Fault diagnosis system and construction method thereof, storage medium and computer

Abstract

The invention provides a fault diagnosis system and a construction method thereof, a storage medium and a computer, and the method constructs an ontology architecture of a fault knowledge graph, and processes maintenance data and historical fault diagnosis data into structured maintenance data and structured diagnosis data based on the ontology architecture of the fault knowledge graph. And further performing knowledge association on the structured maintenance data and the structured diagnosis data to obtain structured diagnosis maintenance data, associating maintenance knowledge with fault diagnosis knowledge, and obtaining a target fault knowledge graph in combination with an ontology architecture of the fault knowledge graph. According to the fault diagnosis system, the construction method thereof, the storage medium and the target fault knowledge graph in the computer, various maintenance knowledge and fault diagnosis knowledge can be effectively associated, maintenance personnel can be accurately guided to find fault points, sufficient maintenance knowledge can be provided together, and the fault diagnosis and maintenance efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile fault diagnosis, and in particular to a fault diagnosis system and a construction method thereof, a storage medium and a computer. Background Art

[0002] The traditional after-sales maintenance method is that when a customer's vehicle breaks down, the maintenance technician uses personal experience and the maintenance manual provided by the OEM to continuously try to troubleshoot the problem. If the problem cannot be solved, the technician will request support from the OEM's experts to ultimately resolve the vehicle failure.

[0003] Among them, the traditional after-sales maintenance method relies heavily on the personal experience of maintenance technicians, but the personal experience of maintenance technicians is limited, and it is difficult to take into account the maintenance needs of various models. Moreover, after the superposition of multiple technical faults, the difficulty of manual troubleshooting will be greatly increased, making manual diagnosis and maintenance less efficient and time-consuming. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a fault diagnosis system and its construction method, storage medium and computer to solve the problem that the repair of vehicle faults in the prior art mainly depends on the personal experience of the maintenance technician, while the efficiency of manual diagnosis and repair is low.

[0005] One aspect of the present invention provides a method for constructing a fault diagnosis system, comprising:

[0006] Construct the ontology architecture of fault knowledge graph;

[0007] Obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data;

[0008] Obtaining structured diagnostic data according to the historical fault diagnosis data and the ontology architecture of the fault knowledge graph;

[0009] According to the ontology architecture of the fault knowledge graph, the structured maintenance data and the structured diagnosis data are subjected to knowledge association processing to obtain structured diagnosis maintenance data;

[0010] According to the structured diagnosis and maintenance data and the ontology architecture of the fault knowledge graph, a target fault knowledge graph is obtained to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

[0011] Optionally, the sequential root nodes of the ontology architecture of the fault knowledge graph include fault phenomenon, fault cause, fault point, maintenance measures and maintenance content, wherein the fault cause is a multi-level structure, and the data element of each fault cause also includes the failure probability of the fault cause.

[0012] Optionally, the step of obtaining structured maintenance data further includes: obtaining a parts catalog and maintenance and disassembly step information of each part according to the structured maintenance data, wherein the parts catalog includes the name and code of the parts department.

[0013] Optionally, the step of obtaining structured diagnostic maintenance data further includes: obtaining fault-causing parts according to the structured diagnostic data, and semantically matching the fault-causing parts with parts in a parts catalog to perform knowledge association between the structured maintenance data and the structured diagnostic data.

[0014] Optionally, the step of obtaining structured diagnosis and maintenance data further includes: merging data having a semantic similarity greater than a merging threshold.

[0015] The present invention also provides a fault diagnosis system, comprising:

[0016] Graph management module, used to build the ontology architecture of fault knowledge graph;

[0017] A first data processing module, used for obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data;

[0018] A second data processing module, used to obtain structured diagnostic data according to the historical fault diagnosis data and the ontology architecture of the fault knowledge graph;

[0019] A third data processing module, configured to perform knowledge association processing on the structured maintenance data and the structured diagnosis data according to the ontology architecture of the fault knowledge graph, so as to obtain structured diagnosis maintenance data;

[0020] Among them, the graph management module is also used to obtain a target fault knowledge graph based on the structured diagnostic and maintenance data and the ontology architecture of the fault knowledge graph, so as to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

[0021] Optionally, the sequential root nodes of the ontology architecture of the fault knowledge graph include fault phenomenon, fault cause, fault point, maintenance measures and maintenance content, wherein the fault cause is a multi-level structure, and the number of levels is less than or equal to four.

[0022] Optionally, the first data processing module includes a PP-StructureV2 document analysis model, and the second data processing module includes a 13B-LLM large model.

[0023] The present invention also provides a storage medium, which is a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium. When the computer program is read and executed by a processor, it is used to implement the above-mentioned fault diagnosis system.

[0024] The present invention also provides a computer, wherein a computer program is stored therein, and when the computer program is read and executed by a processor, it is used to implement the above-mentioned fault diagnosis system.

[0025] The method for constructing a fault diagnosis system provided by the present invention includes: constructing an ontology architecture of a fault knowledge graph; obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data; obtaining structured diagnosis data according to historical fault diagnosis data and the ontology architecture of the fault knowledge graph; performing knowledge association processing on the structured maintenance data and the structured diagnosis data according to the ontology architecture of the fault knowledge graph to obtain structured diagnosis and maintenance data; obtaining a target fault knowledge graph according to the structured diagnosis and maintenance data and the ontology architecture of the fault knowledge graph to guide the diagnosis and maintenance of faults according to the target fault knowledge graph. The method for constructing a fault diagnosis system provided by the present invention can integrate and associate maintenance data and historical fault diagnosis data, and the obtained structured diagnosis and maintenance data includes fault diagnosis data and maintenance data of various vehicle models, which can efficiently guide maintenance personnel to diagnose various faults of various vehicle models, and can also provide detailed maintenance data to improve the efficiency of diagnosis and maintenance.

[0026] The fault diagnosis system provided by the present invention can integrate and associate maintenance data and historical fault diagnosis data, efficiently guide maintenance personnel to diagnose various faults of various vehicle models, and can also provide detailed maintenance data to improve diagnosis and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the main process of the method for constructing a fault diagnosis system in an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of the architecture of the fault knowledge graph of the fault diagnosis system in an embodiment of the present invention;

[0029] Figure 3 Schematic diagram of the main module structure of the fault diagnosis system in an embodiment of the present invention.

[0030] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0031] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0032] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0034] In order to solve the problem that the repair of vehicle failures in the prior art mainly relies on the personal experience of maintenance technicians, while the efficiency of manual diagnosis and maintenance is low, the present invention provides a method for constructing a fault diagnosis system and a fault diagnosis system, which processes maintenance data and historical fault diagnosis data into structured data based on the ontology architecture of the created fault knowledge graph, so as to associate fault diagnosis with related maintenance knowledge. The obtained target fault knowledge graph includes diagnosis and maintenance knowledge of various fault phenomena, which can effectively guide the diagnosis and maintenance of various vehicle models and various faults, reduce the dependence on the personal experience of maintenance technicians, and improve maintenance efficiency.

[0035] Specifically, Figure 1 FIG. 1 is a schematic diagram of the main flow of a method for constructing a fault diagnosis system according to an embodiment of the present invention, including:

[0036] Step S01: constructing the ontology architecture of the fault knowledge graph;

[0037] Step S02: obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data;

[0038] Step S03: obtaining structured diagnostic data according to the historical fault diagnosis data and the ontology architecture of the fault knowledge graph;

[0039] Step S04: performing knowledge association processing on the structured maintenance data and the structured diagnosis data according to the ontology architecture of the fault knowledge graph to obtain structured diagnosis maintenance data;

[0040] Step S05: According to the structured diagnosis and maintenance data and the ontology architecture of the fault knowledge graph, a target fault knowledge graph is obtained to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

[0041] Based on the ontology architecture of the fault knowledge graph, the maintenance information data and historical fault diagnosis data are structured and parsed. The obtained data elements are matched with the nodes of the fault knowledge graph, and the association relationship between the data elements is established according to the root-branch relationship between the nodes of the fault knowledge graph. Therefore, based on the root-branch relationship between the nodes of the fault knowledge graph and starting from the fault phenomenon, the fault point, corresponding maintenance measures and maintenance content can be gradually confirmed, thereby achieving guidance on fault diagnosis and maintenance.

[0042] In step S01, Figure 2 As shown, the sequential root nodes of the ontology architecture of the fault knowledge graph include fault phenomenon, fault cause, fault point, maintenance measures and maintenance content, wherein the fault cause is a multi-level structure, and the data element of each fault cause also includes the failure probability of the fault cause.

[0043] In a specific example, the user inputs the actual fault phenomenon into the fault diagnosis system. The system first analyzes the actual fault phenomenon, confirms the actual fault cause, obtains the semantic information of the actual fault cause through a large language model, and compares the semantic information with the semantic information of each data element in the fault cause node in the target fault knowledge graph. The fault cause in the target fault knowledge graph whose semantic information similarity with the actual fault cause is greater than a preset similarity threshold (for example, 90%) is taken as the target fault cause. Then, the target fault cause and its next-level information are displayed in the root-branch order of the target fault knowledge graph, where the next-level information may include multiple items and are arranged in probability order. The user then selects one of them based on the actual fault phenomenon to advance to the next level until the final maintenance measures and maintenance content are confirmed. When the maintenance measures and maintenance content of the current node flow do not match the actual fault phenomenon, the user can return to the previous node and select other items.

[0044] When the database of the target fault knowledge graph lacks diagnostic and maintenance knowledge of the actual fault phenomenon, the information can be reported after the maintenance is completed. The reported information is added to the database of historical fault diagnosis data according to the structured template file. After processing, the data of the target fault knowledge graph can be expanded to continuously improve the fault diagnosis and maintenance guidance capabilities of the fault diagnosis system.

[0045] To facilitate the guidance of maintenance and disassembly, in this embodiment, in step S02, the step of obtaining structured maintenance data also includes: obtaining a parts catalog and maintenance and disassembly step information of each part according to the structured maintenance data, wherein the parts catalog includes the name and code of the parts department.

[0046] Maintenance data data generally include maintenance manuals, circuit schematics, etc. In order to achieve structured processing of the information therein, the PP-StructureV2 document analysis model can be used to analyze the maintenance manuals and circuit schematics. The images, tables, texts, titles, content information, etc. in the maintenance data data such as maintenance manuals and circuit schematics can be extracted and then stored as structured maintenance data. The content of each data element in the structured maintenance data can be attributed to the corresponding node of the fault knowledge graph.

[0047] In step S03, historical fault diagnosis data generally includes quality report sheets, product problem reports, maintenance cases and other data, and its data format is generally consistent with the preset structured template, and the information content is relatively easy to obtain. It can be processed by large language models such as 13B-LLM to effectively obtain the information. The data obtained by analysis includes information such as fault phenomenon, faulty parts, fault codes, and maintenance methods. Through word vectorization and combined with the ontology architecture of the fault knowledge graph, the information is divided into various data elements according to the fault knowledge graph, and each data element can be attributed to the corresponding node of the fault knowledge graph.

[0048] In order to achieve the association between structured maintenance data and structured diagnostic data, in this embodiment, the step of obtaining structured diagnostic maintenance data also includes: obtaining fault-causing parts based on the structured diagnostic data, and semantically matching the fault-causing parts with parts in the parts catalog to perform knowledge association between the structured maintenance data and the structured diagnostic data.

[0049] At the same time, based on the architecture of the fault knowledge graph, the upper and lower data elements of the corresponding nodes of the faulty parts in the structured diagnostic data and structured maintenance data can be associated and merged. That is, in the step of obtaining structured diagnostic maintenance data, data with semantic similarity greater than the merging threshold are also merged to improve the quality of database data.

[0050] In data merging, in addition to requiring the semantic similarity to be greater than the merging threshold, the component codes of the faulty components involved in the merged data are also compared. When their component codes are completely matched, they are judged to be merged, which can ensure the accuracy of data association and fault diagnosis.

[0051] Specifically, step S04 and step S05 may include: reading structured diagnostic data and structured maintenance data, performing knowledge association on the read data, building entity tags based on the architecture of the fault knowledge graph, and creating graph entities and the relationships between graph entities based on the entity tags, writing the associated data into the corresponding graph entities, removing duplicate data, and generating a target fault knowledge graph.

[0052] The present invention also provides a fault diagnosis system, such as Figure 3 As shown, it mainly includes: a map management module 10, a first data processing module 20, a second data processing module 30 and a third data processing module 40.

[0053] Among them, the graph management module 10 is used to construct the ontology architecture of the fault knowledge graph; the first data processing module 20 is used to obtain structured maintenance data according to the ontology architecture of the fault knowledge graph and the maintenance data data; the second data processing module 30 is used to obtain structured diagnostic data according to historical fault diagnosis data and the ontology architecture of the fault knowledge graph; the third data processing module 40 is used to perform knowledge association processing on the structured maintenance data and the structured diagnostic data according to the ontology architecture of the fault knowledge graph to obtain structured diagnostic maintenance data; the graph management module 10 is also used to obtain a target fault knowledge graph according to the structured diagnostic maintenance data and the ontology architecture of the fault knowledge graph, so as to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

[0054] The graph management module 10 also communicates with the human-computer interaction device 50 to identify and process the fault information (which may be language information or fault code) input by the human-computer interaction device 50, extract the fault phenomenon information therefrom, and then obtain the semantic vector of the fault phenomenon information based on the large language model, and compare it with the vector database of fault causes in the structured diagnosis and maintenance data, and select the fault cause in the structured diagnosis and maintenance data whose semantic similarity is greater than the semantic similarity threshold as the target fault cause, and provide the information of the next level node according to the node order of the target fault knowledge graph, and output it to the human-computer interaction device for display, so as to provide diagnostic and maintenance guidance for users.

[0055] The first data processing module 20 includes the PP-StructureV2 document analysis model, and the second data processing module 30 includes the 13B-LLM large model, which can meet their respective data processing requirements. In practice, other analysis models can also be selected.

[0056] The present invention also provides a storage medium, which is a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium. When the computer program is read and executed by a processor, it is used to implement the above-mentioned fault diagnosis system.

[0057] The present invention also provides a computer, wherein a computer program is stored therein, and when the computer program is read and executed by a processor, it is used to implement the above-mentioned fault diagnosis system.

[0058] Those skilled in the art will appreciate that the logic or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0059] More specific examples of computer-readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in another suitable manner as necessary, and then stored in a computer memory.

[0060] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0061] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0062] The above-mentioned embodiments only express several specific implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for constructing a fault diagnosis system, characterized in that: include: Construct the ontology architecture of fault knowledge graph; Obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data; Obtaining structured diagnostic data according to the historical fault diagnosis data and the ontology architecture of the fault knowledge graph; According to the ontology architecture of the fault knowledge graph, the structured maintenance data and the structured diagnosis data are processed for knowledge association to obtain structured diagnosis maintenance data; According to the structured diagnosis and maintenance data and the ontology architecture of the fault knowledge graph, a target fault knowledge graph is obtained to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

2. The method for constructing a fault diagnosis system according to claim 1, characterized in that: The sequential root nodes of the ontology architecture of the fault knowledge graph include fault phenomenon, fault cause, fault point, maintenance measures and maintenance content, wherein the fault cause is a multi-level structure, and the data element of each fault cause also includes the failure probability of the fault cause.

3. The method for constructing a fault diagnosis system according to claim 1, characterized in that: The step of obtaining structured maintenance data further includes: obtaining a parts catalog and maintenance and disassembly step information of each part according to the structured maintenance data, wherein the parts catalog includes the name and code of the parts department.

4. The method for constructing a fault diagnosis system according to claim 3, characterized in that: The step of obtaining structured diagnostic maintenance data also includes: obtaining fault-causing parts according to the structured diagnostic data, and semantically matching the fault-causing parts with parts in a parts catalog to perform knowledge association between the structured maintenance data and the structured diagnostic data.

5. The method for constructing a fault diagnosis system according to claim 1, characterized in that: The step of obtaining structured diagnosis and maintenance data further includes: merging data with semantic similarity greater than a merging threshold.

6. A fault diagnosis system, characterized in that: include: Graph management module, used to build the ontology architecture of fault knowledge graph; A first data processing module, used for obtaining structured maintenance data according to the ontology architecture of the fault knowledge graph and maintenance data; A second data processing module, used to obtain structured diagnostic data according to the historical fault diagnosis data and the ontology architecture of the fault knowledge graph; A third data processing module, configured to perform knowledge association processing on the structured maintenance data and the structured diagnosis data according to the ontology architecture of the fault knowledge graph, so as to obtain structured diagnosis maintenance data; Among them, the graph management module is also used to obtain a target fault knowledge graph based on the structured diagnostic and maintenance data and the ontology architecture of the fault knowledge graph, so as to guide the diagnosis and maintenance of the fault according to the target fault knowledge graph.

7. The fault diagnosis system according to claim 6, characterized in that: The sequential root nodes of the ontology architecture of the fault knowledge graph include fault phenomenon, fault cause, fault point, maintenance measures and maintenance content, wherein the fault cause is a multi-level structure, and the number of levels is less than or equal to four.

8. The fault diagnosis system according to claim 6, characterized in that: The first data processing module includes the PP-StructureV2 document analysis model, and the second data processing module includes the 13B-LLM large model.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium. When the computer program is read and executed by a processor, it is used to implement the fault diagnosis system according to any one of claims 6 to 8.

10. A computer, characterized in that: The computer stores a computer program, which is used to implement the fault diagnosis system according to any one of claims 6 to 8 when the computer program is read and executed by the processor.

Images