Method and apparatus for improving vehicle loss assessment image identification result, and server

1. A computer-implemented method for automotive part recognition based on a vehicle damage assessment image, comprising:

obtaining a damage assessment image of a target vehicle;

obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle, wherein the automotive part list comprises customized configuration information of automotive parts of the target vehicle; and

determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm, to obtain an automotive part identification serial number of the determined damaged automotive part.

2. The method according to claim 1 , wherein the obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle comprises:

in a process of obtaining the damage assessment image of the target vehicle, querying automotive part data of the target vehicle according to the vehicle identification code, and converting the automotive part data into a plurality of corresponding automotive part identification serial numbers.

3. The method according to claim 1 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

reading the customized configuration information of the automotive parts of the target vehicle in the automotive part list;

recognizing the damaged automotive part in the damage assessment image by using the image recognition algorithm; and

determining the automotive part identification serial number of the recognized damaged automotive part according to the customized configuration information of the automotive parts of the target vehicle in the automotive part list.

4. The method according to claim 1 , wherein the customized configuration information of the automotive parts comprises at least one information selected from the following:

information indicating a feature attribute of automotive parts in a same vehicle model and a same level configuration;

information indicating at least two level classifications of automotive parts; and

data indicating a customized feature of an automotive part on the target vehicle.

5. The method according to claim 1 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

determining an automotive part classification to which the damaged automotive part recognized by using the image recognition algorithm belongs based on the customized configuration information of the automotive parts; and

using the image recognition algorithm to recognize the damaged automotive part based on the automotive part classification.

6. The method according to claim 1 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

in response to the customized configuration information of the automotive parts indicating that there is no automotive part matching the damaged automotive part recognized by using the image recognition algorithm, searching the customized configuration information of the automotive parts for an automotive part having an automotive part inclusion relationship with the recognized damaged automotive part, and determining the automotive part having the inclusion relationship as the recognized damaged automotive part.

7. The method according to claim 6 , wherein the automotive part having the automotive part inclusion relationship with the recognized damaged automotive part includes the recognized damaged automotive part or is included in the recognized damaged automotive part.

8. An apparatus for automotive part recognition based on a vehicle damage assessment image, comprising one or more processors and one or more non-transitory computer-readable memories coupled to the one or more processors and configured with instructions executable by the one or more processors to cause the apparatus to perform operations comprising:

obtaining a damage assessment image of a target vehicle;

obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle, wherein the automotive part list comprises customized configuration information of automotive parts of the target vehicle; and

determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm, to obtain an automotive part identification serial number of the determined damaged automotive part.

9. The apparatus according to claim 8 , wherein the obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle comprises:

in a process of obtaining the damage assessment image of the target vehicle, querying automotive part data of the target vehicle according to the vehicle identification code, and converting the automotive part data into a plurality of corresponding automotive part identification serial numbers.

10. The apparatus according to claim 8 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

reading the customized configuration information of the automotive parts of the target vehicle in the automotive part list;

recognizing the damaged automotive part in the damage assessment image by using the image recognition algorithm; and

determining the automotive part identification serial number of the recognized damaged automotive part according to the customized configuration information of the automotive parts of the target vehicle in the automotive part list.

11. The apparatus according to claim 8 , wherein the customized configuration information of the automotive parts comprises at least one information selected from the following:

information indicating a feature attribute of automotive parts in a same vehicle model and a same level configuration;

information indicating at least two level classifications of automotive parts; and

data indicating a customized feature of an automotive part on the target vehicle.

12. The apparatus according to claim 8 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

determining an automotive part classification to which the damaged automotive part recognized by using the image recognition algorithm belongs based on the customized configuration information of the automotive parts; and

using the image recognition algorithm to recognize the damaged automotive part based on the automotive part classification.

13. The apparatus according to claim 8 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

in response to the customized configuration information of the automotive parts indicating that there is no automotive part matching the damaged automotive part recognized by using the image recognition algorithm, searching the customized configuration information of the automotive parts for an automotive part having an automotive part inclusion relationship with the recognized damaged automotive part, and determining the automotive part having the inclusion relationship as the recognized damaged automotive part.

14. The apparatus according to claim 13 , wherein the automotive part having the automotive part inclusion relationship with the recognized damaged automotive part includes the recognized damaged automotive part or is included in the recognized damaged automotive part.

15. A non-transitory computer-readable storage medium configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

obtaining a damage assessment image of a target vehicle;

obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle, wherein the automotive part list comprises customized configuration information of automotive parts of the target vehicle; and

determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm, to obtain an automotive part identification serial number of the determined damaged automotive part.

16. The non-transitory computer-readable storage medium according to claim 15 , wherein the obtaining an automotive part list of the target vehicle based on a vehicle identification code of the target vehicle comprises:

in a process of obtaining the damage assessment image of the target vehicle, querying automotive part data of the target vehicle according to the vehicle identification code, and converting the automotive part data into a plurality of corresponding automotive part identification serial numbers.

17. The non-transitory computer-readable storage medium according to claim 15 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

reading the customized configuration information of the automotive parts of the target vehicle in the automotive part list;

recognizing the damaged automotive part in the damage assessment image by using the image recognition algorithm; and

determining the automotive part identification serial number of the recognized damaged automotive part according to the customized configuration information of the automotive parts of the target vehicle in the automotive part list.

18. The non-transitory computer-readable storage medium according to claim 15 , wherein the customized configuration information of the automotive parts comprises at least one information selected from the following:

information indicating a feature attribute of automotive parts in a same vehicle model and a same level configuration;

information indicating at least two level classifications of automotive parts; and

data indicating a customized feature of an automotive part on the target vehicle.

19. The non-transitory computer-readable storage medium according to claim 15 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

determining an automotive part classification to which the damaged automotive part recognized by using the image recognition algorithm belongs based on the customized configuration information of the automotive parts; and

using the image recognition algorithm to recognize the damaged automotive part based on the automotive part classification.

20. The non-transitory computer-readable storage medium according to claim 15 , wherein the determining a damaged automotive part of the target vehicle from the damage assessment image based on the customized configuration information of the automotive parts of the target vehicle and an image recognition algorithm comprises:

in response to the customized configuration information of the automotive parts indicating that there is no automotive part matching the damaged automotive part recognized by using the image recognition algorithm, searching the customized configuration information of the automotive parts for an automotive part having an automotive part inclusion relationship with the recognized damaged automotive part, and determining the automotive part having the inclusion relationship as the recognized damaged automotive part.