Granted Patent B1

US 10,043,255 · App. 15/900,306 · Granted Aug 7, 2018

Inventors: Prasad Pathapati (Frisco, TX); Deepa Mohan (Frisco, TX); Mark Morrison (Rowlett, TX)

Assignee: Capital One Services, LLC

G06T7/0002G06F9/451G06K9/6202G06N99/005G06T2207/20081G06T2207/30168G06T2207/30176

Abstract

Claims (113)

1. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, configured to:

receive user interface information associated with a user interface to be provided for a particular platform;

receive design information for a design of the user interface to be provided for the particular platform;

receive a request to visually compare the user interface information and the design information;

utilize, based on the request, a trained machine learning model to visually compare the user interface information and the design information,

wherein the trained machine learning model includes two or more of:

a trained color selection model,

a trained edge detection model,

a trained region of interest model, or

a trained line detection model;

generate information, indicating defects in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information,

the defects including user interface information that does not visually match the design information; and

provide the information indicating the defects in the user interface information.

2. The device of claim 1 , wherein the one or more processors are further configured to:

generate one or more recommendations for correcting the defects based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

provide the one or more recommendations.

3. The device of claim 1 , wherein the one or more processors are further configured to:

generate code for correcting the defects, in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

cause the code for correcting the defects in the user interface information to be implemented to correct the defects in the user interface information.

4. The device of claim 1 , wherein the one or more processors are further configured to:

receive historical user interface information associated with multiple platforms;

train a machine learning model with the historical user interface information; and

generate a trained machine learning model based on training the machine learning model with the historical user interface information.

5. The device of claim 1 , wherein the defects in the user interface information relate to one or more of:

scaling defects associated with the user interface information,

sizing defects associated with the user interface information,

overlapping image defects associated with the user interface information,

content discrepancy defects associated with the user interface information, or

alignment defects associated with the user interface information.

6. The device of claim 1 , wherein:

the trained edge model includes a trained Canny edge model, and

the trained line detection model includes a trained Hough transform line detection model.

7. The device of claim 1 , wherein the one or more processors are further configured to:

automatically correct the defects in the user interface information based on the information indicating the defects in the user interface information.

8. A method, comprising:

receiving, by a device, design information for a design of a user interface to be provided for multiple platforms,

the multiple platforms including different display areas for displaying the user interface;

storing, by the device, the design information;

receiving, by the device, user interface information associated with the user interface to be provided for the multiple platforms;

receiving, by the device and from a client device, a request to visually compare the user interface information and the design information;

utilizing, by the device and based on the request, a trained machine learning model to visually compare the user interface information and the design information,

wherein the trained machine learning model includes two or more of:

a trained color selection model,

a trained edge model,

a trained region of interest model, or

a trained line detection model;

generating, by the device, information, indicating defects in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information,

the defects including user interface information that does not visually match the design information; and

providing, by the device, the information indicating defects in the user interface information for display to the client device.

9. The method of claim 8 , further comprising:

generating one or more recommendations for correcting the defects based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

providing the one or more recommendations for display to the client device.

10. The method of claim 8 , further comprising:

generating code for correcting the defects, in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

utilizing the code to automatically correct the defects in the user interface information.

11. The method of claim 8 , further comprising:

receiving historical user interface information associated with multiple platforms;

storing the historical user interface information;

training a machine learning model with the historical user interface information; and

generating a trained machine learning model based on training the machine learning model with the historical user interface information.

12. The method of claim 8 , wherein the multiple platforms include two or more of:

a television,

a desktop computing device,

a tablet computing device,

a handheld device,

a smartphone device, or

a wearable device.

13. The method of claim 8 , wherein the user interface information includes:

an image of the user interface for each of the multiple platforms, and

information indicating the multiple platforms.

14. The method of claim 8 , further comprising:

automatically correcting the defects in the user interface information based on the information indicating the defects in the user interface information.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to:

receive historical user interface information associated with multiple platforms,

the multiple platforms including different display areas for displaying a same user interface;

train a machine learning model with the historical user interface information;

generate a trained machine learning model based on training the machine learning model with the historical user interface information,

wherein the trained machine learning model includes two or more of:

a trained color selection model,

a trained edge model,

a trained region of interest model, or

a trained line detection model;

receive user interface information associated with the user interface to be provided for a particular platform of the multiple platforms;

receive design information for a design of a user interface to be provided for the particular platform;

receive a request to visually compare the user interface information and the design information;

utilize, based on the request, the trained machine learning model to visually compare the user interface information and the design information;

generate an information, indicating defects in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information,

the defects including user interface information that does not visually match the design information; and

provide the information indicating the defects in the user interface information.

16. The non-transitory computer-readable medium of claim 15 , wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to:

generate one or more recommendations for correcting the defects based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

provide the one or more recommendations.

17. The non-transitory computer-readable medium of claim 15 , wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to:

generate code for correcting the defects, in the user interface information, based on utilizing the trained machine learning model to visually compare the user interface information and the design information; and

cause the code for correcting the defects in the user interface information to be implemented.

18. The non-transitory computer-readable medium of claim 15 , wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to:

automatically correct the defects in the user interface information based on the information indicating defects in the user interface information.

19. The non-transitory computer-readable medium of claim 15 , wherein the multiple platforms include two or more of:

a television,

a desktop computing device,

a tablet computing device,

a handheld device,

a smartphone device, or

a wearable device.

20. The non-transitory computer-readable medium of claim 15 , wherein the user interface information includes:

a user interface image of the user interface for the particular platform, and

information indicating the particular platform.

Assignments (1)

Cited By (8)

US 12,190,620 US 12,197,927 US 12,259,946 US 12,292,960 US 12,423,118 US 12,536,826 US 12,573,227 US 12,602,947