Methods and systems for providing a vehicle suggestion based on image analysis

Patent metadata

Field	Value
Publication number	US-11551283-B2
Application number	US-202017108137-A
Country	US
Kind code	B2
Filing date	Dec 1, 2020
Priority date	Dec 1, 2020
Publication date	Jan 10, 2023
Grant date	Jan 10, 2023

Abstract

Methods and systems are disclosed for providing a vehicle suggestion to a user based on image analysis. The method may include: receiving one or more vehicle images via website data associated with the user; identifying one or more first-level traits from the one or more vehicle images; obtaining one or more vehicle identifications from the one or more vehicle images based on the one or more first-level traits; determining a value of each of the one or more first-level traits and/or the one or more vehicle identifications via one or more algorithms; determining the vehicle suggestion based on the value of each of the one or more first-level traits and/or the one or more vehicle identifications; and transmitting, to a device associated with the user, a notification indicating the vehicle suggestion.

First claim

What is claimed is:

1. A computer-implemented method for providing a vehicle suggestion to a user based on image analysis, the method comprising:
receiving, via one or more processors of a computer system associated with an entity, an indication from a device associated with the user granting the entity access to website data associated with the user from a plurality of resources independent of the entity;
based on the access granted and an occurrence of an initial interaction of the user with one or more of the plurality of resources, receiving, via the one or more processors, an initial set of website data associated with the initial interaction from the one or more of the plurality resources;
identifying, via one or more processors, an initial set of one or more vehicle images from the initial set of website data;
identifying, via the one or more processors, one or more first-level traits from the initial set of one or more vehicle images, wherein the one or more first-level traits comprise at least one of a make, a model, a body style, a color, a door count, or a seat count of one or more vehicles in the initial set of one or more vehicle images;
obtaining, via the one or more processors, one or more vehicle identifications from the initial set of one or more vehicle images based on the one or more first-level traits;
determining, via the one or more processors, a first value of each of the one or more first-level traits and/or the one or more vehicle identifications via one or more algorithms;
determining, via the one or more processors, a vehicle suggestion based on the first value of each of the one or more first-level traits and/or the one or more vehicle identifications;
transmitting, to the device or another device associated with the user, a notification indicating the vehicle suggestion;
based on the access granted and each occurrence of a subsequent interaction of the user with a same or a different one or more of the plurality of resources, iteratively receiving, via the one or more processors, a next set of website data associated with the respective subsequent interaction from the one or more of the plurality resources; and
as each next set of website data is received:
identifying, via the one or more processors, a next set of one or more vehicle images from the next set of website data;
updating, via the one or more processors, the vehicle suggestion by adjusting the first value of at least one of the one or more first-level traits identified and/or the one or more vehicle identifications obtained from the initial set of website data, wherein the first value is adjusted based on a second value determined for each of one or more first-level traits identified from the next set of one or more vehicle images and/or one or more vehicle identifications obtained from the next set of one or more vehicle images; and
transmitting an updated notification indicating the updated vehicle suggestion to the device or the other device associated with the user.

2. The computer-implemented method of claim 1 , wherein the plurality of resources include one or more social network sites, at least one of the initial set of website data or the next set of website data includes data from one or more social network accounts associated with the user received from the one or more network sites, and at least one of the one or more vehicle images identified from the initial set of website data or the next set of website data respectively includes a vehicle image from the one or more social network accounts.

3. The computer-implemented method of claim 2 , wherein
the at least one of the initial interaction of the user or the subsequent interaction of the user includes an association of the vehicle image with the one or more social network accounts.

4. The computer-implemented method of claim 1 , wherein each first value is a weighted value associated with a frequency that each of the one or more first-level traits and/or each of the one or more vehicle identifications appear in the initial set of one or more vehicle images.

5. The computer-implemented method of claim 4 , further including:
generating, via the one or more processors, a matrix of the one or more first-level traits and/or the one or more vehicle identifications based on each weighted value; and
determining, via the one or more processors, the vehicle suggestion based on the matrix.

6. The computer-implemented method of claim 4 , wherein each weighted value includes a weight based on more recently viewed vehicle images from the initial set of website data.

7. The computer-implemented method of claim 1 , further including:
determining, via the one or more processors, one or more second-level traits based on the one or more vehicle identifications obtained from the initial set of one or more vehicle images, wherein the one or more second-level traits comprise at least one of an engine type, a manufacturing region, or a manufacturing year of the one or more vehicles indicated via the initial set of one or more vehicle images;
determining, via the one or more processors, a first value of each of the one or more second-level traits; and
determining, via the one or more processors, the vehicle suggestion based on the first value of each of the one or more first-level traits and the one or more second-level traits.

8. The computer-implemented method of claim 7 , wherein the one or more second-level traits further include at least a vehicle price of the one or more vehicles indicated via the initial set of one or more vehicle images.

9. The computer-implemented method of claim 1 , wherein determining the vehicle suggestion includes determining the vehicle suggestion via a trained machine learning algorithm.

10. The computer-implemented method of claim 1 , wherein the website data includes one or more types of website data, and receiving the indication granting access to website data comprises receiving login information for the one or more types of the website data.

11. The computer-implemented method of claim 1 , wherein the website data associated with the user to which access is granted is only a subset of a plurality of types of website data.

12. A computer system for providing a vehicle suggestion to a user based on image analysis, comprising:
a memory storing instructions; and
one or more processors configured to execute the instructions to perform operations including:
receiving an indication from a device associated with the user granting access to website data associated with the user;
based on the access granted and an occurrence of an initial interaction of the user with an initial set of website data, receiving the initial set of website data;
identifying an initial set of one or more vehicle images from the initial set of website data;
identifying one or more first-level traits from the initial set of one or more vehicle images, wherein the one or more first-level traits comprise at least one of a make, a model, a body style, a color, a door count, or a seat count of one or more vehicles in the initial set of one or more vehicle images;
obtaining one or more vehicle identifications from the initial set of one or more vehicle images based on the one or more first-level traits;
determining a first value of each of the one or more first-level traits and/or the one or more vehicle identifications via one or more algorithms;
determining a vehicle suggestion based on the first value of each of the one or more first-level traits and/or the one or more vehicle identifications;
transmitting, to the device or another device associated with the user, a notification indicating the vehicle suggestion;
base

Assignees

• Capital One Services Llc

Inventors

• Emamdie Michelle
• Tang Qiaochu
• Guo Jiaxin
• Bumpas Derek
• Huang Jeremy

Classifications

• G06F16/9536

  Search customisation based on social or collaborative filtering · CPC title

• G06Q30/0627

  by specifying product or service characteristics, e.g. product dimensions · CPC title

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06V20/20

  in augmented reality scenes · CPC title