Capital One Services, LLC

Steven Dang

Chih-Hsiang Chow

Elizabeth Furlan

Douglas Slattery

Vijaya Pasam

Jason Gould

Jennifer Jiang

Christopher Akatsuka

Accident location data and present vehicle feature data may be obtained, wherein the accident location data indicates one or more locations associated with one or more vehicular accidents, and the present vehicle feature data indicates one or more sets of vehicle features. A set of prediction model parameters of a prediction model may be configured based on the accident location data and the present vehicle feature data for prediction of damage-reduction-related values associated with a set of available vehicle features. The prediction model may be used to determine one or more damage-reduction-related values based on first vehicle data indicating a first vehicle, a set of vehicle features available to the first vehicle, and a first geospatial location. A first set of features for the first vehicle may be generated based on the damage-reduction-related values.

Accident-data-based vehicle feature determination

An inquiry analysis system and method are disclosed. An inquiry analysis system includes a computer configured to receive an electronic communication from a user, the electronic communication comprising an inquiry associated with an article of interest. The inquiry analysis system determines one or more measures including a first result of a first trained model based on one or more content elements of the inquiry, a second result of a second trained model based on one or more sentiment elements of the inquiry, and a valuation divergence model result based on a comparison of the inquiry with a reference value associated with the article of interest. The inquiry analysis system calculates and outputs a composite interest prediction which predicts a level of interest of the user associated with the respective article of interest.

Automated inquiry analysis

According to certain aspects of the disclosure, a computer-implemented method may be used for providing a vehicle recommendation based on user gestures. The method may include displaying an image of a vehicle to a user and receiving at least one gesture from the user performed on the image of the vehicle. Additionally, the method may include assigning a value to the at least one gesture from the user and determining a feature of the vehicle based on the at least one gesture from the user. Additionally, the method may include receiving gesture information related to the at least one gesture and determining a vehicle preference of the user based on the value, the feature of the vehicle, and the gesture information. Additionally, the method may include identifying an available vehicle based on the vehicle preference of the user and displaying the available vehicle to the user.

Systems and methods for vehicle recommendations based on user gestures

Disclosed herein are various embodiments for a vehicle listing generation and optimization system. An embodiment operates by receiving a request to generate a vehicle listing to sell a vehicle on a website. A plurality of vehicle listings similar to the vehicle to be sold are determined, the plurality of vehicle listings including a plurality of features providing information about a respective vehicle featured in the vehicle listing and a performance metric indicating an effectiveness of a respective listing. A first cluster of listings from the plurality of vehicle listings similar to the vehicle are identified based on based on performing artificial intelligence clustering with respect to the metric. Common features amongst a subset of the first cluster of listings are identified. A user interface of a sales template for selling the vehicle associated with the request via the website is generated, wherein the sales template includes the common identified features.

Vehicle listing generation and optimization system

Systems, methods, and computer readable media for vehicular search recommendations using machine learning. A computing model may receive a query for a vehicular recommendation. The model may be trained based on historical queries, webpages visited, and attributes of vehicles. The model may generate a decision tree comprising a plurality of paths for processing the query, the plurality of paths comprising a subset of a plurality of available paths for processing the query, each path associated with a plurality of search phases. The model may select, based on the decision tree, a first path of the plurality of paths for processing the query. The model may select, based on the first path, a first search phase of the plurality of search phases as corresponding to the query. The model may then return a search result corresponding to the first search phase as responsive to the query.

Vehicular search recommendations using machine learning

In certain embodiments, access to a plurality of sites associated with a plurality of users may be obtained. The plurality of sites may comprise categories of the plurality of users and interactions among the plurality of users. Based on the plurality of sites, a plurality of interaction datasets and a plurality of timing datasets may be generated. The plurality of interaction datasets and the plurality of timing datasets may be provided as inputs to a machine learning model and the machine learning model may be configured based on the inputs. Subsequent to the configuration, an interaction dataset and a timing dataset associated with a user may be provided to the machine learning model. A predicted length of time for the user may be obtained via the machine learning model and one or more settings of a program may be configured to the user based on the predicted length of time.

Automated program access configuration based on interaction and timing data

Disclosed herein are system, method, and computer program product embodiments for detecting a potential damage caused to a vehicle when the vehicle is placed on a transporter. The method includes obtaining a first image and a second image taken at different time instances. The first image and the second image are generated by one or more cameras placed around a vehicle on a transporter, and cover a same portion of a body of the vehicle. The method further includes detecting a change between a portion of the first image corresponding to the portion of the body of the vehicle and a portion of the second image corresponding to the portion of the body of the vehicle indicative of a collision. Moreover, the method includes flagging a potential damage to the portion of the body of the vehicle based on the detected change between the first image and the second image.

Damage detection for vehicles on a transporter

An augmented reality system including processors and storage devices storing instructions. The instructions may configure the processors to perform operations including determining a location of a mobile device, identifying a facility based on the location, requesting mapping data from a facility server, the mapping data comprising a plurality of vehicles, vehicle location data, and landmarks, identifying one location attribute in a video feed captured by an augmented reality viewer displayed in the mobile device, and determining whether the one location attribute matches the plurality of vehicles or the landmarks. The operations may also include identifying qualified vehicles from the vehicles based on qualification criteria, determining whether the qualified vehicles is in a field of view of the augmented reality viewer based on object attributes and the vehicle location data, and generating a modified video feed by providing an indication associated with qualified vehicles in the field of view.

Systems and methods for augmented reality navigation

Aspects described herein may allow for generating a filter list to facilitate users to refine their online search. Data items displayed on a web page may be determined based on the user's input data, for example, based on a selection command selecting the data items. Each data item corresponds to a feature of a product. Filters corresponding to the data items may be determined and the weight of each filter may be updated. A filter list may be generated and displayed to facilitate the user to refine his search for a class of products. The filters on the filter list may be automatically ordered based on the weight of each filter. In this way, a user may be able to find filters that are associated with features that he cares about the most and therefore use the filter list to obtain more satisfying results.

Filter list generation system

A set of queries from an application executing on a client computing device is obtained. A first database based on the set of queries is searched to select a set of event types. A set of predicted parameters associated with the set of event types is sent to the application. The application includes instructions to obtain a first parameter and the set of predicted parameters via a user interface of the application and generate a message comprising the first parameter and an indicator identifying the set of predicted parameters. The first parameter and the indicator are obtained via the second message. A combined query including the first parameter and the set of predicted parameters is generated in response to obtaining the indicator. A vehicle record from the vehicle database is obtained based on the combined query. Values of the vehicle record are sent to the client computing device.

Query generation from event-based pattern matching

Aspects described provide systems and methods that relate generally to image analysis and, more specifically, identifying individual components and elements in an image. The systems and methods include a valuation application executing one or more application program interfaces (APIs) communicating with one or more websites via a network, where the user is prompted to enter information and/or take pictures or videos of their vehicle that they would like to sell. The valuation application utilizes a machine learning model to identify and value the various vehicle components within the images and videos. Based on the machine learning model, the valuation application identifies each component according to the images and videos and performs a search to determine the value of the components identified. The valuation application tabulates and summarizes the vehicle component resale values and resell information for the user to view.

Systems and methods for valuation of a vehicle

The disclosure describes a system and methods for implementing a recommendation engine. The recommendation engine can at least receive a travel history log, wherein the travel history log includes a route traversed by a customer; receive a route information from a database for the route, where the route information includes an accident history for the route; generate a route traverse percentage based on the travel history log; generate a route categorization score based on the accident history for the route and the route traverse percentage; and generate a vehicle recommendation based on the route categorization score.

Recommendation engine that utilizes travel history to recommend vehicles for customers

A computer-implemented method that includes receiving a request for a target vehicle including input data associated with an operator, a geographic location, and the target vehicle. The method includes determining a depreciation rate based on third-party transaction data retrieved from databases in accordance with the input data associated with the target vehicle, and a decommission rate based on third-party ownership data retrieved from databases in accordance with the input data associated with the target vehicle. The method includes determining a deterioration rate based on local environmental data retrieved from databases in accordance with the input data associated with the geographic location, and generating a regression model configured to compute an estimated value of the target vehicle during a lifetime of the target vehicle using the input data, depreciation rate, decommission rate, and deterioration rate. The method includes determining an output in response to the request for the target vehicle.

Systems and methods for estimating asset resale value

According to certain aspects of the disclosure, a computer-implemented method may be used for providing vehicle recommendations based on traffic camera data. The method may include acquiring traffic data from a plurality of traffic cameras and determining vehicle information based on the traffic data. Additionally, calculating average idling time of vehicles based on the traffic data from the plurality of traffic cameras. Additionally, determining accident information based on the traffic data from the plurality of traffic cameras and selecting at least one available vehicle for purchase, wherein the at least one available vehicle matches one or more predetermined requirements based on the determined vehicle information, average idling time, and the determined accident information. Additionally, transmitting a recommendation based on the selected at least one available vehicle for purchase.

Growing community of inventors

Plano, TX, United States of America

Steven Dang