Vehicle fault diagnosis method and device, electronic equipment and storage medium
By retrieving fault handling solutions in the fault knowledge graph and associating component data, the existing vehicle fault diagnosis problem is solved, an efficient fault diagnosis process is achieved, and the user's car use experience is improved.
Patent Information
- Application Number
- CN202411684599.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-03-18
AI Technical Summary
The existing vehicle fault diagnosis plan is inefficient, and maintenance personnel need to manually retrieve documents, query component information and software versions, resulting in inefficient diagnosis.
Vehicle fault diagnosis is performed by fuzzy search and semantic search based on fault information in the fault knowledge graph, fault handling plans are obtained, and component data is associated with PDM's BOM data to determine the diagnostic script.
It simplifies the fault search process, improves the efficiency of fault diagnosis, refines the diagnosis goals, and improves the user's car experience.
Smart Images
Figure CN119646177A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle fault diagnosis, and in particular to a vehicle fault diagnosis method, device, electronic equipment and storage medium. Background Art
[0002] Existing automobile maintenance technical information mainly exists in maintenance manuals or related maintenance CDs provided by various controller manufacturers, mainly including diagnostic trouble codes (DTC), fault phenomena, possible causes of faults and troubleshooting steps, etc., with the purpose of guiding users or maintenance personnel to correctly diagnose and solve vehicle faults. At present, this manual development method usually adopts an offline mode, which has problems such as high cost, long book cycle, and cumbersome editing and typesetting. Some automobile manufacturers have also adopted an online writing system based on the Darwin Information Typing Architecture (DITA) concept and Extensible Markup Language (XML) technology. This system can greatly improve the speed of book compilation, realize the decentralized writing mode of manuals, and make full use of previous resources.
[0003] However, the maintenance information for after-sales maintenance personnel is currently displayed in the form of documents, which makes it difficult for maintenance personnel to retrieve. It is also unable to automatically associate the vehicle loading information, and the repair / replacement plan for the diagnosed parts needs to be queried in conjunction with the manufacturing system. During the maintenance process, the software and hardware version query of the electronic control parts requires the use of additional diagnostic instruments or other tools to read their information, and maintenance personnel need to master the use of other tools. The above defects affect the efficiency of maintenance personnel in fault diagnosis, thereby reducing the user's car experience. Summary of the invention
[0004] In view of this, it is necessary to provide a vehicle fault diagnosis method, device, electronic device and storage medium to solve the problem of low efficiency of existing vehicle fault diagnosis solutions.
[0005] In order to solve the above problems, the present invention provides a vehicle fault diagnosis method, comprising: Retrieving a fault handling solution corresponding to the fault information in a fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; Associating component data corresponding to the fault handling solution with BOM data of the PDM, and determining a diagnostic script corresponding to the BOM data based on the BOM data; Vehicle fault diagnosis is performed based on the BOM data and a diagnosis script corresponding to the BOM data.
[0006] In a possible implementation, searching the fault knowledge graph for a fault handling solution corresponding to the fault information based on the fault information includes: Based on the fault information, fuzzy retrieval and / or semantic retrieval is performed in the fault knowledge graph to obtain the fault handling solution.
[0007] In a possible implementation, performing fuzzy retrieval and / or semantic retrieval in the fault knowledge graph based on the fault information to obtain the fault handling solution includes: In the case where the fault information only includes a fault code, a fuzzy search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information only includes a fault description, a semantic search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information includes a fault code and a fault description, fuzzy retrieval and semantic retrieval are performed in the fault knowledge graph to obtain the fault handling solution.
[0008] In a possible implementation, performing fuzzy search in the fault knowledge graph to obtain the fault handling solution includes: Based on the fault code included in the fault information, text similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
[0009] In a possible implementation, performing semantic retrieval in the fault knowledge graph to obtain the fault handling solution includes: Based on the fault description included in the fault information, semantic similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
[0010] In a possible implementation, performing fuzzy retrieval and semantic retrieval in the fault knowledge graph to obtain the fault handling solution includes: The results of fuzzy retrieval and semantic retrieval are deduplicated and reordered to obtain the fault handling solution.
[0011] In a possible implementation, the fault knowledge graph is constructed based on a vehicle maintenance manual, a vehicle maintenance work order, a vehicle transfer order, and a vehicle technical journal.
[0012] The present invention also provides a vehicle fault diagnosis device, comprising: A retrieval module, used to retrieve a fault handling solution corresponding to the fault information in the fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; A determination module, used to associate the component data corresponding to the fault handling solution with the BOM data of the PDM, and determine the diagnosis script corresponding to the BOM data based on the BOM data; A diagnosis module is used to perform vehicle fault diagnosis based on the BOM data and a diagnosis script corresponding to the BOM data.
[0013] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the vehicle fault diagnosis method as described above is implemented.
[0014] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the vehicle fault diagnosis method as described above is implemented.
[0015] The beneficial effects of the present invention are as follows: the vehicle fault diagnosis method, device, electronic device and storage medium provided by the present invention first retrieve the fault handling plan corresponding to the fault information in the fault knowledge graph according to the fault information, thereby simplifying the fault retrieval process and improving the efficiency of fault diagnosis, and then linking the component data corresponding to the fault handling plan to the BOM data of the PDM to determine the diagnostic script corresponding to the BOM data, thereby refining the fault diagnosis target and further improving the efficiency of fault diagnosis, and finally performing vehicle fault diagnosis through the BOM data and the diagnostic script corresponding to the BOM data. While realizing vehicle fault diagnosis, the present invention improves the efficiency of fault diagnosis, thereby improving the user's car experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A schematic diagram of a flow chart of an embodiment of a vehicle fault diagnosis method provided by the present invention; Figure 2 A schematic diagram of a process flow of an embodiment of a vehicle maintenance manual maintenance process provided by the present invention; Figure 3 A flowchart of an embodiment of a semantic search process provided by the present invention; Figure 4 A schematic diagram of a flow chart of an embodiment of a fuzzy search process provided by the present invention; Figure 5 A schematic diagram of a flow chart of an embodiment of a hybrid search process provided by the present invention; Figure 6 A schematic diagram of a process flow of an embodiment of a multi-fault guided diagnosis process provided by the present invention; Figure 7 A schematic diagram of a process flow of an embodiment of a vehicle fault handling process provided by the present invention; Figure 8A schematic diagram of a process flow of an embodiment of a vehicle fault diagnosis process provided by the present invention; Fig. 9 A schematic diagram of an embodiment of a semantic retrieval vector model provided by the present invention; Fig.10 A schematic diagram of an embodiment of a fuzzy retrieval model provided by the present invention; Fig.11 A schematic diagram of an embodiment of a fuzzy retrieval model provided by the present invention; Fig.12 A schematic structural diagram of an embodiment of a vehicle fault diagnosis device provided by the present invention; Fig.13 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.
[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0019] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.
[0020] Existing automobile maintenance technical information mainly exists in maintenance manuals or related maintenance CDs provided by various controller manufacturers, which mainly include DTC, fault phenomena, possible causes of faults and troubleshooting steps, etc., with the purpose of guiding users or maintenance personnel to correctly diagnose and solve vehicle faults. At present, this manual development method usually adopts an offline mode, which has problems such as high cost, long book cycle, and cumbersome editing and typesetting. Some automobile manufacturers have also adopted an online writing system based on DITA concepts and XML technology. This system can greatly improve the speed of book production, realize the decentralized writing mode of manuals, and make full use of previous resources.
[0021] However, the maintenance information currently provided to after-sales maintenance personnel is displayed in the form of documents, which makes it difficult for maintenance personnel to retrieve; and it is unable to automatically associate with the vehicle loading information, and the repair / replacement plan of the parts after diagnosis needs to be queried in conjunction with the manufacturing system; during the maintenance process, the query of the software and hardware versions of the electronic control parts requires the use of additional diagnostic instruments or other tools to read their information, and maintenance personnel need to master the use of other tools.
[0022] In order to solve the above problems, the present invention provides a vehicle fault diagnosis method.
[0023] The specific embodiments are described in detail below: A specific embodiment of the present invention discloses a vehicle fault diagnosis method, combining Figure 1 Come and see, Figure 1 The flowchart of an embodiment of the vehicle fault diagnosis method provided by the present invention includes steps S101 to S103, wherein: In step S101, a fault handling solution corresponding to the fault information is retrieved in a fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; In step S102, the component data corresponding to the fault handling solution is associated with the BOM data of the PDM, and a diagnosis script corresponding to the BOM data is determined based on the BOM data; In step S103, vehicle fault diagnosis is performed based on the BOM data and a diagnosis script corresponding to the BOM data.
[0024] During implementation, the vehicle fault information can be obtained first. The vehicle fault information can include fault codes and / or fault descriptions. The fault codes can include DTC, vehicle identification number (VIN), etc. The fault description can be a paragraph describing the fault phenomenon. The vehicle fault information can be reported by the vehicle to the Internet of Vehicles platform, and then the fault information can be obtained from the Internet of Vehicles platform.
[0025] After obtaining the fault information, the fault handling solution corresponding to the fault information can be retrieved in the fault knowledge graph based on the text data contained in the fault information. The fault knowledge graph can be constructed based on data such as maintenance manuals and historical fault information. By retrieving the fault handling solution corresponding to the fault information in the fault knowledge graph, the efficiency of fault diagnosis can be effectively improved.
[0026] After determining the fault handling solution corresponding to the fault information, the component data corresponding to the fault handling solution can be determined first, that is, the component data involved in the fault handling solution can be determined, and then the component data corresponding to the fault handling solution can be associated with the bill of materials (BOM) data of the product data management (PDM), and then the diagnostic script corresponding to the BOM data can be determined, so as to further refine the fault diagnosis process and improve efficiency. Finally, the vehicle fault diagnosis can be performed based on the BOM data and the diagnostic script corresponding to the BOM data.
[0027] Compared with the prior art, the vehicle fault diagnosis method provided in this embodiment first retrieves the fault handling solution corresponding to the fault information in the fault knowledge graph according to the fault information, thereby simplifying the fault retrieval process and improving the efficiency of fault diagnosis. Then, the component data corresponding to the fault handling solution is associated with the BOM data of the PDM to determine the diagnostic script corresponding to the BOM data, thereby refining the fault diagnosis target and further improving the efficiency of fault diagnosis. Finally, the vehicle fault diagnosis is performed through the BOM data and the diagnostic script corresponding to the BOM data. While realizing vehicle fault diagnosis, the present invention improves the efficiency of fault diagnosis, thereby improving the user's car experience.
[0028] Exemplarily, the retrieving a fault handling solution corresponding to the fault information in the fault knowledge graph based on the fault information includes: Based on the fault information, fuzzy retrieval and / or semantic retrieval is performed in the fault knowledge graph to obtain the fault handling solution.
[0029] Specifically, when searching for the fault handling solution corresponding to the fault information in the fault knowledge graph according to the fault information, fuzzy retrieval and / or semantic retrieval can be performed in the fault knowledge graph according to the fault information to obtain the fault handling solution. The specific retrieval method can be selected according to the content of the fault information. Searching in the fault knowledge graph by fuzzy retrieval and / or semantic retrieval can ensure the accuracy of the retrieval results, and thus ensure the accuracy of the fault diagnosis.
[0030] Exemplarily, the performing fuzzy retrieval and / or semantic retrieval in the fault knowledge graph based on the fault information to obtain the fault handling solution includes: In the case where the fault information only includes a fault code, a fuzzy search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information only includes a fault description, a semantic search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information includes a fault code and a fault description, fuzzy retrieval and semantic retrieval are performed in the fault knowledge graph to obtain the fault handling solution.
[0031] Specifically, when performing fuzzy retrieval and / or semantic retrieval in the fault knowledge graph according to the fault information to obtain the fault handling solution, it is necessary to determine whether to perform semantic retrieval according to whether the fault information includes a fault description, and for the fault code included in the fault information, fuzzy retrieval can be used. Selecting the corresponding retrieval method according to the content included in the fault information can ensure the retrieval efficiency and retrieval accuracy, thereby ensuring the efficiency and accuracy of fault diagnosis.
[0032] Exemplarily, performing fuzzy search in the fault knowledge graph to obtain the fault handling solution includes: Based on the fault code included in the fault information, text similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
[0033] Specifically, when fuzzy retrieval is performed in the fault knowledge graph, text similarity matching can be performed in the fault knowledge graph according to the fault code included in the fault information to obtain a fault handling solution. For example, after the fault code is segmented and stop words are removed, text similarity matching can be performed in the fault knowledge graph to obtain a fault handling solution.
[0034] Exemplarily, performing semantic retrieval in the fault knowledge graph to obtain the fault handling solution includes: Based on the fault description included in the fault information, semantic similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
[0035] Specifically, when semantic retrieval is performed in the fault knowledge graph, semantic similarity matching can be performed in the fault knowledge graph according to the fault description included in the fault information to obtain a fault handling solution. For example, a semantic vector can be extracted from the fault description and the fault knowledge graph by a semantic vector extraction model such as a BGE model, and then the similarity of the semantic vectors can be calculated (for example, the semantic similarity can be determined by calculating the Euclidean distance, or the cosine similarity can be directly calculated), and then the fields corresponding to the semantic vectors whose semantic similarity is greater than a preset threshold are output to obtain a fault handling solution.
[0036] Exemplarily, performing fuzzy retrieval and semantic retrieval in the fault knowledge graph to obtain the fault handling solution includes: The results of fuzzy retrieval and semantic retrieval are deduplicated and reordered to obtain the fault handling solution.
[0037] Specifically, when fuzzy retrieval and semantic retrieval are performed in the fault knowledge graph to obtain a fault handling solution, the results of the fuzzy retrieval and semantic retrieval can be deduplicated and reordered to obtain a fault handling solution.
[0038] Exemplarily, the fault knowledge graph is constructed based on a vehicle maintenance manual, a vehicle maintenance work order, a vehicle transfer order, and a vehicle technical journal.
[0039] Specifically, the fault knowledge graph can be constructed based on materials such as vehicle maintenance manuals, vehicle maintenance work orders, vehicle transfer orders (TR orders), and vehicle technical journals, so as to cover all possible fault scenarios.
[0040] The technical solution of the present invention is better described below with reference to a specific embodiment: The vehicle fault diagnosis method provided by the present invention may include a maintenance manual knowledge platform and a user terminal APP. The user may obtain the fault DTC information reported by the faulty vehicle through the APP, and associate the maintenance knowledge content in the maintenance manual platform with the DTC code. The APP displays the vehicle fault phenomenon and fault code maintenance and disposal suggestions, and matches the knowledge graph to accurately and efficiently perform maintenance troubleshooting steps, and automatically associates the component information of the entire vehicle based on the PDM component BOM, thereby lowering the threshold for fault repair and improving efficiency.
[0041] The fault repair manual platform uses AI to identify maintenance manuals and other documents into the knowledge graph database, uses the knowledge graph to describe the construction relationship between knowledge and vehicle systems, associates multiple fault codes with fault phenomenon inference machines, and identifies key components in various fault handling processes. It associates the PDM's vehicle BOM static data and the actual vehicle controller's diagnostic script to obtain its dynamic data. After-sales personnel can directly match faulty parts to facilitate after-sales repair and replacement of faulty parts.
[0042] Maintenance manuals can be structured to construct knowledge graphs. The knowledge graph data comes from historical maintenance manuals of commercial vehicles, work orders, TR orders, technical journals and other documents. Through natural language analysis, schema recognition of offline files is performed to form diagnostic atomic data, and labels and classifications are generated. Key information such as fault phenomena and DTC are semantically vectorized through BGE and vector databases. During use, users can form accurate maintenance plans and measures through vector similarity calculations and understanding of the association relationships of knowledge graphs.
[0043] Combination Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of the vehicle maintenance manual maintenance process provided by the present invention. When vehicle maintenance manual maintenance is required, the BOM data, fault code data and controller maintenance information configuration information of the newly added controller can be added to the maintenance manual.
[0044] The semantic vector model is mainly used for knowledge alignment / knowledge association in the process of knowledge graph construction, and is mainly used for semantic understanding in the application process of knowledge graph. It converts the query information input by the user into a semantic vector, which enables the model to calculate the semantic similarity in the vector space. Based on the vector database and the graph database, it enables the actual query function / question and answer function / guided troubleshooting function of the business. The query function of the present invention has three input methods: 1. VIN&DTC|fault description; 2. DTC|fault description; 3. VIN. The business scenarios corresponding to the above three input methods are also different, and have different requirements for the accuracy of the retrieval function. For input methods 1 and 2, a semantic retrieval function is required; and for the third function, only a fuzzy retrieval function is required.
[0045] Semantic retrieval requires converting the text information (excluding the DTC code) input by the user into a semantic vector, and then calculating the similarity between the queried semantic vector and the data in the vector database, and outputting the data with a similarity greater than a threshold. Based on the results returned by the semantic retrieval, the corresponding node data and related data are searched in the graph and returned, and sorted again. Figure 3 Come and see, Figure 3 A flowchart of an embodiment of a semantic search process provided by the present invention.
[0046] Fuzzy search is to find the data containing the keywords in the input string from the database and output it based on the input string. On the one hand, when entering VIN / DTC in the front-end interface, you can also enter some keyword data, filter out related data for users to choose and input, and improve input efficiency; on the other hand, if there are new professional terms that cannot be found by the semantic model, you can also perform fuzzy search on the graph database. The specific process is as follows: After fuzzy matching the input data, the data containing the keywords will be recalled for use in subsequent sorting or output results. Figure 4 Come and see, Figure 4 A schematic diagram of a fuzzy search process according to an embodiment of the present invention.
[0047] Hybrid search is to use fuzzy search and semantic search at the same time. In this way, the recall rate and accuracy of the function are relatively high and the reliability is better than that of single search in the query business scenario with fault phenomenon. Semantic search can only guarantee the return of data with semantic similarity greater than the threshold. However, for users, there are still differences in visual recognition of data with high semantic similarity. Fuzzy search can increase the matching of text similarity, and then output it in reverse order according to the results of text similarity. Figure 5 Come and see, Figure 5 A schematic diagram of a flow chart of an embodiment of a hybrid search process provided by the present invention.
[0048] The present invention also realizes the retrieval process under multiple DTC conditions through hybrid retrieval and DTC guided diagnosis. Figure 6 Come and see, Figure 6 A schematic diagram of a flow chart of an embodiment of a multi-fault guided diagnosis process provided by the present invention.
[0049] Combination Figure 7 Come and see, Figure 7 This is a flow chart of an embodiment of the vehicle fault handling process provided by the present invention. The vehicle reports the DTC code / fault phenomenon to the Internet of Vehicles platform, and the fault data is pushed from the Internet of Vehicles platform to the diagnostic platform. The diagnostic platform pushes the fault data to the maintenance manual service. The maintenance manual is associated with the BOM and the diagnostic script for after-sales maintenance processing (including repair / replacement of parts, OTA software upgrades, etc.).
[0050] Combination Figure 8 Come and see, Figure 8 This is a flow chart of an embodiment of a vehicle fault diagnosis process provided by the present invention. The specific process is described as follows: 1. The vehicle reports a fault code or fault phenomenon.
[0051] 2. The terminal APP receives fault information pushed from the diagnostic platform.
[0052] 3. Based on the fault phenomenon description or fault code information, search and match the maintenance manual through the knowledge graph.
[0053] 4. The maintenance manual solution is related to the faulty controller parts.
[0054] 5. The faulty controller part information is associated with the component BOM in PDM.
[0055] 6. Through step 5, the maintenance manual automatically sends the diagnostic script of the component to the diagnostic platform.
[0056] 7. The maintenance manual platform receives dynamic information from the controller.
[0057] 8. The data is transmitted back to the terminal APP to facilitate maintenance technicians to handle faulty parts.
[0058] Combination Fig. 9 Come and see, Fig. 9 This is a schematic diagram of an embodiment of the semantic retrieval vector model provided by the present invention. When searching for content, semantic retrieval can be performed through cosine similarity.
[0059] Combination Fig.10 Come and see, Fig.10 This is a schematic diagram of an embodiment of a fuzzy retrieval model provided by the present invention. When searching for content, fuzzy retrieval can be performed through a data algorithm containing keywords.
[0060] Combination Fig.11 Come and see, Fig.11 This is a schematic diagram of an embodiment of the fuzzy retrieval model provided by the present invention. When searching for content, the outputs of semantic retrieval and fuzzy retrieval can be fused / deduplicated and re-sorted to obtain the final search results.
[0061] In the present invention, users can collect remote Internet of Vehicles data of the faulty vehicle through the APP, obtain the fault code information of the faulty vehicle, and then collect the faulty vehicle signal to the diagnosis platform in real time through the knowledge graph, fault code and fault phenomenon. The diagnosis platform analyzes the vehicle signal and compares it, automatically makes decisions based on the results, outputs the final solution, and guides maintenance personnel to troubleshoot the problem.
[0062] The embodiment of the present invention also provides a vehicle fault diagnosis device, combined with Fig.12 Come and see, Fig.12 This is a schematic diagram of the structure of an embodiment of a vehicle fault diagnosis device provided by the present invention. The vehicle fault diagnosis device 1200 includes: A retrieval module 1201 is used to retrieve a fault handling solution corresponding to the fault information in the fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; A determination module 1202 is used to associate the component data corresponding to the fault handling solution with the BOM data of the PDM, and determine the diagnosis script corresponding to the BOM data based on the BOM data; The diagnosis module 1203 is used to perform vehicle fault diagnosis based on the BOM data and the diagnosis script corresponding to the BOM data.
[0063] The specific implementation of each module of the vehicle fault diagnosis device can refer to the description of the above-mentioned vehicle fault diagnosis method, and has similar beneficial effects, which will not be repeated here.
[0064] The embodiment of the present invention further provides an electronic device, Fig.13 Come and see, Fig.13 This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 1300 includes a processor 1301, a memory 1302, and a computer program stored in the memory 1302 and executable on the processor 1301. When the processor 1301 executes the program, the vehicle fault diagnosis method as described above is implemented.
[0065] As a preferred embodiment, the electronic device 1300 further includes a display 1303 for displaying the vehicle fault diagnosis method as executed by the processor 1301 .
[0066] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 1302, and are executed by the processor 1301 to complete the present invention. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 1300. For example, the computer program may be divided into the retrieval module 1201, the determination module 1202, and the diagnosis module 1203 in the above embodiment. The specific functions of each module are as described above, and are not described one by one here.
[0067] The electronic device 1300 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.
[0068] Among them, the processor 1301 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 1301 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0069] The memory 1302 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 1302 is used to store programs, and the processor 1301 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 1301 or implemented by the processor 1301.
[0070] The display 1303 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.
[0071] Understandably, Fig.13 The structure shown is only a schematic diagram of the structure of the electronic device 1300. The electronic device 1300 may also include Fig.13 More or fewer components as shown. Fig.13 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0072] The electronic device provided according to the above embodiment of the present invention can be implemented with reference to the specific description of the vehicle fault diagnosis method described above according to the present invention, and has similar beneficial effects as the vehicle fault diagnosis method described above, which will not be repeated here.
[0073] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle fault diagnosis method as described above is implemented.
[0074] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.
[0075] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0076] Computer program codes for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. may be used. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0077] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0078] The present invention discloses a vehicle fault diagnosis method, device, electronic device and storage medium. Firstly, a fault handling solution corresponding to the fault information is retrieved in a fault knowledge graph according to the fault information, thereby simplifying the fault retrieval process and improving the efficiency of fault diagnosis. Then, the component data corresponding to the fault handling solution is associated with the BOM data of the PDM to determine the diagnosis script corresponding to the BOM data, thereby refining the fault diagnosis target and further improving the efficiency of fault diagnosis. Finally, the vehicle fault diagnosis is performed through the BOM data and the diagnosis script corresponding to the BOM data. While realizing vehicle fault diagnosis, the present invention improves the efficiency of fault diagnosis, thereby improving the user's vehicle experience.
[0079] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A vehicle fault diagnosis method, characterized in that: include: Retrieving a fault handling solution corresponding to the fault information in a fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; Associating component data corresponding to the fault handling solution with BOM data of the PDM, and determining a diagnostic script corresponding to the BOM data based on the BOM data; Vehicle fault diagnosis is performed based on the BOM data and a diagnosis script corresponding to the BOM data.
2. The vehicle fault diagnosis method according to claim 1, characterized in that: The retrieving a fault handling solution corresponding to the fault information in the fault knowledge graph based on the fault information includes: Based on the fault information, fuzzy retrieval and / or semantic retrieval is performed in the fault knowledge graph to obtain the fault handling solution.
3. The vehicle fault diagnosis method according to claim 2, characterized in that: Based on the fault information, fuzzy retrieval and / or semantic retrieval are performed in the fault knowledge graph to obtain the fault handling solution, including: In the case where the fault information only includes a fault code, a fuzzy search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information only includes a fault description, a semantic search is performed in the fault knowledge graph to obtain the fault handling solution; In the case where the fault information includes a fault code and a fault description, fuzzy retrieval and semantic retrieval are performed in the fault knowledge graph to obtain the fault handling solution.
4. The vehicle fault diagnosis method according to claim 3, characterized in that: The fuzzy search is performed in the fault knowledge graph to obtain the fault handling solution, including: Based on the fault code included in the fault information, text similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
5. The vehicle fault diagnosis method according to claim 3, characterized in that: The performing semantic retrieval in the fault knowledge graph to obtain the fault handling solution includes: Based on the fault description included in the fault information, semantic similarity matching is performed in the fault knowledge graph to obtain the fault handling solution.
6. The vehicle fault diagnosis method according to claim 3, characterized in that: The fuzzy search and semantic search are performed in the fault knowledge graph to obtain the fault handling solution, including: The results of fuzzy retrieval and semantic retrieval are deduplicated and reordered to obtain the fault handling solution.
7. The vehicle fault diagnosis method according to any one of claims 1 to 6, characterized in that: The fault knowledge graph is constructed based on vehicle maintenance manuals, vehicle maintenance work orders, vehicle transfer orders and vehicle technical journals.
8. A vehicle fault diagnosis device, characterized in that: include: A retrieval module, used to retrieve a fault handling solution corresponding to the fault information in the fault knowledge graph based on the fault information, wherein the fault information includes a fault code and / or a fault description; A determination module, used to associate the component data corresponding to the fault handling solution with the BOM data of the PDM, and determine the diagnosis script corresponding to the BOM data based on the BOM data; A diagnosis module is used to perform vehicle fault diagnosis based on the BOM data and a diagnosis script corresponding to the BOM data.
9. An electronic device, characterized in that: The invention comprises a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the vehicle fault diagnosis method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the vehicle fault diagnosis method as claimed in any one of claims 1 to 7 is implemented.