Information processing method and device, equipment and storage medium

Abstract

The invention provides an information processing method and device, equipment and a storage medium, and relates to the technical field of equipment maintenance and management. According to the information processing method, fault description information of maintenance equipment is obtained, the fault description information comprises attribute information of the maintenance equipment, document information related to the maintenance equipment is obtained through retrieval according to the attribute information of the maintenance equipment, and the maintenance equipment is further processed according to the fault description information. And applying the search model to extract target equipment maintenance information corresponding to the fault description information from the document information. According to the method and the device, the target device maintenance information corresponding to the fault description information is extracted from the document information by applying the search model, so that the search efficiency of the device maintenance information can be improved, and the maintenance efficiency of the device is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment maintenance management, and in particular to an information processing method, apparatus, device and storage medium. Background Art

[0002] In the field of equipment maintenance management, each device is equipped with detailed equipment knowledge for managing and maintaining the device. At present, most enterprises archive the equipment knowledge of all devices, such as document knowledge, in the equipment maintenance management system so that equipment maintenance personnel can quickly find and use relevant equipment knowledge when they need to use it. The equipment maintenance management system can be an enterprise asset management system (Enterprise Asset Management, referred to as EAM).

[0003] In the related art, when a device fails, the device maintenance personnel first searches for device knowledge related to the device in the device maintenance management system by keyword matching, and then searches for knowledge related to the device failure by manual search in the found device knowledge. However, this method has the problem of low search efficiency. Summary of the invention

[0004] The present application provides an information processing method, device, equipment and storage medium, which are used to solve the problem of low search efficiency when searching for knowledge related to equipment failure by using a keyword matching search method.

[0005] In a first aspect, the present application provides an information processing method, including: obtaining fault description information for a maintenance device, the fault description information including attribute information of the maintenance device; retrieving document information related to the maintenance device based on the attribute information of the maintenance device; and applying a search model to extract target device maintenance information corresponding to the fault description information from the document information based on the fault description information.

[0006] In one possible implementation, based on the fault description information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information, including: correcting the fault description information to correct the erroneous description in the fault description information; semantically expanding the corrected fault description information to obtain extended fault description information; and applying the search model to extract target device maintenance information corresponding to the extended fault description information from the document information.

[0007] In one possible implementation, based on the fault description information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information, and also includes: converting the extended fault description information into machine-recognizable instruction information; applying the search model to extract a first device maintenance information set corresponding to the instruction information from the document information; performing information extraction on the first device maintenance information set to obtain a second device maintenance information set; integrating the device maintenance information in the second device maintenance information set, and converting the integrated device maintenance information into target device maintenance information.

[0008] In one possible implementation, based on the fault description information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information, and also includes: obtaining context information of the fault description information; based on the extended fault description information and the context information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information.

[0009] In a possible implementation, before correcting the fault description information, the following steps are further included:

[0010] The fault description information is normalized to standardize the fault description information; and the normalized fault description information is segmented at coarse and fine granularity to remove invalid information in the fault description information.

[0011] In one possible implementation, the information processing method also includes: based on the fault description information, applying a search model to extract equipment maintenance related information corresponding to the fault description information in the document information, the equipment maintenance related information including one or more of a text report, an original document link, and a paragraph location.

[0012] In one possible implementation, document information related to the maintenance device is retrieved based on the attribute information of the maintenance device, including: obtaining user attribute information of a target user who logs into the intelligent device management system; determining a device permission set of the target user based on the user attribute information; and retrieving document information related to the maintenance device based on the attribute information and the device permission set of the maintenance device.

[0013] In a second aspect, the present application provides an information processing device, including:

[0014] An acquisition module, used to acquire fault description information of a maintenance device, where the fault description information includes attribute information of the maintenance device;

[0015] A retrieval module, used to retrieve document information related to the maintenance equipment according to the attribute information of the maintenance equipment;

[0016] The extraction module is used to extract the target device maintenance information corresponding to the fault description information from the document information by applying the search model according to the fault description information.

[0017] In one possible implementation, the extraction module is specifically used to: correct the fault description information to correct the erroneous description in the fault description information; semantically expand the corrected fault description information to obtain extended fault description information; and apply the search model to extract the target device maintenance information corresponding to the extended fault description information in the document information.

[0018] In one possible implementation, the extraction module is also used to: convert the extended fault description information into machine-recognizable instruction information; apply the search model to extract the first device maintenance information set corresponding to the instruction information in the document information; perform information extraction on the first device maintenance information set to obtain a second device maintenance information set; integrate the device maintenance information in the second device maintenance information set, and convert the integrated device maintenance information into target device maintenance information.

[0019] In a possible implementation, the extraction module is further used to: obtain context information of the fault description information; and apply a search model to extract target device maintenance information corresponding to the fault description information in the document information based on the extended fault description information and the context information.

[0020] In one possible implementation, the information processing device also includes a processing module (not shown). Before correcting the fault description information, the processing module is used to: normalize the fault description information to standardize the fault description information; and perform coarse and fine granularity word segmentation on the normalized fault description information to remove invalid information in the fault description information.

[0021] In one possible implementation, the extraction module is also used to: apply a search model to extract equipment maintenance related information corresponding to the fault description information in the document information based on the fault description information, and the equipment maintenance related information includes one or more of a text report, an original document link, and a paragraph location.

[0022] In one possible implementation, the retrieval module is specifically used to: obtain user attribute information of a target user who logs into the smart device management system; determine a device permission set of the target user based on the user attribute information; and retrieve document information related to the maintenance device based on the attribute information and device permission set of the maintenance device.

[0023] In a third aspect, the present application provides an electronic device, including: at least one processor;

[0024] and a memory communicatively coupled to the at least one processor;

[0025] The memory is used to store instructions executable by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute the information processing method provided in the first aspect.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the information processing method provided in the first aspect above.

[0027] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed, implements the information processing method provided in the first aspect above.

[0028] The information processing method, apparatus, device and storage medium provided by the present application obtains fault description information of the maintenance equipment, the fault description information includes attribute information of the maintenance equipment, and retrieves document information related to the maintenance equipment based on the attribute information of the maintenance equipment, and further applies a search model to extract target equipment maintenance information corresponding to the fault description information from the document information based on the fault description information. The present application can improve the search efficiency of equipment maintenance information by applying a search model to extract target equipment maintenance information corresponding to the fault description information from the document information, thereby improving the maintenance efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] Figure 1 A schematic diagram of the structure of the intelligent device management system provided in the embodiment of the present application;

[0031] Figure 2 Schematic diagram of the information processing method provided in the embodiment of the present application Figure 1 ;

[0032] Figure 3 Schematic diagram of the information processing method provided in the embodiment of the present application Figure 2 ;

[0033] Figure 4 A schematic diagram of the structure of the information processing method provided in the embodiment of the present application;

[0034] Figure 5 A schematic diagram of the structure of an information processing device provided in one embodiment of the present application;

[0035] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0036] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0037] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0038] In the related technologies, on the one hand, the traditional way of passing on equipment maintenance experience and knowledge mainly relies on word of mouth from senior technicians. However, this traditional way of passing on knowledge often leads to the loss of valuable maintenance experience when faced with technician turnover. For new maintenance personnel, due to the lack of systematic and professional guidance, it is difficult for them to quickly master the maintenance and repair skills of equipment, and they can often only obtain scattered and incoherent fragments of knowledge. This not only affects the work efficiency of maintenance personnel in actual operations, but also increases the possibility of errors.

[0039] On the other hand, with the rapid expansion and continuous accumulation of equipment knowledge data related to equipment, if there is a lack of unified and high-standard data management specifications, the data will fall into a quagmire of redundancy and chaos, and it will become difficult to be deeply mined and efficiently used. This may not only lead to deviations in information retrieval, allowing users to get irrelevant results, but may also seriously hinder the accuracy and execution efficiency of organizational decision-making. At present, the search method based on keyword matching has low maintenance efficiency and is difficult to meet the growing personalized needs of users. Users expect accurate, concise answers that meet their specific application scenarios, rather than vague and lengthy information piles.

[0040] Based on the technical problems existing in the related technology, the embodiment of the present application applies a search model to extract the target equipment maintenance information corresponding to the fault description information from the document information related to the maintenance equipment, which can improve the efficiency of searching the equipment maintenance information and thus improve the maintenance efficiency of the equipment.

[0041] Figure 1 This is a schematic diagram of the structure of the intelligent device management system provided in the embodiment of the present application. Figure 1 As shown, the intelligent device management system includes an information storage / retrieval unit, a search model unit and a reply generation unit.

[0042] The information storage / retrieval unit is used to store the device information of all devices. The device information can be the device information corresponding to the device when it is purchased, or the experience information accumulated during the use of the device. The information storage / retrieval module supports the real-time introduction of the latest device information related to the device. Exemplarily, the document type of the device information can be PDF, Docx, TXT, and URL, etc.; it is also used to retrieve document information related to the maintenance device based on the attribute information of the maintenance device;

[0043] A search model unit, used to retrieve relevant equipment information in the information storage / retrieval module, and to extract equipment maintenance information corresponding to the fault description information of the maintenance equipment from the equipment information related to the maintenance equipment;

[0044] The reply generation unit is used to refine and integrate the equipment maintenance information extracted by the search model to obtain target equipment maintenance information for output to the user, namely the equipment maintenance personnel.

[0045] Exemplarily, the search model is based on pre-training data, and is obtained by sequentially training a pre-training (Pretrain) model, a supervised fine-tuning (Supervised Fine-Tuning, SFT) model, and a human feedback reinforcement learning (Reinforcement Learning from Human Feedback, RLHF) model.

[0046] Exemplarily, the pre-training data may be open source Large Language Model (LLM) knowledge distillation data, industrial knowledge base, open source data, etc. The data format of the open source Large Language Model (LLM) knowledge distillation data may be a question-answer pair.

[0047] Exemplarily, the architecture of the search model can be a Decoder-only Transformer architecture, which has a large number of parameters (approximately 15,553,500,160 billion parameters).

[0048] The intelligent equipment management system (AEAM) can be obtained by combining the AI ​​knowledge question-and-answer platform with the EAM. It is understandable that the intelligent equipment management system can be used to store and manage equipment information related to the equipment, and can also be used to automatically process document information corresponding to the equipment information with the help of AI technology.

[0049] It can be understood that the intelligent device management system provided by the embodiment of the present application has the characteristics of unified efficiency, comprehensive tracking and accurate information analysis. Specifically, the intelligent device management system is based on AI technology. On the one hand, it can realize centralized management of device information to ensure efficient use of resources and support instant sharing and rapid scheduling of device information; on the other hand, it can realize comprehensive tracking. The intelligent device management system records every maintenance and repair activity of the equipment in detail to provide detailed data support related to the equipment information, which is conducive to data-driven decision-making; on the other hand, through in-depth analysis of data related to equipment information, it can realize customized personalized maintenance and repair suggestions for different equipment, thereby optimizing equipment management strategies.

[0050] Exemplarily, when a device fails, that is, the device needs maintenance, the user, that is, the device maintenance personnel, logs into the intelligent device management system loaded in the client and sends a device maintenance request to the intelligent device management system. When the intelligent device management system responds to the device maintenance request sent by the device maintenance personnel, it obtains the fault description information of the maintenance device, and retrieves the document information related to the maintenance device based on the attribute information of the maintenance device. Further, based on AI technology, according to the fault description information, the search model is applied to extract the target device maintenance information corresponding to the fault description information from the document information, and the target device maintenance information is output to the device maintenance personnel, so that the equipment maintenance personnel can maintain the maintenance device based on the target device maintenance information, thereby improving the equipment maintenance efficiency.

[0051] Below Figure 1 The intelligent device management system shown in is the execution body, and the information processing method provided in the embodiment of the present application is described in detail in combination with specific embodiments.

[0052] Figure 2 Schematic diagram of the information processing method provided in the embodiment of the present application Figure 1 .like Figure 2 As shown, the specific implementation of the information processing method may include the following steps:

[0053] S201: Acquire fault description information of a maintenance device, where the fault description information includes attribute information of the maintenance device.

[0054] Exemplarily, the maintenance device may be a device that has failed.

[0055] For example, the fault description information may be a natural language description of a fault occurring in a maintenance device, such as "Device A is overheating", "What should I do if device A has not been used for a long time?", and "Device A S500-41 parameter P10?".

[0056] It can be understood that the fault description information may include one or more of the device name, device model, and device number of the maintenance device.

[0057] Exemplarily, the attribute information of the maintenance device may be the device name, device model, and device number of the maintenance device.

[0058] In this step, the fault description information of the maintenance equipment can exist in the form of an equipment maintenance work order, which can be based on photos taken and uploaded by the user, i.e., the equipment maintenance personnel, in the intelligent equipment management system, or can be based on the fault description information manually input by the equipment maintenance personnel in the intelligent equipment management system.

[0059] S202: Retrieve document information related to the maintenance equipment according to the attribute information of the maintenance equipment.

[0060] It is understandable that when storing device information related to a device in the intelligent device management system, the storage may be performed according to the attribute information of the device.

[0061] In this step, a possible implementation method is that the intelligent device management system responds to the fault description information of the maintenance device, starts the intelligent analysis engine, and based on the intelligent analysis engine, retrieves the document information related to the maintenance device in the device maintenance knowledge base in the intelligent device management system based on the device name, device model and device number of the maintenance device, so as to obtain all the document information related to the maintenance device stored in the device maintenance knowledge base.

[0062] For example, the equipment maintenance knowledge base may include key information such as maintenance manuals, equipment data and manuals, emergency plans, and work order records, providing users with rich and authoritative maintenance reference materials to ensure the professionalism and efficiency of equipment maintenance work.

[0063] S203: According to the fault description information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information.

[0064] Exemplarily, the search model may be an AI knowledge model, which may integrate multi-dimensional knowledge such as general knowledge, industry knowledge, data knowledge, database knowledge, analysis knowledge, and report knowledge.

[0065] Exemplarily, the AI ​​knowledge model may include a variety of model algorithms such as deep big data analysis algorithm, icon interpretation algorithm, convolutional neural network (CNN) algorithm, recurrent neural network (RNN) algorithm and generative adversarial neural network (GAN) algorithm.

[0066] Exemplarily, the target device maintenance information may be an intuitive device maintenance suggestion for the fault description information.

[0067] In this step, in one possible implementation method, based on the fault description information, an AI knowledge model is applied to perform one or more searches such as text search, vector search, semantic search, keyword search, and knowledge graph search on the document information to extract the equipment maintenance information corresponding to the fault description information, achieve complete recall of the associated information corresponding to the fault description information, further refine and integrate the equipment maintenance information, and obtain the target equipment maintenance information.

[0068] For example, when the fault description information is "Device A S500-41 parameter P10?", the corresponding target device maintenance information may be "XX action frequency: 0~120HZ, minimum setting unit: 0.1HZ, factory setting range: 3HZ and refer to page 47".

[0069] In the embodiment of the present application, the fault description information of the maintenance equipment is obtained, and the document information related to the maintenance equipment is retrieved according to the attribute information of the maintenance equipment, and the target equipment maintenance information corresponding to the fault description information is extracted from the document information by applying the search model according to the fault description information. In the embodiment of the present application, the search efficiency of the equipment maintenance information can be improved, thereby improving the maintenance efficiency of the equipment.

[0070] It can be understood that in the embodiments of the present application, the fault condition of the maintenance equipment is intelligently analyzed and targeted maintenance suggestions or solutions are automatically provided to the user, i.e. the maintenance personnel, to assist the user in quickly locating the problem and taking corresponding maintenance measures.

[0071] Optionally, in step S203, based on the fault description information, a specific implementation method of applying a search model to extract target device maintenance information corresponding to the fault description information from the document information may be: correcting the fault description information to correct the erroneous description in the fault description information; semantically expanding the corrected fault description information to obtain extended fault description information; and applying a search model to extract target device maintenance information corresponding to the extended fault description information from the document information.

[0072] For example, when the fault description information is "What should I do if the device A has not been used for a long time and has been over-discharged?", after error correction and semantic expansion of the fault description information, the corresponding extended fault description information can be "What should I do if the device A has not been used for a long time (more than one month) and has been over-discharged (battery over-discharged)?"

[0073] Exemplarily, the keyword search corresponding to the extended fault description information may be "device A / long time / more than one month / long term / unused / unused" and the like.

[0074] It is understandable that the fault description information entered by the equipment maintenance personnel may contain grammatical errors for the machine. Therefore, by correcting the fault description information, the accuracy of the search can be improved. By further semantically expanding the corrected fault description information, a comprehensive search for the equipment maintenance information corresponding to the fault description information can be achieved, thereby improving the accuracy of the target equipment maintenance information obtained by the search.

[0075] It is understandable that machine-recognizable instructions are different from human natural language. Therefore, when the search model searches for equipment maintenance information based on fault description information, it is necessary to first convert the fault description information into machine-recognizable instructions.

[0076] Based on the above embodiments, Figure 3 Another specific implementation method of applying the search model to extract the target device maintenance information corresponding to the fault description information from the document information according to the fault description information in step S203 is described in detail.

[0077] Figure 3 Schematic diagram of the information processing method provided in the embodiment of the present application Figure 2 .like Figure 3 As shown, another specific implementation method of applying a search model to extract target device maintenance information corresponding to the fault description information from the document information according to the fault description information may include the following steps:

[0078] S301, converting the extended fault description information into machine-recognizable instruction information.

[0079] Exemplarily, based on Natural Language Understanding (NLU) technology, the extended fault description information is converted into machine-recognizable instruction information.

[0080] S302: Apply the search model to extract a first device maintenance information set corresponding to the instruction information from the document information.

[0081] The specific implementation method is similar to the above and will not be repeated here.

[0082] Exemplarily, the type corresponding to the equipment maintenance information in the first equipment maintenance information set may be document information, chart data, equipment maintenance work order data, and the like.

[0083] S303: extract information from the first device maintenance information set to obtain a second device maintenance information set.

[0084] It is understandable that the degree of correlation between the information contained in the equipment maintenance information set and the fault description information may be different. Some information may be strongly correlated, and some information may be weakly correlated. Therefore, it is necessary to further refine the information in the equipment maintenance information set extracted based on the search model to obtain equipment maintenance information that is strongly correlated with the fault description information, thereby improving the accuracy of the obtained equipment maintenance information.

[0085] In one possible implementation, each piece of equipment maintenance information in the equipment maintenance information set can be sorted in descending order according to the relevance to the fault description information based on logical order, frequency of occurrence, fusion weight and some complex algorithms, and one or more pieces of equipment maintenance information can be selected as the second equipment maintenance information set in this order.

[0086] S304: Integrate the device maintenance information in the second device maintenance information set, and convert the integrated device maintenance information into target device maintenance information.

[0087] In this step, the equipment maintenance information in the second equipment maintenance information set is integrated to obtain equipment maintenance information that intuitively corresponds to the fault description information. It can be understood that the equipment maintenance information is machine-recognizable instruction information. Therefore, it is necessary to convert the equipment maintenance information in a further step to output natural language that is intuitive and easy for equipment maintenance personnel to understand.

[0088] Exemplarily, the device maintenance information is converted into natural language that is clear and easy to understand for device maintenance personnel, namely, the target device maintenance information, by using natural language generation (NLG) technology.

[0089] In an embodiment of the present application, extended fault description information is converted into machine-recognizable instruction information, a search model is applied to extract a first device maintenance information set corresponding to the instruction information in document information, information is refined on the device maintenance information set to obtain a second device maintenance information set, the device maintenance information in the second device maintenance information set is integrated, and the integrated device maintenance information is converted into target device maintenance information, so as to achieve fast and accurate search for the target device maintenance information, thereby improving equipment maintenance efficiency.

[0090] It is understandable that the intelligent equipment management system uses natural language generation technology to convert these complex data and conclusions, such as integrated equipment maintenance information, into natural language that is clear and easy for users to understand, and provide users with concise maintenance suggestions. These intelligently recommended maintenance solutions, after the natural language conversion between the machine and the user, will be presented to the user in a user-friendly form, ensuring that the user can quickly find a solution, thereby significantly shortening the maintenance time, improving the efficiency of equipment use, and bringing greater value to the enterprise.

[0091] It can be understood that when the fault problem existing in the maintenance equipment cannot be accurately captured based on the fault description information, optionally, in the information processing method provided in the embodiment of the present application, another possible implementation method may be to apply a search model to extract the target device maintenance information corresponding to the fault description information in the document information based on the fault description information: obtaining the context information of the fault description information; and applying a search model to extract the target device maintenance information corresponding to the fault description information in the document information based on the extended fault description information and the context information.

[0092] It should be noted that in the information processing method provided in the embodiment of the present application, when applying a search model to extract the target device maintenance information corresponding to the fault description information from the document information based on the fault description information, the search model can be combined with one or more of the prompt templates in the search model, such as question-answer data pairs, context-related information, and sensitive identification technologies, to extract the target device maintenance information corresponding to the fault description information from the document information, so as to optimize the extraction of the target device maintenance information, thereby improving the quality and accuracy of the extracted target device maintenance information.

[0093] In order to improve the accuracy of the extracted target device maintenance information, optionally, before correcting the fault description information, the information processing method provided in the embodiment of the present application also includes: normalizing the fault description information to standardize the fault description information; performing coarse and fine granularity word segmentation on the normalized fault description information to remove invalid information in the fault description information.

[0094] Exemplarily, the normalization processing of the fault description information may include one or more processing methods such as traditional and simplified Chinese conversion, uppercase and lowercase conversion, full-width and half-width conversion, and query truncation, so as to achieve normalized input of the fault description information.

[0095] Exemplarily, the normalized fault description information is segmented at coarse and fine granularity, that is, the normalized fault description information is split into meaningful words and / or phrases, and the grammatical role of each word is analyzed to filter out invalid information such as punctuation marks and stop words, and only valid information is retained. By segmenting words based on industry knowledge, professional terms can be correctly processed.

[0096] Optionally, the information processing method provided in the embodiment of the present application also includes: based on the fault description information, applying a search model to extract equipment maintenance related information corresponding to the fault description information in the document information, the equipment maintenance related information including one or more of a text report, an original document link, and a paragraph location.

[0097] It is understandable that through advanced semantic decomposition, file content understanding reasoning and analysis technology, the intelligent device management system can form accurate and targeted conclusions, and provide users with intuitive and easy-to-understand result displays, including detailed text reports, original document links and precise paragraph positioning. While providing users with target device maintenance information for fault description information, it also helps users understand and learn more about maintaining equipment.

[0098] Optionally, a possible implementation method of retrieving document information related to the maintenance device based on the attribute information of the maintenance device in step S202 may be: obtaining user attribute information of a target user who logs in to the smart device management system; determining a device permission set of the target user based on the user attribute information; and retrieving document information related to the maintenance device based on the attribute information and the device permission set of the maintenance device.

[0099] Exemplarily, the user attribute information may be a user account when the user logs into the smart device maintenance system.

[0100] It should be noted that in the smart device management system provided in the embodiment of the present application, different users have different corresponding queriable device permissions. Correspondingly, users without device permissions can retrieve different contents of device-related document information. Exemplarily, the higher the device permissions corresponding to the user, the more content of device-related document information that can be retrieved. Conversely, the lower the device permissions corresponding to the user, the less content of device-related document information that can be retrieved.

[0101] Optionally, the information processing method provided in the embodiment of the present application also includes: obtaining user attribute information of the target user logging into the smart device management system; determining the device permission set of the target user based on the user attribute information; determining whether the maintenance device exists in the device permission set; if the maintenance device exists in the device permission set, executing the step of retrieving document information related to the maintenance device based on the attribute information of the maintenance device; if the device to be maintained does not exist in the device permission set, generating a prompt message, which is used to prompt the target user that he does not have information query authority.

[0102] In the information processing method provided in the embodiment of the present application, the user groups are accurately segmented in the intelligent device management system. According to the responsibilities and permissions of each user, the intelligent device management system can intelligently recommend devices closely related to their responsibilities and document information that matches the device specifications. This highly intelligent recommendation mechanism improves the user's work efficiency and decision-making accuracy, and enhances the user's work experience.

[0103] Figure 4 This is a schematic diagram of the structure of the information processing method provided in the embodiment of the present application. Figure 4 As shown, in the information processing method provided by the embodiment of the present application, when the fault description information of the maintenance equipment is obtained, the intelligent analysis engine in the intelligent equipment management system is started, and the intelligent analysis engine retrieves the equipment information related to the maintenance equipment based on the attribute information of the maintenance equipment, and calls the search model so that the search model extracts the target equipment maintenance information corresponding to the fault description information from the document information according to the fault description information. Figure 4 As shown, in extracting the target device maintenance information corresponding to the fault description information from the document information using the search model according to the fault description information, one or more processes may be included, such as rewriting the fault analysis information, such as error correction and semantic expansion, obtaining context-related information, and obtaining other chart data of the maintenance work order where the fault description information is located. After the above processes are completed, the processed fault description information is converted into machine-recognizable instruction information based on natural language understanding technology, and based on the query engine, the device maintenance information set corresponding to the instruction information is queried in the document information according to the instruction information. Furthermore, based on the data channel connector and content organization, the device maintenance information in the device maintenance information set is refined and integrated to obtain the device maintenance information corresponding to the fault description information, and the device maintenance information is converted into target device maintenance information through natural language generation technology and output to the user.

[0104] In the information processing method provided in the embodiment of the present application, the introduction of the AI ​​knowledge question and answer management system, i.e., the intelligent device management system provided in the embodiment of the present application, not only improves the accuracy and efficiency of document information retrieval, but also provides users with a more intelligent and convenient question and answer experience. Whether it is a technical issue or a business process, users can quickly obtain accurate answers and solutions by asking simple natural language questions. In addition, based on the security considerations of the intelligent device management system, a device information list and a device permission module are set up. Different users obtain customized device permission information according to user permissions, thereby protecting the security of device information and reducing the situation of irrelevant answers.

[0105] In summary, in the intelligent equipment management system provided in the embodiment of the present application, by deeply mining the fault description information of the maintenance equipment, it is possible to form detailed statistical reports and accurately analyze key indicators such as the equipment's fault type and fault frequency. AI knowledge questions and answers can transform the knowledge retrieval that is manually completed in related technologies into artificial intelligence content organization through intelligent natural language processing. By using intelligent natural language processing, the intelligent equipment management system can not only simplify the tedious knowledge organization and retrieval work, but also transform the equipment maintenance knowledge base from a single tool to a powerful production equipment management assistant. This transformation not only improves work efficiency, but also makes the equipment maintenance knowledge base an indispensable intelligent partner in enterprise operation and maintenance management.

[0106] In summary, the information processing method provided in the embodiment of the present application can realize functions such as natural language dialogue, associated element query, data reasoning and result generation when applied to the intelligent device management system provided in the embodiment of the present application. Among them, the natural language dialogue function can be used for the user to input in natural language, and the intelligent device management system can understand the user's instructions and the implicit meaning of the instructions, and output an explainable answer to the user according to the association of the context; the associated element function can be used for the intelligent device management system to associate the document content in the device maintenance knowledge base in different dimensions, and query the associated business indicators, dimensions, document materials and data charts according to the user's instructions and the implicit meaning of the instructions; the data function can be used for the intelligent device management system to disassemble the semantics obtained by analyzing the user's instructions and the corresponding dimensions, and understand, reason and analyze the associated content to form a conclusion; the result generation function can be used for the intelligent device management system to generate text reports and the original document links and paragraph positioning of the response based on the reasoning conclusion, and output an intuitive result viewing method for the user.

[0107] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0108] Figure 5 This is a schematic diagram of the structure of an information processing device provided by an embodiment of the present application. Figure 5 As shown, the information processing device 50 provided in this embodiment includes an acquisition module 510 , a retrieval module 520 and an extraction module 530 .

[0109] The acquisition module 510 is used to acquire fault description information of the maintenance equipment, where the fault description information includes attribute information of the maintenance equipment;

[0110] A retrieval module 520, configured to retrieve document information related to the maintenance device according to the attribute information of the maintenance device;

[0111] The extraction module 530 is used to extract the target device maintenance information corresponding to the fault description information from the document information by applying the search model according to the fault description information.

[0112] In one possible implementation, the extraction module 530 is specifically used to: correct the fault description information to correct the erroneous description in the fault description information; semantically expand the corrected fault description information to obtain extended fault description information; and apply the search model to extract the target device maintenance information corresponding to the extended fault description information in the document information.

[0113] In one possible implementation, the extraction module 530 is also used to: convert the extended fault description information into machine-recognizable instruction information; apply the search model to extract the first device maintenance information set corresponding to the instruction information in the document information; perform information extraction on the first device maintenance information set to obtain a second device maintenance information set; integrate the device maintenance information in the second device maintenance information set, and convert the integrated device maintenance information into target device maintenance information.

[0114] In a possible implementation, the extraction module 530 is further used to: obtain context information of the fault description information; and apply a search model to extract target device maintenance information corresponding to the fault description information from the document information based on the extended fault description information and the context information.

[0115] In one possible implementation, the information processing device also includes a processing module (not shown). Before correcting the fault description information, the processing module is used to: normalize the fault description information to standardize the fault description information; and perform coarse and fine granularity word segmentation on the normalized fault description information to remove invalid information in the fault description information.

[0116] In one possible implementation, the extraction module 530 is also used to: apply a search model to extract equipment maintenance related information corresponding to the fault description information in the document information based on the fault description information, and the equipment maintenance related information includes one or more of a text report, an original document link, and a paragraph location.

[0117] In one possible implementation, the retrieval module 520 is specifically used to: obtain user attribute information of a target user who logs into the smart device management system; determine the device permission set of the target user based on the user attribute information; and retrieve document information related to the maintenance device based on the attribute information and device permission set of the maintenance device.

[0118] The processing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0119] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602 .

[0120] Optionally, the electronic device 60 further includes a communication interface 603 and a system bus 604 .

[0121] The memory 602 and the communication interface 603 are connected to the processor 601 via the system bus 604 and communicate with each other. The memory 602 is used to store instructions, and the communication interface 603 is used to communicate with other devices.

[0122] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.

[0123] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0124] In the above-mentioned embodiment, it should be understood that the processor 601 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the invention can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0125] The memory 602 may include a high-speed memory (Random Access Memory, RAM for short), and may also include a non-volatile memory (NVM for short), such as at least one disk memory.

[0126] The system bus 604 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus 604 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the system bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0127] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0128] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0129] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0130] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0131] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0135] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0136] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An information processing method, characterized in that: include: Acquire fault description information of a maintenance device, wherein the fault description information includes attribute information of the maintenance device; Retrieving document information related to the maintenance device according to the attribute information; According to the fault description information, a search model is applied to extract target device maintenance information corresponding to the fault description information from the document information.

2. The information processing method according to claim 1, characterized in that: The extracting target device maintenance information corresponding to the fault description information from the document information by applying the search model according to the fault description information includes: Correcting the fault description information to correct the erroneous description in the fault description information; Performing semantic expansion on the fault description information after error correction to obtain extended fault description information; The search model is applied to extract target device maintenance information corresponding to the extended fault description information from the document information.

3. The information processing method according to claim 2, characterized in that: The extracting target device maintenance information corresponding to the fault description information from the document information by applying the search model according to the fault description information also includes: Converting the extended fault description information into machine-recognizable instruction information; Applying a search model to extract a first device maintenance information set corresponding to the instruction information in the document information; Extracting information from the device maintenance information set to obtain a second device maintenance information set; The device maintenance information in the second device maintenance information set is integrated, and the integrated device maintenance information is converted into the target device maintenance information.

4. The information processing method according to claim 2, characterized in that: The extracting target device maintenance information corresponding to the fault description information from the document information by applying the search model according to the fault description information also includes: Obtaining context information of the fault description information; The search model is applied to extract target device maintenance information corresponding to the fault description information from the document information according to the extended fault description information and the context information.

5. The information processing method according to claim 2, characterized in that: Before correcting the fault description information, the method further includes: Performing normalization processing on the fault description information to normalize the fault description information; The normalized fault description information is segmented at coarse and fine granularity to remove invalid information in the fault description information.

6. The information processing method according to any one of claims 1 to 5, characterized in that: Also includes: According to the fault description information, a search model is applied to extract equipment maintenance related information corresponding to the fault description information in the document information, where the equipment maintenance related information includes one or more of a text report, an original document link, and a paragraph location.

7. The information processing method according to any one of claims 1 to 5, characterized in that: The retrieving document information related to the maintenance device according to the attribute information includes: Obtain user attribute information of the target user who logs into the smart device management system; Determining a device permission set of the target user according to the user attribute information; Document information related to the maintenance device is retrieved according to the attribute information and the device permission set.

8. An information processing device, characterized in that: include: An acquisition module, used to acquire fault description information of a maintenance device, wherein the fault description information includes attribute information of the maintenance device; A retrieval module, used to retrieve document information related to the maintenance equipment according to the attribute information; The extraction module is used to extract the target device maintenance information corresponding to the fault description information from the document information by applying a search model according to the fault description information.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory is used to store instructions executable 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 method according to any one of claims 1 to 7.

10. A computer-readable storage medium / computer program product, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed; The computer program product comprises a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images