Equipment maintenance task execution method, system and device and electronic equipment

Abstract

The invention provides an equipment maintenance task execution method, system and device and electronic equipment, and relates to the technical field of artificial intelligence and industrial internet. According to the implementation scheme, the method comprises the steps of monitoring equipment operation data collected by at least one sensor associated with equipment; generating fault information of the equipment in response to the abnormal indication of the equipment operation data; performing fault analysis on a first retrieval result based on the fault information and the fault information by using a large model to generate a fault work order for creating a maintenance task, the first retrieval result being obtained by retrieving a historical operation knowledge base and an equipment description knowledge base; based on the maintenance data related to the maintenance task, utilizing a large model to generate a report text of a maintenance record based on a preset template; and storing the report text of the maintenance record in the historical operation knowledge base. According to the embodiment of the invention, the intelligence of the equipment inspection and maintenance process can be realized, and the efficiency and accuracy of the equipment inspection and maintenance process are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence and industrial internet, in particular to intelligent operation and maintenance technology, and specifically to a device maintenance task execution method, system, device, electronic device, computer readable storage medium and computer program product. BACKGROUND

[0002] Artificial intelligence (AI) is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of humans, which includes both hardware and software technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, special-purpose artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc.

[0003] In the field of industrial equipment inspection and maintenance, business process management is usually based on office automation systems, and the execution, inspection and pushing of each link rely on manual confirmation.

[0004] The methods described in this section do not necessarily have to be the methods previously conceived or used. Unless otherwise indicated, nothing in this section should be assumed to be prior art merely because it is included in this section. Similarly, any problems mentioned in this section should not be assumed to have been recognized in any prior art unless otherwise indicated. SUMMARY

[0005] The present disclosure provides a device maintenance task execution method, device, electronic device, computer readable storage medium and computer program product.

[0006] According to an aspect of the present disclosure, a device maintenance task execution method is provided, comprising: monitoring device operation data collected by at least one sensor associated with the device; generating fault information of the device in response to the device operation data indicating an abnormality; performing fault analysis on a first search result based on the fault information and the fault information by using a large model to generate a fault work order for creating a maintenance task, wherein the first search result is obtained by searching a historical operation knowledge base and a device description knowledge base; generating a report text of a maintenance record based on a preset template by using a large model based on maintenance data related to the maintenance task; storing the report text of the maintenance record in the historical operation knowledge base.

[0007] According to another aspect of this disclosure, a multi-agent-based system for assisting equipment maintenance is provided, comprising: a monitoring module configured to monitor equipment operation data collected by at least one sensor associated with the equipment; a generation module configured to generate fault information of the equipment in response to an abnormality indicated by the equipment operation data; a work order creation agent configured to perform fault analysis using a large model on a first retrieval result based on the fault information and the fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment description knowledge base; and a report generation agent configured to generate a report text of a maintenance record based on maintenance data related to the maintenance task, using a large model based on a preset template, wherein the report text of the maintenance record is stored in the historical operation knowledge base.

[0008] According to another aspect of this disclosure, an equipment maintenance task execution apparatus is provided, comprising: a monitoring unit configured to monitor equipment operation data collected by at least one sensor associated with the equipment; a fault information generation unit configured to generate fault information of the equipment in response to an abnormality indicated by the equipment operation data; a work order generation unit configured to perform fault analysis on a first retrieval result based on the fault information and the fault information using a large model to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment description knowledge base; a report generation unit configured to generate a report text of a maintenance record based on maintenance data related to the maintenance task and using a large model based on a preset template; and a storage unit configured to store the report text of the maintenance record in the historical operation knowledge base.

[0009] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described according to embodiments of this disclosure.

[0010] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the method described according to embodiments of this disclosure.

[0011] According to another aspect of this disclosure, a computer program product is also provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the method described according to embodiments of this disclosure.

[0012] According to one or more embodiments of this disclosure, the equipment inspection and maintenance process can be made intelligent, thereby improving the efficiency and accuracy of the equipment inspection and maintenance process.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0015] Figure 1 A schematic diagram of an exemplary system in which the various methods described herein may be implemented according to embodiments of the present disclosure is shown; Figure 2 An exemplary flowchart of a method for performing equipment maintenance tasks according to an embodiment of the present disclosure is shown; Figure 3 An example diagram of a multi-agent-based system for assistive device maintenance according to an embodiment of the present disclosure is shown; Figure 4 An exemplary flowchart of a repair process according to an embodiment of the present disclosure is shown; Figure 5 An exemplary block diagram of an apparatus for inspecting and maintaining equipment based on a large model, according to an embodiment of the present disclosure, is shown; Figure 6 Structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure. Detailed Implementation

[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0017] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0018] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0019] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0020] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0021] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of methods according to embodiments of this disclosure.

[0022] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105 and / or 106 under a Software as a Service (SaaS) model.

[0023] exist Figure 1In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0024] Users can use client devices 101, 102, 103, 104, 105, and / or 106 to receive user input and provide output results to the user. The client devices can provide an interface that allows users to interact with the client devices. The client devices can also output information to the user through this interface. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0025] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices are capable of executing various applications, such as various internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and can use various communication protocols.

[0026] Network 110 can be any type of network well known to those skilled in the art, and can support data communication using any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.). By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0027] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0028] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0029] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105 and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105 and / or 106.

[0030] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0031] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0032] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0033] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0034] Figure 2 An exemplary flowchart of a method for performing equipment maintenance tasks according to an embodiment of the present disclosure is shown.

[0035] like Figure 2 As shown, step S202 includes monitoring device operation data collected by at least one sensor associated with the device.

[0036] Step S204 includes generating equipment fault information in response to an abnormality indicated by equipment operating data.

[0037] Step S206 includes using a large model to perform fault analysis on the first retrieval results and fault information based on fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval results are obtained by searching the historical operation knowledge base and the equipment instruction knowledge base.

[0038] Step S208 includes generating a report text of maintenance records based on a preset template using a large model, based on maintenance data related to the maintenance task.

[0039] Step S210 includes storing the report text of the maintenance record in the historical operation knowledge base.

[0040] The methods provided by the embodiments of this disclosure can realize the intelligentization of equipment inspection and maintenance processes, thereby improving the efficiency and accuracy of equipment inspection and maintenance.

[0041] The principles of this disclosure will now be described in detail.

[0042] Step S202 includes monitoring device operation data collected by at least one sensor associated with the device.

[0043] The processes described in the embodiments of this disclosure can be applied to various systems that include devices, particularly industrial equipment, such as Internet of Things (IoT) systems. Exemplary sensors may include vibration sensors, temperature sensors, pressure sensors, etc. Sensors can be used to collect real-time status data of the devices.

[0044] Step S204 includes generating equipment fault information in response to an abnormality indicated by equipment operating data.

[0045] In some embodiments, step S204 may include obtaining the current value of the device operating data; and triggering an alarm mechanism and generating alarm information if the current value exceeds a preset threshold range or if abnormal fluctuations occur.

[0046] In response to the detection that parameter values ​​in the device operation data collected by sensors exceed preset thresholds and / or exhibit abnormal fluctuations, a system alarm can be triggered and alarm information generated. The alarm information may include at least one of the following: timestamp, current value of the operating data, operating data threshold, and anomaly description. In some examples, the alarm information may be structured. In other examples, the alarm information may be unstructured or semi-structured.

[0047] Fault information for a device can be generated based on alarm information. This fault information may include device identifiers, phenomenon descriptions, alarm levels, and other information. In some embodiments, a rule engine can be used to analyze alarm information based on predetermined rules to generate fault information. In other embodiments, alarm information can be processed manually to generate fault information.

[0048] Step S206 includes using a large model to perform fault analysis on the first retrieval results and fault information based on fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval results are obtained by searching the historical operation knowledge base and the equipment instruction knowledge base.

[0049] The large model can be a large language model (LLM) or any model capable of natural language understanding and processing based on general knowledge.

[0050] The historical operation knowledge base may include at least one of the following: historical maintenance records (including structured data such as maintenance time, maintenance personnel, maintenance steps, and component replacement), equipment operation logs, and maintenance records. The equipment instruction knowledge base may include equipment manuals, technical parameter documents, specifications, and failure mode documents.

[0051] Step S206 can be executed by invoking a work order creation agent. Invoking the work order creation agent may include inputting a preset prompt. An example prompt might be, "You are a professional work order processing specialist. Your core task is to perform attribution analysis on the causes of faults and generate a fault analysis work order based on the analysis results, including fault cause analysis, repair plan suggestions, and risk assessment." Example fault causes may include equipment aging, improper operation, and external interference. Example repair plan suggestions may include a spare parts list, repair steps, and safety precautions. Those skilled in the art can configure the preset prompt according to actual conditions to extract information related to equipment faults from the fault information.

[0052] In some embodiments, retrieval augmentation generation (RAG) technology can be utilized in step S206. A first retrieval result can be obtained by performing a semantic-level retrieval of the historical operation knowledge base and the equipment description knowledge base based on fault information. This first retrieval result may include maintenance history and equipment information related to the fault information obtained in step S204. The RAG task can be triggered by concatenating a retrieval command into a prompt word in the work order creation agent. Then, the fault information can be converted into a vector representation and semantically retrieved from at least one of the historical operation knowledge base and the equipment description knowledge base to extract the portion of knowledge documents with a relevance higher than a preset threshold as the first retrieval result. After obtaining the first retrieval result, it can be concatenated with the fault information according to a predetermined format and input into the work order creation agent to output the work order creation result. For example, first input data containing fault information, the first retrieval result, and a first preset prompt word can be constructed. The first input data can be input into a large model to obtain the fault analysis result output by the large model, where the fault analysis result includes the fault cause, maintenance plan suggestions, and risk assessment. By utilizing information retrieved from historical operation knowledge bases and equipment instruction knowledge bases, the intelligent agent created by calling work orders can analyze the fault status of the current equipment by referring to the historical maintenance records and equipment instruction manuals.

[0053] In some examples, vectorized semantic features can be extracted from fault information, and the top N (Top-N) relevant document blocks can be retrieved from the historical operation knowledge base and equipment instruction knowledge base as the first search result. In other examples, different information contents in the fault information can be prioritized and retrieved separately, and the search results corresponding to different information contents can be sorted according to the priority ranking results. The sorting information of the search results and the search results can be input together into the work order creation agent, so that the agent can display different information in priority order in the generated fault work order during the work order creation process, thereby achieving the effect of displaying more important information in a more prominent way. Those skilled in the art can use various suitable methods to implement knowledge base retrieval to obtain relevant knowledge base documents, and no specific limitation is made to the retrieval technology here.

[0054] The intelligent agent created using the work order provided in this disclosure can provide intelligent improvements to work order generation technology, so that the generated work order content not only includes the current status data of the equipment, but also provides more cause analysis and operation suggestions for maintenance tasks, realizing the improvement of work orders from basic information recording function to intelligent decision support function.

[0055] In some embodiments, during the operation of a maintenance task, method 200 may further include: receiving query information related to the maintenance task; performing semantic parsing of the query information using a large model to determine the query intent corresponding to the query information; and analyzing a second retrieval result based on the query intent and the query intent using the large model to generate feedback information for the query information, wherein the second retrieval result is obtained by searching a historical operation knowledge base, an equipment instruction knowledge base, an expert experience knowledge base, and an equipment operation knowledge base. The above-mentioned operation of providing feedback for the query information can be implemented by invoking a maintenance guidance agent. An exemplary prompt for invoking the work order creation agent could be, "You are a professional maintenance expert. Your core task is to provide maintenance solutions based on the currently input problem, which can be proposed through a combination of documents, images, and videos."

[0056] The query information can target at least one of the following: fault diagnosis; component installation / disassembly operations; equipment parameter adjustment operations. During the maintenance process, when maintenance personnel encounter problems, such as complex fault diagnosis, special component disassembly / installation methods, equipment parameter adjustment, etc., they can query the information by calling the maintenance guidance agent in the system.

[0057] An expert experience knowledge base may include at least one of the following: a terminology database; a thesaurus; a problem analysis approach database; and a problem solution database. The terminology database may include specialized terms and their corresponding explanations. The thesaurus may include different terms representing similar semantics. The problem analysis approach database may include frameworks and methodologies for analyzing problems, such as fault tree analysis. The problem solution database may include example problems and specific solutions for those example problems.

[0058] The equipment operation knowledge base may include at least one of the following: equipment manual; equipment drawings; standard documents; operation videos.

[0059] In some embodiments, using a large model to analyze the second search results and the query intent based on the query intent to generate feedback information for the query information includes: constructing second input data containing the second search results, the query intent, and second preset prompts, wherein the second search results include videos and text that match the query intent; inputting the second input data into the large model to obtain multimodal feedback information output by the large model, including at least one of videos, text, and flowcharts, wherein at least a portion of the feedback information comes from the second search results.

[0060] The maintenance guidance agent first performs semantic parsing and intent recognition on the questions raised by maintenance personnel. After clarifying the specific needs, RAG technology can be used to retrieve relevant information from the expert experience knowledge base (a structured experience base formed through actual visits and surveys of senior experts, followed by knowledge extraction and semantic annotation) and the equipment operation knowledge base (equipment operation manuals, operation videos, equipment drawings, maintenance case libraries, etc.). In some examples, vectorized semantic features of the query information and / or query intent can be obtained, and searches can be performed on the historical operation knowledge base, equipment instruction knowledge base, expert experience knowledge base, and equipment operation knowledge base based on the extracted semantic features to obtain related knowledge document blocks. Those skilled in the art can utilize various suitable methods to implement knowledge base retrieval to obtain relevant knowledge base documents; no specific limitations are imposed on the retrieval techniques here.

[0061] In some embodiments, the content in the expert experience knowledge base and the equipment operation knowledge base may include multimodal information, so that the feedback information output by the maintenance guidance agent may also include multimodal content, such as operation videos of solutions to the current maintenance problem retrieved from the knowledge base, so that maintenance personnel can directly solve the current maintenance problem based on the results output by the maintenance guidance agent.

[0062] By utilizing the maintenance guidance intelligent agent provided in this disclosure, the retrieval results of query information related to maintenance tasks are fused, logically reasoned, and summarized through a large model. Finally, the results required by maintenance personnel are output in multiple forms such as structured text, flowcharts, and video clips, achieving accurate matching and efficient delivery of "question-answer".

[0063] Step S208 includes generating a report text of maintenance records based on a preset template using a large model, based on maintenance data related to the maintenance task.

[0064] After the maintenance task is completed, the user can generate a maintenance report by invoking a maintenance report generation agent. An exemplary prompt for the maintenance report generation agent might include: "You are a professional maintenance report generation assistant, specializing in transforming maintenance process data into a well-structured and detailed standardized report. Your task is to generate a professional report based on the provided maintenance information, including a fault description, maintenance process, result verification, and follow-up recommendations." In some embodiments, the prompt may also include a preset template for the maintenance report.

[0065] The intelligent agent for generating maintenance reports can automatically generate maintenance reports that conform to industry standards and company requirements based on maintenance records (including maintenance time, personnel, steps, and spare parts usage), historical equipment status information (such as recent operating parameters, historical fault records, and maintenance cycles), and preset report templates (including standard modules such as fault description, maintenance process, result verification, and follow-up suggestions). It utilizes large-scale model content generation capabilities and format control technology. In some examples, the generated report needs to be reviewed and confirmed by maintenance personnel before being submitted to acceptance personnel. The acceptance personnel compare the report content with the actual on-site conditions to verify the report, ultimately completing the acceptance confirmation and forming a complete closed-loop maintenance management system.

[0066] Step S210 includes storing the report text of the maintenance record in the historical operation knowledge base.

[0067] By storing maintenance record reports in the historical operation knowledge base, the content stored in the historical operation knowledge base can be continuously updated for use in subsequent maintenance tasks.

[0068] In some embodiments, method 200 may further include: receiving device query information for a second device; and analyzing a third search result based on the device query information using a large model to obtain a device status report, wherein the third search result is obtained by searching a historical operation knowledge base. The device status report may include at least one of the following: a device status summary, operational indicator analysis, and risk warning alerts.

[0069] When users need to understand the operational status, they can perform the above-mentioned device query operation by invoking the device query agent. An example prompt for invoking the device query agent may include: "You are a professional equipment maintenance personnel. Your task is to query the equipment's historical maintenance records and operation logs, and generate an equipment query report that includes an equipment status summary, operational indicator analysis, and risk warning prompts."

[0070] The equipment query information can include equipment type, equipment identifier, time period of interest, parameters of interest, etc. The equipment query agent can use RAG technology to search the historical operation knowledge base based on the equipment query information to obtain knowledge document blocks related to the equipment query information as the third search result. Furthermore, it can generate an equipment status report by knowledge fusion of the equipment query information and the third search result, so that the equipment status report can reflect the comprehensive analysis results of the equipment's historical and real-time status.

[0071] In some embodiments, analyzing the third search results based on device query information using a large model to obtain a device status report may include: constructing third input data including device query information, third search results, and preset third prompts, wherein the third search results include historical operation records associated with the second device retrieved from a historical operation knowledge base; inputting the third input data into the large model to obtain a device status report output by the large model, wherein the device status report is associated with the historical operation records of the second device and includes at least one of device status summary, operation indicator analysis, and risk warning prompts.

[0072] By utilizing the aforementioned device query intelligent agent, the natural language processing and report generation capabilities of the large model can be leveraged to automatically generate device query reports related to the device query information, thereby improving the efficiency and accuracy of device queries.

[0073] The various intelligent agents provided in the embodiments of this disclosure can be integrated into the office automation system as plug-ins. Users can log in to the office automation system through various means such as web pages and applications, and call the corresponding intelligent agent plug-ins through the interfaces integrated into the office automation system.

[0074] Figure 3 An example diagram of a multi-agent-based system for assistive device maintenance according to an embodiment of the present disclosure is shown.

[0075] like Figure 3 As shown, system 300 may include monitoring module 310, generation module 320, work order creation agent 330, and report generation agent 340.

[0076] The monitoring module 310 can be configured to monitor equipment operation data collected by at least one sensor associated with the equipment. The generation module 320 can be configured to generate equipment fault information in response to abnormal equipment operation data. The work order creation agent 330 can be configured to perform fault analysis on the first retrieval result based on the fault information and the fault information using a large model to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment specification knowledge base. The report generation agent 340 is configured to generate a report text of the maintenance record based on maintenance data related to the maintenance task, using a large model based on a preset template, wherein the report text of the maintenance record is stored in the historical operation knowledge base.

[0077] In some embodiments, the system 300 may further include a maintenance guidance agent 350, configured to: analyze query information received during maintenance task execution using a large model to determine the query intent corresponding to the query information; and analyze a second retrieval result based on the query intent and the query intent using the large model to generate feedback information for the query information, wherein the second retrieval result is obtained by searching a historical operation knowledge base, an equipment instruction knowledge base, an expert experience knowledge base, and an equipment operation knowledge base.

[0078] In some embodiments, the system 300 may further include a device query agent 360, configured to: receive device query information; and analyze a third search result based on the device query information using a large model to obtain a device status report, wherein the third search result is obtained by searching a historical operation knowledge base.

[0079] Can be used Figure 3 The system implementation shown in the figure combines Figure 2 The methods described above for method 200 are also applicable to system 300. For the sake of brevity, some operations, features, and advantages will not be repeated here.

[0080] Figure 4 An exemplary flowchart of a repair process according to an embodiment of the present disclosure is shown.

[0081] like Figure 4 As shown, in step 401, alarm information including timestamps, current values ​​of device metrics, metric thresholds, and anomaly descriptions can be obtained from the IoT system. In step 402, the information obtained in step 401 can be filled into a structured basic fault work order.

[0082] At step 403, the work order creation agent 410 can be invoked to generate a fault analysis work order. The work order creation agent 410 can generate a fault analysis work order containing fault cause analysis, maintenance plan suggestions, risk assessment, etc., by using the first search result obtained from the historical operation knowledge base 420 and the equipment description knowledge base 421 based on RAG technology and the fault information recorded in the basic fault work order.

[0083] In step 404, the fault analysis work order generated by the work order creation agent 410 can be reviewed in the system and pushed to the maintenance personnel.

[0084] At step 405, on-site repairs can be performed by maintenance personnel. During on-site repairs, the user can invoke the maintenance guidance agent 411 to query for specific repair issues within the repair task. The maintenance guidance agent 411 can generate feedback on the repair issues based on the second search results obtained from searching the historical operation knowledge base 420, equipment instruction knowledge base 421, expert experience knowledge base 422, and equipment operation knowledge base 423 using RAG technology, along with the user-initiated repair issues. This feedback includes operational suggestions in at least one form, such as text, flowcharts, or operation videos.

[0085] At step 406, the maintenance report generation agent 412 can be invoked to generate a maintenance report based on the maintenance record data, and the generated maintenance report can be stored in the historical operation knowledge base.

[0086] In step 407, equipment query information can be received to track and review the equipment maintenance history. The equipment query agent 413 can be invoked to generate an equipment status report including an equipment status summary, operational indicator analysis, and risk warning prompts. Specifically, the equipment query agent 413 can generate the equipment status report based on the third search results obtained from retrieving the historical operation knowledge base 420 using RAG technology and the equipment query information.

[0087] Figure 5 An exemplary block diagram of an apparatus for inspecting and maintaining equipment based on a large model, according to an embodiment of the present disclosure, is shown.

[0088] like Figure 5 As shown, the device 500 may include a monitoring unit 510, a fault information generation unit 520, a work order generation unit 530, a report generation unit 540, and a storage unit 550.

[0089] Monitoring unit 510 can be configured to monitor equipment operation data collected by at least one sensor associated with the equipment. Fault information generation unit 520 can be configured to generate equipment fault information in response to abnormal equipment operation data. Work order generation unit 530 can be configured to perform fault analysis using a large model on a first retrieval result based on the fault information and the fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment specification knowledge base. Report generation unit 540 can be configured to generate a maintenance record report text based on a preset template using a large model, based on maintenance data related to the maintenance task. Storage unit 550 can be configured to store the maintenance record report text in a historical operation knowledge base.

[0090] In some embodiments, generating device fault information in response to device operating data indicating anomalies includes: obtaining the current value of the device operating data; triggering an alarm mechanism and generating alarm information if the current value exceeds a preset threshold range or exhibits abnormal fluctuations; and classifying the alarm information using a rule engine to generate fault information associated with the device, wherein the alarm information includes at least one of a timestamp, current value of an indicator, an indicator threshold, and an abnormal time description.

[0091] In some embodiments, using a large model to perform fault analysis on the first retrieval result and fault information based on fault information to generate a fault work order for creating a maintenance task includes: converting the fault information into a vector representation; performing semantic retrieval in at least one of the historical operation knowledge base and the equipment instruction knowledge base to extract a portion of the knowledge documents with a relevance to the fault information higher than a preset threshold as the first retrieval result; constructing first input data containing the fault information, the first retrieval result, and a first preset prompt word; and inputting the first input data into the large model to obtain the fault analysis result output by the large model, wherein the fault analysis result includes the fault cause, maintenance plan suggestions, and risk assessment.

[0092] In some embodiments, the historical operation knowledge base includes at least one of the following: historical maintenance records; equipment operation logs; maintenance records, and wherein the equipment instruction knowledge base includes equipment instruction manuals.

[0093] In some embodiments, the device 500 further includes a maintenance guidance unit configured to: receive query information related to the maintenance task during maintenance task operation, wherein the query information targets at least one of the following: fault diagnosis, component installation / removal operation, and equipment parameter adjustment operation; perform semantic parsing of the query information using a large model to determine the query intent corresponding to the query information; and analyze a second retrieval result based on the query intent and the query intent using the large model to generate feedback information for the query information, wherein the second retrieval result is obtained by searching a historical operation knowledge base, an equipment instruction knowledge base, an expert experience knowledge base, and an equipment operation knowledge base.

[0094] In some embodiments, the expert experience knowledge base includes at least one of the following: a terminology database; a thesaurus; a problem analysis approach database; and a problem solution database, and wherein the equipment operation knowledge base includes at least one of the following: equipment manual; equipment drawings; specification documents; and operation videos.

[0095] In some embodiments, using a large model to analyze the second search results and the query intent based on the query intent to generate feedback information for the query information includes: constructing second input data containing the second search results, the query intent, and second preset prompts, wherein the second search results include videos and text that match the query intent; inputting the second input data into the large model to obtain multimodal feedback information output by the large model, including at least one of videos, text, and flowcharts, wherein at least a portion of the feedback information comes from the second search results.

[0096] In some embodiments, the apparatus 500 further includes a device query unit configured to: receive device query information for a second device; and analyze a third search result based on the device query information using a large model to obtain a device status report, wherein the third search result is obtained by searching a historical operation knowledge base.

[0097] In some embodiments, analyzing the third search results based on device query information using a large model to obtain a device status report includes: constructing third input data including device query information, third search results, and preset third prompts, wherein the third search results include historical operation records associated with the second device retrieved from a historical operation knowledge base; inputting the third input data into the large model to obtain a device status report output by the large model, wherein the device status report is associated with the historical operation records of the second device and includes at least one of device status summary, operation indicator analysis, and risk warning prompts.

[0098] It should be understood that Figure 5 The various modules or units of the device 500 shown can be connected to the reference. Figure 2The steps in method 200 described correspond to each other. Therefore, the operations, features, and advantages described above for method 200 also apply to apparatus 500 and its included modules and units. For the sake of brevity, some operations, features, and advantages will not be repeated here.

[0099] Although specific functions have been discussed with reference to specific modules above, it should be noted that the functions of the units discussed in this article can be divided into multiple units, and / or at least some functions of multiple units can be combined into a single unit.

[0100] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0101] According to embodiments of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described according to embodiments of the present disclosure.

[0102] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the methods described according to embodiments of the present disclosure.

[0103] According to embodiments of the present disclosure, a computer program product is also provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the method described according to embodiments of the present disclosure.

[0104] refer to Figure 6 The present invention describes a structural block diagram of an electronic device 600 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, 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 disclosure described and / or claimed herein.

[0105] like Figure 6As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0106] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device, and can include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 607 can be any type of device capable of presenting information, and can include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 can include, but is not limited to, disk and optical disk. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and can include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0107] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as method 200. For example, in some embodiments, method 200 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform method 200 by any other suitable means (e.g., by means of firmware).

[0108] Various embodiments of the systems and techniques described above herein 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 may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0112] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0113] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0114] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0115] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A method for performing equipment maintenance tasks, comprising: Monitor device operation data collected by at least one sensor associated with the device; In response to the abnormality indicated by the device's operating data, fault information for the device is generated; A large model is used to perform fault analysis on the first retrieval result based on the fault information and the fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching the historical operation knowledge base and the equipment instruction knowledge base; Based on the maintenance data related to the maintenance task, a report text of the maintenance record is generated using a large model based on a preset template; The report text of the maintenance record is stored in the historical operation knowledge base.

2. The method as described in claim 1, wherein, The step of generating fault information for the device in response to abnormal device operating data includes: Obtain the current value of the device's operating data; if the current value exceeds a preset threshold range or exhibits abnormal fluctuations, trigger an alarm mechanism and generate alarm information; The alarm information is classified using a rule engine to generate fault information associated with the device, wherein the alarm information includes at least one of timestamp, current value of metric, metric threshold, and abnormal time description.

3. The method as described in claim 1, wherein, The step of using a large model to perform fault analysis on the first retrieval results based on the fault information and the fault information to generate a fault work order for creating a maintenance task includes: The fault information is converted into a vector representation; Semantic retrieval is performed in at least one of the historical operation knowledge base and the equipment description knowledge base to extract a portion of the knowledge documents whose relevance to the fault information is higher than a preset threshold as the first retrieval result; Construct first input data that includes the fault information, the first search result, and the first preset prompt word; The first input data is input into the large model to obtain the fault analysis results output by the large model, wherein the fault analysis results include fault causes, maintenance plan suggestions and risk assessments.

4. The method of claim 1, wherein the historical operation knowledge base includes at least one of the following: historical maintenance records, equipment operation logs, maintenance records, and wherein the equipment instruction knowledge base includes equipment instruction manuals.

5. The method of claim 1, further comprising: During the operation of the maintenance task, query information related to the maintenance task is received, wherein the query information is for at least one of the following: fault diagnosis, component installation / disassembly operation, and equipment parameter adjustment operation; The query information is semantically parsed using a large model to determine the query intent corresponding to the query information; The second search result based on the query intent and the query intent are analyzed using a large model to generate feedback information for the query information. The second search result is obtained by searching the historical operation knowledge base, the equipment instruction knowledge base, the expert experience knowledge base, and the equipment operation knowledge base.

6. The method of claim 5, wherein, The expert experience knowledge base includes at least one of the following: a professional terminology database, a thesaurus, a problem analysis approach database, and a problem solution database, and the equipment operation knowledge base includes at least one of the following: equipment manuals, equipment drawings, specification documents, and operation videos.

7. The method of claim 6, wherein, The step of using a large model to analyze the second search results based on the query intent and the query intent to generate feedback information for the query information includes: Construct second input data containing the second search result, the query intent, and the second preset prompt words, wherein the second search result includes videos and text that match the query intent; The second input data is input into the large model to obtain multimodal feedback information output by the large model, including at least one of video, text, and flowchart, wherein at least a portion of the feedback information comes from the second search result.

8. The method according to any one of claims 1-7, further comprising: Receive device query information for the second device; The third search results based on the device query information are analyzed using a large model to obtain a device status report, wherein the third search results are obtained by searching a historical operation knowledge base.

9. The method of claim 8, wherein, The process of analyzing the third search results based on the device query information using a large model to obtain a device status report includes: Construct third input data including the device query information, the third search result, and the preset third prompt word, wherein the third search result includes historical operation records associated with the second device retrieved from the historical operation knowledge base; The third input data is input into the large model to obtain the equipment status report output by the large model. The equipment status report is associated with the historical operation record of the second equipment and includes at least one of the following: equipment status summary, operation index analysis, and risk warning prompt.

10. A multi-agent-based system for assisting equipment maintenance, comprising: The monitoring module is configured to monitor device operation data collected by at least one sensor associated with the device; The generation module is configured to generate fault information for the device in response to an abnormality indicated by the device's operating data. The work order creation agent is configured to perform fault analysis using a large model on the first retrieval result based on the fault information and the fault information to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment description knowledge base; The report generating agent is configured to generate a report text of the maintenance record based on the maintenance data related to the maintenance task, using a large model based on a preset template, wherein the report text of the maintenance record is stored in the historical operation knowledge base.

11. The system of claim 10, further comprising a maintenance guidance agent configured to: The large model is used to analyze the query information received during the operation of the maintenance task in order to determine the query intent corresponding to the query information; A large model is used to analyze the second search results based on the query intent and the query intent itself, in order to generate feedback information for the query information, wherein... The second search result is obtained by searching the historical operation knowledge base, the equipment instruction knowledge base, the expert experience knowledge base, and the equipment operation knowledge base.

12. The system of claim 10, further comprising a device query agent configured to: Receive device query information; The third search results based on the device query information are analyzed using a large model to obtain a device status report, wherein the third search results are obtained by searching a historical operation knowledge base.

13. A device for executing equipment maintenance tasks, comprising: The monitoring unit is configured to monitor device operation data collected by at least one sensor associated with the device; The fault information generation unit is configured to generate fault information for the device in response to an abnormality indicated by the device's operating data. The work order generation unit is configured to perform fault analysis on the first retrieval result based on the fault information and the fault information using a large model to generate a fault work order for creating a maintenance task, wherein the first retrieval result is obtained by searching a historical operation knowledge base and an equipment instruction knowledge base; The report generation unit is configured to generate a report text of the maintenance record based on the maintenance data related to the maintenance task and using a large model based on a preset template. The storage unit is configured to store the report text of the maintenance record in the historical operation knowledge base.

14. An electronic device comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

16. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-9.

Images