Vehicle listing image detection and alert system
AssigneeCapital One Services, LLC
InventorsQiaochu Tang, Geoffrey Dagley, Micah Price, Avid Ghamsari, Jason Richard Hoover
Life of this patent
Estimating the term…
Abstract
An image error identification system retrieves an image associated with a vehicle listing and uses various machine learning models to classify the image and generate identification data that may include a vehicle make, model, trim level, and/or various features of the vehicle present in the image. The identification data is compared to the rest of the vehicle listing to detect a mismatch between the image and the vehicle listing. An alert is generated, when a mismatch is detected, indicating the one of the image or the data in the vehicle listing is incorrect.
Claims20
A computer-implemented method comprising:
- retrieving an image from a data set corresponding to an individual identifier;
- classifying, using a first machine learning model, the image to determine a first portion of identification data for the image;
- classifying, using a second machine learning model, the image to determine a second portion of the identification data, in response to successfully classifying the image using the first machine learning model;
- comparing at least one portion of the identification data to a member of the data set to determine whether there is a mismatch between the at least one portion of the identification data and the member of the data set;
- and
- generating a mismatch alert to indicate an error in the data set, in response to the mismatch between the at least one portion of the identification data and the member of the data set.
A system comprising:
- a processor;
- and
- a memory coupled to the processor, wherein the processor and the memory are configured to:
- retrieve an image from a data set corresponding to an individual identifier;
- classify, using a first machine learning model, the image to determine a first portion of identification data for the image;
- classify, using a second machine learning model, the image to determine a second portion of the identification data, in response to successfully classifying the image using the first machine learning model;
- compare at least one portion of the identification data to a member of the data set to determine whether there is a mismatch between the at least one portion of the identification data and the member of the data set;
- and
- generate a mismatch alert to indicate an error in the data set, in response to the mismatch between the at least one portion of the identification data and the member of the data set.
A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
- retrieving an image from a data set corresponding to an individual identifier;
- classifying, using a first machine learning model, the image to determine a first portion of identification data for the image;
- classifying, using a second machine learning model, the image to determine a second portion of the identification data, in response to successfully classifying the image using the first machine learning model;
- comparing at least one portion of the identification data to a member of the data set to determine whether there is a mismatch between the at least one portion of the identification data and the member of the data set;
- and
- generating a mismatch alert to indicate an error in the data set, in response to the mismatch between the at least one portion of the identification data and the member of the data set.
Dependencies are inferred from the claim text.