Repair method of equipment in operation and maintenance system, equipment, medium and program product

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and discloses a method for repairing equipment in an operation and maintenance system, the equipment, a medium and a program product. The method comprises the following steps: acquiring a fault associated parameter value of each device in the operation and maintenance system; obtaining a pre-constructed operation and maintenance knowledge base, inputting the fault associated parameter values into the operation and maintenance knowledge base for data comparison, and determining an equipment fault repair scheme; according to the influence of fault repair on service interruption, the fault repair cost and the fault repair success rate, optimizing the fault repair scheme to obtain a target fault repair scheme; and adopting the target fault repair scheme to perform fault repair of the equipment. According to the method, the fault repair scheme is determined through the operation and maintenance knowledge base and is optimized, so that automatic repair of the equipment fault is realized, the efficiency and the success rate of automatic repair are improved, and the repair cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology and can be applied to the financial technology field. In particular, it relates to a method, device, medium, and program product for repairing equipment in an operation and maintenance system. Background Technology

[0002] With the rapid development of information technology, various network devices such as servers play a crucial role in business operations, and their stable operation is of paramount importance. However, various malfunctions and performance problems inevitably occur during the operation of these devices.

[0003] Traditional equipment maintenance methods rely primarily on manual experience for troubleshooting and repair, which is inefficient and prone to human error. While technological advancements enable basic fault monitoring and early warning, they often fall short for complex faults and struggle to achieve automated repair. Summary of the Invention

[0004] This invention provides a method, device, medium, and program product for repairing equipment in an operation and maintenance system, so as to achieve automatic fault repair, reduce repair costs, and improve repair efficiency and success rate.

[0005] According to one aspect of the present invention, a method for repairing equipment in an operation and maintenance system is provided, the method comprising:

[0006] Collect fault-related parameter values ​​of each device in the operation and maintenance system;

[0007] Obtain a pre-built operation and maintenance knowledge base, and input the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan;

[0008] Based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate, the fault repair scheme is optimized to obtain the target fault repair scheme.

[0009] The target fault repair scheme is used to repair the equipment faults.

[0010] According to another aspect of the present invention, a device for repairing equipment in an operation and maintenance system is provided, the device comprising:

[0011] The fault association parameter value acquisition module is used to collect fault association parameter values ​​of various devices in the operation and maintenance system;

[0012] The equipment fault repair solution determination module is used to obtain a pre-built operation and maintenance knowledge base, and input the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair solution;

[0013] The fault repair scheme optimization module is used to optimize the fault repair scheme based on the impact of fault repair on business interruption, fault repair cost and fault repair success rate, so as to obtain the target fault repair scheme.

[0014] A fault repair module is used to repair equipment faults using the target fault repair scheme. According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the device repair method in the operation and maintenance system according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the device repair method in the operation and maintenance system according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the device repair method in the operation and maintenance system described in any embodiment of the present invention.

[0020] The technical solution of this invention collects fault-related parameter values ​​of various devices in the operation and maintenance system; obtains a pre-built operation and maintenance knowledge base, and inputs the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine a device fault repair plan; optimizes the fault repair plan based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain a target fault repair plan; and uses the target fault repair plan to repair device faults, solving the problem of preventive maintenance and automatic repair of devices. By determining and optimizing the fault repair plan through the operation and maintenance knowledge base, automatic repair of device faults is achieved, improving the efficiency and success rate of automatic repair and reducing repair costs.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a device repair method in an operation and maintenance system according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of a device repair method in an operation and maintenance system according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a device repair device in an operation and maintenance system according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the device repair method in the operation and maintenance system of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1This is a flowchart of a device repair method in an operation and maintenance system according to Embodiment 1 of the present invention. This embodiment is applicable to situations where preventive maintenance and automatic fault repair are performed during device operation and maintenance. The method can be executed by a device repair device in the operation and maintenance system. This device can be implemented in hardware and / or software and can be configured in electronic devices such as operation and maintenance controllers or computers. Figure 1 As shown, the method includes:

[0031] Step 110: Collect the fault-related parameter values ​​of each device in the operation and maintenance system.

[0032] The equipment can be a component requiring maintenance. For example, the equipment could be a server. This could involve monitoring the operation of servers in a financial center system to achieve automatic fault repair. Fault-related parameters can include: hardware information, operating system information, and application runtime information. Fault-related parameter values ​​can be collected in various ways. For example, they can be collected using the system's built-in Application Programming Interface (API), reading log files, or obtaining hardware status information.

[0033] The hardware information may include one or more of the following: CPU, memory, and disk space usage; network bandwidth and performance data; hardware temperature, humidity, voltage, and utilization rate. For example, hardware information can be obtained through a server management interface. The data collection frequency can be set to once per minute or adjusted as needed.

[0034] Operating system information can include one or more of the following: system logs, process status, kernel parameters, etc. For example, by utilizing the APIs and log file reading functions provided by the operating system, information such as process status and system logs can be collected in real time. For instance, the process list can be scanned every 5 minutes to record the running status and resource usage of processes (such as CPU usage, memory usage, etc.), while simultaneously reading the system log file to extract error messages, warning messages, etc., related to server operation.

[0035] Application runtime information can include one or more of the following: application logs, error reports, transaction data, and performance metrics. For example, application log collection configures the application's log output method, sending logs to a specified log collection server or storing them directly in a specific local directory. The system periodically reads the application log files, parses the log content, and extracts data such as the application's runtime status, error messages, and performance metrics. For example, for web applications, data such as request response time, number of requests, and percentage of incorrect requests can be collected.

[0036] By obtaining real-time fault-related parameter values ​​of the equipment, fault monitoring can be performed, and problems can even be repaired before they occur, thus preventing equipment downtime from affecting business operations.

[0037] Step 120: Obtain the pre-built operation and maintenance knowledge base, and input the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

[0038] The operations and maintenance (O&M) knowledge base can be a database compiled from historical O&M data of the equipment. This knowledge base records fault descriptions, causes, and solutions during equipment maintenance. In practical applications, large-scale language model training can be performed using extensive historical O&M data to fully understand fault issues and construct the O&M knowledge base.

[0039] Optionally, a pre-built operation and maintenance knowledge base is obtained, including: constructing training samples based on historical operation and maintenance data of the operation and maintenance system; wherein the training samples include fault descriptions, fault cause analyses, and fault solutions; dividing the training samples into first training samples and second training samples; performing vocabulary masking on the data in the first training samples, and performing network model pre-training based on the masking results; and adjusting the model pre-training results using the second training samples to obtain the operation and maintenance knowledge base.

[0040] The training samples can be obtained by cleaning, organizing, and classifying historical equipment operation and maintenance data to extract valuable information, such as fault phenomena, causes, and solutions. During network model training, the operation and maintenance knowledge base can be accurately established through pre-training and fine-tuning phases.

[0041] During the pre-training phase, the first training samples can be lexically masked before model training. This allows the model to learn the statistical patterns and semantic information of language, as well as the contextual relationships and semantic representations between words. One masking method is to divide the data in the first training samples into paragraphs and randomly mask the words in each paragraph. For example, for a paragraph describing a server network failure, such as "The server cannot connect to the network normally, possibly due to a network interface failure or routing configuration error. [mask]", the model needs to predict the masked words, learning vocabulary and semantic information related to network failures in the process.

[0042] After the pre-training phase is completed, a fine-tuning phase can be performed. In this phase, the model's pre-training results can be adjusted using a second training sample to obtain the operations and maintenance (O&M) knowledge base. The first training sample can be historical O&M data on equipment failures in general scenarios, while the second training sample can be historical O&M data on equipment failures in specific scenarios. By fine-tuning the model using data from specific scenarios, a mapping relationship from fault descriptions to cause analysis and solutions can be established for specific application scenarios, improving the reliability of the O&M knowledge base.

[0043] For example, the input text for one of the second training samples could be "The server suddenly crashed during operation, with CPU usage reaching 100%", and the output text could be "The possible cause is that a process got stuck in an infinite loop, causing CPU resources to be exhausted. The solution is to first use operating system commands to find the process consuming a lot of CPU, and then terminate that process. If the problem persists, check if there are any vulnerabilities in the application code that could cause an infinite loop." The second training sample is then input into a pre-trained model for fine-tuning. The model adjusts its parameters using the backpropagation algorithm, enabling it to more accurately generate cause analysis and solutions based on the fault description.

[0044] In actual operation, the current server fault description, such as fault association parameter values, is input into the large model operation and maintenance knowledge base. The model can generate corresponding fault causes and fault repair solutions based on the learned mapping relationships.

[0045] Step 130: Optimize the fault repair plan based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain the target fault repair plan.

[0046] The fault repair solutions obtained by comparing them with the operation and maintenance knowledge base are the most suitable solutions for the current fault-related parameter values ​​in the database, but they are not entirely suitable for the current condition of the equipment. Therefore, based on the fault repair solutions obtained from the operation and maintenance knowledge base, the solutions are optimized to obtain the target fault repair solution. There are various ways to optimize the solutions, such as using optimal solution search algorithms or large language model optimization to optimize the parameters in the fault repair solutions to obtain the target fault repair solution.

[0047] When optimizing fault repair solutions, several factors should be considered, including the impact of fault repair on business interruption, repair costs, and repair success rates. The impact of fault repair on business interruption can be multifaceted, encompassing both the duration and scope of the interruption. By considering this impact, appropriate time windows can be selected for repair operations based on factors such as current server load and business operation status, minimizing disruption to services. Furthermore, by considering the impact of repair costs and success rates, the correlation and order between different repair strategies can be considered to generate comprehensive and feasible repair solutions, improving success rates and reducing costs.

[0048] Optionally, the fault repair scheme can be optimized based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain a target fault repair scheme. This includes: determining the performance function of the fault repair scheme based on the business interruption time, the scope of business interruption impact, fault repair cost, fault repair success rate, and preset parameter weights; and selecting, adjusting, and modifying the steps of multiple fault repair schemes based on the performance function to obtain the target fault repair scheme.

[0049] The performance function can be expressed as Y = 100 - (w1×x1 + w2×x2 + w3×x3 - w4×x4). In this formula, x1, x2, x3, and x4 represent the service interruption time, the scope of service interruption impact, the fault repair cost, and the fault repair success rate, respectively. w1, w2, w3, and w4 are preset parameter weights, namely, the weights for service interruption time, the scope of service interruption impact, the fault repair cost, and the fault repair success rate, respectively. These preset parameter weights can be set according to actual business needs and experience.

[0050] In specific optimization, parameters can be adjusted based on the fault repair schemes determined by the operation and maintenance knowledge base to generate an initial population. The performance function of each scheme is calculated in the initial population. Parent schemes are selected based on the performance function, and crossover and / or mutation operations are performed to generate offspring fault repair schemes. For example, crossover operations can be used to exchange parameters or steps of schemes in the initial population. Mutation operations can randomly change the order or parameter value of a repair step in a scheme. Thus, parent schemes are selected based on the performance function, and offspring are generated through crossover and / or mutation. Multiple iterations are performed to obtain the final target fault repair scheme.

[0051] For example, one fault repair solution is to immediately restart the application to reload the configuration file. This may cause a brief business interruption of approximately 5 minutes, affecting counter transactions at all first-tier branches. The repair cost is low, and the expected success rate is 80%. Another fault repair solution is to manually modify the configuration file and then restart the application. The business interruption may be 8 minutes, affecting online business at a specific first-tier branch. The repair cost is higher (requiring manual operation and testing), but the expected success rate is 90%. According to performance function calculations, the second fault repair solution has a higher performance function value. Then, a selection operation is performed based on the performance function, choosing the individual with the higher performance function value as the parent. Cross-operations (such as swapping some repair steps or parameters) and mutation operations (such as randomly changing the order of a repair step or parameter value) are performed to generate new child fault repair solutions. After multiple generations of evolution, an optimized target fault repair solution is finally obtained. For example, after manually modifying the configuration file in a test environment and verifying its correctness, the application is restarted during a low-traffic period at night. This ensures a high success rate while minimizing the impact on business.

[0052] By optimizing fault repair solutions, comprehensive and feasible repair plans can be generated, improving the success rate of fault repair, reducing fault repair costs, and minimizing the impact on business operations.

[0053] Step 140: Use the target fault repair solution to repair the equipment fault.

[0054] By implementing a targeted fault repair solution for equipment, preventative maintenance can be achieved, minimizing equipment failure rates and enabling timely automatic repair when equipment malfunctions occur. This reduces manual operation, improves fault repair efficiency and success rate, and lowers fault repair costs.

[0055] The technical solution of this embodiment collects fault-related parameter values ​​of various devices in the operation and maintenance system; obtains a pre-built operation and maintenance knowledge base, and inputs the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the device fault repair plan; optimizes the fault repair plan based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain the target fault repair plan; and uses the target fault repair plan to repair the device fault, solving the problem of preventive maintenance and automatic repair of the device. By determining the fault repair plan through the operation and maintenance knowledge base and optimizing the plan, automatic repair of device faults is achieved, and the efficiency and success rate of automatic repair are improved, while the repair cost is reduced.

[0056] Example 2

[0057] Figure 2This is a flowchart of a device repair method in an operation and maintenance system according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0058] Step 210: Collect the fault-related parameter values ​​of each device in the operation and maintenance system.

[0059] Step 220: Based on the current and historical values ​​of the fault-related parameters, determine the changing trend of each fault-related parameter, and predict the fault of the equipment based on the changing trend to obtain the cause of the fault prediction.

[0060] The trend analysis can be obtained by analyzing the current and historical values ​​of fault-related parameters using algorithms such as logistic regression, time series analysis, or large language models. For example, based on CPU utilization data from the past 24 hours, the range of CPU utilization changes in the next hour can be predicted. This trend analysis and prediction can help identify potential server health issues early, such as performance bottlenecks or resource exhaustion.

[0061] Based on the changing trends of fault-related parameters, equipment failures can be predicted, and the cause of the failure can be determined. For example, if the trend shows that the server's memory usage will continue to rise and approach its limit in the near future, causing the equipment to crash due to insufficient memory, then it can be predicted that the next cause of the equipment failure will be insufficient memory.

[0062] When the predicted causes of a fault are input into the operations and maintenance knowledge base to determine a fault repair solution, solutions such as increasing memory capacity and optimizing memory usage strategies can be obtained. This can prevent server performance from degrading or even crashing due to insufficient memory, thereby ensuring that the server is always in a healthy and stable operating state and providing a solid guarantee for the continuous operation of business.

[0063] Step 230: Obtain the pre-built operation and maintenance knowledge base.

[0064] Optionally, a pre-built operation and maintenance knowledge base is obtained, including: constructing training samples based on historical operation and maintenance data of the operation and maintenance system; wherein the training samples include fault descriptions, fault cause analyses, and fault solutions; dividing the training samples into first training samples and second training samples; performing vocabulary masking on the data in the first training samples, and performing network model pre-training based on the masking results; and adjusting the model pre-training results using the second training samples to obtain the operation and maintenance knowledge base.

[0065] Step 240: Input the fault-related parameter values, changing trends, and predicted fault causes into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

[0066] Optionally, the fault-related parameter values, changing trends, and fault prediction causes can be input into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan. This includes: classifying faults according to the fault-related parameter values, changing trends, and fault prediction causes to obtain fault categories; and inputting the fault categories, fault-related parameter values, changing trends, and fault prediction causes into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

[0067] The fault categories can include different types such as hardware faults, software faults, and network faults. There are various methods for fault classification, such as classification using natural language understanding and reasoning, classification algorithms in machine learning, or clustering algorithms. By first classifying faults based on their associated parameter values, trends, and predicted causes, and then determining the equipment fault repair plan based on the fault category, the reliability of the fault repair plan can be improved. For example, for software faults, an operations and maintenance knowledge base can be used to consider factors such as application error logs and operating system process states to determine whether the fault is caused by software code errors, software configuration problems, or software compatibility issues.

[0068] For example, if a server is experiencing performance degradation, collect associated parameter values ​​such as increased CPU utilization, increased memory usage, and longer application response time. Convert this data into natural language descriptions to determine the input text, such as "Server performance is degraded; CPU utilization has increased to 90%, memory usage has reached 80%, and application response time exceeds 5 seconds." Encode the input text and extract key features such as "performance degradation," "high CPU utilization," "high memory usage," and "long response time." Then, match it with fault cases in the operations and maintenance knowledge base to find similar fault descriptions. For example, the knowledge base contains the case: "Server performance is degraded; CPU utilization frequently exceeds 80%, memory usage is high, and application response is slow. The reason is that a background process is consuming too many resources. The solution is to find the process and optimize its resource usage or terminate the process." By calculating similarity, the current fault description is found to be highly similar to this case. Simultaneously, a classification algorithm categorizes this fault as a software fault. Next, the cause of the failure was further analyzed. Considering that the longer application response time might be related to background processes, and combining experience and logical reasoning from the operation and maintenance knowledge base, it was determined that the cause of the failure was that a certain background process was consuming too many resources. A corresponding fault diagnosis report was generated, including the fault type, cause, and suggested repair directions.

[0069] Step 250: Optimize the fault repair plan based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain the target fault repair plan.

[0070] Optionally, the fault repair scheme can be optimized based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain a target fault repair scheme. This includes: determining the performance function of the fault repair scheme based on the business interruption time, the scope of business interruption impact, fault repair cost, fault repair success rate, and preset parameter weights; and selecting, adjusting, and modifying the steps of multiple fault repair schemes based on the performance function to obtain the target fault repair scheme.

[0071] Step 260: Use the target fault repair solution to repair the equipment fault.

[0072] Optionally, the target fault repair scheme is used to repair the equipment fault, including: during the process of using the target fault repair scheme to repair the equipment fault, collecting fault repair operation steps, execution time, and repair results; and adjusting the target fault repair scheme based on the fault repair operation steps, execution time, and repair results.

[0073] During the execution of the target fault repair plan, the server status and the execution status of the repair operations can be monitored in real time. Based on the execution status, the success of configuration file modifications and the ability of applications to start and run normally can be checked in real time. If repair failures or new problems occur, the repair plan can be adjusted promptly, and the repair operations can be repeated until the server returns to normal operation or it is determined that the repair is unrecoverable. There are several ways to adjust the plan. For example, manual adjustments can be made based on fault repair failure alerts. Alternatively, real-time execution status can be used to compare data with the operation and maintenance knowledge base to determine the repair steps and parameter adjustment methods of the target fault repair plan. Another option is to use a large language model combined with the execution status and the target fault repair plan to predict the adjustment methods for the target fault repair plan.

[0074] In addition, by recording detailed information about the entire repair process, such as operation steps, execution time, and results, it is easier to analyze and summarize equipment operation and maintenance, and further optimize the operation and maintenance knowledge base.

[0075] Optionally, the target fault repair solution is used to repair the device fault, including: when the target fault repair solution is a virtual machine restart repair solution, performing a snapshot backup before restarting the virtual machine.

[0076] By performing a snapshot backup before repair, snapshot recovery and rollback can be achieved if the application cannot be restored normally after a virtual machine restart, ensuring business continuity. Before restarting, you can check the disk partition mount information at system startup and analyze whether system files such as ( / etc / fstab) are complete. If the system files are incomplete, they can be restored through snapshot backup.

[0077] The technical solution of this invention collects fault-related parameter values ​​of various devices in the operation and maintenance system; determines the changing trend of each fault-related parameter based on its current and historical values, and predicts device faults based on the changing trend to obtain the cause of the fault prediction; acquires a pre-built operation and maintenance knowledge base; inputs the fault-related parameter values, changing trends, and fault prediction causes into the operation and maintenance knowledge base for data comparison to determine a device fault repair plan; optimizes the fault repair plan based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate to obtain a target fault repair plan; and uses the target fault repair plan to repair device faults, solving the problem of preventive maintenance and automatic repair of equipment. By determining and optimizing the fault repair plan through the operation and maintenance knowledge base, automatic repair of device faults is achieved, improving the efficiency and success rate of automatic repair, reducing repair costs, and ensuring the stable operation of equipment.

[0078] Example 3

[0079] Figure 3 This is a schematic diagram of the structure of a device repair device in an operation and maintenance system according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a fault-related parameter value acquisition module 310, a device fault repair scheme determination module 320, a fault repair scheme optimization module 330, and a fault repair module 340. Wherein:

[0080] The fault association parameter value acquisition module 310 is used to collect fault association parameter values ​​of various devices in the operation and maintenance system.

[0081] The equipment fault repair solution determination module 320 is used to obtain a pre-built operation and maintenance knowledge base, and input the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair solution;

[0082] The fault repair scheme optimization module 330 is used to optimize the fault repair scheme based on the impact of fault repair on business interruption, fault repair cost and fault repair success rate, so as to obtain the target fault repair scheme.

[0083] The fault repair module 340 is used to repair equipment faults using the target fault repair scheme.

[0084] Optionally, the equipment fault repair solution determination module 320 includes:

[0085] The fault prediction unit is used to determine the changing trend of each fault-related parameter based on the current and historical values ​​of the fault-related parameters, and to predict the fault of the equipment based on the changing trend, thereby obtaining the cause of the fault prediction.

[0086] The equipment fault repair plan determination unit is used to input fault-related parameter values, changing trends, and fault prediction causes into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

[0087] Optionally, the fault repair solution optimization module 330 includes:

[0088] The performance function determination unit is used to determine the performance function of the fault repair scheme based on the service interruption time, the scope of the service interruption impact, the fault repair cost, the fault repair success rate, and the preset parameter weights.

[0089] The target fault repair scheme determination unit is used to select schemes, adjust scheme parameters, and adjust scheme steps from multiple fault repair schemes based on the performance function to obtain the target fault repair scheme.

[0090] Optionally, the equipment fault repair solution determination module 320 includes:

[0091] The training sample construction unit is used to construct training samples based on the historical operation and maintenance data of the operation and maintenance system; the training samples include fault descriptions, fault cause analyses, and fault solutions.

[0092] The training sample partitioning unit is used to divide the training samples into a first training sample and a second training sample.

[0093] The model pre-training unit is used to perform vocabulary masking on the data in the first training sample and to pre-train the network model based on the masking results.

[0094] The model adjustment unit is used to adjust the model pre-training results using the second training samples to obtain the operation and maintenance knowledge base.

[0095] Optional, the fault repair scheme optimization unit includes:

[0096] The fault classification subunit is used to classify faults and obtain fault categories based on fault-related parameter values, changing trends, and predicted causes of faults.

[0097] The fault repair scheme optimization subunit is used to input the fault category, fault-related parameter values, change trends, and fault prediction causes into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair scheme.

[0098] Optional, the fault repair module 340 includes:

[0099] The data acquisition unit is used to collect fault repair operation steps, execution time, and repair results during the fault repair process of the equipment using the target fault repair solution.

[0100] The repair plan adjustment unit is used to adjust the target fault repair plan based on the fault repair operation steps, execution time, and repair results.

[0101] Optional, the fault repair module 340 includes:

[0102] The snapshot backup unit is used to perform snapshot backups before restarting the virtual machine when the target fault repair solution is a virtual machine restart repair solution.

[0103] The device repair apparatus in the operation and maintenance system provided in the embodiments of the present invention can execute the device repair method in the operation and maintenance system provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0104] Example 4

[0105] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0106] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0108] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as repair methods for equipment in an operation and maintenance system.

[0109] In some embodiments, the device repair method in the operation and maintenance system can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the device repair method in the operation and maintenance system described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the device repair method in the operation and maintenance system by any other suitable means (e.g., by means of firmware).

[0110] 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), payload-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.

[0111] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. 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).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include 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), blockchain networks, and the Internet.

[0115] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0116] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0117] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for repairing equipment in an operation and maintenance system, characterized in that, include: Collect fault-related parameter values ​​of each device in the operation and maintenance system; Obtain a pre-built operation and maintenance knowledge base, and input the fault-related parameter values ​​into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan; Based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate, the fault repair scheme is optimized to obtain the target fault repair scheme. The target fault repair scheme is used to repair the equipment faults.

2. The method according to claim 1, characterized in that, The fault-related parameter values ​​are input into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan, including: Based on the current and historical values ​​of the fault-related parameters, the changing trend of each fault-related parameter is determined, and the fault prediction of the equipment is performed based on the changing trend to obtain the cause of the fault prediction. The fault-related parameter values, the changing trends, and the predicted causes of the fault are input into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

3. The method according to claim 1, characterized in that, Based on the impact of fault repair on business interruption, fault repair cost, and fault repair success rate, the fault repair scheme is optimized to obtain the target fault repair scheme, including: The performance function of the fault repair scheme is determined based on the service interruption time, the scope of service interruption impact, the fault repair cost, the fault repair success rate, and the preset parameter weights. Based on the performance function, the solution is selected from multiple fault repair solutions, the solution parameters are adjusted, and the solution steps are adjusted to obtain the target fault repair solution.

4. The method according to claim 1, characterized in that, Access a pre-built operations and maintenance knowledge base, including: Training samples are constructed based on historical operation and maintenance data of the operation and maintenance system; wherein, the training samples include fault descriptions, fault cause analyses and fault solutions; The training samples are divided into a first training sample and a second training sample; The data in the first training sample is processed by word masking, and the network model is pre-trained based on the masking results; The second training sample is used to adjust the model pre-training results to obtain the operation and maintenance knowledge base.

5. The method according to claim 2, characterized in that, The fault-related parameter values ​​are input into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan, including: Based on the fault association parameter values, the changing trends, and the fault prediction causes, fault classification is performed to obtain fault categories; The fault category, the fault-related parameter value, the change trend, and the fault prediction cause are input into the operation and maintenance knowledge base for data comparison to determine the equipment fault repair plan.

6. The method according to claim 1, characterized in that, The equipment is repaired using the target fault repair scheme, including: During the equipment fault repair process using the target fault repair scheme, the fault repair operation steps, execution time, and repair results are collected. The target fault repair plan is adjusted based on the fault repair operation steps, execution time, and repair results.

7. The method according to claim 1, characterized in that, The equipment is repaired using the target fault repair scheme, including: When the target fault repair solution is a virtual machine restart repair solution, a snapshot backup is performed before restarting the virtual machine.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the device repair method in the operation and maintenance system according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the device repair method in any one of claims 1-7 in the operation and maintenance system.

10. A computer program product comprising a computer program that, when executed by a processor, implements a method for repairing equipment in an operation and maintenance system according to any one of claims 1-7.

Images