Industrial equipment after-sales intelligent auxiliary method, device and equipment and storage medium

Abstract

The invention discloses an industrial equipment after-sales intelligent auxiliary method and device, equipment and a storage medium, and the method comprises the steps: collecting equipment fault information inputted by a user, and converting the equipment fault information into a keyword set; obtaining multi-modal knowledge resources uploaded by a user, and labeling the multi-modal knowledge resources to generate a vector database containing semantic association; matching the keyword set with data in a vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; and calling a preset large language model to analyze the knowledge fragment to generate maintenance guidance content. According to the method, the multi-modal knowledge resources are converted into the vector database containing the semantic association, and the maintenance guidance content is generated for fault diagnosis of the equipment through the retrieval enhancement generation mechanism and the preset large language model, so that compared with the prior art, the equipment fault diagnosis efficiency and the response speed and accuracy of equipment maintenance are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent after-sales assistance method, device, equipment and storage medium for industrial equipment. Background Art

[0002] Traditional fault diagnosis and repair methods for industrial equipment after-sales service rely primarily on manual support, resulting in high costs, low efficiency, and poor accuracy. Maintenance personnel rely on personal experience to troubleshoot, and the transmission of technical support information is delayed, resulting in long repair times and a high risk of equipment downtime. Furthermore, traditional maintenance manuals and troubleshooting tables cannot quickly adapt to changes in equipment technology and lack real-time updating and sharing mechanisms, impacting repair quality and customer satisfaction.

[0003] Therefore, there is an urgent need for an intelligent after-sales assistance method for industrial equipment that can improve the efficiency of equipment fault diagnosis, thereby improving the response speed and accuracy of equipment maintenance and enhancing user experience. Summary of the Invention

[0004] The main purpose of the present invention is to provide an intelligent auxiliary method, device, equipment and storage medium for after-sales service of industrial equipment, aiming to solve the technical problems of low equipment fault diagnosis efficiency and low response speed and accuracy of equipment maintenance in the existing technology of industrial equipment after-sales service.

[0005] To achieve the above objectives, the present invention provides an intelligent after-sales assistance method for industrial equipment, the method comprising the following steps: Collecting device failure information input by the user and converting the device failure information into a keyword set; Acquire multimodal knowledge resources uploaded by users, label the multimodal knowledge resources, and generate a vector database containing semantic associations; Matching the keyword set with the data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; The preset large language model is called to parse the knowledge fragment to generate maintenance guidance content.

[0006] Optionally, the step of obtaining multimodal knowledge resources uploaded by users, labeling the multimodal knowledge resources, and generating a vector database containing semantic associations includes: Acquiring multimodal knowledge resources uploaded by a user, wherein the multimodal knowledge resources include at least one of a technical description document, a device structure diagram, and a training demonstration video; Selecting corresponding resource tags based on the types of the multimodal knowledge resources to label the multimodal knowledge resources, and assigning unique identifiers to bind to the resource tags; The annotated multimodal knowledge resources are vectorized using a preset semantic encoding model, and the vectorized results are stored in a vector database containing semantic associations.

[0007] Optionally, the resource tag includes: Fault type label, used to describe equipment abnormality; Device model tag, used to associate the model of the device; Operation category label, used to describe the operation category of the device; Point-to-point tags are used to link to related video, drawing, or document resources.

[0008] Optionally, the step of matching the keyword set with data in the vector database based on the retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information includes: Vectorizing the keyword set to generate a semantic vector; Using a retrieval enhancement generation mechanism, the semantic vector is similarly matched with the data in the vector database to obtain a similarity matching result; Target content having a similarity greater than a preset similarity threshold is screened out based on the similarity matching result, and the target content is used as a knowledge fragment related to the device fault information.

[0009] Optionally, after the step of collecting the device failure information input by the user and converting the device failure information into a keyword set, the method further includes: Collecting device operating status data, wherein the device operating status data includes at least one of device temperature, device operating parameters, and alarm logs; The device operating status data is associated with the keyword set and stored.

[0010] Optionally, the step of calling a preset large language model to parse the knowledge fragment to generate maintenance instruction content includes: Calling a preset large language model to parse the knowledge fragment and the device operation status data to obtain a parsing result; The analysis results are subjected to natural language processing to generate maintenance guidance content, and the maintenance guidance content is displayed through an interface. The maintenance guidance content includes at least one of processing suggestions, operation steps, precautions and related resource links.

[0011] Optionally, after the step of calling a preset large language model to parse the knowledge fragment and generate maintenance instruction content, the method further includes: Obtaining auxiliary operation instructions triggered by the user according to the maintenance guidance content; Resource recommendations and corresponding auxiliary operations are performed according to the auxiliary operation instructions.

[0012] In addition, to achieve the above-mentioned purpose, the present invention also proposes an industrial equipment after-sales intelligent assistance device, the device comprising: An information conversion module, configured to collect device failure information input by a user and convert the device failure information into a keyword set; The resource annotation module is used to obtain multimodal knowledge resources uploaded by users, label the multimodal knowledge resources, and generate a vector database containing semantic associations; a data matching module, configured to match the keyword set with data in the vector database based on a search enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; The result generation module is used to call a preset large language model to parse the knowledge fragment and generate maintenance guidance content.

[0013] In addition, to achieve the above-mentioned purpose, the present invention also proposes an industrial equipment after-sales intelligent assistance device, which includes: a memory, a processor, and an industrial equipment after-sales intelligent assistance program stored on the memory and runnable on the processor, and the industrial equipment after-sales intelligent assistance program is configured to implement the steps of the industrial equipment after-sales intelligent assistance method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which an industrial equipment after-sales intelligent assistance program is stored. When the industrial equipment after-sales intelligent assistance program is executed by a processor, the steps of the industrial equipment after-sales intelligent assistance method described above are implemented.

[0015] The present invention discloses a method for collecting device failure information input by a user and converting the device failure information into a keyword set; obtaining multimodal knowledge resources uploaded by the user and labeling the multimodal knowledge resources to generate a vector database containing semantic associations; matching the keyword set with data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the device failure information; and calling a preset large language model to parse the knowledge fragments to generate maintenance guidance content. Because the present invention converts multimodal knowledge resources into a vector database containing semantic associations and realizes the generation of maintenance guidance content for device fault diagnosis through a retrieval enhancement generation mechanism and a preset large language model, compared to the existing technology, the present invention improves the efficiency of device fault diagnosis and the response speed and accuracy of device maintenance, thereby enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the first embodiment of the industrial equipment after-sales intelligent assistance method of the present invention; Figure 2 This is a flow chart of a second embodiment of the industrial equipment after-sales intelligent assistance method of the present invention; Figure 3 This is a flow chart of a third embodiment of the industrial equipment after-sales intelligent assistance method of the present invention; Figure 4 This is a structural block diagram of the first embodiment of the after-sales intelligent auxiliary device for industrial equipment of the present invention; Figure 5 It is a structural diagram of an industrial equipment after-sales intelligent auxiliary device in the hardware operating environment involved in the embodiment of the present invention.

[0017] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] The embodiment of the present invention provides an industrial equipment after-sales intelligent assistance method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the industrial equipment after-sales intelligent assistance method of the present invention.

[0020] In this embodiment, the industrial equipment after-sales intelligent assistance method includes steps S10 to S40: Step S10: collecting device failure information input by the user, and converting the device failure information into a keyword set.

[0021] It should be noted that the execution entity of this embodiment can be a computer server device with data processing, network communication, and program execution functions used in industrial equipment fault analysis scenarios, such as a server, tablet computer, or personal computer, or an electronic device capable of performing the aforementioned functions (such as an intelligent after-sales assistance device for industrial equipment). The following uses a system including an intelligent after-sales assistance device for industrial equipment (hereinafter referred to as the system) as an example to illustrate this embodiment and the following embodiments.

[0022] It should be understood that users can input device fault information through the web and mobile operation interfaces provided by the system. The device fault information input by users can be input through natural language text or voice input, and this embodiment does not limit this.

[0023] It is understandable that the above-mentioned device fault information may include device model, fault description, alarm code, etc.

[0024] It should be understood that directly searching the complete text entered by the user is inefficient and prone to errors. However, keyword sets can accurately reflect the core points of the user's question. The system can quickly filter out highly matching knowledge fragments from the knowledge base based on the keywords. For example, if a user enters a complex equipment failure description and converts it into a keyword set, the system can quickly locate knowledge items such as failure cases and maintenance manuals that contain these keywords without having to compare the entire text word for word. This greatly shortens search time and improves search accuracy.

[0025] In practice, continuous text input by users can be segmented into independent vocabulary units according to specific rules. For example, if a user inputs "The motor experiences abnormal vibration and is accompanied by high temperature," the segmentation process will convert it into vocabulary such as "motor, occurrence, abnormality, vibration, and, accompanied by, high temperature." Only by correctly segmenting the text into words can keywords be extracted. In the segmentation results, meaningless or generalized words like "occur" and "and" (also known as stop words) are not very helpful in expressing the core content of the user input. Therefore, these stop words should be removed before converting the keyword set, retaining meaningful words such as "motor," "abnormality," "vibration," and "high temperature."

[0026] For another example, the keyword set may be determined by calculating the frequency of occurrence of each word in the device fault information input by the user.

[0027] In the implementation, the frequency of each word in the user's input text is counted. Generally speaking, words with higher frequency tend to better represent the core theme of the user's input. For example, if words like "overheating" and "stuttering" appear frequently in multiple device failure descriptions, they are likely to be the key points expressing these failure conditions. A frequency threshold is set and words above this threshold are filtered to form a keyword set. For example, if a large number of user feedback texts about a device failure are collected and statistics show that "unable to start" and "black screen" appear much more frequently than other words, these words will be used as keywords to reflect the main intention of the user's input.

[0028] For example, a domain knowledge base for industrial equipment can be pre-built, which contains a large number of professional terms related to equipment failure, operation, maintenance, etc. When the user enters content, it is matched with the terms in the knowledge base, and the terms in the input text that match the knowledge base are selected as the keyword set. The initially extracted keywords can also be expanded based on the semantic relationships between the terms in the domain knowledge base, such as synonyms, hyponyms, and hyponyms. For example, if the keyword "equipment overheating" is extracted, related terms such as "too high temperature" and "poor heat dissipation" can be expanded based on the semantic relationships in the domain knowledge base. This allows the keyword set to more comprehensively express the semantics of the user input and better support subsequent knowledge matching and other operations.

[0029] Step S20: Acquire the multimodal knowledge resources uploaded by the user, label the multimodal knowledge resources, and generate a vector database containing semantic associations.

[0030] It should be noted that multimodal knowledge resources refer to information resources that integrate multiple types, including but not limited to text, images, audio, video, and sensor data. Knowledge can be expressed and transmitted through a variety of symbolic resources and modes. In this embodiment, the multimodal knowledge resources include at least one of technical documentation, device structure diagrams, and training demonstration videos.

[0031] It should be understood that combining multimodal knowledge resources such as technical description documents, equipment structure diagrams, and training demonstration videos can help maintenance personnel quickly locate equipment failures, provide maintenance suggestions and operational guidance, and improve the quality of after-sales service.

[0032] It should be explained that in order to ensure standardized data management and subsequent retrieval, multimodal knowledge resources can be uniformly stored in the MinIO object storage system and bound to resource tags through unique IDs.

[0033] It should be understood that the MinIO object storage system is a high-performance, open source object storage system designed for cloud-native environments that supports the storage and management of massive unstructured data such as images, videos, logs, backup files, etc.

[0034] In a specific implementation, multimodal knowledge resources uploaded by users can be obtained, and the multimodal knowledge resources include at least one of technical description documents, equipment structure diagrams, and training demonstration videos; corresponding resource tags are selected based on the type of each multimodal knowledge resource to label the multimodal knowledge resources, and unique identifiers are assigned to bind to each resource tag; the labeled multimodal knowledge resources are vectorized using a preset semantic coding model, and the vectorization results are stored in a vector database containing semantic associations.

[0035] It should be noted that the above-mentioned preset semantic coding model can be the Ollama semantic coding model, or other models with similar functions, and this embodiment does not limit this.

[0036] It should be explained that the above-mentioned resource labels include: fault type labels, which are used to describe abnormal equipment phenomena (such as "abnormal motor vibration", "bearing overheating"); equipment model labels, which are used to associate equipment models (such as "inverter A900"); operation category labels, which are used to describe the operation category of the equipment (such as "troubleshooting", "replace parts", "software configuration"); and directional labels, which are used to link associated videos, drawings or document resources (such as "associated video: V_231", "related drawings: D_032").

[0037] Step S30: matching the keyword set with the data in the vector database based on the retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information.

[0038] It should be understood that the Retrieval-Augmented Generation (RAG) mechanism is a model that combines retrieval and generation technologies. It generates answers or content by referencing information from an external knowledge base. It has strong interpretability and customization capabilities and is suitable for multiple natural language processing tasks such as question-answering systems, document generation, and intelligent assistants.

[0039] In a specific implementation, the keyword set can be vectorized to generate a semantic vector; the semantic vector can be similarly matched with the data in the vector database using a retrieval enhancement generation mechanism to obtain a similarity matching result; based on the similarity matching result, target content with a similarity greater than a preset similarity threshold is filtered out, and the target content is used as a knowledge fragment related to the equipment fault information.

[0040] Step S40: calling a preset large language model to parse the knowledge fragment to generate maintenance guidance content.

[0041] Understandably, a Large Language Model (LLM) is a large deep learning model in the field of natural language processing (NLP) that can model and generate text data. These models are typically based on artificial neural networks, especially the Transformer architecture, and are trained on massive amounts of text data to learn the patterns, semantics, and grammatical structure of language, enabling them to perform various natural language tasks such as text generation, question answering, translation, and summarization.

[0042] In this embodiment, the preset large language model can be a local Ollama-ChatGLM, a cloud-based large language model such as DeepSeek, or other large language models, which is not limited in this embodiment.

[0043] In the specific implementation, a preset large language model can be called to parse the knowledge fragments to generate question and answer results. The question and answer results include maintenance guidance content such as question restatement, processing suggestions, operating steps and precautions, and are accompanied by directional links (videos, documents, drawings, etc.).

[0044] In addition, the question and answer results can be displayed through the system interface, supporting further operation instructions (such as "generate maintenance work order", "create task"), etc.

[0045] This embodiment discloses collecting device fault information input by a user and converting the device fault information into a keyword set; obtaining multimodal knowledge resources uploaded by the user and labeling the multimodal knowledge resources to generate a vector database containing semantic associations; matching the keyword set with data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the device fault information; and calling a preset large language model to parse the knowledge fragments to generate maintenance guidance content. Because this embodiment converts multimodal knowledge resources into a vector database containing semantic associations, and generates maintenance guidance content for device fault diagnosis through a retrieval enhancement generation mechanism and a preset large language model, compared to existing technologies, this embodiment improves the efficiency of device fault diagnosis and the response speed and accuracy of device maintenance, thereby enhancing the user experience.

[0046] refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the industrial equipment after-sales intelligent assistance method of the present invention.

[0047] Based on the first embodiment described above, in this embodiment, after step S10, steps S101 to S102 are further included: Step S101: collecting equipment operating status data, where the equipment operating status data includes at least one of equipment temperature, equipment operating parameters, and alarm logs.

[0048] Step S102: The device operation status data is associated with the keyword set and stored.

[0049] It should be noted that, by accessing the IoT module, the device operation status data can be collected in real time, and the device operation status data includes at least one of the device temperature, device operation parameters and alarm logs.

[0050] It's important to explain that an IoT module, or Internet of Things module, is a small electronic device embedded within an IoT device. It collects real-time data from physical devices, such as temperature and current, and transmits this data to the cloud or other end devices via communication technologies, enabling real-time monitoring and analysis of device status. Through the cloud or mobile applications, users can remotely monitor and control connected IoT devices, enabling intelligent management and improving convenience and productivity.

[0051] It should be noted that associating and storing equipment operating status data with keyword sets can serve as supplementary information for problem context analysis and auxiliary judgment when subsequently generating maintenance guidance content, thereby improving the accuracy of equipment fault diagnosis and maintenance.

[0052] In a specific implementation, a preset large language model can be called to parse the knowledge fragments and the equipment operation status data to obtain a parsing result; natural language processing is performed on the parsing result to generate maintenance guidance content, and the maintenance guidance content is displayed through an interface. The maintenance guidance content includes at least one of processing suggestions, operating steps, precautions and related resource links.

[0053] This embodiment discloses collecting device fault information input by a user and converting the device fault information into a keyword set; collecting device operating status data; associating and storing the device operating status data with the keyword set; obtaining multimodal knowledge resources uploaded by the user, and labeling the multimodal knowledge resources to generate a vector database containing semantic associations; matching the keyword set with the data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the device fault information; calling a preset large language model to parse the knowledge fragments and the device operating status data to obtain a parsing result; performing natural language processing on the parsing result to generate maintenance guidance content, and displaying the maintenance guidance content through an interface. Since this embodiment associates and stores the device operating status data with a keyword set, and generates maintenance guidance content by calling a preset large language model for the knowledge fragments and the device operating status data, compared with the existing technology, this embodiment improves the accuracy of equipment fault diagnosis and maintenance.

[0054] refer to Figure 3 , Figure 3 2 is a flow chart of the third embodiment of the industrial equipment after-sales intelligent assistance method of the present invention.

[0055] Based on the above embodiments, in this embodiment, after step S40, steps S50 to S60 are further included: Step S50: Acquire auxiliary operation instructions triggered by the user according to the maintenance guidance content.

[0056] Step S60: performing resource recommendations and corresponding auxiliary operations according to the auxiliary operation instructions.

[0057] It should be noted that after the maintenance guidance content is generated, the system will automatically recommend relevant resource files, including drawings, videos, documents, etc., and support users to directly jump to browse, download and view, or perform operations within the system. For example, auxiliary operations for users can include creating maintenance task orders and querying spare parts inventory; auxiliary operations for engineers can include equipment expertise query, real-time viewing of equipment IOT parameters, and issuing equipment IOT instructions (servo reset, equipment restart, etc.).

[0058] This embodiment discloses the collection of equipment failure information input by the user, and converting the equipment failure information into a keyword set; obtaining multimodal knowledge resources uploaded by the user, and labeling the multimodal knowledge resources to generate a vector database containing semantic associations; matching the keyword set with the data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment failure information; calling a preset large language model to parse the knowledge fragments to generate maintenance guidance content; obtaining auxiliary operation instructions triggered by the user according to the maintenance guidance content; and performing resource recommendations and corresponding auxiliary operations according to the auxiliary operation instructions. Compared to the prior art, after generating the maintenance guidance content, this embodiment recommends resources and corresponding auxiliary operations according to the auxiliary operation instructions triggered by the user, thereby improving the after-sales processing efficiency of industrial equipment and the content of users' independent problem solving.

[0059] In addition, an embodiment of the present invention also proposes a storage medium, on which an industrial equipment after-sales intelligent assistance program is stored. When the industrial equipment after-sales intelligent assistance program is executed by a processor, the steps of the industrial equipment after-sales intelligent assistance method described above are implemented.

[0060] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the industrial equipment after-sales intelligent assistance device of the present invention.

[0061] like Figure 4 As shown, the industrial equipment after-sales intelligent assistance device proposed in the embodiment of the present invention includes: an information conversion module 501, a resource labeling module 502, a data matching module 503 and a result generation module 504.

[0062] The information conversion module 501 is used to collect device failure information input by a user and convert the device failure information into a keyword set.

[0063] The resource tagging module 502 is used to obtain multimodal knowledge resources uploaded by users, and tag the multimodal knowledge resources to generate a vector database containing semantic associations.

[0064] The data matching module 503 is configured to match the keyword set with the data in the vector database based on a search enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information.

[0065] The result generation module 504 is used to call a preset large language model to parse the knowledge fragment and generate maintenance guidance content.

[0066] The resource annotation module 502 is also used to obtain multimodal knowledge resources uploaded by users, and the multimodal knowledge resources include at least one of technical description documents, equipment structure diagrams and training demonstration videos; select corresponding resource tags based on the type of each multimodal knowledge resource to annotate the multimodal knowledge resources, and assign unique identifiers to bind to each resource tag; use a preset semantic coding model to vectorize the annotated multimodal knowledge resources, and store the vectorization results in a vector database containing semantic associations.

[0067] The data matching module 503 is further used to vectorize the keyword set to generate a semantic vector; use a retrieval enhancement generation mechanism to perform similarity matching on the semantic vector and the data in the vector database to obtain a similarity matching result; based on the similarity matching result, filter out target content with a similarity greater than a preset similarity threshold, and use the target content as a knowledge fragment related to the equipment fault information.

[0068] This device embodiment discloses collecting device fault information input by a user and converting the device fault information into a keyword set; obtaining multimodal knowledge resources uploaded by the user and labeling the multimodal knowledge resources to generate a vector database containing semantic associations; matching the keyword set with data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the device fault information; and calling a preset large language model to parse the knowledge fragments to generate maintenance guidance content. Because this device embodiment converts multimodal knowledge resources into a vector database containing semantic associations, and generates maintenance guidance content for device fault diagnosis through a retrieval enhancement generation mechanism and a preset large language model, compared to existing technologies, this device embodiment improves the efficiency of equipment fault diagnosis and the response speed and accuracy of equipment maintenance, thereby enhancing the user experience.

[0069] Based on the first embodiment of the industrial equipment after-sales intelligent assistance device of the present invention, a second embodiment of the industrial equipment after-sales intelligent assistance device of the present invention is proposed.

[0070] In this embodiment, the information conversion module 501 is also used to collect equipment operating status data, which includes at least one of equipment temperature, equipment operating parameters and alarm logs; and associate the equipment operating status data with the keyword set for storage.

[0071] The result generation module 504 is also used to call a preset large language model to parse the knowledge fragment and the equipment operation status data to obtain a parsing result; perform natural language processing on the parsing result to generate maintenance guidance content, and display the maintenance guidance content through an interface. The maintenance guidance content includes at least one of processing suggestions, operation steps, precautions and related resource links.

[0072] Other embodiments or specific implementations of the industrial equipment after-sales intelligent assistance device of the present invention can refer to the above-mentioned method embodiments and will not be repeated here.

[0073] The present application provides an intelligent after-sales assistance device for industrial equipment, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent after-sales assistance method for industrial equipment in the above-mentioned embodiment one.

[0074] Reference below Figure 5 , which shows a schematic diagram of the structure of an industrial equipment after-sales intelligent assistance device suitable for implementing the embodiments of the present application. The industrial equipment after-sales intelligent assistance device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The industrial equipment after-sales intelligent auxiliary device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0075] like Figure 5As shown, the industrial equipment after-sales intelligent assistance device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in read-only memory 1002 or programs loaded from storage device 1003 into random access memory 1004. Random access memory 1004 also stores various programs and data required for the operation of the industrial equipment after-sales intelligent assistance device. Processing device 1001, read-only memory 1002, and random access memory 1004 are interconnected via bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the industrial equipment after-sales intelligent assistance device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the industrial equipment after-sales intelligent assistance device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0076] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0077] The intelligent after-sales assistance device for industrial equipment provided in this application utilizes the intelligent after-sales assistance method for industrial equipment described in the aforementioned embodiments, addressing the technical issues of low equipment fault diagnosis efficiency, low maintenance response speed, and low accuracy in prior art industrial equipment after-sales services. Compared to the prior art, the beneficial effects of the intelligent after-sales assistance device for industrial equipment provided in this application are the same as those of the intelligent after-sales assistance method for industrial equipment provided in the aforementioned embodiments. Other technical features of the intelligent after-sales assistance device for industrial equipment are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0078] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0079] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0080] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0081] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0082] Through the above description of the embodiments, those skilled in the art will clearly understand that the above-mentioned embodiments and methods can be implemented by means of software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0083] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent after-sales assistance method for industrial equipment, characterized in that: The method comprises: Collecting device failure information input by the user and converting the device failure information into a keyword set; Acquire multimodal knowledge resources uploaded by users, label the multimodal knowledge resources, and generate a vector database containing semantic associations; Matching the keyword set with the data in the vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; The preset large language model is called to parse the knowledge fragment to generate maintenance guidance content.

2. The industrial equipment after-sales intelligent assistance method according to claim 1, characterized in that: The step of obtaining multimodal knowledge resources uploaded by users, labeling the multimodal knowledge resources, and generating a vector database containing semantic associations includes: Acquiring multimodal knowledge resources uploaded by a user, wherein the multimodal knowledge resources include at least one of a technical description document, a device structure diagram, and a training demonstration video; Selecting corresponding resource tags based on the types of the multimodal knowledge resources to label the multimodal knowledge resources, and assigning unique identifiers to bind to the resource tags; The annotated multimodal knowledge resources are vectorized using a preset semantic encoding model, and the vectorized results are stored in a vector database containing semantic associations.

3. The industrial equipment after-sales intelligent assistance method according to claim 2, characterized in that: The resource tag includes: Fault type label, used to describe equipment abnormality; Device model tag, used to associate the device model; Operation category label, used to describe the operation category of the device; Point-to-point tags are used to link to related video, drawing, or document resources.

4. The industrial equipment after-sales intelligent assistance method according to claim 1, characterized in that: The step of matching the keyword set with the data in the vector database based on the retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information includes: Vectorizing the keyword set to generate a semantic vector; Using a retrieval enhancement generation mechanism, the semantic vector is similarly matched with the data in the vector database to obtain a similarity matching result; Target content having a similarity greater than a preset similarity threshold is screened out based on the similarity matching result, and the target content is used as a knowledge fragment related to the device fault information.

5. The industrial equipment after-sales intelligent assistance method according to claim 1, characterized in that: After the step of collecting the device failure information input by the user and converting the device failure information into a keyword set, the method further includes: Collecting device operating status data, wherein the device operating status data includes at least one of device temperature, device operating parameters, and alarm logs; The device operating status data is associated with the keyword set and stored.

6. The industrial equipment after-sales intelligent assistance method according to claim 5, characterized in that: The step of calling a preset large language model to parse the knowledge fragment and generate maintenance instruction content includes: Calling a preset large language model to parse the knowledge fragment and the device operation status data to obtain a parsing result; The analysis results are subjected to natural language processing to generate maintenance guidance content, and the maintenance guidance content is displayed through an interface. The maintenance guidance content includes at least one of processing suggestions, operation steps, precautions and related resource links.

7. The industrial equipment after-sales intelligent assistance method according to claim 1, characterized in that: After the step of calling the preset large language model to parse the knowledge fragment to generate maintenance instruction content, the method further includes: Obtaining auxiliary operation instructions triggered by the user according to the maintenance guidance content; Resource recommendations and corresponding auxiliary operations are performed according to the auxiliary operation instructions.

8. An intelligent after-sales auxiliary device for industrial equipment, characterized in that: The device comprises: An information conversion module, configured to collect device failure information input by a user and convert the device failure information into a keyword set; The resource annotation module is used to obtain multimodal knowledge resources uploaded by users, label the multimodal knowledge resources, and generate a vector database containing semantic associations; a data matching module, configured to match the keyword set with data in the vector database based on a search enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; The result generation module is used to call a preset large language model to parse the knowledge fragment and generate maintenance guidance content.

9. An intelligent after-sales auxiliary device for industrial equipment, characterized in that: The device includes: a memory, a processor, and an industrial equipment after-sales intelligent assistance program stored in the memory and executable on the processor, wherein the industrial equipment after-sales intelligent assistance program is configured to implement the steps of the industrial equipment after-sales intelligent assistance method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an industrial equipment after-sales intelligent assistance program, and when the industrial equipment after-sales intelligent assistance program is executed by the processor, the steps of the industrial equipment after-sales intelligent assistance method according to any one of claims 1 to 7 are implemented.

Images