CN-121998065-A - Knowledge base updating method, device, equipment and storage medium

CN121998065ACN 121998065 ACN121998065 ACN 121998065ACN-121998065-A

Abstract

The application discloses a knowledge base updating method, a device, equipment and a storage medium, which relate to the technical field of data processing and comprise the steps of receiving a query request, wherein the query request is a request which is reported by a fault vehicle and contains fault data corresponding to the fault vehicle, and/or the query request is a request which is sent by a client and contains the identification of the queried vehicle, determining a target fault label corresponding to the query request and a corresponding target solution when the query request triggers the update of the vehicle fault knowledge base, and updating the vehicle fault knowledge base based on the target fault label and the target solution. Therefore, the vehicle fault knowledge base is updated in real time through two dimensions of active triggering of the vehicle and passive triggering of the client, and the vehicle fault knowledge base can cover faults of the vehicle more comprehensively while the updating timeliness of the vehicle fault knowledge base is improved.

Inventors

ZHANG QIYU
Luo Qinyue
FU GUANG
ZHANG TAO
XIAO LEI

Assignees

上汽通用五菱汽车股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260112

Claims (10)

1. A method of updating a knowledge base, the method comprising: receiving a query request, wherein the query request is a request which is reported by a fault vehicle and contains fault data corresponding to the fault vehicle, and/or the query request is a request which is sent by a client and contains the identification of the queried vehicle; under the condition that the query request triggers the update of a vehicle fault knowledge base, determining a target fault label corresponding to the query request and a corresponding target solution; and updating the vehicle fault knowledge base based on the target fault label and the target solution.
2. The method of claim 1, wherein the query request is a request reported by a failed vehicle and including failure data corresponding to the failed vehicle, and wherein determining that the query request triggers a vehicle failure knowledge base update comprises: Determining a first fault label corresponding to the fault vehicle according to the fault data corresponding to the fault vehicle; under the condition that the first fault label does not exist in the vehicle fault knowledge base, a historical fault label corresponding to the historical fault vehicle of the query request is reported in a preset time period before the current moment is determined; Determining a total number of historical failure tags that are the same as the first failure tag; And determining that the query request triggers a vehicle fault knowledge base update if the total number is greater than a number threshold.
3. The method of claim 1, wherein the query request is a request sent by a client and containing an identification of a queried vehicle, the determining that the query request triggers a vehicle failure knowledge base update comprising: Acquiring real-time data corresponding to the queried vehicle based on the identification of the queried vehicle; Determining a second fault label corresponding to the queried vehicle according to the real-time data; And determining that the query request triggers the updating of the vehicle fault knowledge base under the condition that the second fault label does not exist in the vehicle fault knowledge base.
4. The method of claim 1, wherein after the updating of the vehicle fault knowledge base based on the target fault signature and the target solution, the method further comprises: determining a target score corresponding to each solution in the updated vehicle fault knowledge base; And updating any solution under the condition that the target score corresponding to the solution is smaller than the preset score.
5. The method of claim 4, wherein determining a target score for each solution in the updated vehicle fault knowledge base comprises: Determining the historical retrieval times corresponding to the vehicle fault labels of each solution and the success times of each solution for solving the fault; Determining the ratio of the success times corresponding to each solution to the historical retrieval times as the matching success rate corresponding to each solution; And determining a target score corresponding to each solution according to at least one of the matching success rate, the engineer feedback score and the user feedback score corresponding to each solution.
6. The method of any of claims 1-5, wherein after the updating of the vehicle fault knowledge base based on the target fault signature and the target solution, the method further comprises: determining the historical retrieval times corresponding to each vehicle fault label in the updated vehicle fault knowledge base; and determining the retrieval priority corresponding to each vehicle fault label based on the historical retrieval times, wherein the historical retrieval times and the retrieval priorities are in positive correlation.
7. The method of any of claims 1-5, further comprising, prior to the updating the vehicle fault knowledge base based on the target fault signature and the target solution: after-sales data of the vehicle are structured, and a fault solution, a vehicle model corresponding to the fault solution, a vehicle system type, a software version and a fault type are determined; Determining the vehicle model, the vehicle system type, the software version and the fault type as a vehicle fault label corresponding to the fault solution; And storing the fault solution and the vehicle fault label into the vehicle fault knowledge base.
8. A knowledge base updating apparatus, characterized in that the knowledge base updating apparatus comprises: The system comprises a receiving module, a receiving module and a processing module, wherein the receiving module is used for receiving a query request, wherein the query request is a request which is reported by a fault vehicle and contains fault data corresponding to the fault vehicle, and/or the query request is a request which is sent by a client and contains the identification of the queried vehicle; the determining module is used for determining a target fault label corresponding to the query request and a corresponding target solution under the condition that the query request triggers the update of the vehicle fault knowledge base; and the updating module is used for updating the vehicle fault knowledge base based on the target fault label and the target solution.
9. A knowledge base updating device, characterized in that the device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the knowledge base updating method according to any of claims 1 to 7.
10. A storage medium, characterized in that the storage medium is a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the knowledge base updating method according to any of claims 1 to 7.

Description

Knowledge base updating method, device, equipment and storage medium Technical Field The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for updating a knowledge base. Background The fault scene of the intelligent network-connected automobile is diversified, refined and dynamic along with vehicle type iteration, software version updating, vehicle system upgrading and the like. In order to quickly respond to vehicle fault resolution requirements, a vehicle fault knowledge base may be employed as a fault matching solution. However, the updating of the knowledge base mostly depends on the manual recording of new faults and solutions by engineers, or the knowledge base is updated in batches at regular time, so that the updating time is low, and the timeliness and the accuracy of the vehicle fault treatment are further affected. Disclosure of Invention The application mainly aims to provide a knowledge base updating method, device, equipment and storage medium, and aims to solve the technical problems that the updating timeliness of a vehicle fault knowledge base is low and the timeliness and accuracy of vehicle fault processing are affected. In order to achieve the above object, the present application provides a method for updating a knowledge base, the method comprising: receiving a query request, wherein the query request is a request which is reported by a fault vehicle and contains fault data corresponding to the fault vehicle, and/or the query request is a request which is sent by a client and contains the identification of the queried vehicle; under the condition that the query request triggers the update of a vehicle fault knowledge base, determining a target fault label corresponding to the query request and a corresponding target solution; and updating the vehicle fault knowledge base based on the target fault label and the target solution. In some embodiments, the query request is a request that is reported by a faulty vehicle and includes fault data corresponding to the faulty vehicle, and the determining that the query request triggers a vehicle fault knowledge base update includes: Determining a first fault label corresponding to the fault vehicle according to the fault data corresponding to the fault vehicle; under the condition that the first fault label does not exist in the vehicle fault knowledge base, a historical fault label corresponding to the historical fault vehicle of the query request is reported in a preset time period before the current moment is determined; Determining a total number of historical failure tags that are the same as the first failure tag; And determining that the query request triggers a vehicle fault knowledge base update if the total number is greater than a number threshold. In some embodiments, the query request is a request sent by a client and containing an identification of a queried vehicle, and the determining that the query request triggers a vehicle failure knowledge base update includes: Acquiring real-time data corresponding to the queried vehicle based on the identification of the queried vehicle; Determining a second fault label corresponding to the queried vehicle according to the real-time data; And determining that the query request triggers the updating of the vehicle fault knowledge base under the condition that the second fault label does not exist in the vehicle fault knowledge base. In some embodiments, after the updating of the vehicle fault knowledge base based on the target fault tag and the target solution, the method further comprises: determining a target score corresponding to each solution in the updated vehicle fault knowledge base; And updating any solution under the condition that the target score corresponding to the solution is smaller than the preset score. In some embodiments, the determining the target score corresponding to each solution in the updated vehicle fault knowledge base includes: Determining the historical retrieval times corresponding to the vehicle fault labels of each solution and the success times of each solution for solving the fault; Determining the ratio of the success times corresponding to each solution to the historical retrieval times as the matching success rate corresponding to each solution; And determining a target score corresponding to each solution according to at least one of the matching success rate, the engineer feedback score and the user feedback score corresponding to each solution. In some embodiments, after the updating of the vehicle fault knowledge base based on the target fault tag and the target solution, the method further comprises: determining the historical retrieval times corresponding to each vehicle fault label in the updated vehicle fault knowledge base; and determining the retrieval priority corresponding to each vehicle fault label based on the historical retrieval times, wh