Fault analysis method, electronic equipment and storage medium
By building a fault knowledge graph and utilizing preset models, the problem of low efficiency of manual experience failure analysis is solved, and more efficient and accurate fault solution generation is achieved.
Patent Information
- Application Number
- CN202410045800.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-10
- Publication Date
- 2025-07-11
AI Technical Summary
In the prior art, fault analysis relies on manual experience, resulting in poor efficiency and low accuracy, especially in industrial production and error-prone.
Build a first fault knowledge graph and a second fault knowledge graph, determine the target fault name through the fault description information entered by the user, and find the corresponding fault information in the graph, and use the preset model to generate a fault solution.
Improves the efficiency and accuracy of fault analysis, avoids the difficulty of finding information due to name mismatch, and outputs richer and more reliable solutions.
Smart Images
Figure CN120295819A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing, and particularly to a fault analysis method, an electronic device, and a storage medium. Background Art
[0002] In different fields, fault analysis (FA) often relies on manual experience to conduct one-by-one inspections. This operation method will lead to poor efficiency and low accuracy in product fault analysis. Taking the industrial production field as an example, in order to improve the production efficiency and quality of products, it is necessary to manually draw a fishbone diagram based on experience and conduct experimental inspections for each fault cause in the fishbone diagram. However, this experimental inspection method is not only very time-consuming but also prone to errors, thus reducing the efficiency of fault analysis and affecting industrial production. Summary of the Invention
[0003] In view of the above, it is necessary to provide a fault analysis method, an electronic device, and a storage medium that can solve the technical problem of poor efficiency in fault analysis.
[0004] On the one hand, this application provides a fault analysis method, and the method includes: constructing a first fault knowledge graph and a second fault knowledge graph based on historical fault information in a historical fault file; determining an original fault name corresponding to the fault description information based on the fault description information input by a user; searching for a target fault name corresponding to the original fault name in the first fault knowledge graph; if a text identifier corresponding to the target fault name is found in the second fault knowledge graph, obtaining target fault information corresponding to the text identifier from the historical fault file; inputting the target fault information into a preset model; and determining a target fault solution corresponding to the fault description information according to the output information of the preset model for the target fault information.
[0005] In some embodiments of this application, the constructing a first fault knowledge graph based on historical fault information in a historical fault file includes: extracting a plurality of historical fault names from the historical fault information, obtaining the original fault names similar to each of the historical fault names, determining the similarity relationship between any one of the historical fault names and each corresponding original fault name, constructing a fault name triple according to the plurality of historical fault names, each corresponding original fault name, and the similarity relationship, and constructing the first fault knowledge graph according to the fault name triple.
[0006] In some embodiments of the present application, constructing the first fault knowledge graph according to the fault name triple includes: using any one of the historical fault names in the fault name triple as the first entity node, using each of the original fault names corresponding to any one of the historical fault names as the second entity node associated with the first entity node, and using the similarity relationship as an edge to connect the first entity node with each of the associated second entity nodes to generate the first fault knowledge graph.
[0007] In some embodiments of the present application, finding the target fault name corresponding to the original fault name in the first fault knowledge graph includes: determining the historical fault name corresponding to the original fault name in the first fault knowledge graph as the target fault name.
[0008] In some embodiments of the present application, constructing the second fault knowledge graph according to the historical fault information in the historical fault file includes: extracting the fault cause and fault solution corresponding to each historical fault name from the historical fault information, determining the first association relationship between each historical fault name and each corresponding fault cause and the second association relationship between each historical fault name and each corresponding fault solution, and constructing a fault information triple according to multiple historical fault names, each fault cause, each fault solution, the first association relationship, the second association relationship, the first text identifier corresponding to each historical fault name in the historical fault file, the second text identifier corresponding to each fault cause in the historical fault file, and the third text identifier corresponding to each fault solution in the historical fault file, and constructing the second fault knowledge graph according to the fault information triple.
[0009] In some embodiments of the present application, constructing the second fault knowledge graph according to the fault information triple includes: using the fault cause corresponding to any one of the historical fault names in the fault information triple as the third entity node associated with the first entity node, using the fault solution corresponding to any one of the historical fault names in the fault information triple as the fourth entity node associated with the first entity node, using the first association relationship as an edge to connect the first entity node with the third entity node associated with the first entity node, using the second association relationship as an edge to connect the first entity node with the fourth entity node associated with the first entity node, setting the attribute of each first entity node to the corresponding first text identifier, setting the attribute of each third entity node to the corresponding second text identifier, and setting the attribute of each fourth entity node to the corresponding third text identifier to generate the second fault knowledge graph.
[0010] In some embodiments of the present application, each of the first text identifiers includes a first paragraph index of the corresponding historical fault name in the historical fault file, each of the second text identifiers includes a second paragraph index of the corresponding fault cause in the historical fault file, and each of the third text identifiers includes a third paragraph index of the corresponding fault solution in the historical fault file. The search for the text identifier corresponding to the target fault name includes: searching for the first entity node, the third entity node, and the fourth entity node to which the target fault name belongs in the second fault knowledge graph, and using the first paragraph index corresponding to the found first entity node, the second paragraph index corresponding to the found third entity node, and the third paragraph index corresponding to the found fourth entity node as the text identifier corresponding to the target fault name.
[0011] In some embodiments of the present application, if the text identifier corresponding to the target fault name is not found in the second fault knowledge graph, the method further includes: prompting the user to input information, and updating the second fault knowledge graph according to the input information, where the input information includes text identifiers, references, and fault solutions.
[0012] On the other hand, the present application provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the fault analysis method described above.
[0013] On the other hand, the present application provides a computer-readable storage medium storing at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the fault analysis method described above.
[0014] Through the above embodiments, the information in the first fault knowledge graph and the second fault knowledge graph is structured information. Since structured information has the characteristics of clear organization and easy processing, the search efficiency of the target fault name and text identifier can be improved. Since it is not necessary to check one by one through a fishbone diagram, the fault analysis efficiency can be improved. By searching for the target fault information corresponding to the target fault name in the historical fault files, it is possible to avoid the situation where the target fault information cannot be found in the historical fault files due to the difference between the original fault name and the historical fault names in the historical fault files. In addition, since the target fault information includes complete fault information with logic and coherence, such as the historical fault name, fault manifestation, fault cause, and fault solution corresponding to the fault description information, the natural language model can better understand the fault problem and user requirements, avoiding the "hallucination" problem, so that the output information includes richer, more accurate, and more reliable target fault solutions to solve the fault problem corresponding to the fault description information. Description of the Drawings
[0015] Figure 1 is a structural diagram of an electronic device provided by an embodiment of the present application.
[0016] Figure 2 is a flowchart of a fault analysis method provided by an embodiment of the present application.
[0017] Figure 3 is a flowchart of a method for constructing a first fault knowledge graph provided by an embodiment of the present application.
[0018] Figure 4 is a flowchart of a method for constructing a second fault knowledge graph provided by an embodiment of the present application.
[0019] Figure 5 is a functional module diagram of a fault analysis device provided by an embodiment of the present application. Detailed Embodiments
[0020] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0021] It should be noted that "at least one" in the present application means one or more, and "a plurality" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B may be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and drawings of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence.
[0022] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.
[0023] In different fields, fault analysis (FA) often relies on manual inspection one by one based on experience. This operation method will result in poor efficiency and low accuracy of product fault analysis. Taking the industrial production field as an example, in order to improve the production efficiency and quality of products, it is necessary to manually draw a fishbone diagram based on experience and conduct experimental inspections for each fault cause in the fishbone diagram. However, this experimental inspection method is not only very time-consuming but also prone to errors, thus reducing the efficiency of fault analysis and affecting industrial production.
[0024] To solve the above technical problems, the present application provides a fault analysis method, an electronic device, and a storage medium, which can improve the efficiency of fault analysis. The fault analysis method provided by the embodiments of the present application can be applied to one or more electronic devices.
[0025] As Figure 1 shown, it is a structural diagram of an electronic device provided by an embodiment of the present application. The electronic device 10 may be an electronic device such as a mobile phone, a tablet computer, a laptop computer, a computer, etc. The embodiments of the present application do not impose any restrictions on the specific type of the electronic device.
[0026] As Figure 1 shown, the electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is respectively coupled to the communication module 101, the memory 102, and the input / output interface 104 through the bus 105.
[0027] The communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more of the solutions for wired communication such as the universal serial bus (USB), Controller Area Network (CAN), etc. The wireless communication module may provide one or more of the solutions for wireless communication such as wireless fidelity (Wi-Fi), Bluetooth (BT), mobile communication network, frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.
[0028] The memory 102 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM). The random access memory can be directly read and written by the processor 103, can be used to store executable programs (such as machine instructions) of other running programs, and can also be used to store user and application data, etc. The random access memory may include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.
[0029] The non-volatile memory can also store executable programs and store user and application data, etc., and can be pre-loaded into the random access memory for the processor 103 to directly read and write. The non-volatile memory may include disk storage devices, flash memory.
[0030] The memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include a plurality of instructions. When the plurality of instructions are executed by the processor 103, a fault analysis method executable on the electronic device 10 can be implemented.
[0031] In other embodiments, such as Figure 1The illustrated electronic device 10 further includes an external memory interface for connecting to an external memory to implement the expansion of the storage capacity of the electronic device 10.
[0032] The processor 103 may include one or more processing units. For example, the processor 103 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.
[0033] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute the computer program stored in the memory 102 to implement the above-mentioned fault analysis method.
[0034] The input / output interface 104 is used to provide channels for user input or output. For example, the input / output interface 104 can be used to connect various input / output devices, such as a mouse, a keyboard, a touch device, a display screen, etc., so that the user can input information or visualize the information.
[0035] The bus 105 is at least used to provide a communication channel between the communication module 101, the memory 102, the processor 103, and the input / output interface 104 in the electronic device 10.
[0036] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device 10. In other embodiments of the present application, the electronic device 10 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0037] As Figure 2 shown, it is a flowchart of a fault analysis method provided by an embodiment of the present application. According to different requirements, the order of each step in this flowchart can be adjusted according to actual requirements, and some steps can be omitted. The execution subject of the method is an electronic device, such as Figure 1 the illustrated electronic device 10.
[0038] S11, construct a first fault knowledge graph and a second fault knowledge graph according to the historical fault information in the historical fault file.
[0039] In some embodiments of the present application, the historical fault file includes various historical fault information of the product. The historical fault information in the historical fault file includes, but is not limited to: historical fault names, fault causes corresponding to the historical fault names, fault solutions, and fault manifestations, etc. Since the historical fault file is obtained by collecting and recording real fault cases of the product, the historical fault information recorded in the historical fault file has accuracy, reliability, and understandability. The product can be a mobile phone, a computer, etc., and the present application does not limit the product.
[0040] In some embodiments of the present application, the first fault knowledge graph may include multiple historical fault names and original fault names similar to each historical fault name. The second fault knowledge graph includes multiple historical fault names, the fault causes, fault manifestations, and fault solutions corresponding to each historical fault name, etc. Among them, the fault causes, fault manifestations, and fault solutions in the second fault knowledge graph may be cause keywords corresponding to the complete fault causes in the historical fault file, the fault manifestations in the second knowledge graph may be information keywords corresponding to the complete fault manifestations in the historical fault file, and the fault solutions in the second knowledge graph may be solution keywords corresponding to the complete fault solutions in the historical fault file, etc.
[0041] For example, if the product is a mobile phone, the historical fault names in the historical fault file may be "charging fault" and "bright spots on the screen", etc. The information keyword of the fault manifestation corresponding to "charging fault" may be "unable to charge", the information keyword of the fault manifestation corresponding to "bright spots on the screen" may be "there are bright spots on the screen", the cause keyword of the fault cause corresponding to "charging fault" may be "battery damage", the cause keyword of the fault cause corresponding to "bright spots on the screen" may be "static electricity not discharged (removed) during the assembly process", the solution keyword of the fault solution corresponding to "charging fault" may be "battery repair", and the solution keyword of the fault solution corresponding to "bright spots on the screen" may be "static electricity repair", etc.
[0042] S12. Based on the fault description information input by the user, determine the original fault name corresponding to the fault description information.
[0043] In some embodiments of the present application, the fault description information may be any information describing the product fault, and the present application does not limit the fault description information.
[0044] In some embodiments of the present application, the electronic device may perform natural language processing (NLP) on the fault description information to obtain the original fault name corresponding to the fault description information. Among them, natural language processing includes semantic vectorization processing (Semantic Vectorization) and entity recognition processing (Entity Recognition), etc.
[0045] In this embodiment, the electronic device performs semantic vectorization processing on the fault description information to obtain a plurality of word vectors, and performs entity recognition processing on each word vector to obtain the original fault name corresponding to the fault description information.
[0046] S13. Search for the target fault name corresponding to the original fault name in the first fault knowledge graph.
[0047] In some embodiments of the present application, when the electronic device searches for the target fault name corresponding to the original fault name in the first fault knowledge graph, it includes: the electronic device determines the historical fault name corresponding to the original fault name in the first fault knowledge graph as the target fault name.
[0048] S14. Determine whether the text identifier corresponding to the target fault name is found in the second fault knowledge graph.
[0049] In some embodiments of the present application, the text identifier includes, but is not limited to: paragraph index, paragraph number, etc.
[0050] In some embodiments of the present application, each first text identifier includes the first paragraph index of the corresponding historical fault name in the historical fault file, each second text identifier includes the second paragraph index of the corresponding fault cause in the historical fault file, and each third text identifier includes the third paragraph index of the corresponding fault solution in the historical fault file. Searching for the text identifier corresponding to the target fault name includes: the electronic device searches for the first entity node, the third entity node, and the fourth entity node to which the target fault name belongs in the second fault knowledge graph, and uses the first paragraph index corresponding to the found first entity node, the second paragraph index corresponding to the found third entity node, and the third paragraph index corresponding to the found fourth entity node as the text identifier corresponding to the target fault name.
[0051] In this embodiment, if the text identifier corresponding to the target fault name is found in the second fault knowledge graph, the electronic device executes step S15, or, if the text identifier corresponding to the target fault name is not found in the second fault knowledge graph, the electronic device executes step S17.
[0052] S15. Obtain the target fault information corresponding to the text identifier from the historical fault file.
[0053] In some embodiments of the present application, if the text identifier corresponding to the target fault name includes a first paragraph index, a second paragraph index, and a third paragraph index, the electronic device determines the information of all paragraphs corresponding to the first paragraph index, the second paragraph index, and the third paragraph index in the historical fault file as the target fault information.
[0054] In this embodiment, by searching in the historical fault file through the first paragraph index, the second paragraph index, and the third paragraph index, the target fault information found can include complete fault information such as the historical fault name, fault manifestation, fault cause, and fault solution corresponding to the fault description information, which is logical and well-organized.
[0055] S16, input the target fault information into a preset model, and determine the target fault solution corresponding to the fault description information according to the output information of the preset model for the target fault information.
[0056] In some embodiments of the present application, the preset model includes a natural language processing model, and the present application does not limit the natural language processing model. For example, the natural language model can be the LLaMA model.
[0057] In this embodiment, since the target fault information includes complete fault information such as the historical fault name, fault manifestation, fault cause, and fault solution corresponding to the fault description information, which is logical and well-organized, the natural language model can better understand the fault problem and user needs, avoiding the "hallucination" problem, so that the output information includes a richer, more accurate, and more reliable target fault solution to solve the fault problem corresponding to the fault description information.
[0058] In the related art, due to the uncertainty of the training samples, the trained natural language processing model may have the "hallucination problem". The hallucination problem refers to the situation where when the input content is controversial or ambiguous, the natural language processing model outputs inaccurate or misleading responses. In addition, the information in the knowledge graph of the related art is single, the amount of information is small, and the described information is limited and rigid. Directly inputting the information obtained from the knowledge graph into the natural language processing model will cause the natural language processing model to be difficult to output richer and more effective information. In this embodiment, since the target fault information includes complete fault information such as the historical fault name, fault manifestation, fault cause, and fault solution corresponding to the fault description information, which is logical and well-organized, the natural language model can better understand the fault problem and user needs, avoiding the "hallucination" problem, so that the output information includes a richer, more accurate, and more reliable target fault solution to solve the fault problem corresponding to the fault description information.
[0059] S17. Prompt the user to input information, and update the second fault knowledge graph according to the input information.
[0060] In some embodiments of the present application, the input information includes, but is not limited to: text identifiers, reference documents, fault solutions, etc.
[0061] In some embodiments of the present application, the process of the electronic device updating the second fault knowledge graph according to the input information is basically the same as the generation process of the second fault knowledge graph, so the present application will not repeat the description.
[0062] In this embodiment, updating the second fault knowledge graph through the input information can make the second fault knowledge graph more complete and accurate.
[0063] Through the above implementation manners, the information in the first fault knowledge graph and the second fault knowledge graph is all structured information. Since the structured information has the characteristics of clear organization and easy processing, the search efficiency of the target fault name and text identifier can be improved. Since there is no need to check one by one through the fishbone diagram, the fault analysis efficiency can be improved. By searching for the target fault information corresponding to the target fault name in the historical fault files, the situation that the target fault information cannot be found in the historical fault files due to the difference between the original fault name and the historical fault name in the historical fault files can be avoided. In addition, since the target fault information is the historical fault information in the historical fault files, the target fault information has high accuracy and understandability. By inputting the target fault information into the preset model, the understanding ability of the preset model can be improved, so that the preset model can quickly and accurately output the fault solution for the fault description information, thereby improving the efficiency of fault analysis.
[0064] In some embodiments of the present application, as Figure 3 shown, it is a flowchart of a method for constructing a first fault knowledge graph provided by an embodiment of the present application, including the following steps:
[0065] S111. Extract multiple historical fault names from the historical fault information, and obtain the original fault names similar to each historical fault name.
[0066] In some embodiments of the present application, there may be multiple original fault names similar to each historical fault name. For example, the original fault names similar to the historical fault name "charging fault" may be "poor charging", "slow charging", "charging interruption", "low charging efficiency", etc.
[0067] S112. Determine the similarity relationship between any historical fault name and each corresponding original fault name.
[0068] For example, the original fault names similar to "charging failure" include "poor charging", "slow charging", "charging interruption", and "low charging efficiency". The electronic device can determine that the relationship between "charging failure" and "poor charging", "slow charging", "charging interruption", and "low charging efficiency" is similarity.
[0069] S113. Construct a fault name triple according to multiple historical fault names, each corresponding original fault name, and the similarity relationship.
[0070] In some embodiments of the present application, the fault name triple includes entity - relationship - entity. The two entities connected by the relationship in the fault name triple are each historical fault name and the original fault name similar to each historical fault name, and the relationship between the two connected entities is similarity. The fault name triple corresponding to each historical fault name can be one or more.
[0071] For example, if the original fault names similar to the historical fault name "charging failure" can be "poor charging", "slow charging", "charging interruption", and "low charging efficiency", then the fault name triples corresponding to "charging failure" can include: charging failure - similarity - poor charging, slow charging, low charging efficiency.
[0072] S114. Construct a first fault knowledge graph according to the fault name triple.
[0073] In some embodiments of the present application, the electronic device constructs a first fault knowledge graph according to the fault name triple, including: the electronic device takes any historical fault name in the fault name triple as the first entity node, takes each original fault name corresponding to any historical fault name as the second entity node associated with the first entity node, and takes the similarity relationship as the edge to connect the first entity node and each associated second entity node to generate a first fault knowledge graph.
[0074] Among them, in the first fault knowledge graph, each first entity node is connected to one or more corresponding second entity nodes.
[0075] In some embodiments of the present application, as Figure 4 shown, is a flowchart of a method for constructing a second fault knowledge graph provided by an embodiment of the present application, including the following steps:
[0076] S115. Extract the fault cause and fault solution corresponding to each historical fault name from the historical fault information.
[0077] In some embodiments of the present application, the electronic device can extract the cause keywords of the fault cause corresponding to each historical fault name and the solution keywords of the fault solution corresponding to each historical fault name.
[0078] S116. Determine a first association relationship between each historical fault name and each corresponding fault cause, and a second association relationship between each historical fault name and each corresponding fault solution.
[0079] In some embodiments of the present application, the first association relationship between each historical fault name and each corresponding fault cause is "fault cause", and the second association relationship between each historical fault name and each corresponding fault solution is "fault solution".
[0080] For example, if the association relationship between the historical fault name "charging fault" and the cause keyword "battery damage" of the fault cause is "fault cause", and the second association relationship between the historical fault name "charging fault" and the solution keyword "battery repair" of the corresponding fault solution is "fault solution".
[0081] S117. Construct a fault information triple according to multiple historical fault names, each fault cause, each fault solution, the first association relationship, the second association relationship, the first text identifier corresponding to each historical fault name in the historical fault file, the second text identifier corresponding to each fault cause in the historical fault file, and the third text identifier corresponding to each fault solution in the historical fault file.
[0082] In this embodiment, there can be multiple fault information triples, and the form of the fault information triples can include entity-relationship-entity and entity-attribute. The entities in the fault information triple include historical fault names, fault causes, and fault solutions. The attribute of the entity in the fault information triple is the text identifier, and the relationship in the fault information triple is the association relationship between entities.
[0083] For example, if the fault cause of "charging fault" is "battery damage" and the fault solution of "charging fault" is "battery repair", then the fault information triples in the form of entity-relationship-entity can include: charging fault - fault cause - battery damage, and charging fault - fault solution - battery repair. The fault information triples in the form of entity-attribute can include: charging fault - first text identifier, fault cause - second text identifier, and fault solution - third text identifier.
[0084] S118. Construct a second fault knowledge graph according to the fault information triple.
[0085] In some embodiments of the present application, the electronic device constructs a second fault knowledge graph based on the fault information triple, including: the electronic device uses the fault cause corresponding to any historical fault name in the fault information triple as the third entity node associated with the first entity node, and uses the fault solution corresponding to any historical fault name in the fault information triple as the fourth entity node associated with the first entity node. The electronic device uses the first association relationship as an edge to connect the first entity node and the third entity node associated with the first entity node, uses the second association relationship as an edge to connect the first entity node and the fourth entity node associated with the first entity node, sets the attribute of each first entity node to the corresponding first text identifier, sets the attribute of each third entity node to the corresponding second text identifier, and sets the attribute of each fourth entity node to the corresponding third text identifier to generate a second fault knowledge graph.
[0086] As Figure 5 shown, it is a functional module diagram of a fault analysis device provided by an embodiment of the present application. The fault analysis device 11 includes a construction unit 110, a determination unit 111, a search unit 112, an acquisition unit 113, and an input unit 114. The module / unit mentioned in the present application refers to a series of computer-readable instruction segments that can be Figure 1 acquired by the processor 103 in Figure 1 and can complete fixed functions, and is stored in
[0087] The construction unit 110 is used to construct a first fault knowledge graph and a second fault knowledge graph based on the historical fault information in the historical fault file.
[0088] The determination unit 111 is used to determine the original fault name corresponding to the fault description information based on the fault description information input by the user.
[0089] The search unit 112 is used to search for the target fault name corresponding to the original fault name in the first fault knowledge graph.
[0090] The acquisition unit 113 is used to, if the text identifier corresponding to the target fault name is found in the second fault knowledge graph, acquire the target fault information corresponding to the text identifier from the historical fault file.
[0091] The input unit 114 is used to input the target fault information into a preset model, and determine the target fault solution corresponding to the fault description information according to the output information of the preset model for the target fault information.
[0092] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions, and the method implemented when the program instructions are executed may refer to the methods in the above-mentioned various embodiments of the present application.
[0093] Among them, the computer-readable storage medium may be the internal memory of the electronic device described in the above embodiment, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.
[0094] In some embodiments, the computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area may store an operating system, application programs required for at least one function, etc.; the storage data area may store data created according to the use of the electronic device.
[0095] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.
[0096] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this document can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but this implementation should not be considered to exceed the scope of this application.
[0097] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A fault analysis method, characterized in that, The method includes: Constructing a first fault knowledge graph and a second fault knowledge graph according to historical fault information in a historical fault file; Based on the fault description information input by the user, determining the original fault name corresponding to the fault description information; Searching in the first fault knowledge graph for the target fault name corresponding to the original fault name; If a text identifier corresponding to the target fault name is found in the second fault knowledge graph, obtaining the target fault information corresponding to the text identifier from the historical fault file; Inputting the target fault information into a preset model, and determining the target fault solution corresponding to the fault description information according to the output information of the preset model for the target fault information.
2. The fault analysis method according to claim 1, wherein, The constructing the first fault knowledge graph according to historical fault information in the historical fault file includes: Extracting a plurality of historical fault names from the historical fault information, and obtaining the original fault names similar to each historical fault name; Determining the similarity relationship between any one of the historical fault names and each corresponding original fault name; Constructing a fault name triple according to the plurality of historical fault names, each corresponding original fault name, and the similarity relationship; Constructing the first fault knowledge graph according to the fault name triple.
3. The fault analysis method according to claim 2, wherein The constructing the first fault knowledge graph according to the fault name triple includes: Taking any one of the historical fault names in the fault name triple as a first entity node, taking each original fault name corresponding to any one of the historical fault names as a second entity node associated with the first entity node, and taking the similarity relationship as an edge to connect the first entity node and each associated second entity node, to generate the first fault knowledge graph.
4. The fault analysis method according to claim 2, characterized in that, The searching in the first fault knowledge graph for the target fault name corresponding to the original fault name includes: Determining the historical fault name corresponding to the original fault name in the first fault knowledge graph as the target fault name.
5. The fault analysis method according to claim 3, characterized in that, The constructing the second fault knowledge graph according to historical fault information in the historical fault file includes: Extracting the fault cause and fault solution corresponding to each historical fault name from the historical fault information; Determining a first association relationship between each historical fault name and each corresponding fault cause, and a second association relationship between each historical fault name and each corresponding fault solution; Constructing a fault information triple according to the plurality of historical fault names, each fault cause, each fault solution, the first association relationship, the second association relationship, the first text identifier corresponding to each historical fault name in the historical fault file, the second text identifier corresponding to each fault cause in the historical fault file, and the third text identifier corresponding to each fault solution in the historical fault file; Constructing the second fault knowledge graph according to the fault information triple.
6. The fault analysis method according to claim 5, wherein The constructing the second fault knowledge graph according to the fault information triple includes: Use the cause of the fault corresponding to any of the historical fault names in the fault information triple as the third entity node associated with the first entity node, and use the solution to the fault corresponding to any of the historical fault names in the fault information triple as the fourth entity node associated with the first entity node; Use the first association relationship as an edge to connect the first entity node and the third entity node associated with the first entity node, use the second association relationship as an edge to connect the first entity node and the fourth entity node associated with the first entity node, set the attribute of each first entity node to the corresponding first text identifier, set the attribute of each third entity node to the corresponding second text identifier, and set the attribute of each fourth entity node to the corresponding third text identifier to generate the second fault knowledge graph.
7. The fault analysis method according to claim 6, wherein Each of the first text identifiers includes the first paragraph index of the corresponding historical fault name in the historical fault file, each of the second text identifiers includes the second paragraph index of the corresponding cause of the fault in the historical fault file, and each of the third text identifiers includes the third paragraph index of the corresponding solution to the fault in the historical fault file. The search for the text identifier corresponding to the target fault name includes: Search for the first entity node, the third entity node, and the fourth entity node to which the target fault name belongs in the second fault knowledge graph, and use the first paragraph index corresponding to the found first entity node, the second paragraph index corresponding to the found third entity node, and the third paragraph index corresponding to the found fourth entity node as the text identifier corresponding to the target fault name.
8. The fault analysis method according to claim 1, wherein If the text identifier corresponding to the target fault name is not found in the second fault knowledge graph, the method further includes: Prompt the user to input information, and update the second fault knowledge graph according to the input information, where the input information includes text identifiers, references, and solutions to faults.
9. An electronic device, characterized in that, The electronic device includes: A memory that stores at least one instruction; and A processor that implements the fault analysis method according to any one of claims 1 to 8 by executing the at least one instruction.
10. A computer-readable storage medium, characterized in that: At least one instruction is stored in the computer-readable storage medium, and when the at least one instruction is executed by a processor in an electronic device, the fault analysis method according to any one of claims 1 to 8 is implemented.