Image analysis and identification using machine learning with output personalization

Patent metadata

Field	Value
Publication number	US-10783580-B2
Application number	US-201816165351-A
Country	US
Kind code	B2
Filing date	Oct 19, 2018
Priority date	Mar 8, 2018
Publication date	Sep 22, 2020
Grant date	Sep 22, 2020

Abstract

Systems and methods for processing an image using machine learning are provided. The system includes a processor in communication with a client device, and a storage medium storing instructions that, when executed, cause the processor to perform operations including: receiving an image of a vehicle from the client device; extracting one or more features from the image; determining a make and a model of the vehicle based on the extracted features and using a machine learning algorithm. The operations also include: obtaining user information relating to a financing request for the vehicle; determining and transmitting to the client device a real-time quote for the vehicle based on the make, the model, and the user information.

First claim

What is claimed is:

1. A system for processing an image including a vehicle, comprising:
a processor in communication with a client device; and
a storage medium storing instructions that, when executed, configure the processor to perform operations comprising:
receiving an image of a vehicle from the client device;
inputting the image to an input layer of a first convolutional neural network;
extracting one or more features from an output layer of the first convolutional neural network;
inputting the extracted features to an input layer of a second convolutional neural network;
determining a make and a model of the vehicle, from an output layer of the second convolutional neural network;
transmitting, to the client device, a prompt for authentication information;
receiving, from the client device and in response to the prompt,
authentication information associated with a user;

accessing an account associated with the user using the received authentication information;
obtaining user information related to the account;
determining a purchase quote for the vehicle based on the make, the model, and the user information; and
transmitting the purchase quote for display on the client device.

2. The system of claim 1 , wherein the authentication information comprises a user name and a password.

3. The system of claim 1 , wherein the extracted features include at least one of a logo of the vehicle and a shape of headlights of the vehicle.

4. The system of claim 1 , wherein the operations further comprise, based on identified attributes of the vehicle, determining a year and a trim of the vehicle.

5. The system of claim 1 , wherein the operations further comprise:
determining that the image is unacceptable; and
transmitting information for display on the client device, the information including at least one of an error message and user guidance.

6. The system of claim 1 , wherein the operations further comprise:
enabling the user to the client device configured to allow the user to manipulate different factors using the quote displayed on the client device.

7. The system of claim 6 , wherein the operations further comprise:
receiving a modification to at least one factor from the client device that was entered using the quote;
updating the real-time quote based on the modification; and
transmitting the updated real-time quote for display on the client device.

8. The system of claim 7 , wherein the modification comprises the addition of a service contract.

9. The system of claim 7 , wherein the modification comprises the addition of gap insurance.

10. The system of claim 7 , wherein the modification comprises the modification of a down payment.

11. A system for processing an image including a vehicle, comprising:
a processor in communication with a client device; and
a storage medium storing instructions that, when executed, configure the processor to perform operations comprising:
receiving an image of a vehicle from the client device;
inputting the image to an input layer of a first convolutional neural network;
extracting one or more features from an output layer of the first convolutional neural network;
inputting the extracted features to an input layer of a second convolutional neural network;
determining a make and a model of the vehicle, from an output layer of the second convolutional neural network;
transmitting, to the client device, a prompt for authentication information;
receiving, from the client device and in response to the prompt,
authentication information associated with a user;

accessing an account associated with the user using the received authentication information;
obtaining first user information related to the account;
transmitting, to the client device, a questionnaire;
receiving second user information from the client device that was entered into the questionnaire;
determining a purchase quote for the vehicle based on the make, the model, the first user information, and the second user information; and
transmitting the purchase quote for display on the client device.

12. The system of claim 11 , wherein the authentication information comprises a user name and a password.

13. The system of claim 11 , wherein the first user information comprises at least one of a name, an email address, a home address, a phone number, a mailing address, a date of birth, and a social security number.

14. The system of claim 11 , wherein the first user information comprises employment information.

15. The system of claim 14 , wherein the employment information comprises at least one of a name of an employer, a job title, and an annual income.

16. The system of claim 11 , wherein the second user information comprises a vehicle condition, a credit associated with the user, an amount desired for financing, and a preferred term length for financing.

17. The system of claim 11 , wherein the real-time quote comprises at least one of a vehicle price, a monthly payment amount, an interest rate, a term length, and an amount financed.

18. The system of claim 11 , wherein the real-time quote is based on an estimated down payment and a monthly payment comprising at least one of a mean or a median of the down payment and the monthly payment for individuals financing vehicles matching the determined make and model.

19. The system of claim 11 , wherein obtaining the second user information further comprises:
transmitting a selector to the client device for selecting between leasing and loaning; and
receiving a selection of leasing or loaning from the client device that was entered using the selector,
wherein the real-time quote is determined based on the received selection.

20. A system for processing an image including a vehicle, comprising:
a processor in communication with a client device; and
a storage medium storing instructions that, when executed, configure the processor to perform operations comprising:
transmitting a registration website to the client device;
receiving user information from the client device that was entered into the website;
receiving authentication information from the client device that was entered into the website;
storing the received user information in association with the received authentication information;
receiving an image of a vehicle from the client device;
inputting the image to an input layer of a first convolutional neural network;
extracting one or more features from an output layer of the first convolutional neural network;
inputting the extracted features to an input layer of a second convolutional neural network;
determining a make and a model of the vehicle, from an output layer of the second convolutional neural network;
transmitting, to the client device, a prompt for the authentication information;
receiving, from the client device and in response to the prompt, the authentication information;
accessing the stored user information using the received authentication information;
determining a purchase quote for the vehicle based on the make, the model, and the user information; and
transmitting the purchase quote for display on the client device.

Assignees

• Capital One Services Llc

Inventors

• Tang Qiaochu
• Vasisht Sunil Subrahmanyam
• Wylie Stephen Michael
• Dagley Geoffrey
• Price Micah
• Hoover Jason Richard
• Yajnik Sanjiv
• Bajaj Raman
• Dugal Arjun

Classifications

• G06V20/20

  in augmented reality scenes · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06Q40/03

  Credit; Loans; Processing thereof · CPC title

• G06F18/217

  Validation; Performance evaluation; Active pattern learning techniques · CPC title