Abstract: A computer-implemented method for adjusting one or more electronic medical bills for a claimant injured in an accident comprises generating a user interface to be presented to a claims adjuster; receiving a first user input identifying a claimant; responsive to the first user input, retrieving and aggregating multiple electronic medical bills each having at least one line; generating one or more findings and multiple scenarios by providing the aggregated electronic medical bills as inference input to a trained machine learning model, wherein the trained machine learning model has been trained with historical electronic medical bills and corresponding findings and scenarios, wherein responsive to the inference input, the trained machine learning model outputs the one or more findings and the multiple scenarios, wherein the one or more findings represent rationales for approving, denying, or repricing, and wherein the multiple scenarios include cost estimates based on the one or more findings.

Abstract: 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.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response provides a predicted severity class indicating a severity of the physical damage sustained by the damaged vehicle during the collision event; providing the predicted severity class, damaged vehicle physical damage claim data related to the damaged vehicle and the collision event, and bodily injury claim data related to an occupant of the damaged vehicle during the collision event to a trained regression machine learning model, which in response provides a predicted frequency and/or duration of medical treatments to treat bodily injury sustained by the occupant during the collision event; and providing the predicted frequency and/or duration of medical treatments to an analyst for use in evaluating a bodily injury claim related to the occupant.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response provides indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators to a trained classifier machine learning model, which in response provides a predicted class of bodily injury sustained by an occupant of the damaged vehicle during the collision event and a confidence indicator representing a level of confidence that the predicted class of bodily injury is correct; and providing the predicted class of bodily injury and the confidence indicator to an analyst for use in evaluating a bodily injury claim related to the occupant of the damaged vehicle and the collision event.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response provides indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators of physical damage to a trained classifier machine learning model, which in response provides a predicted class of bodily injury sustained by an occupant of the damaged vehicle during the collision event and a confidence indicator representing a level of confidence that the predicted class of bodily injury is correct; determining a likelihood of attorney representation of the occupant concerning the bodily injury based on the predicted class of bodily injury; and providing the likelihood of attorney representation of the occupant to an analyst for use in evaluating a bodily injury claim related to the occupant.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, wherein responsive to the first inference input, which in response provides indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators to a trained classifier machine learning model, which in response provides predicted standard medical diagnostic codes related to bodily injury sustained by an occupant of the damaged vehicle during the collision event and confidence indicators representing levels of confidence that the one or more predicted standard medical diagnostic codes are correct; and providing the predicted standard medical diagnostic codes and the confidence indicators to an analyst for use in evaluating a bodily injury claim related to the occupant of the damaged vehicle and the collision event.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators, damage claim data related to the collision event, and bodily injury claim data related to an occupant of the damaged vehicle during the collision event to a trained regression machine learning model, which in response provides a projected cost to repair the damaged vehicle and a projected cost to treat bodily injury sustained by the occupant during the collision event, and providing the projected costs to an analyst for use in evaluating a bodily injury claim related to the occupant of the damaged vehicle and the collision event and a damaged vehicle physical damage claim related to the collision event.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response provides indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators to a trained classifier machine learning model, which in response provides a predicted likelihood that bodily injury was sustained by an occupant of the damaged vehicle during the collision event and a confidence indicator representing a level of confidence that the predicted likelihood that bodily injury was sustained is correct; and providing the predicted likelihood of bodily injury and the confidence indicator to an analyst for use in evaluating a bodily injury claim related to the occupant of the damaged vehicle and the collision event.

Abstract: A computer-implemented method comprises providing images and attributes of a damaged vehicle that has been damaged in a collision event to a trained computer vision machine learning model, which in response provides indicators of physical damage sustained by the damaged vehicle during the collision event; providing the indicators to a trained classifier machine learning model, which in response provides a predicted likelihood that bodily injury was sustained by an occupant of the damaged vehicle during the collision event and a confidence indicator representing a level of confidence that the predicted likelihood that bodily injury was sustained is correct; and providing the predicted likelihood of bodily injury and the confidence indicator to an analyst for use in evaluating a bodily injury claim related to the occupant of the damaged vehicle and the collision event.

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.

Abstract: 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.

Abstract: 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 the part of the vehicle that has sustained damage. Damage data on an extent of the damage in the identified part of the vehicle is determined using the deep neural network which has stored knowledge data encoded from one or more stored property damage images. The identified generic part of the vehicle is used to obtain a corresponding Part ID Code by using a parts dictionary. Part Qualifier information obtained using VIN information is then used in conjunction with the Part ID to obtain the OEM-specific part and then generate one or more repair lines for the repair estimate.

Abstract: Systems and methods are provided for automating the process of generating image metadata related to a vehicle and damage sustained by the vehicle during a collision event by using image analysis tools employing machine learning algorithms. The image with collision metadata renders the image capable of being analyzed using content-based searching.

Abstract: Systems and methods are provided for automating the process of generating image metadata related to a vehicle and damage sustained by the vehicle during a collision event by using image analysis tools employing machine learning algorithms. The image with collision metadata renders the image capable of being analyzed using content-based searching.

Abstract: 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 damaged part and may be used to determine one or more adjacent parts based on the vehicle information and the repair operation type.

Abstract: In some embodiments, a computer-implemented method comprises: storing associations between explanation codes and hierarchical ranks in a database; receiving a first electronic document representing an insurance claim comprising a line comprising a procedure code and at least two explanation codes; determining hierarchical ranks for the explanation codes by at least one of: applying the explanation codes to the database, and executing rules selected according to the explanation codes; determining, according to the determined hierarchical ranks, whether the line should be modified; modifying the line; ordering the explanation codes according to the hierarchical ranks; providing a user interface displaying the modified line with the ordered explanation codes and user-operable controls; adjusting the line responsive to user operation of the user-operable controls; and outputting a second electronic document representing the insurance claim after adjusting the line.

Abstract: 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.

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 a determination of relatedness likelihood of individual DTC, which in turn decreases costs and increases savings.

Abstract: 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.

Abstract: Automated vehicle repair estimation by aggregate ensembling of multiple artificial intelligence functions is provided. A method comprises receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle; aggregating a plurality of the recommended vehicle repair operations; generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations; and providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems.