damage information, repair estimate information, and repair procedure information may be obtained based on the damaged vehicle information. Individual repair procedures and their order are determined by analyzing the damage information, repair estimate information, repair procedure information, diagnostic codes, and historical repair data. The user may use the system in a handsfree manner by viewing the repair procedures in a display of a computer wearable device which allows the user to view the repair information while performing the repairs. Additionally, the user may use voice commands or gesture to control the display of particular repair procedures.
Systems and methods are provided for automatically generating a repair estimate report for repairing a damaged vehicle. A user may be directed to capture data that includes vehicle information (e.g., VIN) and damage information (e.g., images of damaged panels and parts) using a computer wearable device based on intake instructions generated by the system. The damage information may be analyzed to obtain repair information. The repair estimate may be submitted to an insurance carrier and a notification specifying an approval or rejection may be generated. The user may use the system in a handsfree manner by viewing and/or listening to intake instructions, vehicle information, and the status of the repair estimate approval in a display and/or through speakers, respectively, of a computer wearable device.
A method, non-transitory computer readable medium, and an apparatus for automated estimation of repair data includes applying a first generated artificial intelligence model on a received vehicle damage image associated with an electronic claim to identify damaged component(s) on a vehicle without using any metadata. A heat map analysis is performed on the received actual vehicle damage image to identify a damage severity value associated with at least one of the identified damaged component(s). A second generated artificial intelligence model is applied on the received actual vehicle damage image and the damage severity value associated with the identified damaged component(s) to determine repair data and a repair-or-replace designation. The determined repair data and the determined repair-or-replace designation for at least one of the identified one or more damaged components is provided in response to the received actual vehicle damage image associated with the electronic claim.
A method, non-transitory computer readable medium, and apparatus that automated assessment of conditioning includes automatically analyzing one or more electronic images of a total loss property based on one or more prior condition assessments and condition guidelines rating data associated with the total loss property. A prior property conditioning of the total loss property is determined based on the analysis of the one or more obtained images. The determined prior property conditioning of the total loss property is provided.
A method, non-transitory computer readable medium and apparatus for providing predictive estimates of repair lines includes receives vehicle damage data including a plurality of images, videos, and vehicle diagnostic data. One or more damages are identified based on the received vehicle damage data. One or more repair parts data and labor data are determined for the identified one or more damages based on historical repair parts data and historical labor data. The determined one or more repair parts data and the labor data is provided via a graphical user interface.
28.
METHODS FOR ANALYZING INSURANCE DATA AND DEVICES THEREOF
Methods, non-transitory computer readable media, and computing apparatus that assist with analyzing data includes obtaining vehicle data from one of the plurality of data sources in a plurality of formats. The obtained vehicle data is aggregated based on one or more geographic locations obtained from one of the plurality of sources. A sampling threshold size is determined for sampling the aggregated vehicle data based on one or more threshold rules. One or more machine learning algorithms are applied to the aggregated vehicle data to generate sampling data when the aggregated vehicle data is greater than the determined sampling threshold size. The generated sampling data is represented in a graphical representation format via a graphical user interface.
A method, non-transitory computer readable medium and apparatus for vehicle valuation includes integrating with an insurance claim application executed by an agent device in response to a received electronic request for a claim for a vehicle. Automated valuation of the claim vehicle in the insurance claim application executed by an agent computing device is managed. Corresponding build sheet data from a build sheet data server device for the comparable vehicles and the claim vehicle based on a corresponding vehicle identifier for each is obtained. A comparable base value of each of the comparable vehicles to the claim vehicle is adjusted based on differences between the obtained build sheet data for each. A claim base value for the claim vehicle is determined based on the adjusted comparable base values for each of the identified comparable vehicles. The determined claim base value is set in the insurance claim application executed by the agent device.
A new automotive collision repair technology is provided, including system and data flow architectures that are designed to provide enhanced data and enhanced data flow in the context of vehicle diagnosis and repair, particularly when repairs are necessary due to collisions. In some examples, the data flow through the network is streamlined, to avoid network congestion, to use fewer computer and network resources and/or to enable the utilization of smaller databases. In other examples, enhanced access to data in real-time and near real-time enabled by a Workflow Module supports more accurate and timely decisions on vehicle repair. An advantage of this new automotive collision repair technology is that it enables proper and proven repairs, which in turns increases operation safety of repaired vehicle and people safety.
G06Q 10/20 - Administration of product repair or maintenance
B60S 5/00 - Servicing, maintaining, repairing, or refitting of vehicles
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
31.
SYSTEMS AND METHODS FOR USE OF DIAGNOSTIC SCAN TOOL IN AUTOMOTIVE COLLISION REPAIR
A new automotive collision repair technology is provided, including system and data flow architectures that are designed to provide enhanced data and enhanced data flow in the context of vehicle diagnosis and repair, particularly when repairs are necessary due to collisions. In some examples, the data flow through the network is streamlined, to avoid network congestion, to use fewer computer and network resources and/or to enable the utilization of smaller databases. In other examples, enhanced access to data in real-time and near real-time enabled by a Workflow Module supports more accurate and timely decisions on vehicle repair. An advantage of this new automotive collision repair technology is that it enables proper and proven repairs, which in turns increases operation safety of repaired vehicle and people safety.
ABSTRACT A new automotive collision repair technology is provided, including system and data flow architectures that are designed to provide enhanced data and enhanced data flow in the context of vehicle diagnosis and repair, particularly when repairs are necessary due to collisions. In some examples, the data flow through the network is streamlined, to avoid network congestion, to use fewer computer and network resources and/or to enable the utilization of smaller databases. In other examples, enhanced access to data in real-time and near real-time enabled by a Workflow Module supports more accurate and timely decisions on vehicle repair. An advantage of this new automotive collision repair technology is that it enables proper and proven repairs, which in turns increases operation safety of repaired vehicle and people safety. Date Recue/Date Received 2020-09-08
G06Q 10/20 - Administration of product repair or maintenance
B60S 5/00 - Servicing, maintaining, repairing, or refitting of vehicles
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
A method, non-transitory computer readable medium, and apparatus that improves automated damage appraisal includes analyzing one or more obtained images of property using a deep neural network with multiple hidden layers of units between an input and output and which has stored knowledge data encoded from one or more stored property damage images to identify which area of the property has damage. Damage data on an extent of the damage in the identified area of the property is determined using the deep neural network which has stored knowledge data encoded from one or more stored property damage images. The identified area of the property with the damage is mapped to one of a plurality of stored repair procedure templates to generate a list of one or more parts and one or more repair lines to make a repair. The generated data list for the identified area of the property with the damage is provided.