Capital One Services, LLC

Walmart Apollo, LLC

Chi-san Ho

Micah Price

Yue Duan

Sunil Subrahmanyam Vasisht

Aamer Charania

Avid Ghamsari

Yogananda Domlur Seetharama

Rebecca Hummel

Rajasekhar Jetty

Jaehyuk Choi

Ieshan A Vaidya

Maheshwar Ramakrishnan

A computer-implemented method for providing a personalized interface to a user based on whether the user is serious about making a purchase may include: obtaining customer identification data and customer input data a customer, wherein the customer input data comprises a request from the customer; determining a request status of the customer based on the customer identification data and the customer input data; obtaining customer interface activity data of the customer based on the request status; obtaining customer purchasing data of the customer based on the request status; generating a prediction model based on the customer interface activity data and the customer purchasing data; training the generated prediction model by classifying the customer based on the customer interface activity data and the customer purchasing data; obtaining user identification data and user interface activity data of a user via a user device, the user interface activity data indicating interactive activities between the user and a user interface displayed on the user device; determining a rating of the user to purchase a product based on the user identification data, the user interface activity data, and the prediction model; and providing, to the user, an updated user interface on the user device based on the determined rating.

Methods and systems for updating a user interface based on level of user interest

Disclosed embodiments provide systems, methods, and computer-readable storage media for enhancing a vehicle identification with preprocessing. The system may comprise memory and processor devices to execute instructions for receiving an image depicting a vehicle. The image may be analyzed and first predicted identity and first confidence value may be determined. The first confidence value may be compared to a predetermined threshold. The processors may further select a processing technique for modifying the image and further analyze the modified image determining a second predicted identity of the vehicle. And a second confidence value may be determined. And the system may further compare the second confidence value to the predetermined threshold to select the first or second predicted identity for transmission to a user.

Systems and methods for enhancing real-time image recognition

A device receives user interface interaction data that identifies an interaction that a user has with an interface that displays an image of a vehicle. The device generates, by using a data model to process at least a portion of the image, an array of vectors that includes one or more vectors relating to vehicle characteristics of the vehicle. The device assigns one or more weights to the one or more vectors based on the user interface action data. The device determines, based on a similarity analysis, similarity scores that indicate similarities between the array of vectors that include the one or more vectors that have been weighted and other arrays relating to the vehicles depicted in the images. The device selects a subset of the images based on the similarity scores and causes the subset of the images to be displayed.

Vehicle inventory search recommendation using image analysis driven by machine learning

There are provided systems and methods for assisting consumers with merchandise purchases at a retail facility. The system may include an application to facilitate purchase of merchandise items at a retail facility, which may be executed on a user's mobile device. The application may receive input regarding items scanned at the retail facility using the mobile device and may facilitate payment for the scanned items by the mobile device. The system may also include a control circuit that: accesses database(s) to determine the user's purchase history; determines candidate items to be considered for recommendation to the user; computes a ranking of candidate items based on a weighted combination of recency and frequency of purchases of each candidate item, merchandise category of other candidate items, and price of the candidate item; and causes the display on the mobile device of additional recommended merchandise items for purchase by the user.

Systems and methods for assisting with merchandise purchases at a retail facility

A system for inspecting the reliability of an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: obtaining a plurality of images; categorizing the images into a plurality of image classes; calculating a plurality of probability outcomes; determining whether highest predicted probabilities of the images are less than a first threshold and whether an entropy of a predicted density of the probability outcomes exceeds a second threshold; indicating whether the image is associated with the image classes; ranking, the image amongst the plurality of images; filtering, a plurality of low reliability images according to a third threshold; providing, a likelihood of whether a user scanned a vehicle object associated with the image; and identifying a percentage of user scan failures.

Artificial intelligence system for inspecting image reliability

Systems and methods for clustering data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving, from a first client device, a classification data associated with a classification model and receiving feature data corresponding to the classification model output. The operations may include training a meta-model to predict the classification data based on the feature data and/or additional data associated with the classification data such as location data or environmental data. The operations may include generating a meta-model output based on the classification data, the feature data, and/or the additional data. The operations may include updating the classification model based on the meta-model output and transmitting the updated classification model to at least one of the first client device or a second client device.

Systems and methods for diagnosing computer vision model performance issues

Disclosed are systems and methods for displaying content on a user device. For example, a method of displaying content on a user device may include: receiving a first set of content data; arranging and displaying the first set of content in a first sequence of consecutive segments; detecting user input indicative of a scroll pattern of the user through the first sequence of consecutive segments; determining a preferred category based on the detected user input; receiving a second set of content data; arranging the second set of content data into a second sequence of consecutive segments based on the preferred category; and displaying the second set of content data in the arranged second sequence of consecutive segments on the display of the user device.

Methods and systems for displaying content based on a scroll pattern

Methods and systems are described herein for improvements for reducing client-server network traffic. For example, methods and systems allow for the reduction of client-server network traffic by altering search filters based on their respective rank and/or frequencies of being searched with other search filters included in a search query. In this way, users do not have to resubmit queries that are illogical or would return a null set of search results. For example, a first query may be received. A first search may be performed based on the first query. A first search filter may be selected based on a hierarchical tree structure of search filters. A second query may be generated comprising the first search filter and one or more other search filters, wherein the second query comprises fewer search filters than the first query, and a second search may be performed based on the second query.

System and method for reducing client-server network traffic for internet database queries

Disclosed are methods, systems, and non-transitory computer-readable medium for determining color labeling for a vehicle search service. For instance, the method may include: obtaining vehicle images for a plurality of vehicles; filtering the vehicle images to obtain exterior and/or interior images of the plurality of vehicles, determining super-pixel values for the exterior images and/or the interior images; generating a standard color mapping by associating the super-pixel values to standard color names; and storing searchable vehicle information at least based on the standard color mapping.

Methods and systems for determining color labeling for a vehicle search service

An apparatus for performing image searches including a camera, storage devices storing a set of instructions, and a processor coupled to the at least one storage device and the camera. The instructions configure the at least one processor to perform operations including identifying attributes of the captured image using a classification model; identifying first results based on the identified attributes; selecting a subset of first results based on corresponding probability scores, generating a first graphical user interface including interactive icons corresponding to first results in the subset, an input icon, and a first button. The operations may also include receiving a selection of the first button, performing a search to identify second results, and generating a second graphical user interface displaying the second results.

Systems and methods for presenting image classification results

Disclosed embodiments provide systems and user devices for enhancing vehicle identification with preprocessing. The systems or user devices may comprise at least one memory device, an augmentation tool, and at least one processor. The at least one processor may be configured to execute instructions to receive an image depicting a vehicle, analyze the image, and determine a first predicted identity of the vehicle and a first confidence value distribution. The at least one processor may further select a processing technique for modifying the image and analyze the modified image to determine a second predicted identity of the vehicle and a second confidence value distribution. The system may further compare the second confidence value distribution to a predetermined threshold or to the first confidence value distribution to select the first or second predicted identity for transmission to a user.

A system for generating graphical user interfaces. The system may include processors and storage devices storing instructions. The instructions may configure the one or more processors to perform operations including identifying a plurality of attributes from an image captured with a client device, identifying a plurality of first results based on the attributes, generating a first graphical user interface for display in the client device. The first graphical user interface may include a plurality of result icons corresponding to a subset of the first results having confidence scores above a threshold, a plurality of filter icons displaying options, and a search button. The operations may also include receiving a selection of at least one of the result icons or at least one of the filter icons, performing a search, based on the selection, and generating a second graphical user interface.

Systems and methods for generating graphical user interfaces

The present disclosure provides devices, systems and computer-readable media for identifying object characteristics using a machine learning model trained to de-emphasize brightness values. The machine learning model can be trained using modified training data. Modifying the training data can include converting the training data from an original color space into a color space having a brightness channel. The values of the brightness channel for the, training data can then be modified. After the values of the brightness channel are modified, the training data can be converted back into the original color space and used to train the machine learning model. A detection device can be configured with the machine learning model and used to identify object characteristics.

Growing community of inventors

Allen, TX, United States of America

Chi-san Ho