CN-122020041-A - Fault diagnosis method based on knowledge graph and electronic equipment

CN122020041ACN 122020041 ACN122020041 ACN 122020041ACN-122020041-A

Abstract

The embodiment of the application discloses a fault diagnosis method based on a knowledge graph and electronic equipment. According to the method, the multi-modal data of the vehicle are processed to obtain at least one fault entity with a fault, the knowledge graph is traversed according to the fault entity to obtain the associated entity of the at least one fault entity, and then the fault information of the vehicle can be generated based on the at least one associated entity, so that the multi-modal data of the vehicle are integrated, meanwhile, the dynamic network of the fault entity and the associated entity is constructed by utilizing the knowledge graph, the multi-dimensional association analysis of the fault phenomenon and the potential root cause is realized, the technical problems of data splitting and knowledge fragmentation in the vehicle fault diagnosis process are solved, the accurate positioning of the fault root cause is realized, and the diagnosis efficiency and accuracy are improved.

Inventors

LIU XIN
LIU ZIYUAN
LIU GUANJUN

Assignees

深圳市元征软件开发有限公司

Dates

Publication Date: 20260512
Application Date: 20260126

Claims (10)

1. The fault diagnosis method based on the knowledge graph is characterized by comprising the following steps of: Processing the multi-mode data of the vehicle to obtain at least one fault entity of the vehicle with the fault; traversing a preset knowledge graph according to the fault entity to obtain at least one associated entity of the fault entity; fault information of the vehicle is generated based on at least one of the associated entities.
2. The knowledge-graph-based fault diagnosis method according to claim 1, wherein said at least one fault entity comprises a first fault entity and a second fault entity; The processing the multi-mode data of the vehicle to obtain at least one fault entity of the vehicle with the fault comprises the following steps: collecting fault codes of the vehicle and voice information describing the faults by a user; and generating the first fault entity according to the fault code, and generating the second fault entity according to the voice information.
3. The knowledge-graph-based fault diagnosis method according to claim 2, wherein said generating the second fault entity from the speech information comprises: Acquiring a historical maintenance work order text of the fault code of the vehicle, and acquiring video information of the user for checking the vehicle by adopting an AR technology; and extracting gesture information of the user from the video information, and generating the second fault entity according to the historical maintenance work order text, the gesture information and the voice information.
4. The fault diagnosis method based on the knowledge graph according to claim 3, wherein traversing the preset knowledge graph according to the fault entity to obtain at least one associated entity of the fault entity comprises: collecting environment information when the vehicle has the fault; Determining a fault threshold value of the fault of the vehicle according to the environment information; determining whether a dynamic operating condition parameter of the vehicle when the fault occurs exceeds the fault threshold; And if the dynamic working condition parameter exceeds the fault threshold, traversing the knowledge graph according to the first fault entity and the second fault entity to obtain at least one associated entity.
5. The knowledge-graph-based fault diagnosis method according to claim 4, wherein said determining whether a dynamic operating condition parameter of said vehicle at which said fault occurs exceeds said fault threshold value comprises: Collecting the dynamic working condition parameters and determining brand information of an electronic control unit of the vehicle; Based on the brand information, converting the dynamic working condition parameters by adopting a preset parameter conversion matrix to obtain target dynamic working condition parameters; Determining whether the target dynamic operating condition parameter exceeds the fault threshold.
6. The knowledge-graph-based fault diagnosis method according to claim 5, wherein said generating said second fault entity from said historical repair worksheet text, said gesture information, and said voice information comprises: Extracting feature information describing the vehicle from the voice information, and splicing the feature information, the target dynamic working condition parameters and the gesture information to obtain target feature information for diagnosing the fault; and generating the second fault entity according to the historical maintenance work order text and the target characteristic information.
7. The knowledge-based fault diagnosis method according to any one of claims 1-6, wherein said processing the multimodal data of the vehicle to obtain at least one fault entity of the vehicle that has the fault comprises: Carrying out space-time alignment processing on the multi-modal data by adopting a dynamic time warping algorithm to obtain space-time aligned multi-modal data; and extracting at least one fault entity from the multi-modal data after the time-space alignment.
8. The knowledge-graph-based fault diagnosis method according to any one of claims 1-6, further comprising: Collecting historical data of the vehicle, and generating first weight information for updating association information between the fault entity and the associated entity time according to the historical data; generating second weight information of the associated information according to the fault information; And dynamically updating the knowledge graph according to the first weight information and the second weight information.
9. The knowledge-graph-based fault diagnosis method according to any one of claims 1-6, wherein said generating fault information of the vehicle based on at least one of the associated entities comprises: processing at least one associated entity and at least one fault entity by adopting an Apriori algorithm to obtain a target entity of the fault of the vehicle; and generating fault information of the vehicle according to the target entity.
10. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the knowledge-graph based fault diagnosis method of any one of claims 1 to 9 when executing the computer program.

Description

Fault diagnosis method based on knowledge graph and electronic equipment Technical Field The application relates to the technical field of automobile fault diagnosis, in particular to a fault diagnosis method based on a knowledge graph and electronic equipment. Background The traditional automobile diagnosis system mainly relies on fault codes to perform fault identification, but key information such as dynamic working condition data, historical maintenance records and the like generated in the running process of the automobile are not integrated. When a composite fault phenomenon occurs to a vehicle, for example, cold start shake and a cylinder fire-deficiency fault code are presented at the same time, the system cannot be related to the spark plug replacement record in the historical maintenance information, so that the diagnosis process is limited to single fault code matching, further, the diagnosis result often deviates from the real fault source, maintenance personnel need to check item by item, the efficiency is low, and maintenance resource waste and customer waiting time are prolonged. Disclosure of Invention Aiming at the defects of the prior art, the application provides a fault diagnosis method based on a knowledge graph and electronic equipment, which can realize the accurate positioning of fault root causes and improve the diagnosis efficiency and accuracy. In a first aspect, the present application provides a fault diagnosis method based on a knowledge graph, which includes: Processing the multi-mode data of the vehicle to obtain at least one fault entity of the vehicle with faults; Traversing the preset knowledge graph according to the fault entity to obtain at least one associated entity of the fault entity; Fault information for the vehicle is generated based on the at least one associated entity. In a second aspect, the present application also provides a fault diagnosis device based on a knowledge graph, which includes: the processing unit is used for processing the multi-mode data of the vehicle to obtain at least one fault entity of the vehicle with faults; The traversing unit is used for traversing the preset knowledge graph according to the fault entity to obtain at least one associated entity of the fault entity; and the generating unit is used for generating the fault information of the vehicle based on the at least one associated entity. In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the knowledge-graph-based fault diagnosis method provided in the first aspect when executing the computer program. In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program when executed by a processor causes the processor to perform the method for diagnosing a fault based on a knowledge graph provided in the first aspect. In a fifth aspect, embodiments of the present application further provide a computer program product, including a computer program or instructions, where the computer program or instructions is executed by a processor to perform the knowledge-graph-based fault diagnosis method provided in the first aspect. According to the fault diagnosis method based on the knowledge graph, the multi-modal data of the vehicle are processed to obtain at least one fault entity with a fault of the vehicle, and the knowledge graph is traversed according to the fault entity to obtain the associated entity of the at least one fault entity, so that the fault information of the vehicle can be generated based on the at least one associated entity, the multi-modal data of the vehicle is integrated, meanwhile, the dynamic network of the fault entity and the associated entity is constructed by utilizing the knowledge graph, the multi-dimensional association analysis of the fault phenomenon and the potential root cause is realized, the technical problems of data splitting and knowledge fragmentation in the vehicle fault diagnosis process are solved, the accurate positioning of the fault root cause is realized, and the diagnosis efficiency and accuracy are improved. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 is an application scenario diagram of a fault diagnosis method based on a knowledge graph provided by an embodiment of the present application; fig. 2 is a flow c