Granted Patent B2

US 12,229,732 · App. 18/379,484 · Granted Feb 18, 2025

Inventor: Abhijeet Gulati (San Diego, CA)

Assignee: Mitchell International, Inc.

G06Q10/20G06F18/2148G06N5/04G06N20/00G06N20/20G06Q10/10G06Q40/08G06T7/0002G06T7/0004G06T2207/20081G06T2207/30248

Abstract

Claims (57)

1. A system, comprising:

a hardware processor; and

a non-transitory machine-readable storage medium encoded with instructions executable by the hardware processor to perform a method comprising:

receiving a vehicle damage object for a damaged vehicle;

providing the vehicle damage object to multiple first artificial intelligence functions;

receiving multiple vehicle repair recommendation sets for the damaged vehicle from the multiple first artificial intelligence functions, wherein each of the multiple vehicle repair recommendation sets identifies one of multiple vehicle repair operations for a component of the damaged vehicle, and wherein at least two of the multiple vehicle repair recommendation sets identify different recommended vehicle repair operations for the component of the damaged vehicle;

selecting, by a trained second artificial intelligence function, one of the multiple recommended vehicle repair operations for the component of the damaged vehicle based on multiple weights, wherein the multiple weights are associated with the multiple recommended vehicle repair operations for the component of the damaged vehicle for one of the multiple first artificial intelligence functions;

generating a composite vehicle repair recommendation set that identifies the selected recommended vehicle repair operation; and

retraining the trained second artificial intelligence function by adjusting the multiple weights.

2. The system of claim 1 , the method further comprising:

providing the composite vehicle repair recommendation set to one or more claims management systems.

3. The system of claim 1 , wherein:

at least two of the first artificial intelligence functions differ from each other.

4. The system of claim 1 , wherein:

the first artificial intelligence functions each include a trained machine learning model.

5. The system of claim 4 , the method further comprising:

requesting one or more of the trained machine learning models be re-trained when a predetermined event occurs.

6. The system of claim 5 , the method further comprising:

retraining the trained machine learning models responsive to the requesting.

7. The system of claim 6 , wherein retraining the trained machine learning models comprises:

adjusting the multiple weights according to vehicle damage objects received, and corresponding composite vehicle repair recommendations generated, since a last training of the trained machine learning models.

8. One or more non-transitory machine-readable storage media encoded with instructions that, when executed by one or more hardware processors of a computing system, cause the computing system to perform a method comprising:

receiving a vehicle damage object for a damaged vehicle;

providing the vehicle damage object to multiple first artificial intelligence functions;

receiving multiple vehicle repair recommendation sets for the damaged vehicle from the multiple first artificial intelligence functions, wherein each of the multiple vehicle repair recommendation sets identifies one of multiple vehicle repair operations for a component of the damaged vehicle, and wherein at least two of the multiple vehicle repair recommendation sets identify different recommended vehicle repair operations for the component of the damaged vehicle;

selecting, by a trained second artificial intelligence function, one of the multiple recommended vehicle repair operations for the component of the damaged vehicle based on multiple weights, wherein the multiple weights are associated with the multiple recommended vehicle repair operations for the component of the damaged vehicle for one of the multiple first artificial intelligence functions;

generating a composite vehicle repair recommendation set that identifies the selected recommended vehicle repair operation; and

retraining the trained second artificial intelligence function by adjusting the multiple weights.

9. The one or more non-transitory machine-readable storage media of claim 8 , the method further comprising:

providing the composite vehicle repair recommendation set to one or more claims management systems.

10. The one or more non-transitory machine-readable storage media of claim 8 , wherein:

at least two of the first artificial intelligence functions differ from each other.

11. The one or more non-transitory machine-readable storage media of claim 8 , wherein:

the first artificial intelligence functions each include a trained machine learning model.

12. The one or more non-transitory machine-readable storage media of claim 11 , the method further comprising:

requesting one or more of the trained machine learning models be re-trained when a predetermined event occurs.

13. The one or more non-transitory machine-readable storage media of claim 12 , the method further comprising:

retraining the trained machine learning models responsive to the requesting.

14. The one or more non-transitory machine-readable storage media of claim 13 , wherein retraining the trained machine learning models comprises:

adjusting the multiple weights according to vehicle damage objects received, and corresponding composite vehicle repair recommendations generated, since a last training of the trained machine learning models.

15. A computer-implemented method comprising:

receiving, by a computing system, a vehicle damage object for a damaged vehicle;

providing, by the computing system, the vehicle damage object to multiple first artificial intelligence functions;

receiving, by the computing system, multiple vehicle repair recommendation sets for the damaged vehicle from the multiple first artificial intelligence functions, wherein each of the multiple vehicle repair recommendation sets identifies one of multiple vehicle repair operations for a component of the damaged vehicle, and wherein at least two of the multiple vehicle repair recommendation sets identify different recommended vehicle repair operations for the component of the damaged vehicle;

selecting, by a trained second artificial intelligence function, one of the multiple recommended vehicle repair operations for the component of the damaged vehicle based on multiple weights, wherein the multiple weights are associated with the multiple recommended vehicle repair operations for the component of the damaged vehicle for one of the multiple first artificial intelligence functions;

generating, by the computing system, a composite vehicle repair recommendation set that identifies the selected recommended vehicle repair operation; and

retraining, by the computing system, the trained second artificial intelligence function by adjusting the multiple weights.

16. The computer-implemented method of claim 15 , the method further comprising:

providing, by the computing system, the composite vehicle repair recommendation set to one or more claims management systems.

17. The computer-implemented method of claim 15 , wherein:

at least two of the first artificial intelligence functions differ from each other.

18. The computer-implemented method of claim 15 , wherein:

the first artificial intelligence functions each include a trained machine learning model.

19. The computer-implemented method of claim 18 , the method further comprising:

requesting, by the computing system, one or more of the trained machine learning models be re-trained when a predetermined event occurs.

20. The computer-implemented method of claim 19 , the method further comprising:

retraining, by the computing system, the trained machine learning models responsive to the requesting.

Assignments (1)

Continuity (5)

References Cited (96)