Operation and maintenance management method, system and equipment based on artificial intelligence and medium

Abstract

The invention discloses an operation and maintenance management method, system and device based on artificial intelligence, and a medium, mainly relates to the technical field of operation and maintenance management, and is used for solving the problems of insufficient correlation analysis, low knowledge utilization efficiency and lack of self-healing ability in an existing scheme. Comprising the following steps: when a preset alarm self-healing processing program runs abnormally, progressively decreasing a quality evaluation value of a preset maintenance document set corresponding to the preset alarm self-healing processing program according to a first preset numerical value, adding the target alarm item, the equipment node corresponding to the target alarm item, the maintenance capability level, the quality evaluation value corresponding to the target maintenance document set and the maintenance explanation information to a preset manual maintenance management interface, and deleting the target alarm item, the equipment node corresponding to the target alarm item, the maintenance capability level, the quality evaluation value corresponding to the target maintenance document set and the maintenance explanation information from a preset automatic operation and maintenance management interface; and when the target maintenance document set does not exist, directly adding the target alarm item and the corresponding equipment node to a preset manual maintenance management interface.

Description

Technical Field

[0001] This application relates to the field of operation and maintenance management technology, and in particular to an operation and maintenance management method, system, equipment and medium based on artificial intelligence. Background Technology

[0002] Currently, HPC cluster operation and maintenance primarily relies on a passive response model combining manual experience and rule engines. Specifically, this manifests in the following ways: 1) Static topology maps are used for fault location, failing to dynamically perceive implicit relationships between devices; 2) Maintenance documents are stored in discrete knowledge bases, lacking quality assessment and version control mechanisms; 3) Fault handling processes are rigid, requiring manual judgment of alarm priorities and execution of standardized scripts. Existing technologies, such as cluster monitoring systems, achieve fault isolation through predefined rule chains, but this approach does not consider the dynamic evolution of fault propagation paths.

[0003] The above solution has significant drawbacks: 1) Insufficient correlation analysis: The static topology network cannot reflect the device coupling status in high-concurrency scenarios in real time, resulting in a high false alarm rate; 2) Inefficient knowledge utilization: The maintenance documents and alarm items lack an intelligent matching mechanism, and engineers need an average of 15 minutes to locate an effective solution; 3) Lack of self-healing capability: When the preset script fails to execute, the system cannot automatically degrade or trigger manual intervention, resulting in a prolonged fault recovery time. Summary of the Invention

[0004] This application provides an AI-based operation and maintenance management method, system, equipment, and medium to address the problems of insufficient correlation analysis, inefficient knowledge utilization, and lack of self-healing capabilities in existing solutions.

[0005] Firstly, this application provides an operation and maintenance management method based on artificial intelligence, the method comprising: Obtain the current alarm item and determine the device node corresponding to the current alarm item; based on the preset device association topology network, determine the device nodes associated with the device node corresponding to the current alarm item; use the alarm items generated by the associated device nodes and the current alarm item as the target alarm item; Upload a set of preset maintenance documents through device nodes, build a preset maintenance database, calculate the quality assessment value of each set of preset maintenance documents, and configure the preset alarm self-healing processing program and program running priority corresponding to the set of preset maintenance documents. Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; display the target alarm item, the corresponding device node and maintenance explanation information on the preset automatic operation and maintenance management interface; Through the preset automatic operation and maintenance management interface, obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set; and run the preset alarm self-healing processing program in sequence according to the running priority. When the preset alarm self-healing process malfunctions, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing process will be reduced by the first preset value. The target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set, and the maintenance explanation information will be added to the preset manual maintenance management interface and deleted from the preset automatic operation and maintenance management interface. When the target maintenance document set does not exist, the target alarm item and the corresponding device node are directly added to the preset manual maintenance management interface.

[0006] In one implementation of this application, the preset maintenance database consists of several preset maintenance document sets; the preset maintenance document sets contain alarm triggering conditions for alarm items that can be resolved; Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database, specifically including: Determine whether the target alarm item has a preset bound target alarm item; wherein, the preset bound target alarm item includes at least one preset maintenance document set; When there is no preset target alarm item, determine whether the alarm triggering condition of the target alarm item exists in the alarm triggering conditions of the alarm item resolved by the preset maintenance document set; When an alarm trigger condition exists in an alarm item that is resolved in the target maintenance document set, the target maintenance document set for the current target alarm item is determined from the corresponding preset maintenance document set. When an alarm trigger condition does not exist in the alarm items that can be resolved in the preset maintenance document set, calculate the matching degree between the alarm trigger condition of the target alarm item and the alarm trigger conditions of the alarm items that can be resolved in each preset maintenance document set. Obtain a preset maintenance document set with a matching degree greater than a preset threshold, and determine the target maintenance document set for the current target alarm item from the corresponding preset maintenance document set; When the maximum matching degree is less than the preset threshold, it is determined that the target maintenance document set does not exist in the preset maintenance database.

[0007] In one implementation of this application, determining the target maintenance document set for the current target alarm item from the corresponding preset maintenance document set specifically includes: When the number of preset maintenance documents is less than or equal to a preset threshold, the entire preset maintenance document set is determined as a single target maintenance document set. When the number of preset maintenance document sets exceeds a preset threshold, obtain the quality assessment value of each preset maintenance document set; select the preset maintenance document sets with the highest quality assessment values ​​as a whole target maintenance document set.

[0008] In one implementation of this application, a preset maintenance document set is uploaded by a device node, a preset maintenance database is constructed, the quality assessment value of each preset maintenance document set is calculated, and a preset alarm self-healing processing program corresponding to the preset maintenance document set is configured, specifically including: Obtain the initial set of maintenance documents; Obtain the evaluation values ​​of the initial maintenance document set on preset quality dimensions, and accumulate them to generate a document quality evaluation value; When the document quality assessment value is lower than the preset assessment threshold, a modification prompt is generated, and the document is returned to the upload terminal of the initial maintenance document set. When the document quality assessment value is not lower than the preset assessment threshold, it is added to the preset maintenance database as a preset maintenance document set; Configure the preset alarm self-healing program corresponding to the preset maintenance document set through the preset interface.

[0009] In one implementation of this application, after running the preset alarm self-healing processing program sequentially according to its running priority, the method further includes: Once the operation is successful, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing procedure will be increased according to the second preset value.

[0010] In one implementation of this application, after decreasing the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing processing procedure by a first preset value, the method further includes: When the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold, a modification prompt is generated and the document is returned to the upload terminal of the preset maintenance document set.

[0011] Secondly, this application provides an AI-based operation and maintenance management system, the system comprising: The target module is used to obtain the current alarm item, determine the device node corresponding to the current alarm item; determine the device nodes associated with the device node corresponding to the current alarm item according to the preset device association topology network; and use the alarm items generated by the associated device nodes and the current alarm item as the target alarm item. The module is used to upload a set of preset maintenance documents through device nodes, build a preset maintenance database, calculate the quality assessment value of each set of preset maintenance documents, and configure the preset alarm self-healing processing program and program running priority corresponding to the set of preset maintenance documents. The document module is used to determine whether a target maintenance document set exists in the preset maintenance database based on the alarm triggering conditions of the target alarm item; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; and display the target alarm item, the corresponding device node and maintenance explanation information on the preset automatic operation and maintenance management interface. The program module is used to obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set through the preset automatic operation and maintenance management interface; and to run the preset alarm self-healing processing program in sequence according to the running priority. The exception module is used to reduce the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing process according to the first preset value when the preset alarm self-healing process is abnormal. It also adds the target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set, and the maintenance explanation information to the preset manual maintenance management interface and deletes them from the preset automatic operation and maintenance management interface. The add module is used to directly add target alarm items and corresponding device nodes to the preset manual maintenance management interface when the target maintenance document set does not exist.

[0012] In one implementation of this application, the system further includes a return module. This is used to generate a modification prompt and return the preset maintenance document set to the upload terminal when the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold.

[0013] Thirdly, this application provides an AI-based operation and maintenance management device, the device comprising: processor; And a memory containing executable code, which, when executed, causes the processor to perform an AI-based operation and maintenance management method, as described above.

[0014] Fourthly, this application provides a non-volatile computer storage medium storing computer instructions thereon, which, when executed, implement an artificial intelligence-based operation and maintenance management method as described above.

[0015] As can be seen from the above technical solutions, this application has the following advantages: Real-time correlation analysis optimization: By dynamically constructing a device correlation topology network, the system can capture the device coupling status in high-concurrency scenarios in real time, upgrading the static topology to a dynamic response mechanism. When a device node triggers an alarm, the system automatically correlates the alarm items generated by its upstream and downstream device nodes to form a target alarm item set. This design significantly reduces the false alarm rate caused by device status lag, making alarm information more accurately reflect the real fault chain and providing a precise data foundation for subsequent processing.

[0016] Intelligent Knowledge Matching and Maintenance: Through the collaborative work of a pre-set maintenance database and a large language model, intelligent matching of alarm items and maintenance documents is achieved. Engineers no longer need to manually filter documents; the system automatically extracts the maintenance explanation information corresponding to the target alarm item and integrates alarm details, device nodes, and solutions into the operation and maintenance interface. This mechanism reduces the traditional 15-minute manual location time to a second-level response time. Simultaneously, it dynamically rates maintenance documents through quality assessment values ​​to ensure that the pushed solutions always possess high reliability.

[0017] A tiered self-healing and manual intervention mechanism: Pre-set alarm self-healing procedures automatically execute fault recovery based on running priority, forming a multi-level defense. When a program malfunctions, the system automatically triggers a quality assessment value decrement mechanism, transferring the fault information to the manual maintenance interface while preserving the complete context (including maintenance document quality assessment values, explanatory information, etc.). This avoids interruption of fault handling and provides a basis for manual intervention. This design seamlessly switches processing modes when script execution fails, shortening the fault recovery waiting time. Attached Figure Description

[0018] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description 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.

[0019] Figure 1 This is a flowchart of an AI-based operation and maintenance management method provided in an embodiment of this application.

[0020] Figure 2 This is a schematic diagram of the internal structure of an AI-based operation and maintenance management system provided in an embodiment of this application.

[0021] Figure 3 This is a schematic diagram of the internal structure of an AI-based operation and maintenance management device provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0023] Those skilled in the art should understand that the embodiments described below are merely preferred embodiments of this disclosure and do not imply that this disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely used to explain the technical principles of this disclosure and are not intended to limit the scope of protection of this disclosure. Based on the preferred embodiments provided by this disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of this disclosure.

[0024] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0025] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0026] The embodiment provides an AI-based operation and maintenance management method, such as... Figure 1 As shown in the embodiments of this application, the method mainly includes the following steps: Step 110: Obtain the current alarm item and determine the device node corresponding to the current alarm item; based on the preset device association topology network, determine the device node associated with the device node corresponding to the current alarm item; use the alarm items generated by the associated device node and the current alarm item as the target alarm item.

[0027] Understandably, by dynamically constructing a device association topology network, the system can identify the device nodes corresponding to alarm items and their associated nodes in real time, and automatically integrate alarm items generated by associated devices to form a target alarm item set. This mechanism eliminates the device status lag problem caused by static topology analysis, ensuring that alarm information accurately reflects the faulty link, while avoiding the time-consuming operation of manual association analysis, providing a complete and real-time fault context for subsequent processing.

[0028] In some embodiments, the preset maintenance database consists of several preset maintenance document sets; the preset maintenance document sets contain alarm triggering conditions for alarm items that can be resolved; Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database, specifically including: Determine whether the target alarm item has a preset bound target alarm item; wherein, the preset bound target alarm item includes at least one preset maintenance document set; When there is no preset target alarm item, determine whether the alarm triggering condition of the target alarm item exists in the alarm triggering conditions of the alarm item resolved by the preset maintenance document set; When an alarm trigger condition exists in an alarm item that is resolved in the target maintenance document set, the target maintenance document set for the current target alarm item is determined from the corresponding preset maintenance document set. When an alarm trigger condition does not exist in the alarm items that can be resolved in the preset maintenance document set, calculate the matching degree between the alarm trigger condition of the target alarm item and the alarm trigger conditions of the alarm items that can be resolved in each preset maintenance document set. Obtain a preset maintenance document set with a matching degree greater than a preset threshold, and determine the target maintenance document set for the current target alarm item from the corresponding preset maintenance document set; When the maximum matching degree is less than the preset threshold, it is determined that the target maintenance document set does not exist in the preset maintenance database.

[0029] Understandably, the intelligent matching mechanism of the pre-set maintenance database achieves precise association between alarm items and maintenance documents. First, it checks whether the target alarm item is directly bound to the pre-set set of maintenance documents. If not, it matches based on alarm trigger conditions, including full match and filtering based on match degree. When the trigger condition completely matches the alarm conditions resolved by the document set, the target maintenance document is directly located; if not, the similarity between trigger conditions is calculated, and a set of documents with a match degree exceeding a threshold is selected as alternatives. This design avoids the inefficient operation of manual document screening, and at the same time, the pre-set threshold ensures the reliability of the matching results. When the match degree is insufficient, it automatically determines that there is no corresponding document, providing a clear basis for subsequent processing.

[0030] The target maintenance document set for the current target alarm item is determined from the corresponding preset maintenance document set, specifically including: When the number of preset maintenance documents is less than or equal to a preset threshold, the entire preset maintenance document set is determined as a single target maintenance document set. When the number of preset maintenance document sets exceeds a preset threshold, obtain the quality assessment value of each preset maintenance document set; select the preset maintenance document sets with the highest quality assessment values ​​as a whole target maintenance document set.

[0031] Understandably, the intelligent filtering mechanism based on a pre-defined set of maintenance documents enables efficient matching of target alarm items with maintenance documents. When the number of documents in the set does not exceed a pre-defined threshold, the system automatically integrates all relevant documents into the target maintenance document set, ensuring complete coverage of possible solutions. When the number of documents exceeds the threshold, the system filters out the optimal set of documents based on a quality assessment value, avoiding information overload and prioritizing the delivery of highly reliable documents. This design, through dynamic threshold control and a quality assessment mechanism, effectively improves the accuracy of document matching while ensuring the comprehensiveness of the solution, providing high-quality maintenance references for subsequent processing.

[0032] Step 120: Upload the preset maintenance document set through the device node, build the preset maintenance database, calculate the quality assessment value of each preset maintenance document set, and configure the preset alarm self-healing processing program and program running priority corresponding to the preset maintenance document set.

[0033] Understandably, a database is built using a set of pre-set maintenance documents uploaded by device nodes, and the quality assessment value of each document set is automatically calculated. Simultaneously, corresponding alarm self-healing procedures and their execution priorities are configured. This design achieves standardized storage and dynamic management of maintenance documents. The quality assessment mechanism quantifies document reliability, providing a priority basis for subsequent processing. Through the pre-configuration of pre-set alarm self-healing procedures, the system can quickly match the appropriate handling plan when an alarm is triggered, and combined with execution priorities, ensure that critical faults are handled first, thereby improving the efficiency and accuracy of fault response.

[0034] Upload a set of preset maintenance documents to the device node, construct a preset maintenance database, calculate the quality assessment value of each preset maintenance document set, and configure the preset alarm self-healing processing program corresponding to the preset maintenance document set. Specifically, this includes: Obtain the initial set of maintenance documents; Obtain the evaluation values ​​of the initial maintenance document set on preset quality dimensions, and accumulate them to generate a document quality evaluation value; When the document quality assessment value is lower than the preset assessment threshold, a modification prompt is generated, and the document is returned to the upload terminal of the initial maintenance document set. When the document quality assessment value is not lower than the preset assessment threshold, it is added to the preset maintenance database as a preset maintenance document set; Configure the preset alarm self-healing program corresponding to the preset maintenance document set through the preset interface.

[0035] Understandably, a database is built using maintenance documents uploaded from device nodes, and document quality assessment values ​​are automatically calculated. When the assessment value falls below a preset threshold, a modification prompt is generated and returned to the uploading terminal, ensuring the reliability of the documents in the database. Documents that meet the quality standards are automatically associated with corresponding alarm self-healing procedures. This design achieves standardized database entry and dynamic management of maintenance documents, controls document quality through preset thresholds, and provides pre-configured self-healing procedures for subsequent fault handling, thereby improving system maintenance efficiency and fault response accuracy.

[0036] Step 130: Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; display the target alarm item, the device node corresponding to the target alarm item, and the maintenance explanation information on the preset automatic operation and maintenance management interface.

[0037] Understandably, the system achieves intelligent matching between alarm items and maintenance documents through the collaborative work of a pre-set maintenance database and a large language model. The system automatically retrieves the corresponding document set from the database based on the triggering conditions of the target alarm item, sends the matching results to the large language model to extract maintenance explanation information, and finally integrates and displays the alarm details, device nodes, and solutions on the operation and maintenance interface. This design avoids the inefficient operation of manually searching for documents, and at the same time, through the natural language processing capabilities of the large language model, transforms technical documents into directly understandable explanations, providing operation and maintenance personnel with clear fault handling guidance and improving the efficiency of problem localization and resolution.

[0038] Step 140: Through the preset automatic operation and maintenance management interface, obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set; run the preset alarm self-healing processing program in sequence according to the running priority.

[0039] Understandably, the system achieves intelligent scheduling of alarm self-healing procedures through a pre-defined automated operation and maintenance management interface. The system automatically obtains the self-healing procedures associated with the target maintenance document set and their execution priorities, executing them sequentially according to a preset order. This design avoids the inefficient operation of manually selecting procedures, ensures that critical faults are handled first through a priority mechanism, and standardizes the procedure execution process, reducing the risk of errors caused by human intervention. When a procedure malfunctions, the system can automatically trigger subsequent processing flows, providing a coherent execution path for fault recovery.

[0040] Step 150: When the preset alarm self-healing process is abnormal, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing process is reduced by the first preset value, and the target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set and the maintenance explanation information are added to the preset manual maintenance management interface and deleted from the preset automatic operation and maintenance management interface.

[0041] Understandably, a dynamic adjustment mechanism is used to handle anomalies in the self-healing process. When the preset alarm self-healing procedure malfunctions, the system automatically reduces the quality assessment value of the maintenance document set associated with that procedure by a first preset value. Simultaneously, it transfers complete fault information (including alarm items, device nodes, maintenance capability levels, quality assessment values, and maintenance explanations) to the manual maintenance management interface and removes it from the automated maintenance interface. This design achieves automatic degradation of low-quality documents, provides a complete fault context for manual intervention, avoids information loss due to program anomalies, and ensures continuity of fault handling through interface switching.

[0042] After running the preset alarm self-healing procedures sequentially according to their running priority, the method also includes: Once the operation is successful, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing procedure will be increased according to the second preset value.

[0043] Understandably, a dynamic quality assessment mechanism enables closed-loop management of the self-healing procedure. When a preset alarm self-healing procedure runs successfully, the system automatically increments the quality assessment value of the maintenance document set associated with that procedure by a second preset value. This design establishes a positive feedback mechanism between the procedure's execution effect and document quality, effectively maintaining the timeliness of the maintenance database. Simultaneously, quantitative assessment ensures the continuous optimization of highly reliable documents, providing more accurate maintenance references for subsequent fault handling.

[0044] After decreasing the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing procedure by a first preset value, the method further includes: When the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold, a modification prompt is generated and the document is returned to the upload terminal of the preset maintenance document set.

[0045] Understandably, a dynamic quality monitoring mechanism is used to continuously optimize maintenance documents. When the quality assessment value of a pre-set set of maintenance documents drops below a pre-set threshold due to an anomaly in the self-healing process, the system automatically generates a modification prompt and returns the document to the upload terminal. This design ensures the reliability of document quality in the maintenance database, urging document updates through an automated feedback mechanism and preventing the long-term retention of low-quality documents from affecting subsequent troubleshooting. Simultaneously, the return operation preserves the traceability path of document modifications, providing document maintenance personnel with clear directions for improvement.

[0046] Step 160: When there is no target maintenance document set, directly add the target alarm item and the corresponding device node to the preset manual maintenance management interface.

[0047] Understandably, the ability to directly add target alarm items and their corresponding device nodes to the preset manual maintenance management interface allows maintenance personnel to quickly obtain the alarm information and associated device node information that needs to be processed within the interface, eliminating the need to query and integrate this data through other systems or processes, thus reducing the steps involved in information searching and summarizing. Furthermore, associating alarm items with device nodes and adding them to the management interface ensures that both information is presented at the same entry point, preventing mismatches between alarm items and device nodes during maintenance. This provides clear and accurate basic information support for subsequent manual maintenance operations, ensuring that manual maintenance work can be carried out in an orderly manner based on clearly defined targets.

[0048] As described above, this embodiment dynamically constructs a device relationship topology network, enabling real-time capture of device coupling states in high-concurrency scenarios, upgrading the static topology to a dynamic response mechanism. When a device node triggers an alarm, the system automatically associates the alarm items generated by its upstream and downstream device nodes to form a target alarm item set. This design significantly reduces the false alarm rate caused by device status lag, making alarm information more accurately reflect the actual fault chain and providing a precise data foundation for subsequent processing.

[0049] By leveraging a pre-set maintenance database and a large language model, intelligent matching of alarm items and maintenance documents is achieved. Engineers no longer need to manually filter documents; the system automatically extracts the maintenance explanation information corresponding to the target alarm item and integrates the alarm details, device nodes, and solutions into the operations and maintenance interface. This mechanism reduces the traditional 15-minute manual location time to a second-level response time. Simultaneously, it dynamically rates maintenance documents using quality assessment values ​​to ensure that the pushed solutions always possess high reliability.

[0050] The pre-set alarm self-healing procedure automatically performs fault recovery according to running priority, forming a multi-level defense. When the program malfunctions, the system automatically triggers a quality assessment value decrement mechanism, transferring the fault information to the manual maintenance interface while retaining the complete context (including maintenance document quality assessment values, explanatory information, etc.). This avoids interruption of fault handling and provides a basis for manual intervention. This design seamlessly switches processing modes when script execution fails, shortening the fault recovery waiting time.

[0051] In addition, this application Figure 2 This application provides an artificial intelligence-based operation and maintenance management system. Figure 2 As shown in the embodiments of this application, the system mainly includes: The target module 210 is used to obtain the current alarm item, determine the device node corresponding to the current alarm item, determine the device node associated with the device node corresponding to the current alarm item according to the preset device association topology network, and take the alarm items generated by the associated device nodes and the current alarm item as the target alarm item. Module 220 is used to upload a set of preset maintenance documents through device nodes, build a preset maintenance database, calculate the quality assessment value of each set of preset maintenance documents, and configure the preset alarm self-healing processing program and program running priority corresponding to the set of preset maintenance documents. Document module 230 is used to determine whether a target maintenance document set exists in the preset maintenance database based on the alarm triggering conditions of the target alarm item; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; and display the target alarm item, the device node corresponding to the target alarm item, and the maintenance explanation information on the preset automatic operation and maintenance management interface. Program module 240 is used to obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set through the preset automatic operation and maintenance management interface; and run the preset alarm self-healing processing program in sequence according to the running priority. The exception module 250 is used to, when the preset alarm self-healing processing program runs abnormally, decrease the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing processing program according to the first preset value, add the target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set and the maintenance explanation information to the preset manual maintenance management interface, and delete it from the preset automatic operation and maintenance management interface. Add module 260 to directly add target alarm items and corresponding device nodes to the preset manual maintenance management interface when the target maintenance document set does not exist.

[0052] The system also includes a rollback module. This is used to generate a modification prompt and return the preset maintenance document set to the upload terminal when the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold.

[0053] As described above, this embodiment dynamically constructs a device relationship topology network, enabling real-time capture of device coupling states in high-concurrency scenarios, upgrading the static topology to a dynamic response mechanism. When a device node triggers an alarm, the system automatically associates the alarm items generated by its upstream and downstream device nodes to form a target alarm item set. This design significantly reduces the false alarm rate caused by device status lag, making alarm information more accurately reflect the actual fault chain and providing a precise data foundation for subsequent processing.

[0054] By leveraging a pre-set maintenance database and a large language model, intelligent matching of alarm items and maintenance documents is achieved. Engineers no longer need to manually filter documents; the system automatically extracts the maintenance explanation information corresponding to the target alarm item and integrates the alarm details, device nodes, and solutions into the operations and maintenance interface. This mechanism reduces the traditional 15-minute manual location time to a second-level response time. Simultaneously, it dynamically rates maintenance documents using quality assessment values ​​to ensure that the pushed solutions always possess high reliability.

[0055] The pre-set alarm self-healing procedure automatically performs fault recovery according to running priority, forming a multi-level defense. When the program malfunctions, the system automatically triggers a quality assessment value decrement mechanism, transferring the fault information to the manual maintenance interface while retaining the complete context (including maintenance document quality assessment values, explanatory information, etc.). This avoids interruption of fault handling and provides a basis for manual intervention. This design seamlessly switches processing modes when script execution fails, shortening the fault recovery waiting time.

[0056] The above are method embodiments of this application. Based on the same inventive concept, this application also provides an operation and maintenance management device based on artificial intelligence. Figure 3 As shown, the device includes: a processor; and a memory storing executable code thereon, which, when executed, causes the processor to perform an AI-based operation and maintenance management method as described in the above embodiment.

[0057] Specifically, the server obtains the current alarm item and determines the device node corresponding to it; based on the preset device association topology network, it determines the device nodes associated with the device node corresponding to the current alarm item; it uses the alarm items generated by the associated device nodes and the current alarm item as the target alarm item; it uploads a preset maintenance document set through the device node, constructs a preset maintenance database, calculates the quality assessment value of each preset maintenance document set, and configures the preset alarm self-healing processing program and program execution priority corresponding to the preset maintenance document set; based on the alarm triggering conditions of the target alarm item, it determines whether the target maintenance document set exists in the preset maintenance database; it sends the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; and it displays the target alarm item, the device node corresponding to the target alarm item, and the maintenance explanation information. On the preset automatic operation and maintenance management interface; through the preset automatic operation and maintenance management interface, obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set; run the preset alarm self-healing processing program in sequence according to the running priority; when the preset alarm self-healing processing program runs abnormally, decrease the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing processing program according to the first preset value, and add the target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set, and the maintenance explanation information to the preset manual maintenance management interface, and delete it from the preset automatic operation and maintenance management interface; when there is no target maintenance document set, directly add the target alarm item and the corresponding device node to the preset manual maintenance management interface.

[0058] In addition, this application embodiment also provides a non-volatile computer storage medium storing executable instructions, which, when executed, implement an artificial intelligence-based operation and maintenance management method as described above.

[0059] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An operation and maintenance management method based on artificial intelligence, characterized in that, The method includes: Obtain the current alarm item and determine the device node corresponding to the current alarm item; based on the preset device association topology network, determine the device nodes associated with the device node corresponding to the current alarm item; use the alarm items generated by the associated device nodes and the current alarm item as the target alarm item; Upload a set of preset maintenance documents through device nodes, build a preset maintenance database, calculate the quality assessment value of each set of preset maintenance documents, and configure the preset alarm self-healing processing program and program running priority corresponding to the set of preset maintenance documents. Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; display the target alarm item, the corresponding device node and maintenance explanation information on the preset automatic operation and maintenance management interface; Through the preset automatic operation and maintenance management interface, obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set; and run the preset alarm self-healing processing program in sequence according to the running priority. When the preset alarm self-healing process malfunctions, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing process will be reduced by the first preset value. The target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set, and the maintenance explanation information will be added to the preset manual maintenance management interface and deleted from the preset automatic operation and maintenance management interface. When the target maintenance document set does not exist, the target alarm item and the corresponding device node are directly added to the preset manual maintenance management interface.

2. The operation and maintenance management method based on artificial intelligence according to claim 1, characterized in that, The preset maintenance database consists of several preset maintenance document sets; each preset maintenance document set contains the alarm triggering conditions for alarm items that can be resolved. Based on the alarm triggering conditions of the target alarm item, determine whether the target maintenance document set exists in the preset maintenance database, specifically including: Determine whether the target alarm item has a preset bound target alarm item; wherein, the preset bound target alarm item includes at least one preset maintenance document set; When there is no preset target alarm item, determine whether the alarm triggering condition of the target alarm item exists in the alarm triggering conditions of the alarm item resolved by the preset maintenance document set; When an alarm trigger condition exists in an alarm item that is resolved in the target maintenance document set, the target maintenance document set for the current target alarm item is determined from the corresponding preset maintenance document set. When an alarm trigger condition does not exist in the alarm items that can be resolved in the preset maintenance document set, calculate the matching degree between the alarm trigger condition of the target alarm item and the alarm trigger conditions of the alarm items that can be resolved in each preset maintenance document set. Obtain a preset maintenance document set with a matching degree greater than a preset threshold, and determine the target maintenance document set for the current target alarm item from the corresponding preset maintenance document set; When the maximum matching degree is less than the preset threshold, it is determined that the target maintenance document set does not exist in the preset maintenance database.

3. The operation and maintenance management method based on artificial intelligence according to claim 2, characterized in that, The target maintenance document set for the current target alarm item is determined from the corresponding preset maintenance document set, specifically including: When the number of preset maintenance documents is less than or equal to a preset threshold, the entire preset maintenance document set is determined as a single target maintenance document set. When the number of preset maintenance document sets exceeds a preset threshold, obtain the quality assessment value of each preset maintenance document set; select the preset maintenance document sets with the highest quality assessment values ​​as a whole target maintenance document set.

4. The operation and maintenance management method based on artificial intelligence according to claim 1, characterized in that, Upload a set of preset maintenance documents to the device node, construct a preset maintenance database, calculate the quality assessment value of each preset maintenance document set, and configure the preset alarm self-healing processing program corresponding to the preset maintenance document set. Specifically, this includes: Obtain the initial set of maintenance documents; Obtain the evaluation values ​​of the initial maintenance document set on preset quality dimensions, and accumulate them to generate a document quality evaluation value; When the document quality assessment value is lower than the preset assessment threshold, a modification prompt is generated, and the document is returned to the upload terminal of the initial maintenance document set. When the document quality assessment value is not lower than the preset assessment threshold, it is added to the preset maintenance database as a preset maintenance document set; Configure the preset alarm self-healing program corresponding to the preset maintenance document set through the preset interface.

5. The operation and maintenance management method based on artificial intelligence according to claim 1, characterized in that, After running the preset alarm self-healing processing program sequentially according to the running priority, the method further includes: Once the operation is successful, the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing procedure will be increased according to the second preset value.

6. The operation and maintenance management method based on artificial intelligence according to claim 1, characterized in that, After decreasing the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing processing procedure by a first preset value, the method further includes: When the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold, a modification prompt is generated and the document is returned to the upload terminal of the preset maintenance document set.

7. An operation and maintenance management system based on artificial intelligence, characterized in that, The system includes: The target module is used to obtain the current alarm item, determine the device node corresponding to the current alarm item; determine the device nodes associated with the device node corresponding to the current alarm item according to the preset device association topology network; and use the alarm items generated by the associated device nodes and the current alarm item as the target alarm item. The module is used to upload a set of preset maintenance documents through device nodes, build a preset maintenance database, calculate the quality assessment value of each set of preset maintenance documents, and configure the preset alarm self-healing processing program and program running priority corresponding to the set of preset maintenance documents. The document module is used to determine whether a target maintenance document set exists in the preset maintenance database based on the alarm triggering conditions of the target alarm item; send the target maintenance document set to the preset large language model to extract the maintenance explanation information of the corresponding target alarm item; and display the target alarm item, the corresponding device node and maintenance explanation information on the preset automatic operation and maintenance management interface. The program module is used to obtain the preset alarm self-healing processing program and the preset alarm self-healing processing program running priority corresponding to the preset maintenance document set in the target maintenance document set through the preset automatic operation and maintenance management interface; and to run the preset alarm self-healing processing program in sequence according to the running priority. The exception module is used to reduce the quality assessment value of the preset maintenance document set corresponding to the preset alarm self-healing process according to the first preset value when the preset alarm self-healing process is abnormal. It also adds the target alarm item, the device node corresponding to the target alarm item, the maintenance capability level, the quality assessment value corresponding to the target maintenance document set, and the maintenance explanation information to the preset manual maintenance management interface and deletes them from the preset automatic operation and maintenance management interface. The add module is used to directly add target alarm items and corresponding device nodes to the preset manual maintenance management interface when the target maintenance document set does not exist.

8. The AI-based operation and maintenance management system according to claim 7, characterized in that, The system also includes a return module. This is used to generate a modification prompt and return the preset maintenance document set to the upload terminal when the quality assessment value of the preset maintenance document set is lower than the preset assessment threshold.

9. An operation and maintenance management device based on artificial intelligence, characterized in that, The device includes: processor; And a memory having executable code stored thereon, which, when executed, causes the processor to perform an AI-based operation and maintenance management method as described in any one of claims 1-6.

10. A non-volatile computer storage medium, characterized in that, It stores computer instructions, which, when executed, implement an artificial intelligence-based operation and maintenance management method as described in any one of claims 1-6.

Images