Equipment operation and maintenance method and device based on large model, electronic equipment and storage medium

Abstract

The invention discloses an equipment operation and maintenance method and device based on a large model and a storage medium, and belongs to the technical field of operation and maintenance. The equipment operation and maintenance method based on the large model comprises the steps of monitoring operation state data of target equipment; determining an equipment fault and a target fault level of the target equipment according to the large model, the operation state data and a fault knowledge base; and performing operation and maintenance on the target equipment according to the large model, the target fault level, the equipment fault and the operation and maintenance knowledge base, thereby reducing professional requirements on operation and maintenance personnel and improving operation and maintenance efficiency.

Description

Technical Field

[0001] The present application belongs to the field of operation and maintenance technology, and in particular, relates to a large model-based equipment operation and maintenance method, device, electronic device and storage medium. Background Art

[0002] Equipment operation and maintenance refers to a series of activities to maintain, manage and optimize equipment, aiming to ensure the normal operation of equipment, improve equipment reliability and efficiency, reduce equipment failure rate, and thus ensure the smooth production and service of the enterprise.

[0003] At present, the operation and maintenance of ATM equipment mostly relies on operation and maintenance personnel. For example, when an ATM equipment fails, the operation and maintenance personnel perform a series of operations on the ATM equipment based on their own experience to determine the specific fault problem and perform corresponding maintenance operations. However, with the continuous development of the business scale and intelligence of ATM equipment, the operation and maintenance tasks of ATM equipment are becoming increasingly difficult. Simply relying on operation and maintenance personnel to operate and maintain ATM equipment not only requires operation and maintenance personnel to have strong professional knowledge, but also has high labor costs and low operation and maintenance efficiency. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a large-model-based equipment operation and maintenance method, device, electronic device and storage medium, which can use the large model to realize equipment fault diagnosis and operation and maintenance, reduce the professional requirements for operation and maintenance personnel, and improve operation and maintenance efficiency.

[0005] In a first aspect, the present application provides a large model-based equipment operation and maintenance method, comprising:

[0006] Monitor the operating status data of the target device;

[0007] Determine the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base;

[0008] The target device is operated and maintained according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

[0009] In some embodiments, determining the device fault and target fault level of the target device according to the big model, the operating status data and the fault knowledge base includes:

[0010] Determine key fault diagnosis information based on the operating status data using a large model;

[0011] Determine the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base;

[0012] The fault level corresponding to the equipment fault is determined from a preset fault level table to obtain a target fault level, wherein the fault level table includes multiple faults and a fault level corresponding to each of the faults.

[0013] In some embodiments, determining the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base includes:

[0014] Searching a fault knowledge base according to the key fault diagnosis information, wherein the fault knowledge base includes a plurality of faults and symptom information corresponding to each of the faults;

[0015] When the symptom information matching the fault diagnosis key information is retrieved, the fault corresponding to the matching symptom information is regarded as a device fault;

[0016] When the symptom information matching the key fault diagnosis information is not retrieved, the large model is used to estimate the fault corresponding to the key fault diagnosis information to obtain the equipment fault.

[0017] In some embodiments, the performing operation and maintenance on the target device according to the large model, the target fault level, the target fault and the operation and maintenance knowledge base includes:

[0018] Searching for at least one operation and maintenance solution corresponding to the target fault from an operation and maintenance knowledge base to obtain a target operation and maintenance solution, wherein the operation and maintenance knowledge base includes multiple faults and at least one operation and maintenance solution corresponding to each fault;

[0019] The target device is operated and maintained according to the large model, the target fault level and the target operation and maintenance plan.

[0020] In some embodiments, the operating and maintaining the target device according to the large model, the target fault level and the target operation and maintenance plan includes:

[0021] When the target fault level is a medium level or a low level, a preset prompt template corresponding to the target fault level is obtained; using the large model, a function call instruction is generated according to the preset prompt template and the target operation and maintenance solution, and the target device is operated and maintained based on the function call instruction;

[0022] When the target fault level is a high level, the large model is used to generate a fault diagnosis report according to the target operation and maintenance plan and the equipment fault, and the fault diagnosis report is provided to the user so that the user can operate and maintain the target equipment according to the fault diagnosis report.

[0023] In some embodiments, the large model-based equipment operation and maintenance method further includes:

[0024] Obtaining feedback and evaluation information returned by the user regarding the fault diagnosis report;

[0025] Generate reinforcement learning training data according to the feedback evaluation information;

[0026] Reinforcement learning is performed on the large model according to the reinforcement learning training data.

[0027] In a second aspect, the present application provides a large model-based equipment operation and maintenance device, including:

[0028] A monitoring module, used to monitor the operating status data of the target device;

[0029] A determination module, used for determining the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base;

[0030] An operation and maintenance module is used to operate and maintain the target device according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

[0031] In some embodiments, the determining module is used to:

[0032] Determine key fault diagnosis information based on the operating status data using a large model;

[0033] Determine the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base;

[0034] The fault level corresponding to the equipment fault is determined from a preset fault level table to obtain a target fault level, wherein the fault level table includes multiple faults and a fault level corresponding to each of the faults.

[0035] In some embodiments, the determining module is used to:

[0036] Searching a fault knowledge base according to the key fault diagnosis information, wherein the fault knowledge base includes a plurality of faults and symptom information corresponding to each of the faults;

[0037] When the symptom information matching the fault diagnosis key information is retrieved, the fault corresponding to the matching symptom information is regarded as a device fault;

[0038] When the symptom information matching the key fault diagnosis information is not retrieved, the large model is used to estimate the fault corresponding to the key fault diagnosis information to obtain the equipment fault.

[0039] In some embodiments, the operation and maintenance module is used to:

[0040] Searching for at least one operation and maintenance solution corresponding to the target fault from an operation and maintenance knowledge base to obtain a target operation and maintenance solution, wherein the operation and maintenance knowledge base includes multiple faults and at least one operation and maintenance solution corresponding to each fault;

[0041] The target device is operated and maintained according to the large model, the target fault level and the target operation and maintenance plan.

[0042] In some embodiments, the operation and maintenance module is used to:

[0043] When the target fault level is a medium level or a low level, a preset prompt template corresponding to the target fault level is obtained; using the large model, a function call instruction is generated according to the preset prompt template and the target operation and maintenance solution, and the target device is operated and maintained based on the function call instruction;

[0044] When the target fault level is a high level, the large model is used to generate a fault diagnosis report according to the target operation and maintenance plan and the equipment fault, and the fault diagnosis report is provided to the user so that the user can operate and maintain the target equipment according to the fault diagnosis report.

[0045] In some embodiments, the large model-based equipment operation and maintenance device further includes a training module for:

[0046] Obtaining feedback and evaluation information returned by the user regarding the fault diagnosis report;

[0047] Generate reinforcement learning training data according to the feedback evaluation information;

[0048] Reinforcement learning is performed on the large model according to the reinforcement learning training data.

[0049] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the large model-based equipment operation and maintenance method described in any one of the above items is implemented.

[0050] In a fourth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the large model-based equipment operation and maintenance method described in any one of the above items is implemented.

[0051] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned large-model-based equipment operation and maintenance methods.

[0052] The big model-based equipment operation and maintenance method, apparatus, storage medium, electronic device and computer program product provided in the embodiments of the present application monitor the operating status data of the target equipment; determine the equipment fault and target fault level of the target equipment according to the big model, the operating status data and the fault knowledge base; operate and maintain the target equipment according to the big model, the target fault level, the equipment fault and the operation and maintenance knowledge base, that is, use the big model to realize equipment fault diagnosis and operation and maintenance, reduce the dependence on operation and maintenance personnel, thereby not only reducing the professional requirements for operation and maintenance personnel and reducing labor costs, but also being able to promptly perform fault repairs to eliminate the fault when the target equipment has already failed, or perform preventive maintenance on the equipment to reduce the occurrence of equipment failures when the target equipment is about to fail, thereby improving operation and maintenance efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0054] Figure 1 It is a flowchart of a large model-based equipment operation and maintenance method provided in an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the framework of the equipment operation and maintenance method based on the large model provided in the embodiment of the present application;

[0056] Figure 3 is another flow chart of the equipment operation and maintenance method based on a large model provided in an embodiment of the present application;

[0057] Figure 4 It is a structural schematic diagram of a large model-based equipment operation and maintenance device provided in an embodiment of the present application;

[0058] Figure 5 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0059] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0060] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0061] The embodiments of the present application provide a large model-based equipment operation and maintenance method, apparatus, storage medium, electronic device and computer program product.

[0062] See also Figure 1 , Figure 1 1 is a flow chart of a device operation and maintenance method based on a large model provided in an embodiment of the present application. The device operation and maintenance method based on a large model is applied to an electronic device, and can be executed by the electronic device or a functional module or functional entity in the electronic device. The device operation and maintenance method based on a large model includes the following steps 101-103, wherein:

[0063] 101. Monitor the operating status data of the target device, where the operating status data includes data collected by the internal sensor of the target device and response feedback data during the business handling process;

[0064] 102. Determine the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base;

[0065] 103. Perform operation and maintenance on the target device according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

[0066] The big model-based equipment operation and maintenance method provided in the embodiment of the present application monitors the operating status data of the target equipment; determines the equipment fault and target fault level of the target equipment according to the big model, the operating status data and the fault knowledge base; operates and maintains the target equipment according to the big model, the target fault level, the equipment fault and the operation and maintenance knowledge base, that is, uses the big model to realize equipment fault diagnosis and operation and maintenance, reduces the dependence on operation and maintenance personnel, thereby reducing the professional requirements for operation and maintenance personnel and improving operation and maintenance efficiency.

[0067] The above steps 101-103 will be further described in detail below.

[0068] 101. Monitor the operating status data of the target device.

[0069] The operation status data includes data collected by the internal sensors of the target device and response feedback data during the business process. The sensors include temperature sensors, and the response feedback data mainly includes transaction response time, CPU usage, etc. The operation status data is data collected over a period of time, such as a day or a few hours, and can include multiple types of data such as text, images and / or videos. Please refer to Figure 2 , Figure 2This is a schematic diagram of the framework of the device operation and maintenance method based on the big model provided in the embodiment of the present application. The target device may be an ATM device that communicates with the master control system. The master control system can monitor the operation status data of the ATM device 24 hours a day, including but not limited to the total transaction volume, historical operation and maintenance records, CPU operation percentage, collection temperature and other key indicators, and summarize these data every hour and push them to the big model, calling the big model for subsequent processing.

[0070] 102. Determine the equipment fault and target fault level of the target equipment based on the big model, the operation status data and the fault knowledge base.

[0071] Among them, equipment failure means that the target equipment has already failed or is about to fail. Large Model (also known as Foundation Model) refers to a machine learning model with a large number of parameters (usually more than one billion) and complex structure, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc.

[0072] In some embodiments, see Figure 3 , Figure 3 1021 to 1023, wherein:

[0073] 1021. Use the big model to determine the key information for fault diagnosis based on the operating status data.

[0074] Among them, after the large model receives the operating status data sent by the master control system, such as CPU usage, transaction response time, temperature of each part and other data, if there is non-text data, it is necessary to convert the non-text data into text data first. For example, for image data, it can be converted into text using image-to-text technology. After that, it uses its own powerful context understanding ability to aggregate multiple natural language descriptions (i.e. text data) into key information for fault diagnosis.

[0075] Fault diagnosis key information is used to help the large model analyze whether the device has a fault. It includes information on multiple indicators, which can reflect whether the device has a fault or is about to fail. For example, indicators can include CPU usage and average transaction response time. Under normal circumstances, the CPU usage of ATM devices is about 30%, and the average transaction response time does not exceed 2 seconds. Therefore, if the CPU usage of the target device is 50%, the average transaction response time is 30 seconds, and this state has lasted for a period of time, it can be reflected that the device has a fault.

[0076] 1022. Determine the equipment failure of the target equipment based on the big model, key fault diagnosis information and fault knowledge base.

[0077] Among them, the fault knowledge base is created in advance, and the operation and maintenance related data can be collected through various channels, and the operation and maintenance professional knowledge can be accumulated to create the fault knowledge base. These channels include web crawlers, public data, bank accumulation and API interfaces, etc. The collected data can include structured data, semi-structured data and unstructured data. For example, the collected data includes knowledge equipment manuals, maintenance records, videos, experience reports, texts, videos, pictures and tables and other multi-source data. After that, data annotation, text mining and other technologies are used to further analyze and summarize the data collected from these channels to obtain the fault knowledge base.

[0078] In some embodiments, the above step 1022 specifically includes:

[0079] Searching in a fault knowledge base according to key fault diagnosis information, the fault knowledge base includes multiple faults and symptom information corresponding to each fault;

[0080] When symptom information matching the key information for fault diagnosis is retrieved, the fault corresponding to the matching symptom information is regarded as a device fault;

[0081] When symptom information matching the key information of fault diagnosis is not retrieved, the large model is used to estimate the fault corresponding to the key information of fault diagnosis to obtain the equipment fault.

[0082] Among them, failures may include low-level performance degradation, short-term network fluctuations, mild resource consumption anomalies, non-critical service failures, log or monitoring data anomalies, etc.; they may also include medium-level continuous resource overloads, key service response delays or intermittent interruptions, continuous deterioration of network quality, data storage anomalies, external dependent service failures, etc.; and they may also include high-level critical system crashes, data corruption or loss, network interruptions, major hardware damage, etc.

[0083] The big model can match the indicator information in the key information of fault diagnosis with the symptom information in the fault knowledge base, and find out all the symptom information that matches the indicator information. If it can be found, the found fault will be used as the equipment fault of the target device. If it cannot be found, the big model will analyze and estimate the fault corresponding to the key information of fault diagnosis based on the knowledge it has learned.

[0084] 1023. Determine a fault level corresponding to the equipment fault from a preset fault level table to obtain a target fault level. The fault level table includes multiple faults and a fault level corresponding to each fault.

[0085] Among them, the user sets and stores the fault level table in advance. The setting of the fault level must follow certain principles. Under normal circumstances, the greater the impact caused by the fault and the higher the difficulty of repair, the higher the fault level.

[0086] 103. Perform operation and maintenance on the target equipment based on the big model, target fault level, equipment fault and operation and maintenance knowledge base.

[0087] In some embodiments, see Figure 3 , the above step 103 specifically includes:

[0088] 1031. Searching for at least one operation and maintenance solution corresponding to a target fault from an operation and maintenance knowledge base to obtain a target operation and maintenance solution. The operation and maintenance knowledge base includes multiple faults and at least one operation and maintenance solution corresponding to each fault.

[0089] 1032. Perform operation and maintenance on the target equipment according to the large model, target fault level and target operation and maintenance plan.

[0090] Among them, for medium and low-level faults, the operation and maintenance solutions stored in the operation and maintenance knowledge base mainly involve the names of the repair functions that need to be called, such as the cooling repair function used to solve high-temperature faults. For high-level faults, the operation and maintenance knowledge base can store the top N operation and maintenance solutions.

[0091] In some embodiments, the above step 1032 specifically includes:

[0092] When the target fault level is medium or low, obtain a preset prompt template corresponding to the target fault level; use the large model to generate function call instructions according to the preset prompt template and the target operation and maintenance plan, and operate and maintain the target device based on the operation and maintenance machine instructions;

[0093] When the target fault level is high, a large model is used to generate a fault diagnosis report based on the target operation and maintenance plan and the equipment fault, and the fault diagnosis report is provided to the user so that the user can operate and maintain the target equipment according to the fault diagnosis report.

[0094] Please continue to see Figure 2, various repair functions are stored in the master control system. For medium-level and low-level faults, the master control system uses the big model, according to the preset prompt template and the searched target operation and maintenance plan, to generate function call instructions based on the prompt engineering prompt, which is equivalent to using the big model to convert the target operation and maintenance plan in natural language into machine language, without the need for manual writing by the operation and maintenance personnel. The subsequent corresponding function call based on the function call instruction can solve the fault and realize the automatic repair of ATM equipment faults. For example, in the hot summer, the normal temperature of the ATM CPU is between 20 and 60 degrees. If the CPU temperature exceeds 60 degrees in the key fault diagnosis information obtained by the large model from the operation status data pushed from the master control system, the ATM will be concluded to have a low-level fault and is working with the fault by searching the fault knowledge base. At the same time, the repair function of the fault is obtained from the operation and maintenance knowledge base, and the corresponding function call instruction is generated and pushed to the master control system. The master control system calls the cooling repair function stored in advance based on the function call quality to control the ATM to start the cooling and cooling function, such as starting the fan (the fan is on standby under normal circumstances to save electricity), killing irrelevant background running processes and shutting down non-essential loads (such as printers, card issuing machines, ID card recognition devices, etc.). Working with the fault can cause unpredictable faults in the ATM, such as interrupted operation, card machine, card swallowing, and even smoke and fire inside the machine, burning cash banknotes. This operation can solve very common but fatal problems in actual scenarios, and the same operation is performed for intermediate problems. If it cannot be automatically repaired, the fault level is increased to medium and high levels.

[0095] For high-level faults, since they may involve damaged parts, they need to be replaced to be solved. The traditional approach is that when the machine breaks down, the staff notifies the operation and maintenance personnel to go to the site for repair. In this application scheme, the large model sends the fault diagnosis report to the master control system, and the master control system can not only send the fault diagnosis report to the client, but also find the user account of the operation and maintenance personnel bound to the target device, and send a fault prompt message to the user account. The presentation form of the fault prompt message depends on the type of user account. For example, if the user account is a mobile phone number, the fault prompt message can be in the form of SMS or MMS. After receiving the fault prompt message, the relevant operation and maintenance personnel can log in to the client to download the fault diagnosis report, and operate and maintain the target device based on the fault diagnosis report, so that when the target device has already failed, timely fault repair can be performed to eliminate the fault, or when the target device is about to fail, preventive maintenance can be performed on the device to reduce the occurrence of equipment failures.

[0096] In addition, a real-time connection communication mechanism can be established between the master control system and the client, based on which data streaming can be achieved between the master control system and the client. Fault diagnosis can be performed regularly and actively by the master control system, or it can be triggered by the user. For example, the operation and maintenance personnel can input the fault conclusion or fault description information on the client and send it to the master control system. For example, the description information is that the CPU temperature reaches 90° and the machine has a card swallowing phenomenon. The master control system will feed back the user input content to the big model so that the big model can perform intent recognition, fault analysis and knowledge matching, and finally generate a fault diagnosis report and return it to the operation and maintenance personnel.

[0097] In addition, each time the operation and maintenance personnel perform equipment operation and maintenance according to the fault diagnosis report provided by the big model, they can submit the solution to the fault and the corresponding classification level, fault description, etc. to the master control system. The system will organize the content according to the predetermined template based on the fault information, fault level and solution, and automatically update it to the knowledge base. The operation and maintenance personnel can also provide the master control system with feedback and evaluation information on the fault diagnosis report, such as the accuracy of fault prediction, maintenance difficulties, customer satisfaction, etc. The master control system continuously optimizes the analysis and decision-making capabilities of the big model by recording the results, logs and service feedback of each fault handling, and helps the big model to continuously learn and evolve. That is, the equipment operation and maintenance method based on the big model also includes:

[0098] Obtain feedback and evaluation information returned by the user regarding the fault diagnosis report;

[0099] Generate reinforcement learning training data according to the feedback evaluation information;

[0100] Reinforcement learning is performed on the large model according to the reinforcement learning training data.

[0101] Among them, the feedback evaluation information may include the accuracy of fault prediction, the difficulty of the maintenance process, customer satisfaction, etc. The master control system can collect feedback evaluation information over a period of time and generate reinforcement learning training data. After that, a reward model is trained using the reinforcement learning training data, and then the large model is adjusted through the reward model, thereby optimizing the analysis and generation capabilities of the large model, improving the prediction accuracy of the model, and forming a closed-loop improvement mechanism.

[0102] From the above, it can be seen that the big model-based equipment operation and maintenance method provided in the embodiment of the present application monitors the operating status data of the target equipment; determines the equipment fault and target fault level of the target equipment according to the big model, the operating status data and the fault knowledge base; operates and maintains the target equipment according to the big model, the target fault level, the equipment fault and the operation and maintenance knowledge base, that is, using the big model to realize equipment fault diagnosis and operation and maintenance, reducing the dependence on operation and maintenance personnel, which not only reduces the professional requirements for operation and maintenance personnel and reduces labor costs, but also can promptly perform fault repairs to eliminate the fault when the target equipment has already failed, or perform preventive maintenance on the equipment when the target equipment is about to fail to reduce the occurrence of equipment failures, thereby improving operation and maintenance efficiency and accuracy.

[0103] According to the method described in the above embodiment, the present application embodiment also provides a large model-based equipment operation and maintenance device, which is used to execute the steps in the above large model-based equipment operation and maintenance method. Figure 4 , Figure 4 2 is a schematic diagram of a device operation and maintenance apparatus 200 based on a large model provided in an embodiment of the present application. The device operation and maintenance apparatus 200 based on a large model is applied to an electronic device, and the device operation and maintenance method can be executed by the electronic device or a functional module or functional entity in the electronic device.

[0104] Specifically, the equipment operation and maintenance device 200 based on the large model includes a monitoring module 201, a determination module 202 and an operation and maintenance module 203, wherein:

[0105] Monitoring module 201, used to monitor the operating status data of the target device;

[0106] A determination module 202, for determining a device fault and a target fault level of a target device according to the large model and the operation status data;

[0107] The operation and maintenance module 203 is used to operate and maintain the target device according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

[0108] In some embodiments, the determination module 202 is used to:

[0109] Using the large model, key fault diagnosis information is determined based on the operating status data;

[0110] Determine the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base;

[0111] The fault level corresponding to the equipment fault is determined from a preset fault level table to obtain a target fault level. The fault level table includes multiple faults and the fault level corresponding to each of the faults.

[0112] In some embodiments, the determination module 202 is used to:

[0113] Searching a fault knowledge base according to the fault diagnosis key information, the fault knowledge base including a plurality of faults and symptom information corresponding to each of the faults;

[0114] When the symptom information matching the fault diagnosis key information is retrieved, the fault corresponding to the matching symptom information is regarded as a device fault;

[0115] When the symptom information matching the key fault diagnosis information is not retrieved, the large model is used to estimate the fault corresponding to the key fault diagnosis information to obtain the equipment fault.

[0116] In some embodiments, the operation and maintenance module 203 is used to:

[0117] Searching for at least one operation and maintenance solution corresponding to the target fault from an operation and maintenance knowledge base to obtain a target operation and maintenance solution, wherein the operation and maintenance knowledge base includes multiple faults and at least one operation and maintenance solution corresponding to each fault;

[0118] According to the large model, the target fault level and the target operation and maintenance plan, the target device is operated and maintained. In some embodiments, the operation and maintenance module 203 is used to:

[0119] When the target fault level is medium or low, a preset prompt template corresponding to the target fault level is obtained; using the large model, a function call instruction is generated according to the preset prompt template and the target operation and maintenance solution, and the target device is operated and maintained based on the function call instruction;

[0120] When the target fault level is a high level, the large model is used to generate a fault diagnosis report according to the target operation and maintenance plan and the equipment fault, and the fault diagnosis report is provided to the user so that the user can operate and maintain the target equipment according to the fault diagnosis report.

[0121] In some embodiments, the large model-based equipment operation and maintenance device further includes a training module for:

[0122] Obtain feedback and evaluation information returned by the user regarding the fault diagnosis report;

[0123] Generate reinforcement learning training data according to the feedback evaluation information;

[0124] Reinforcement learning is performed on the large model according to the reinforcement learning training data.

[0125] It should be noted that the specific details of each module unit in the above-mentioned large model-based equipment operation and maintenance device 200 have been described in detail in the embodiment of the above-mentioned large model-based equipment operation and maintenance method, and will not be repeated here.

[0126] As can be seen from the above, the equipment operation and maintenance device based on the big model provided in the embodiment of the present application monitors the operating status data of the target equipment through the monitoring module 201; the determination module 202 determines the equipment fault and the target fault level of the target equipment according to the big model, the operating status data and the fault knowledge base; the operation and maintenance module 203 operates and maintains the target equipment according to the big model, the target fault level, the equipment fault and the operation and maintenance knowledge base, that is, the big model is used to realize the fault diagnosis and operation and maintenance of the equipment, reducing the dependence on the operation and maintenance personnel, thereby not only reducing the professional requirements for the operation and maintenance personnel and reducing the labor cost, but also being able to promptly perform fault repairs to eliminate the fault when the target equipment has already failed, or to perform preventive maintenance on the equipment when the target equipment is about to fail to reduce the occurrence of equipment failures, thereby improving the operation and maintenance efficiency and accuracy.

[0127] In some embodiments, the large model-based equipment operation and maintenance device in the embodiments of the present application can be an electronic device, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a server, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The embodiments of the present application are not specifically limited.

[0128] In some embodiments, Figure 5 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the program is executed by the processor 301, each process of the above-mentioned large-model-based equipment operation and maintenance method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0129] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0130] Figure 6 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0131] The electronic device 400 includes but is not limited to: a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, a processor 410 and other components.

[0132] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 6 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0133] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (Graphics Processing Unit, GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and at least one of other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0134] The memory 409 can be used to store software programs and various data. The memory 409 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 409 may include a volatile memory or a non-volatile memory, or the memory 409 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 409 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0135] The processor 410 may include one or more processing units; the processor 410 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 410.

[0136] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned large-model-based equipment operation and maintenance method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0137] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0138] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned large model-based equipment operation and maintenance method when executed by a processor.

[0139] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0140] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0142] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0143] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0144] In the description of the present application, “plurality” means two or more.

[0145] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0146] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A large model-based equipment operation and maintenance method, characterized in that: include: Monitor the operating status data of the target device; Determine the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base; The target device is operated and maintained according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

2. The equipment operation and maintenance method based on a large model according to claim 1 is characterized in that: The determining of the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base includes: Determine key fault diagnosis information based on the operating status data using a large model; Determine the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base; The fault level corresponding to the equipment fault is determined from a preset fault level table to obtain a target fault level, wherein the fault level table includes multiple faults and a fault level corresponding to each of the faults.

3. The equipment operation and maintenance method based on a large model according to claim 2 is characterized in that: Determining the device fault of the target device according to the large model, the key fault diagnosis information and the fault knowledge base includes: Searching a fault knowledge base according to the key fault diagnosis information, wherein the fault knowledge base includes a plurality of faults and symptom information corresponding to each of the faults; When the symptom information matching the fault diagnosis key information is retrieved, the fault corresponding to the matching symptom information is regarded as a device fault; When the symptom information matching the key fault diagnosis information is not retrieved, the large model is used to estimate the fault corresponding to the key fault diagnosis information to obtain the equipment fault.

4. The equipment operation and maintenance method based on a large model according to claim 1 is characterized in that: The operating and maintaining the target device according to the large model, the target fault level, the target fault and the operation and maintenance knowledge base includes: Searching for at least one operation and maintenance solution corresponding to the target fault from an operation and maintenance knowledge base to obtain a target operation and maintenance solution, wherein the operation and maintenance knowledge base includes multiple faults and at least one operation and maintenance solution corresponding to each fault; The target device is operated and maintained according to the large model, the target fault level and the target operation and maintenance plan.

5. The equipment operation and maintenance method based on a large model according to claim 4 is characterized in that: The operating and maintaining the target device according to the large model, the target fault level and the target operation and maintenance plan includes: When the target fault level is a medium level or a low level, a preset prompt template corresponding to the target fault level is obtained; using the large model, a function call instruction is generated according to the preset prompt template and the target operation and maintenance solution, and the target device is operated and maintained based on the function call instruction; When the target fault level is a high level, the large model is used to generate a fault diagnosis report according to the target operation and maintenance plan and the equipment fault, and the fault diagnosis report is provided to the user so that the user can operate and maintain the target equipment according to the fault diagnosis report.

6. The equipment operation and maintenance method based on a large model according to claim 5 is characterized in that: Also includes: Obtaining feedback and evaluation information returned by the user regarding the fault diagnosis report; Generate reinforcement learning training data according to the feedback evaluation information; Reinforcement learning is performed on the large model according to the reinforcement learning training data.

7. A large model-based equipment operation and maintenance device, characterized in that: include: A monitoring module, used to monitor the operating status data of the target device; A generating module, used for determining the equipment fault and target fault level of the target equipment according to the large model, the operation status data and the fault knowledge base; An operation and maintenance module is used to operate and maintain the target device according to the large model, the target fault level, the device fault and the operation and maintenance knowledge base.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the large model-based equipment operation and maintenance method as described in any one of claims 1 to 6 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the large model-based equipment operation and maintenance method as described in claims 1-6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the large model-based equipment operation and maintenance method as described in claims 1-6 is implemented.

Images