Knowledge graph-fused FMEA analysis method, system and device and medium

Abstract

The embodiment of the invention relates to the field of quality management software, and discloses an FMEA analysis method, system and equipment fusing a knowledge graph and a medium. The method comprises the following steps: acquiring FMEA instance data, and performing entity fusion on the FMEA instance data; the entity fusion comprises the steps that after the FMEA instance data are recognized and classified, entity alignment is conducted on the FMEA instance data according to a predefined entity alignment rule; an alignment result of the entity alignment is stored in a knowledge graph; and an AI module is utilized to query and retrieve the knowledge graph, and FMEA creation and fault reason investigation are performed through a natural language processing technology. Information such as product structures, functions and failure modes is integrated through a knowledge graph, and automatic failure analysis is performed in combination with an A I technology, so that the efficiency and quality of FMEA can be greatly improved. The method can be at least used for solving the technical problems of insufficient efficiency and quality in the FMEA method.

Description

Technical Field

[0001] The present application relates to the field of quality management, and in particular to an FMEA analysis method, system, equipment and medium integrating a knowledge graph. Background Art

[0002] Failure Mode and Effects Analysis (FMEA) is a systematic analysis method widely used in the automotive, aerospace, manufacturing and other fields to identify potential failure modes and evaluate their impact on products or processes. FMEA helps companies identify and eliminate potential problems in the early stages of product development, reduce the risk of product failure, and improve product quality through the analysis of product design (DFMEA) or process manufacturing (PFMEA). However, the traditional FMEA method has the following problems in practical applications:

[0003] During the FMEA analysis process, engineers need to deal with a large amount of redundant data, such as product names, functional descriptions, failure modes, preventive measures, etc. These data sources are complex and often scattered in different documents or systems, making it difficult to efficiently integrate and reuse information. In addition, FMEA data across products and projects is usually not interoperable and shareable, making it difficult to refer to each other in failure analysis of similar products or processes, increasing duplication of work and the difficulty of failure analysis.

[0004] Traditional FMEA reports usually exist in the form of offline documents and cannot form a structured knowledge base. This means that in subsequent failure analysis, it is difficult for engineers to quickly find and reuse previous analysis results, resulting in information waste. When quality problems occur in products, the potential causes of failure in FMEA reports are difficult to quickly retrieve through automated means, and there is a lack of visualization tools to help engineers intuitively locate problems, which affects the efficiency of troubleshooting. Summary of the invention

[0005] One purpose of the present application is to provide a FMEA analysis method, system, device and medium that integrates a knowledge graph, at least to solve the problems of insufficient efficiency and quality in the FMEA method.

[0006] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0007] In the first aspect, some embodiments of the present application also provide a FMEA analysis method integrating a knowledge graph, including obtaining FMEA instance data and performing entity fusion on the FMEA instance data; the entity fusion includes identifying and classifying the FMEA instance data, and then performing entity alignment on the FMEA instance data according to predefined entity alignment rules; storing the alignment results of the entity alignment in a knowledge graph; using an AI module to query and retrieve the knowledge graph, and performing FMEA creation and fault cause troubleshooting through natural language processing technology.

[0008] On the second aspect, some embodiments of the present application also provide a FMEA analysis system that integrates a knowledge graph, including a graph module for acquiring multiple FMEA instance data; after identifying and classifying the FMEA instance data, entity alignment is performed on the FMEA instance data according to predefined entity alignment rules; the alignment results of the entity alignment are stored in the knowledge graph; an AI module is used to query and retrieve the knowledge graph, and perform FMEA creation and fault cause troubleshooting through natural language processing technology.

[0009] In a third aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0010] In a fourth aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0011] Compared with related technologies, the solution provided in the embodiment of this application combines knowledge graphs with artificial intelligence technology to improve the automation and intelligence level of FMEA analysis. By integrating information such as product structure, function, and failure mode through knowledge graphs and combining AI technology for automated failure analysis, the efficiency and quality of FMEA can be greatly improved, the reuse of historical data can be promoted, and companies can locate failure causes more quickly and take effective preventive measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0013] Figure 1 A schematic diagram of a FMEA analysis method integrating a knowledge graph according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the architecture of an FMEA analysis method integrating a knowledge graph provided according to an embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of a FMEA analysis system integrating a knowledge graph provided according to an embodiment of the present application;

[0016] Figure 4 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] First embodiment

[0019] The first embodiment of the present application relates to a FMEA analysis method integrating a knowledge graph. Figure 1 As shown, the method may include the following steps:

[0020] S101, acquiring FMEA instance data, and performing entity fusion on the FMEA instance data; the entity fusion includes identifying and classifying the FMEA instance data, and then performing entity alignment on the FMEA instance data according to a predefined entity alignment rule;

[0021] S102, storing the alignment result of the entity alignment in a knowledge graph;

[0022] S103, using the AI ​​module to query and retrieve the knowledge graph, and using natural language processing technology to create FMEA and troubleshoot fault causes.

[0023] The following is a detailed description of each of the above steps.

[0024] For step S101, instance data is extracted from existing FMEA data, including DFMEA (Design Failure Mode and Effect Analysis) and PFMEA (Process Failure Mode and Effect Analysis) instances. DFMEA instance data usually includes product name, product function, product characteristics, product failure, preventive measures and detection measures, while PFMEA instance includes product name, process name, product failure, element failure, preventive measures and detection measures.

[0025] After obtaining the FMEA instance data, the data is subjected to entity recognition and classification. After recognition, similar or identical entities are aligned according to pre-defined entity alignment rules. Specifically, product names can be aligned by string matching and keyword matching. For product names with different expressions, the constructed synonym library is used for processing; while product functions, product features, preventive measures, detection measures and failure modes are aligned through semantic analysis and text similarity calculation combined with the domain knowledge base.

[0026] For step S102, after the entity alignment is completed, the alignment results are stored in the knowledge graph. The storage structure of the knowledge graph can effectively manage various entity and relationship information in FMEA analysis, such as the structural relationship of products, the association between functions and failures, etc. By storing data in the knowledge graph, data sharing and reuse across instances and products can be easily achieved, providing basic data support for subsequent analysis processes.

[0027] For step S103, during the FMEA creation and troubleshooting process, the AI ​​module searches the knowledge graph. The user inputs product information or process information, and the mixed prompt words and user-input information assist in completing the structural analysis, functional analysis, and failure mode analysis of the FMEA.

[0028] At the same time, during the troubleshooting process, the AI ​​module uses natural language processing to understand the intent of the problem and extract key entity information. It matches and queries the knowledge graph data based on the intent and key entity information, finds possible causes of failure, and generates troubleshooting suggestions. This step not only improves the speed and accuracy of problem location, but also supports dynamic updates to the knowledge graph after troubleshooting, gradually enriching the enterprise's knowledge base.

[0029] It is not difficult to find that compared with the related art, the solution provided in the embodiment of the present application realizes efficient management and sharing of FMEA data through automatic entity alignment and storage of knowledge graphs, reducing duplication of work and generation of redundant data. When creating a new FMEA, existing data can be quickly called to avoid manual search and repeated analysis.

[0030] By using AI modules and natural language processing technology, we can accurately understand the user's problem intentions and provide accurate fault cause suggestions based on the data in the knowledge graph. This not only speeds up the problem location process, but also ensures the scientificity and consistency of the troubleshooting results.

[0031] By dynamically updating the knowledge graph, each FMEA analysis and troubleshooting will further enrich the company's knowledge base. As data accumulates, it can provide richer references for future analysis and gradually improve the comprehensiveness and depth of FMEA analysis.

[0032] Second embodiment

[0033] The second embodiment of the present application relates to a FMEA analysis method integrating a knowledge graph. The second implementation method is an improvement on the first embodiment, and the specific improvements are:

[0034] like Figure 2 As shown, the method realizes the intelligent process of FMEA creation and auxiliary troubleshooting of fault causes through the cooperation of AI module and atlas module. The main scenario applications of this method include intelligent creation of FMEA and auxiliary troubleshooting of fault analysis causes. Specifically, the atlas module is responsible for data extraction and entity fusion from FMEA instance data, storing it in the atlas to form a basic knowledge base. Subsequently, the AI ​​module searches and analyzes the stored atlas data through natural language understanding (NLU) and query retrieval technology to generate intelligent FMEA analysis results or troubleshooting suggestions.

[0035] In the FMEA creation scenario, users can use the AI ​​module to input natural language. The AI ​​module's natural language generation (NLG) capability combines with the graph data to automatically generate FMEA analysis documents, simplifying the FMEA creation process. In the fault analysis scenario, users input the failure phenomenon of the product, and the AI ​​module can quickly find the relevant data in the graph and generate a fault cause analysis for the specific problem to help engineers locate the cause of the problem.

[0036] DFMEA instance, the DFMEA instance includes product name, product function, product characteristics, product failure, preventive measures and detection measures; PFMEA instance, the PFMEA instance includes product name, process name, product failure, element failure, preventive measures and detection measures.

[0037] DFMEA is mainly used to analyze the possible failure modes of products during the design phase and the impact of these failures on product functions and performance. DFMEA instances usually contain the following data types: product name, the specific name of the product, used to identify the object of analysis; product function, the function that the product design needs to achieve, which clarifies the expected working state of the product; product characteristics, key parameters or attributes related to product design, which determine the realization of product functions; product failure, possible failure modes, that is, the situation where the product does not meet the design requirements or functional failure during use; preventive measures, measures taken to avoid the occurrence of failure modes, such as design improvements or quality control measures; detection measures, measures to detect failure modes, usually detection systems or methods, used to identify potential problems before failure occurs.

[0038] PFMEA mainly analyzes the failure modes in the production process to ensure that the failure modes can be effectively avoided in the manufacturing process. PFMEA instances include the following data types: product name, the name of the product involved in the manufacturing process, which is consistent with the product name in DFMEA; process name, the name of the specific process step in the production or manufacturing process, such as assembly, testing, etc.; product failure, the failure mode that may occur in the product during the manufacturing process, such as poor assembly or functional failure; element failure, the failure of specific elements in the manufacturing process, such as equipment failure or process deviation; preventive measures, preventive measures taken for failure modes in the manufacturing process, such as process improvement or personnel training; detection measures, measures to detect failures in the production process, used to promptly discover problems in the manufacturing process, such as online monitoring systems.

[0039] After acquiring multiple FMEA (DFMEA, PFMEA) data, entities of the same data type and similar semantics need to be aligned and merged. Entity alignment includes: string matching and keyword matching of the product name, as well as processing different expressions of the product name by building a synonym library; alignment of the product functions, product features, preventive measures, detection measures and failure modes through semantic analysis, and matching using text similarity calculation algorithms (such as cosine similarity) combined with domain knowledge bases.

[0040] String matching is to identify identical products by directly comparing the character consistency of product names. Keyword matching is to find keywords with similar or related meanings in the name through keyword matching when the string does not match completely, and perform fuzzy matching. For example, "engine" and "engine" can be considered keyword matching.

[0041] Synonym library processing,In order to handle the differences in the expression of product names, a domain-specific synonym library is built to align product names with different expressions but the same meaning.,For example, "car" and "vehicle" are regarded as the same product in the synonym library.,By expanding the synonym library, the diverse expressions of product names can be handled more accurately.

[0042] Alignment of product functions, product features, preventive measures, detection measures, and failure modes. For these entities involving functions, features, and measures, semantic analysis techniques are used. By parsing the semantic meaning of these descriptions, similarities between different descriptions can be identified. For example, the descriptions of two product functions can represent the same or similar functions semantically, although they use different words.

[0043] Text similarity calculation,To further quantify the similarity between different descriptions,,a text similarity calculation algorithm is used, such as,cosine similarity.,This algorithm evaluates the semantic proximity of two text vectors by,calculating the angle between them.,The higher the text similarity, the more similar the two functions or,features are.

[0044] In combination with the domain knowledge base for matching, based on semantic analysis and similarity calculation, the industry and technical standards in the domain knowledge base are also used to further improve the accuracy of alignment. The domain knowledge base contains professional terms, technical parameters and failure mode standards related to FMEA, which helps to accurately identify and align entities with professional meanings.

[0045] FMEA creation includes: generating lower-level component or part names according to the obtained product names for structural analysis; filling in the functional description of the corresponding product according to the obtained product names for functional analysis; functionally associating the functions under different products according to the functional descriptions; querying the corresponding product failures from the knowledge graph according to the product functions; performing failure association on the product failures under different products; and querying the preventive measures and detection measures of the corresponding product according to the product failures.

[0046] According to the root node product name of FMEA, the graph database is queried for names that are the same or similar to the product name, and the node information of its subordinate products is retrieved. For the queried subordinate product nodes, their names are extracted and returned to the user. In the FMEA interface, these subordinate product names are displayed in the selection list. Users can select some or all of the subordinate products as subordinate components or parts of the root node according to their needs to form a complete product structure. If further generation of subordinate components is required, the structural analysis of the subordinate products will continue according to the same steps, and the subordinate structures will be generated step by step until the structural hierarchy of the entire product is completed.

[0047] After the product structure is generated, the graph database is queried according to each product name to retrieve the functional information related to the product name. In the graph database, there is a "function" relationship between each product node and its functional node. Through this relationship, the function of the product is queried and a list of all possible functions is returned to the selection interface. Users can select the function that matches the product or add a new functional description to generate a complete functional analysis under the product.

[0048] Next, we will conduct a functional correlation analysis on the functions of different products. By querying the correlation between the functions in the graph database, we can show the potential relationship between the functions. For example, there may be a causal or complementary relationship between some functions. These correlations will be visualized in the form of an FMEA relationship tree to help users intuitively understand the mutual influence of product functions.

[0049] After completing the functional association, the failure mode corresponding to the function is directly queried from the graph database according to the functional description of each product. Since each functional node in the graph database has a direct "failure" relationship with its failure mode node, the failure mode list of the product can be quickly returned, and users can select the most relevant failure mode for analysis.

[0050] For the failure modes of different products, further query the relationship between failures. For example, some failure modes may have mutual influence or chain reactions. By analyzing these relationships, more comprehensive failure association information can be provided to users, and the association of these failure modes can be displayed in the FMEA relationship tree interface.

[0051] After the failure mode is confirmed, the graph database will be used to query the preventive measures and detection measures corresponding to each failure mode. A large number of preventive and detection measures are stored in the graph database, and there is a corresponding relationship with each failure mode. The detailed description of these measures will be returned, and the user can select the appropriate measures for FMEA analysis. The description of the preventive measures usually includes the specific operation steps and the corresponding O value (Occurrence, the probability of failure), while the detection measures are used to ensure that potential problems can be detected in time before failure occurs.

[0052] The above steps assist users in completing the process of generating structural analysis, functional analysis and risk analysis corresponding to the product. For PFMEA (Process Failure Mode and Effects Analysis), the difference from DFMEA (Design Failure Mode and Effects Analysis) is that the root node of PFMEA is the process name, not the product name. The lower-level nodes of PFMEA analysis are sub-process steps, and the sub-process steps contain elements. According to the root node of PFMEA - the process name, the relevant process information in the graph database is queried, and the sub-process steps and element hierarchy are generated based on the process. The other steps are similar to DFMEA, and structural analysis, functional analysis and failure analysis are also performed based on the existing data and the relationship nodes in the graph database.

[0053] Fault cause troubleshooting includes: performing intent recognition and entity extraction on fault problems raised by users; returning possible causes related to the product failure by querying the nodes related to the fault problem in the knowledge graph; performing correlation analysis on the queried fault causes and the existing FMEA analysis results, and generating corresponding replies in combination with the AI ​​model.

[0054] In problem analysis, based on the name of the failed product and the product failure phenomenon, the knowledge graph is accessed through intelligent question query to query the possible causes within the enterprise. Engineers locate the cause of the failure based on the possible causes. Currently, there are two solutions for question answering in the general field. One is to vectorize the question and match it with the text of the knowledge base. The results returned by this method are relatively uncertain. Another method is to perform intent recognition and entity recognition on the question based on the language understanding ability of the large model, query the graph database and return it to the model, and then use the large language model generation ability combined with the returned data to generate the corresponding reply. In order to achieve a relatively high accuracy, this method is adopted.

[0055] Question intent understanding and entity extraction: Send the user question + prompt word to the local open source model or cloud model. The prompt word content includes 1. Extract key information, such as "product name" and failure description. Extract the intent of the question, such as the cause and consequence of a product failure, and return the extracted key information and intent information in jason format.

[0056] Retrieval query, the intention corresponds to the relationship type of the node to be queried, and the corresponding data information is returned to the big model based on the node information and relationship type. The returned data information and the previous question are combined into a new prompt word and sent to the big model. The big model will integrate background knowledge and generate answers for users. Assist engineers in problem analysis. At the same time, after the problem analysis is completed, the newly added analysis content, such as old faults caused by new reasons, is updated in the knowledge graph, gradually helping enterprises accumulate a large amount of industry experience.

[0057] The AI ​​module uses a large language model to semantically understand the questions input by the user, and generates context-based failure troubleshooting suggestions and preventive measures in combination with the knowledge graph.

[0058] The queries input by users are usually made in natural language, such as failure phenomena or potential problems of a product. The AI ​​module uses a large language model to perform semantic analysis on the input content and understand the intention of the user's question. For example, the user may ask "What are the functions and requirements of car air conditioners" or "What are the components of the compressor?" or "Why does the cooling effect of car air conditioners not meet the requirements?" or "Why does the compressor not work properly?" The large language model has a strong language understanding ability and can accurately extract the key entities in the question (such as product name, failure mode, etc.) and the user's needs (such as finding the cause of failure or preventive measures).

[0059] The AI ​​module not only analyzes the semantics of the current question, but also further refines its understanding of the question based on the user’s contextual query history, FMEA analysis progress, and related product or process information. For example, if the user has previously queried failure information for related components, the AI ​​module will combine these historical queries with the current question to provide the user with a more accurate answer.

[0060] Based on semantic understanding, the AI ​​module will query the knowledge graph data related to the user's problem. The knowledge graph stores a large amount of FMEA instance data, product functions, failure modes, preventive measures, and detection measures. Through the entity associations in the graph, the AI ​​module can find the failure modes, historical failure causes, and recorded prevention and detection measures related to the user's problem. For example, when a user queries the failure cause of a product, the AI ​​module will first retrieve the failure records related to the product in the graph, and generate relevant troubleshooting suggestions based on the historical data in the graph.

[0061] The AI ​​module generates failure troubleshooting suggestions for users based on the reasoning capabilities of the large language model and the data in the knowledge graph. The suggestions not only cover possible failure causes, but also provide detailed troubleshooting steps and related technical documentation in context. For example, for the failure of product X at a specific temperature, the AI ​​module can provide multiple potential causes, list related failure modes, and recommend users to check specific product functions or component features.

[0062] While troubleshooting failures, the AI ​​module will also provide preventive measures for the failure mode through the knowledge graph. Preventive measures include relevant operational recommendations, quality control steps, and detection methods. For example, the AI ​​module may recommend specific material selection when designing components, or adding certain detection procedures during the manufacturing process to reduce the probability of failure. Combined with the O value (failure incidence) in the graph, the AI ​​module can also evaluate the effectiveness of preventive measures and provide optimization suggestions.

[0063] It is not difficult to find that in the embodiments of the present application, it helps enterprises improve the efficiency of FMEA and provides a way to integrate the redundant text data of FMEA. The integrated data can be efficiently and accurately reused as a knowledge base in the FMEA analysis of similar products or similar processes, thereby improving the efficiency and quality of FMEA analysis, helping enterprises to complete the output of FMEA files to the content of FMEA analysis in the analysis problem, conduct problem troubleshooting, and improve the value of FMEA itself as knowledge.

[0064] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0065] Third embodiment

[0066] The third embodiment of the present application relates to a FMEA analysis system integrating a knowledge graph, such as Figure 3 As shown, the system comprises:

[0067] A graph module is used to obtain multiple FMEA instance data; after identifying and classifying the FMEA instance data, entity alignment is performed on the FMEA instance data according to a predefined entity alignment rule; and the alignment result of the entity alignment is stored in a knowledge graph;

[0068] The AI ​​module is used to query and retrieve the knowledge graph, and to create FMEA and troubleshoot fault causes through natural language processing technology.

[0069] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0070] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0071] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0072] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 4 An exemplary structural diagram of the electronic device is disclosed. Figure 4 As shown, the electronic device includes: one or more processors 1101, memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0073] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0074] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0075] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0076] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0077] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0078] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0079] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0080] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0081] Computer program code for performing the operations of the present application 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" language or similar programming languages. 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., using an Internet service provider to connect via the Internet).

[0082] In the above-described embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0083] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive so lid state di sk (SSD)), etc.

[0084] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0085] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0086] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A FMEA analysis method integrating knowledge graph, characterized in that: The method comprises: Acquire FMEA instance data, and perform entity fusion on the FMEA instance data; the entity fusion includes identifying and classifying the FMEA instance data, and then performing entity alignment on the FMEA instance data according to a predefined entity alignment rule; and storing the alignment result of the entity alignment in a knowledge graph; The AI ​​module is used to query and retrieve the knowledge graph, and natural language processing technology is used to create FMEA and troubleshoot fault causes.

2. The method according to claim 1, characterized in that: The FMEA example data includes: DFMEA example, which includes product name, product function, product characteristics, product failure, preventive measures and detection measures; PFMEA example, the PFMEA example includes product name, process name, product failure, element failure, preventive measures and detective measures.

3. The method according to claim 2, characterized in that The entity alignment includes: Performing string matching and keyword matching on the product name, and processing different expressions of the product name by building a synonym library; The product functions, product features, preventive measures, detection measures and failure modes are aligned through semantic analysis and matched using a text similarity calculation algorithm combined with a domain knowledge base.

4. The method according to any one of claims 1 to 3, characterized in that: The FMEA creation includes: Generate the sub-assembly or part name based on the obtained product name for structural analysis; Fill in the functional description of the corresponding product according to the obtained product name to conduct functional analysis; Functionally associate the functions of different products according to the functional description; Querying corresponding product failures from the knowledge graph according to the functions of the products; Failure correlation of the product failures under different products; Query the preventive measures and detection measures for the corresponding products based on the product failure.

5. The method according to claim 4, characterized in that The method further comprises: The FMEA relationship tree interface displays the association between functions of different products and the association between failures of the products; based on the functional association and failure association, the product is subjected to risk analysis.

6. The method according to any one of claims 1 to 3, characterized in that: The fault cause investigation includes: Perform intent recognition and entity extraction on fault questions raised by users; By querying the nodes related to the fault problem in the knowledge graph, possible causes related to product failure are returned; The queried fault causes are correlated with the existing FMEA analysis results, and the corresponding responses are generated in combination with the AI ​​model.

7. The method according to claim 1, characterized in that The AI ​​module uses a large language model to semantically understand the questions input by the user, and generates context-based failure troubleshooting suggestions and preventive measures in combination with the knowledge graph.

8. A FMEA analysis system integrating knowledge graph, characterized in that: The system comprises: A graph module is used to obtain multiple FMEA instance data; after identifying and classifying the FMEA instance data, entity alignment is performed on the FMEA instance data according to a predefined entity alignment rule; and the alignment result of the entity alignment is stored in a knowledge graph; The AI ​​module is used to query and retrieve the knowledge graph, and to create FMEA and troubleshoot fault causes through natural language processing technology.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

10. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images