Intelligent Q&A Method, System, Device, Equipment and Medium for Customized Industrial Equipment

Abstract

The present invention discloses an intelligent question-answering method, system, device, equipment and medium for custom industrial equipment. This method is executed by the knowledge base question-answering tool in the industrial equipment operation support system, and includes: obtaining the user input question and parsing the user input question; determining at least one target document segment associated with the user input question according to the question parsing result and the pre-established index document; wherein, the index document includes the document segments proprietary to the custom industrial equipment; sending the pre-set system prompt words, application prompt words and the target document segments to the artificial intelligence model together, and obtaining the target answer fed back by the artificial intelligence model; sending the target answer to the device-side dialogue tool for the device-side dialogue tool to display the target answer to the user. By adopting the above technical solution, it is possible to effectively answer the questions proprietary to the custom industrial equipment, effectively improve the after-sales response speed of the equipment, and improve the customer use experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to an intelligent question-answering method, system, device, equipment and medium for customized industrial equipment. Background Art

[0002] For the complex mechatronic equipment delivered in the discrete manufacturing industry, it is generally delivered as a single set. Due to its highly customized functions, there are almost no exactly the same equipment. After the equipment is delivered, there is a lack of sufficient functional testing. Due to factors such as the continuous increase in equipment usage time, inherent defects in hardware, or software vulnerabilities, the equipment will inevitably have abnormalities or failures.

[0003] The operators of customers generally only have operation knowledge and lack maintenance knowledge. When the equipment has abnormalities or failures, they often need to contact the engineers of the developer for remote network troubleshooting or on-site fault diagnosis and repair. The response time of the fault is relatively long, which affects the user experience of the customers.

[0004] In the prior art, generally only the common general equipment can be questioned and answered through an AI (Artificial Intelligence) large model. However, since various equipment delivered in the discrete manufacturing industry is customized according to customer requirements and the quantity is small, there is a lack of sufficient historical usage data as a reference, and it is even more impossible to train the AI large model for intelligent question-answering. That is, the prior art cannot solve the intelligent question-answering requirements of customized complex mechatronic equipment. Summary of the Invention

[0005] The present invention provides an intelligent question-answering method, system, device, equipment and medium for customized industrial equipment, which can effectively answer questions specific to customized industrial equipment, is applicable to complex industrial equipment delivered in the discrete manufacturing industry, and can effectively improve the after-sales response speed of the equipment and improve the user experience of the customers.

[0006] According to one aspect of the present invention, there is provided an intelligent question-answering method for customized industrial equipment, which is executed by a knowledge base question-answering tool in an industrial equipment operation support system, including:

[0007] Obtain a user input question and parse the user input question;

[0008] According to the question parsing result and a pre-established index document, determine at least one target document segment associated with the user input question; wherein, the index document includes document segments specific to customized industrial equipment;

[0009] Send the preset system prompt words, application prompt words, and the segmented target document to the artificial intelligence model in the industrial equipment operation support system, and obtain the target answer fed back by the artificial intelligence model;

[0010] Send the target answer to the device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user.

[0011] According to one aspect of the present invention, there is provided an industrial equipment operation support system, including a device-side dialogue tool, a knowledge base Q&A tool, and an artificial intelligence model; wherein,

[0012] The device-side dialogue tool is used to send the content input by the user to the knowledge base Q&A tool and display the target answer fed back by the knowledge base Q&A tool to the user;

[0013] The knowledge base Q&A tool is used to execute the intelligent Q&A method for customizing industrial equipment according to any embodiment of the present invention;

[0014] The artificial intelligence model is used to perform large language processing based on the system prompt words, application prompt words, and the segmented target document sent by the knowledge base Q&A tool, and send the generated target answer to the knowledge base Q&A tool.

[0015] According to another aspect of the present invention, there is provided an intelligent Q&A device for customizing industrial equipment, which is executed by the knowledge base Q&A tool in the industrial equipment operation support system, including:

[0016] An input question processing module, configured to obtain a user input question and parse the user input question;

[0017] A document segment acquisition module, configured to determine at least one target document segment associated with the user input question according to the question parsing result and a pre-established index document; wherein, the index document includes document segments proprietary to the customized industrial equipment;

[0018] An answer generation module, configured to send the preset system prompt words, application prompt words, and the target document segment to the artificial intelligence model in the industrial equipment operation support system, and obtain the target answer fed back by the artificial intelligence model;

[0019] An answer feedback module, configured to send the target answer to the device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user.

[0020] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein

[0023] the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the intelligent question - answering method for customized industrial equipment according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, there is provided a computer - readable storage medium storing computer instructions for implementing the intelligent question - answering method for customized industrial equipment according to any embodiment of the present invention when executed by a processor.

[0025] The technical solution of the embodiment of the present invention can effectively answer questions specific to customized industrial equipment by obtaining a user - input question, parsing the user - input question, determining at least one target document segment associated with the user - input question according to the question - parsing result and a pre - established index document, jointly sending a preset system prompt word, an application prompt word, and the target document segment to an artificial intelligence model, obtaining a target answer fed back by the artificial intelligence model, and sending the target answer to a device - side dialogue tool for the device - side dialogue tool to display the target answer to the user. This solves the problem that existing artificial intelligence models cannot effectively answer questions related to customized equipment, is applicable to complex industrial equipment delivered in the discrete manufacturing industry, can effectively improve the after - sales response speed of the equipment, enhance the customer experience, and can also adapt to the problem of insufficient training of new operators caused by changes in customer operators. At the same time, it supports online updating of the knowledge - base content, can quickly deliver the latest and effective equipment operation and maintenance knowledge and skills, and continuously improve the accuracy and precision of intelligent question - answering.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained without creative efforts based on these drawings.

[0028] Figure 1It is a flowchart of an intelligent question - answering method for customizing industrial equipment provided by Embodiment 1 of the present invention;

[0029] Figure 2 It is a schematic structural diagram of an industrial equipment operation support system provided by Embodiment 2 of the present invention;

[0030] Figure 3 It is a schematic structural diagram of an intelligent question - answering device for customizing industrial equipment provided by Embodiment 3 of the present invention;

[0031] Figure 4 It is a schematic structural diagram of an electronic device for implementing the intelligent question - answering method of the customized industrial equipment of the embodiments of the present invention. Detailed implementation manners

[0032] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above - mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non - exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] Figure 1 It is a flowchart of an intelligent question - answering method for customizing industrial equipment provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of providing intelligent question - answering for customized industrial equipment. This method can be executed by an intelligent question - answering device for customizing industrial equipment. The intelligent question - answering device for customizing industrial equipment can be implemented in the form of hardware and / or software, and is generally configured in a knowledge - base question - answering tool with data - processing functions. The knowledge - base question - answering tool can be configured under a cloud server. As Figure 1 shown, this method includes:

[0036] S110. Obtain the user input question and parse the user input question.

[0037] Optionally, an intelligent question - answering support can be provided for customized industrial equipment through an industrial equipment operation support system. The industrial equipment operation support system may include a device - side dialogue tool, a knowledge - base question - answering tool, and an artificial intelligence model. Among them, the knowledge - base question - answering tool and the artificial intelligence model are deployed on a cloud server. Information interaction between the knowledge - base question - answering tool and the artificial intelligence model is achieved through an API (Application Programming Interface). The device - side dialogue tool can be deployed in a computer on the customized industrial equipment side, run under a computer system, and access the cloud server through a public network or an industrial Internet, and then interact with the knowledge - base question - answering tool through the API for information interaction.

[0038] Optionally, the operator of the customer can initiate a question through the device - side dialogue tool. The content input by the operator may include, but is not limited to, questions in the form of text, pictures, voice, or a combination of text and pictures.

[0039] Among them, obtaining the user input question may include any one of the following:

[0040] When the content input by the user through the device - side dialogue tool is in text form, use the content input by the user as the user input question; and

[0041] When the content input by the user through the device - side dialogue tool is in the form of a picture or voice, send the content input by the user to the artificial intelligence model, and use the text content fed back after the artificial intelligence model recognizes or converts the content input by the user as the user input question.

[0042] Optionally, when the content input by the user includes a picture or voice, after receiving the content input by the user, the content input by the user can be sent to the artificial intelligence model. The artificial intelligence model can be a public large - language model for the artificial intelligence model to recognize or convert the content input by the user and feed it back to the knowledge - base question - answering tool in the form of a text description. After receiving the text description fed back by the artificial intelligence model, use the text description returned by the artificial intelligence model as the user input question.

[0043] Optionally, parsing the user input question may include: obtaining keywords, abstracts, and question summaries according to the user input question.

[0044] S120. Determine at least one target document segment associated with the user input question according to the question parsing result and a pre - established index document.

[0045] It is understandable that for customized industrial equipment, during the design and production process, designers retain complete design documents, simulation data, etc. Using these data can solve most problems of customized industrial equipment.

[0046] Optionally, multiple knowledge bases are pre-loaded in the knowledge base Q&A tool, such as equipment knowledge base, maintenance knowledge base, etc. Each knowledge base includes a general folder and a proprietary folder. Among them, the general folder stores general information related to the theme of the knowledge base. The general information has wide applicability and can be applied to any other relevant device, not limited to customized industrial equipment; the proprietary folder stores information that the knowledge base theme is only applicable to customized industrial equipment. For example, the proprietary folder can include design documents, simulation data retained by designers during the design and production process, and can also include on-site maintenance information for a certain time, etc.

[0047] Optionally, the information stored in the general folder or the proprietary folder is stored in the form of text documents, and each folder includes at least one text document.

[0048] Optionally, the index document can be established according to each knowledge base in the knowledge base Q&A tool. In the index document, it includes multiple document segments and segment identifiers corresponding to each document segment. For example, the index document can store the segment identifiers and the document segments in two columns respectively. The first column stores the segment identifiers, and the second column stores the document segments corresponding to each segment identifier.

[0049] Optionally, each line in the index document stores a unique document segment. The document segment can be a single paragraph in the text document or a combination of multiple paragraphs with strong relevance.

[0050] It is understandable that the document segments in the index document include the paragraphs of each document in the general folder of each knowledge base and the paragraphs of each document in the proprietary folder. The advantage of this setting is that: by searching the index document, proprietary information of customized industrial equipment can be obtained, and general information can also be obtained, so as to be able to conduct a comprehensive analysis of customer problems. The answers with added proprietary information can be more targeted and thus solve customer problems more accurately.

[0051] Among them, the index document includes document segments that are proprietary to customized industrial equipment.

[0052] Among them, the index document can include multiple segment identifiers and document segments respectively corresponding to each segment identifier.

[0053] Among them, according to the problem parsing result and the pre-established index document, determining at least one target document segment associated with the user input problem may include:

[0054] According to the problem analysis result, determine at least one target segment identifier that matches in the index document, and determine the document segment corresponding to each target segment as the target document segment;

[0055] Among them, the segment identifier is a keyword, an abstract, or a preset question.

[0056] Optionally, the segment identifier can also be a pairwise combination of the abstract, keyword, and preset question, or can also include the abstract, keyword, and preset question at the same time.

[0057] Optionally, according to the problem analysis result, the keyword, abstract, and question summary corresponding to the user's problem can be determined. After obtaining the problem analysis result, the problem analysis result can be matched with the segment abstract in the index document. The matching method can be: when the field in the segment identifier is the same as the field in the problem analysis result, determine the segment identifier as the target segment identifier; it can also be: calculate the similarity between the segment identifier and the problem analysis result, and when the similarity is greater than the preset value, determine the segment identifier as the target segment identifier, but it is not limited to the above matching methods.

[0058] Optionally, the index document is generated or updated by an artificial intelligence model based on the knowledge base.

[0059] Optionally, the process of the artificial intelligence model generating the index document can include: before the industrial equipment operation support system goes online, perform RAG (Retrieval-Augmented Generation) retrieval enhancement on each text document in each knowledge base to generate each segment identifier.

[0060] Optionally, performing RAG retrieval enhancement to generate each segment identifier can include: performing vectorization processing on each text document, and performing abstract summary, keyword extraction, and / or generating question-answer pairs on the vectorized text document.

[0061] Optionally, generating question-answer pairs can refer to generating question-answer pairs that match the document segment according to the vectorized document segment. Among them, the question in the question-answer pair is summarized and generated by the artificial intelligence model based on the document segment, and the answer is the document segment.

[0062] Optionally, after the knowledge base is updated, the artificial intelligence model can also be called to update the index document according to the updated knowledge base.

[0063] Specifically, after the knowledge base is updated, the updated text document can be determined in the knowledge base, and the artificial intelligence model can be called to perform RAG retrieval enhancement on the updated text document, determine the segment identifier of each segment in the updated text document, and update the index document.

[0064] Optionally, when the knowledge base needs to be updated, a new knowledge base can be created, and the updated content can be updated in the new knowledge base. Then, the artificial intelligence model can be called to perform RAG retrieval enhancement on the new knowledge base, thereby reducing the repeated RAG process and eliminating the need for substantial changes to the indexed documents.

[0065] S130. Send the pre-set system prompt words, application prompt words, and segmented target documents to the artificial intelligence model in the industrial equipment operation support system, and obtain the target answer feedback by the artificial intelligence model.

[0066] Optionally, the system prompt words can be used to inform the artificial intelligence model of key information such as the overall background, objectives, and rules of the current task, guiding the model to understand the overall framework of the entire task. For example, the system prompt words can be used to instruct the artificial intelligence model to play a role so that the artificial intelligence model can summarize the answer in this context.

[0067] Optionally, the application prompt words can be used to provide more targeted guidance to the model for specific application scenarios, question types, or specific equipment, etc. For example, it can be used to explain to the artificial intelligence model that it is necessary to summarize the answer and organize the language according to the segmented target documents.

[0068] Optionally, the target answer can include content such as text or pictures in the segmented target documents.

[0069] S140. Send the target answer to the device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user.

[0070] Optionally, the device-side dialogue tool can be configured in the device operation software or called when the device operation software is started.

[0071] The technical solution of the embodiment of the present invention can effectively answer questions specific to customized industrial equipment by obtaining the user's input question, parsing the user's input question, determining at least one target document segment associated with the user's input question according to the question parsing result and the pre-established index document, sending the pre-set system prompt words, application prompt words and the target document segment to the artificial intelligence model, obtaining the target answer fed back by the artificial intelligence model, and sending the target answer to the device-side dialogue tool for the device-side dialogue tool to display the target answer to the user. This solves the problem that the existing artificial intelligence model cannot effectively answer questions related to customized equipment, is applicable to complex industrial equipment delivered in the discrete manufacturing industry, can effectively improve the after-sales response speed of the equipment, improve the customer experience, and can also adapt to the problem of insufficient training of new operators caused by changes in customer operators. At the same time, it supports online updating of the knowledge base content, can quickly deliver the latest and effective equipment operation and maintenance knowledge and skills, and continuously improve the accuracy and precision of intelligent answering.

[0072] Embodiment 2

[0073] Figure 2 FIG. is a schematic structural diagram of an industrial equipment operation support system provided by Embodiment 2 of the present invention. As Figure 2 shown, the industrial equipment operation support system includes: a device-side dialogue tool 210, a knowledge base Q&A tool 220, and an artificial intelligence model 230.

[0074] The device-side dialogue tool 210 is configured to send the content input by the user to the knowledge base Q&A tool and display the target answer fed back by the knowledge base Q&A tool to the user.

[0075] The knowledge base Q&A tool 220 is configured to execute the intelligent Q&A method for the customized industrial equipment described in the embodiment of the present invention.

[0076] The artificial intelligence model 230 is configured to perform large language processing according to the system prompt words, application prompt words and the target document segment sent by the knowledge base Q&A tool, and send the generated target answer to the knowledge base Q&A tool.

[0077] Optionally, the device-side dialogue tool 210 can run together with the device operation software under a computer system, such as the Windows system. The device-side dialogue tool 210 can be a component in the device operation software, provide a Q&A box in response to the user's click operation, or run independently under the computer system and be directly called when the device operation software is started.

[0078] Optionally, the device-side dialogue tool 210 provides a question input box and a question-and-answer display box. The question input box supports users to input content in multiple formats such as text, images, and voices.

[0079] Among them, the knowledge base question-and-answer tool 220 stores multiple knowledge bases. Each knowledge base includes a general folder and a proprietary folder, and each folder includes at least one text document.

[0080] Optionally, the artificial intelligence model 230 can specifically be used to: perform language restructuring or reasoning on the segmented target document according to the system prompt words, application prompt words, and segmented target document sent by the knowledge base question-and-answer tool.

[0081] Among them, the artificial intelligence model 230 can also be used to:

[0082] Perform vectorization processing on the target text document, and generate a segmentation identifier corresponding to each document segment in the target text document according to the vectorized target text document;

[0083] Update the index document according to the segmentation identifier and the document segment with a corresponding relationship.

[0084] Optionally, when the index document is generated for the first time, the target text document is all the documents in the knowledge base. If some text documents in the knowledge base are updated and the index document has been established, the target text document is the updated text document that has an update behavior in the knowledge base.

[0085] Among them, the knowledge base question-and-answer tool 220 and the artificial intelligence model 230 are deployed on the cloud server. The knowledge base question-and-answer tool 220 and the artificial intelligence model 230 perform data interaction through the API; the device-side dialogue tool 210 runs under the computer system on the customized industrial device side. The device-side dialogue tool 210 is connected to the cloud server where the knowledge base question-and-answer tool 220 is located through the public network or the industrial Internet, and performs data interaction with the knowledge base question-and-answer tool through the API.

[0086] Optionally, the public network can be a wired network or a wireless local area network.

[0087] The technical solution of the embodiment of the present invention can effectively answer questions specific to customized industrial equipment by configuring a device-side dialogue tool, a knowledge base question-and-answer tool, and an artificial intelligence model in the industrial equipment operation support system. It is applicable to complex industrial equipment delivered in the discrete manufacturing industry, and can effectively improve the after-sales response speed of the equipment and improve the customer experience.

[0088] Embodiment Three

[0089] Figure 3The following is a schematic structural diagram of an intelligent question - answering device for custom industrial equipment provided in Embodiment 3 of the present invention. As Figure 3 shown, the device includes: an input question processing module 310, a document segmentation acquisition module 320, an answer generation module 330, and an answer feedback module 340.

[0090] The input question processing module 310 is used to obtain the user - input question and parse the user - input question.

[0091] The document segmentation acquisition module 320 is used to determine at least one target document segment associated with the user - input question according to the question parsing result and a pre - established index document; wherein, the index document includes document segments proprietary to custom industrial equipment.

[0092] The answer generation module 330 is used to jointly send a pre - set system prompt word, an application prompt word, and the target document segment to an artificial intelligence model in an industrial equipment operation support system, and obtain a target answer fed back by the artificial intelligence model.

[0093] The answer feedback module 340 is used to send the target answer to a device - side dialogue tool in the industrial equipment operation support system for the device - side dialogue tool to display the target answer to the user.

[0094] The technical solution of the embodiment of the present invention, by obtaining the user - input question, parsing the user - input question, determining at least one target document segment associated with the user - input question according to the question parsing result and a pre - established index document, jointly sending a pre - set system prompt word, an application prompt word, and the target document segment to an artificial intelligence model, obtaining a target answer fed back by the artificial intelligence model, and sending the target answer to a device - side dialogue tool for the device - side dialogue tool to display the target answer to the user, can effectively answer questions proprietary to custom industrial equipment, solve the problem that existing artificial intelligence models cannot effectively answer questions related to custom equipment, is applicable to complex industrial equipment delivered in the discrete manufacturing industry, and can effectively improve the after - sales response speed of the equipment, improve the customer experience, and also adapt to the problem of insufficient training of new operators caused by changes in customer operators. At the same time, it supports online updating of the knowledge base content, can quickly deliver the latest and effective equipment operation and maintenance knowledge and skills, and continuously improve the accuracy and precision of intelligent question - answering.

[0095] Based on the above - mentioned embodiments, the input question processing module 310 can be used to perform any one of the following:

[0096] When the content input by the user through the device - side dialogue tool is in text form, use the content input by the user as the user - input question; and

[0097] When the content input by the user through the device-side dialogue tool is in the form of a picture or voice, the content input by the user is sent to the artificial intelligence model, and the text content fed back after the artificial intelligence model recognizes or converts the content input by the user is used as the user input question.

[0098] Based on the above embodiments, the index document includes a plurality of segmentation identifiers and document segments respectively corresponding to the segmentation identifiers.

[0099] The document segment acquisition module 320 may specifically be used for:

[0100] According to the problem analysis result, at least one target segmentation identifier that matches is determined in the index document, and the document segments corresponding to the target segments are determined as target document segments.

[0101] Wherein, the segmentation identifier is a keyword, an abstract or a preset question.

[0102] The intelligent question and answer device for customizing industrial equipment provided by the embodiments of the present invention can execute the intelligent question and answer method for customizing industrial equipment provided by any embodiment of the present invention, and has function modules and beneficial effects corresponding to the execution method.

[0103] Embodiment 4

[0104] Figure 4 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0105] Such as Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0106] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the intelligent question-answering method for custom industrial equipment as described in the embodiments of the present invention. That is:

[0108] Obtain the user input question and parse the user input question;

[0109] According to the question parsing result and a pre-established index document, determine at least one target document segment associated with the user input question; wherein, the index document includes document segments proprietary to the custom industrial equipment;

[0110] Send a preset system prompt word, an application prompt word, and the target document segment to an artificial intelligence model in the industrial equipment operation support system, and obtain a target answer fed back by the artificial intelligence model;

[0111] Send the target answer to a device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user.

[0112] In some embodiments, the intelligent question-answering method for customizing industrial equipment can be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the intelligent question-answering method for customizing industrial equipment described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the intelligent question-answering method for customizing industrial equipment by any other suitable means (e.g., by means of firmware).

[0113] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a dedicated computer, or other programmable data processing devices, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: 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) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0117] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of the communication network include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0118] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is generated by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0119] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0120] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent Q&A method for customizing industrial equipment, which is executed by the knowledge base Q&A tool in the industrial equipment operation support system, is characterized in that, Including: Obtain the user input question and parse the user input question; According to the question parsing result and the pre-established index document, determine at least one target document segment associated with the user input question; wherein, the index document includes document segments proprietary to customized industrial equipment; Send the pre-set system prompt words, application prompt words and the target document segment to the artificial intelligence model in the industrial equipment operation support system, and obtain the target answer fed back by the artificial intelligence model; Send the target answer to the device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user; Among them, obtaining the user input question includes: When the content input by the user through the device-side dialogue tool is in the form of a picture or voice, send the content input by the user to the artificial intelligence model, and use the text content fed back after the artificial intelligence model recognizes or converts the content input by the user as the user input question; Among them, parsing the user input question includes: obtaining keywords, abstracts and question summaries according to the user input question; The index document is generated or updated by the artificial intelligence model according to the knowledge base; the index document includes multiple segment identifiers and the document segments corresponding to each segment identifier respectively; the segment identifier includes an abstract, a keyword and a preset question; each knowledge base includes a general folder and a proprietary folder; the proprietary folder includes design documents, simulation data and on-site maintenance information retained by the designer during the design and production process; Among them, the process of the artificial intelligence model generating the index document includes: performing vectorization processing on each text document, and performing abstract summary, keyword extraction and / or generating question and answer pairs on the vectorized text document; wherein, the question in the question and answer pair is generated by the artificial intelligence model according to the summary of the document segment, and the answer is the document segment.

2. The method according to claim 1, characterized in that, Obtaining the user input question includes: When the content input by the user through the device-side dialogue tool is in text form, use the content input by the user as the user input question.

3. The method according to claim 1, wherein The index document includes multiple segment identifiers and the document segments corresponding to each segment identifier respectively; According to the question parsing result and the pre-established index document, determining at least one target document segment associated with the user input question includes: According to the question parsing result, determine at least one target segment identifier that matches in the index document, and determine the document segment corresponding to each target segment as the target document segment; Among them, the segment identifier is a keyword, an abstract or a preset question.

4. An industrial equipment operation support system, characterized in that Including a device-side dialogue tool, a knowledge base question and answer tool and an artificial intelligence model; wherein, The device-side dialogue tool is used to send the content input by the user to the knowledge base question and answer tool and display the target answer fed back by the knowledge base question and answer tool to the user; The knowledge base question and answer tool is used to execute the intelligent question and answer method for customized industrial equipment described in any one of claims 1-3; The artificial intelligence model is used to perform large language processing based on the system prompt words, application prompt words, and segmented target documents sent by the knowledge base Q&A tool, and send the generated target answers after processing to the knowledge base Q&A tool.

5. The system according to claim 4, wherein Multiple knowledge bases are stored in the knowledge base Q&A tool. Each knowledge base includes a general folder and a proprietary folder, and each folder includes at least one text document.

6. The system according to claim 5, characterized in that, The artificial intelligence model is further used for: Performing vectorization processing on the target text document, and generating segmented identifiers corresponding to each document segment in the target text document according to the vectorized target text document; Updating the index document according to the segmented identifiers and document segments with corresponding relationships.

7. The system according to claim 4, characterized in that The knowledge base Q&A tool and the artificial intelligence model are deployed on a cloud server. The knowledge base Q&A tool and the artificial intelligence model perform data interaction through an application programming interface (API). The device-side dialogue tool runs under a computer system customized for industrial equipment. The device-side dialogue tool is connected to the cloud server where the knowledge base Q&A tool is located through a public network or an industrial Internet, and performs data interaction with the knowledge base Q&A tool through the API.

8. An intelligent Q&A device for customizing industrial equipment, which is executed by the knowledge base Q&A tool in the industrial equipment operation support system, is characterized in that It includes: An input question processing module, which is used to obtain the user input question and parse the user input question; A document segment acquisition module, which is used to determine at least one target document segment associated with the user input question according to the question parsing result and a pre-established index document; wherein, the index document includes document segments proprietary to the customized industrial equipment. An answer generation module, which is used to send the preset system prompt words, application prompt words, and the target document segment to the artificial intelligence model in the industrial equipment operation support system, and obtain the target answer fed back by the artificial intelligence model; An answer feedback module, which is used to send the target answer to the device-side dialogue tool in the industrial equipment operation support system for the device-side dialogue tool to display the target answer to the user; Among them, the input question processing module is used for: When the content input by the user through the device-side dialogue tool is in the form of a picture or voice, sending the content input by the user to the artificial intelligence model, and using the text content recognized or converted by the artificial intelligence model for the content input by the user as the user input question; Among them, parsing the user input question includes: obtaining keywords, summaries, and question summaries according to the user input question; Among them, the index document is generated or updated by the artificial intelligence model according to the knowledge base; the index document includes multiple segmented identifiers and the document segments corresponding to each segmented identifier respectively; the segmented identifiers include summaries, keywords, and preset questions; each knowledge base includes a general folder and a proprietary folder; the proprietary folder includes design documents, simulation data, and on-site maintenance information retained by designers during the design and production process. Among them, the process of the artificial intelligence model generating the index document includes: performing vectorization processing on each text document, and performing summary, keyword extraction, and / or generating question-and-answer pairs on the vectorized text document; among them, the questions in the question-and-answer pairs are generated by the artificial intelligence model according to the segmented summary of the document, and the answers are the document segments.

9. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent question-and-answer method of the customized industrial device according to any one of claims 1-3.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the intelligent question-and-answer method of the customized industrial device according to any one of claims 1-3 when executed by a processor.

Images