Intelligent operation and maintenance methods, equipment, and storage media

Abstract

The present invention relates to the field of cluster operation and maintenance, and discloses an intelligent operation and maintenance method, device, and storage medium. The method includes: obtaining a current alarm item, and determining a target alarm item corresponding to the current alarm item based on a pre-built device topology network; judging whether a target document sequence set corresponding to the target alarm item exists in each candidate document sequence set based on the target alarm item; in response to the existence of the target document sequence set, interpreting and processing the target document sequence set based on the subject quality assessment value corresponding to the alarm processing user, and displaying it on the target device; in response to the absence of the target document sequence set, generating a target question-and-answer instruction based on the target alarm item, determining target information corresponding to the target alarm item based on the target question-and-answer instruction and a preset large language model, and displaying the target information on the target device. The present invention can improve the feasibility and adaptability of operation and maintenance documents and improve the efficiency of alarm processing.

Description

Technical Field

[0001] The present invention relates to the field of cluster operation and maintenance, and in particular to an intelligent operation and maintenance method, device and storage medium. Background Art

[0002] With the popularization of HPC (High Performance Computing) scientific computing applications and the acceleration of enterprise digital transformation, HPC clusters are showing the characteristics of "three highs and two fasts", namely high concurrency, high complexity, high coupling, rapid iteration, and rapid fault propagation.

[0003] Currently, traditional operations and maintenance systems face three core challenges: low-value conversion of massive amounts of data, difficulty in accumulating and reusing tacit knowledge, and a strong reliance on manual intervention for fault response. Equipment failure resolution requires time-consuming manual search for relevant information. Existing solutions rely heavily on operations and maintenance documentation, which is time-consuming to input and difficult to iterate. Traditional knowledge bases only support document or keyword searches and are unable to provide recommendations for sporadic failures with no precedent. Traditional knowledge bases are difficult to iterate on and are prone to mixing up failed solutions, resulting in inefficient troubleshooting.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides an intelligent operation and maintenance method, device and storage medium, which can improve the feasibility and adaptability of operation and maintenance documents and improve the efficiency of alarm processing.

[0006] An embodiment of the present invention provides an intelligent operation and maintenance method, which includes:

[0007] Obtaining a current alarm item, and determining a target alarm item corresponding to the current alarm item based on a pre-built device topology network;

[0008] According to the target alarm item, determining whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set;

[0009] In response to the existence of the target document sequence set, interpreting and processing the target document sequence set according to the subject quality evaluation value corresponding to the alarm processing user, and displaying it on the target device;

[0010] In response to the absence of the target document sequence set, a target question and answer instruction is generated based on the target alarm item, and the target information corresponding to the target alarm item is determined based on the target question and answer instruction and a preset large language model, and the target information is displayed on the target device.

[0011] An embodiment of the present invention provides an electronic device, comprising:

[0012] processor and memory;

[0013] The processor is used to execute the steps of the intelligent operation and maintenance method described in any embodiment by calling the program or instructions stored in the memory.

[0014] An embodiment of the present invention provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of the intelligent operation and maintenance method described in any embodiment.

[0015] The embodiments of the present invention have the following technical effects:

[0016] By obtaining the current alarm item and determining the target alarm item corresponding to the current alarm item based on the pre-built device topology network, the main alarm item is analyzed and interference is eliminated. Then, based on the target alarm item, it is determined whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set, so as to find the operation and maintenance document that can solve the sequence arrangement of the target alarm item through precise and fuzzy retrieval methods. In response to the existence of the target document sequence set, the target document sequence set is interpreted and processed according to the subject quality evaluation value corresponding to the alarm processing user, and displayed on the target device, so as to explain the document in combination with the user's ability when providing the operation and maintenance document, thereby reducing the situation where the user does not understand the document content. In response to the absence of the target document sequence set, a target question and answer instruction is generated according to the target alarm item. According to the target question and answer instruction and the preset large language model, the target information corresponding to the target alarm item is determined, and the target information is displayed on the target device, so as to perform information retrieval and expansion through the preset large language model, and provide a reference for the alarm processing user, thereby achieving the effect of improving the feasibility and adaptability of the operation and maintenance document and improving the efficiency of alarm processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of an intelligent operation and maintenance method provided by an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of an intelligent operation and maintenance system provided by an embodiment of the present invention;

[0020] Figure 3It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0022] The intelligent operation and maintenance method provided by the embodiment of the present invention is mainly applicable to situations where an alarm occurs on a device in a cluster and an operation and maintenance personnel is required to handle the situation. The intelligent operation and maintenance method provided by the embodiment of the present invention can be executed by an electronic device.

[0023] Example 1

[0024] Figure 1 This is a flow chart of an intelligent operation and maintenance method provided by an embodiment of the present invention. Figure 1 , the intelligent operation and maintenance method specifically includes:

[0025] S110: Acquire a current alarm item, and determine a target alarm item corresponding to the current alarm item based on a pre-built device topology network.

[0026] The current alarm item can be an alarm identifier. Each alarm identifier has a corresponding alarm device and at least one alarm condition. The device topology network is the topology network consisting of the devices requiring maintenance. This topology network can be constructed based on the cabinet or cluster in which it is located. The target alarm item is the root cause alarm item among the current alarm items, that is, the source of the alarm.

[0027] Specifically, current alarm items may be received, which may be alarm items generated by comparing various alarm conditions based on device signals and device logs of various basic devices. Root cause detection is performed on one or more current alarm items within a pre-built device topology network to determine one or more target alarm items that caused these current alarm items.

[0028] Based on the above example, you can also build a device topology network for each device that needs to be maintained, and build other related nodes affected by each device node. Specifically, it can be:

[0029] Obtain basic information of each basic device and build a device topology network based on the basic information;

[0030] For each device node in the device topology network, the upstream node of the device node is determined, and the upstream node and each downstream node corresponding to the upstream node are used as the impact service chain corresponding to the device node.

[0031] Basic devices are devices that require maintenance. Basic information includes the device name, cabinet, cluster, device role, device IP address, manufacturer, serial number, and maintenance date. The impact chain is a collection of other device nodes that may be affected by a device node failure.

[0032] Specifically, basic information about each basic device is obtained. Based on the basic knowledge of each basic device and the relationships between them, a device topology network is constructed. For each device node in the device topology network, the node immediately preceding the device node is used as the upstream node of the device node. The upstream node and all downstream nodes below it are used as the corresponding service chain of the device node. If the device node does not have a corresponding upstream node, the device node and all downstream nodes below it are used as the corresponding service chain of the device node.

[0033] Based on the above example, the target alarm item corresponding to the current alarm item can be determined based on the pre-built device topology network in the following way:

[0034] Determine the alarm service chain based on the current alarm item;

[0035] Determine at least one target service chain based on the alarm service chain and the impact service chains corresponding to each device node in the pre-built device topology network, and use the device node corresponding to the target service chain as the target node;

[0036] The current alarm item corresponding to the target node is used as the target alarm item.

[0037] The alarm service chain is the service chain consisting of the basic devices corresponding to each current alarm item. The target service chain is the impact service chain that can cover the alarm service chain. The target node is the device node corresponding to each target service chain.

[0038] Specifically, the basic devices corresponding to each current alarm item are determined, and these basic devices are organized into alarm service chains based on device associations. The alarm service chains are then matched against the impact service chains corresponding to each device node in the pre-built device topology network. The alarm service chains are then disassembled to obtain the minimum number of target service chains that cover the entire alarm service chain. The device nodes corresponding to each target service chain are then used as target nodes. Furthermore, at least one current alarm item corresponding to each target node is used as a target alarm item.

[0039] S120 . According to the target alarm item, determine whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set.

[0040] The candidate document sequence set is a set of multiple documents written by operation and maintenance personnel that need to be executed continuously. The target document sequence set is a sequence combination of candidate documents that may be able to solve the target alarm item.

[0041] Specifically, the target alarm item is compared with the alarm items that can be resolved by each candidate document sequence set, and it is determined whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set.

[0042] Based on the above example, the following method can be used to determine whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set according to the target alarm item:

[0043] According to the target alarm item, determining whether there is at least one candidate document sequence set bound to the target alarm item;

[0044] In response to the existence of a candidate document sequence set bound to the target alarm item, the candidate document sequence set bound to the target alarm item is used as the target document sequence set;

[0045] In response to the absence of a candidate document sequence set bound to the target alarm item, determining the candidate matching degree corresponding to the target alarm item and each candidate document sequence set respectively according to the alarm triggering condition corresponding to the target alarm item and the alarm triggering condition corresponding to each candidate document sequence set;

[0046] In response to the presence of at least one candidate matching degree being greater than or equal to the matching degree threshold, the candidate document sequence sets corresponding to the candidate matching degrees greater than or equal to the matching degree threshold are used as reference document sequence sets, and a target document sequence set corresponding to the target alarm item is determined based on the document quality assessment value corresponding to each reference document sequence set and a preset reference quantity;

[0047] In response to the absence of at least one candidate having a matching degree greater than or equal to the matching degree threshold, it is determined that there is no target document sequence set corresponding to the target alarm item in each candidate document sequence set.

[0048] Among them, the alarm trigger condition is one or more trigger conditions corresponding to each alarm item. The candidate matching degree is the vector similarity between the vectorized representation of the alarm trigger condition corresponding to the target alarm item and the vectorized representation of the alarm trigger condition corresponding to each candidate document sequence set. The matching degree threshold is a pre-set matching degree value used to determine whether the candidate matching degree meets the preliminary matching requirements. The reference document sequence set is a candidate document sequence set corresponding to each candidate matching degree that is greater than or equal to the matching degree threshold. The document quality assessment value is a comprehensive value of each candidate document sequence set evaluated on each quality assessment dimension, which is used to characterize the quality of each candidate document sequence set. The quality assessment dimensions may include readability, feasibility, clarity, standardization, etc. The preset reference quantity is the maximum number of reference document sequence sets that can be provided in advance.

[0049] Specifically, for each candidate document sequence set, determine whether the candidate alarm item bound to the candidate document sequence set is consistent with the target alarm item. If there is at least one that is consistent, it is determined that there is at least one candidate document sequence set bound to the target alarm item; otherwise, there is no at least one candidate document sequence set bound to the target alarm item. If there is a candidate document sequence set bound to the target alarm item, it means that there is a completely matched alarm item, and the candidate document sequence set bound to the target alarm item can be used as the target document sequence set. If there is no candidate document sequence set bound to the target alarm item, it means that the target alarm item cannot be accurately matched. Therefore, a fuzzy matching method is used to vectorize the alarm trigger conditions corresponding to the target alarm item and the alarm trigger conditions corresponding to each candidate document sequence set, and calculate the vector similarity corresponding to the vectorized representation of the alarm trigger condition corresponding to the target alarm item and the vectorized representation of the alarm trigger condition corresponding to each candidate document sequence set as the candidate matching degree corresponding to the target alarm item and each candidate document sequence set. Further, the candidate document sequence set is screened by the candidate matching degree. If there is at least one candidate matching degree greater than or equal to the matching degree threshold, the candidate document sequence sets corresponding to each candidate matching degree greater than or equal to the matching degree threshold are used as reference document sequence sets, and each reference document sequence set is processed according to the preset reference quantity limit. If the number of reference document sequence sets is greater than the preset reference quantity, they are sorted from large to small according to the document quality assessment value, and each reference document sequence set within the preset reference quantity is determined as the target document sequence set corresponding to the target alarm item. If there is not at least one candidate matching degree greater than or equal to the matching degree threshold, it is determined that there is no target document sequence set corresponding to the target alarm item in each candidate document sequence set.

[0050] Based on the above example, the target document sequence set corresponding to the target alarm item can be determined according to the document quality evaluation value corresponding to each reference document sequence set and the preset reference quantity in the following manner:

[0051] In response to the number of reference document sequence sets being less than or equal to a preset reference number, each reference document sequence set is used as a target document sequence set corresponding to the target alarm item, and each target document sequence set is sorted from largest to smallest according to the corresponding document quality evaluation value;

[0052] In response to the number of reference document sequence sets being greater than a preset reference number, each reference document sequence set is sorted from large to small according to its corresponding document quality evaluation value. If there are at least two reference document sequence sets with the same document quality evaluation value, at least two reference document sequence sets are sorted from large to small according to their corresponding subject quality evaluation values. The sorted reference document sequence sets are selected according to the preset reference number to determine the target document sequence set corresponding to the target alarm item.

[0053] The subject quality assessment value is determined based on the document quality assessment values of each candidate document sequence set uploaded by the target user corresponding to the reference document sequence set. The subject quality assessment value is a comprehensive value used to evaluate the quality of each candidate document sequence set uploaded by the operator who uploaded the reference document sequence set.

[0054] Specifically, if the number of reference document sequence sets is less than or equal to a preset reference number, it indicates that each reference document sequence set meets the requirements. Therefore, each reference document sequence set is used as the target document sequence set corresponding to the target alarm item. Furthermore, each target document sequence set is sorted from largest to smallest according to its corresponding document quality assessment value, so that operations and maintenance personnel can view the documents in descending order of document quality assessment value. If the number of reference document sequence sets is greater than the preset reference number, each reference document sequence set is sorted from largest to smallest according to its corresponding document quality assessment value. During the sorting process, if at least two reference document sequence sets have the same document quality assessment value, each reference document sequence set with the same document quality assessment value is sorted from largest to smallest according to the corresponding uploaded subject quality assessment value of the operations and maintenance personnel. Furthermore, the sorted reference document sequence sets are selected according to the preset reference number, and each reference document sequence set ranked within the preset reference number is determined as the target document sequence set corresponding to the target alarm item.

[0055] Based on the above example, we can also perform quality analysis and scoring on the initial document sequence set uploaded by the operation and maintenance personnel, that is, the target users, and make a reasonable assessment of the capabilities of each target user to determine the subject quality assessment value corresponding to the target user. Specifically, it can be:

[0056] Receive the initial document sequence set uploaded by the target user and the initial alarm item corresponding to the initial document sequence set, perform structural processing on the initial document sequence set, and update the initial document sequence set;

[0057] Determine the dimension evaluation value of the initial document sequence set on each quality evaluation dimension according to the evaluation rules corresponding to each quality evaluation dimension;

[0058] Determine the document quality evaluation value corresponding to the initial document sequence set based on the evaluation value of each dimension;

[0059] In response to the document quality evaluation value corresponding to the initial document sequence set being less than a preset evaluation value, document modification information is generated, and the document modification information and the initial document sequence set are fed back to the target user. Upon receiving the initial document sequence set updated by the target user, the step of returning to the step of executing the evaluation rules corresponding to each quality evaluation dimension to determine the dimension evaluation value of the initial document sequence set in each quality evaluation dimension is performed;

[0060] In response to the document quality evaluation value corresponding to the initial document sequence set being greater than or equal to the preset evaluation value, the initial document sequence set is used as a candidate document sequence set, and the initial alarm item is used as a candidate alarm item corresponding to the candidate document sequence set;

[0061] For each target user, the subject quality evaluation value corresponding to the target user is determined according to the document quality evaluation values corresponding to each candidate document sequence set uploaded by the target user.

[0062] Among them, the target user is the operation and maintenance personnel who uploaded the initial document sequence set. The initial document sequence set is a set of operation and maintenance documents uploaded by the target user for processing alarm items, which are arranged in the order of use. The initial alarm items are alarm items that can be resolved by the initial document sequence set. The evaluation rules are rules set for each quality assessment dimension, such as increasing a preset value when a certain rule is met. The dimension evaluation value is the final value obtained by analyzing the evaluation rules corresponding to the quality assessment dimension. The preset evaluation value is a pre-set value used to determine whether the initial document sequence set can be stored in the library for selection. Document modification information is information that prompts the target user that the initial document sequence set uploaded cannot be stored in the library and the document content needs to be modified.

[0063] Specifically, the initial document sequence set uploaded by the target user and the initial alarm item corresponding to the initial document sequence set are received. The initial document sequence set is subjected to structured processing, such as text extraction, table recognition, drawing parsing, etc., and the recognized content is subjected to structured processing to obtain an updated initial document sequence set. According to the pre-established evaluation rules corresponding to each quality assessment dimension, the initial document sequence set is scored on each quality assessment dimension to obtain the dimension evaluation value on each quality assessment dimension. Furthermore, the evaluation values of each dimension are fused, such as summation, weighted summation, fusion using a preset formula, etc., to obtain the document quality evaluation value corresponding to the initial document sequence set. If the document quality assessment value corresponding to the initial document sequence set is less than the preset assessment value, it means that the initial document sequence set does not meet the storage conditions. Therefore, document modification information is generated and the document modification information and the initial document sequence set are fed back to the target user. The target user can make modifications and re-upload the modified and updated initial document sequence set. Therefore, when the initial document sequence set updated by the target user is received, the step of determining the dimensional assessment value of the initial document sequence set in each quality assessment dimension according to the assessment rules corresponding to each quality assessment dimension can be returned to re-evaluate the updated initial document sequence set. If the document quality assessment value corresponding to the initial document sequence set is greater than or equal to the preset assessment value, the initial document sequence set is used as a candidate document sequence set, and the initial alarm item is used as the candidate alarm item corresponding to the candidate document sequence set. For each target user, the corresponding document quality assessment values of each candidate document sequence set uploaded by the target user are comprehensively processed according to a preset method, such as calculating the mean or median, to obtain the main quality assessment value corresponding to the target user.

[0064] Based on the above example, after the target documents are sequentially assembled and displayed on the target device in the order of the documents, the document quality evaluation value can also be updated in combination with the user's selection and feedback in the alarm processing. Specifically, it can be:

[0065] In response to the candidate alarm item bound to the target document sequence set being the same as the target alarm item, receiving a processing result corresponding to the target document sequence set;

[0066] In response to the processing result being successful, updating the document quality evaluation value corresponding to the target document sequence set according to the first preset incentive value;

[0067] In response to a processing result of processing failure, the document quality evaluation value corresponding to the target document sequence set is updated according to the second preset incentive value, and if the updated document quality evaluation value is less than the preset evaluation value, the target document sequence set is deleted.

[0068] The processing result is the result of whether the target document sequence set can resolve the target alarm item, and can include processing success or processing failure. The first preset incentive value is an incentive value for increasing the document quality assessment value, and the second preset incentive value is an incentive value for decreasing the document quality assessment value. The absolute values of the first preset incentive value and the second preset incentive value can be the same or different.

[0069] Specifically, when the candidate alarm item bound to the target document sequence set is the same as the target alarm item, that is, the target document sequence set can accurately match the target alarm item, then the processing result corresponding to the target document sequence set can be received. If the processing result is successful, it means that the target alarm item can be resolved using the selected target document sequence set. Therefore, the first preset incentive value can be added to the document quality evaluation value of the target document sequence set as the updated document quality evaluation value corresponding to the target document sequence set. If the processing result is failed, it means that the target alarm item cannot be resolved using the selected target document sequence set. Therefore, it is necessary to reduce the document quality evaluation value corresponding to the target document sequence set to reduce its probability of being selected, that is, to reduce the second preset incentive value from the document quality evaluation value of the target document sequence set as the updated document quality evaluation value corresponding to the target document sequence set. When the updated document quality evaluation value is less than the preset evaluation value, it means that the target document sequence set should no longer be selected. Therefore, the target document sequence set is deleted from the library.

[0070] S130 : In response to the existence of the target document sequence set, interpret and process the target document sequence set according to the subject quality evaluation value corresponding to the alarm processing user, and display it on the target device.

[0071] The target device is the device used by the alarm processing user.

[0072] Specifically, if there is a target document sequence set, it means that these documents need to be provided to the alarm processing user. Therefore, the ability level of the subject quality assessment value corresponding to the alarm processing user is first determined, and the target document sequence set is interpreted and processed accordingly according to the ability level. The target document sequence set after interpretation and processing is displayed on the target device for the alarm processing user to view, so as to avoid the problem that the alarm processing user is insufficient in ability and cannot understand the document content.

[0073] Based on the above example, the target document sequence set can be interpreted and processed according to the subject quality evaluation value corresponding to the alarm processing user in the following way:

[0074] Determine the capability level of the alarm processing user according to the subject quality evaluation value of the alarm processing user;

[0075] According to the capability level of the alarm processing user, each difficult information in the target document sequence set is determined, and based on each difficult information and the preset large language model, the corresponding explanation information of each difficult information is determined;

[0076] According to the explanation information corresponding to each difficult information, the target document sequence set is interpreted and processed.

[0077] The capability level is used to assess the ability of alarm processing users to write and understand operational documentation. Difficult information refers to incomprehensible information within the sequential set of target documents analyzed according to the capability level. The pre-set large language model is used to retrieve answers. Explanation information is the information provided by the pre-set large language model to resolve difficult information.

[0078] Specifically, the subject quality assessment value corresponding to the alarm processing user is matched according to the score intervals divided into each level to obtain the ability level corresponding to the alarm processing user. Based on the ability level corresponding to the alarm processing user, the target document sequence set is identified, and various difficult information in the target document sequence set can be obtained. It can be identified using a preset large language model combined with the ability level, or it can be identified based on preset vocabulary, etc. It can also be matched in the target document sequence set according to the query information of other users of the same ability level, and the query information that is successfully matched is used as difficult information. Then, each difficult information is input into the preset large language model for interpretation to obtain the explanation information corresponding to each difficult information. The target document sequence set is interpreted and processed using the explanation information corresponding to each difficult information.

[0079] S140. In response to the absence of a target document sequence set, a target question-and-answer instruction is generated according to the target alarm item. According to the target question-and-answer instruction and a preset large language model, the target information corresponding to the target alarm item is determined, and the target information is displayed on the target device.

[0080] The target question-answering instruction is a question instruction used to solve the target alarm item, and the target information is the answer information fed back by the preset large language model to the target question-answering instruction.

[0081] Specifically, if there is no target document sequence set, it means that there is no operation and maintenance document corresponding to the target alarm item in the library. Therefore, the alarm processing personnel need to solve the target alarm item without reference information. Therefore, the target alarm item is used to generate a target question and answer instruction, and the target question and answer instruction is input into the preset large language model. The preset large language model provides answer information for solving the target alarm item, that is, the target information, and displays the target information on the target device for reference by the alarm processing personnel.

[0082] Based on the above example, after determining the target alarm item corresponding to the current alarm item, you can also use the self-healing script to process the alarm item. This allows you to simultaneously introduce documents and scripts to improve the efficiency of alarm item processing. Specifically, you can:

[0083] In response to the existence of a target self-healing script corresponding to the target alarm item, executing the self-healing script and determining whether the target alarm item has been processed;

[0084] In response to completion of processing of the target alarm item, the target document sequence set or target information is cancelled from display on the target device.

[0085] Among them, the target self-healing script is an operation and maintenance script that aims to make the target alarm item self-heal and can be executed automatically.

[0086] Specifically, if a target self-healing script exists for the target alarm, it will automatically execute. During execution, it will determine in real time whether the target alarm has been processed, that is, whether the target alarm has stopped. If the target alarm has been processed, no manual processing by the operator (alarm processing user) is required, and the target document sequence set or target information can be removed from the target device.

[0087] It is understandable that during the execution of the target self-healing script, the target document sequence set or target information can still be displayed on the target device for operation and maintenance personnel to view.

[0088] The present invention has the following technical effects: by obtaining the current alarm item and determining the target alarm item corresponding to the current alarm item based on a pre-built device topology network, the main alarm item is analyzed and interference is eliminated. Then, based on the target alarm item, it is judged whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set, so as to find an operation and maintenance document that can solve the sequence arrangement of the target alarm item through precise and fuzzy retrieval methods. In response to the existence of the target document sequence set, the target document sequence set is interpreted and processed according to the subject quality evaluation value corresponding to the alarm processing user, and displayed on the target device, so that the document is interpreted and explained in combination with the user's ability when providing the operation and maintenance document, reducing the situation where the user does not understand the document content. In response to the absence of the target document sequence set, a target question and answer instruction is generated according to the target alarm item. According to the target question and answer instruction and a preset large language model, the target information corresponding to the target alarm item is determined, and the target information is displayed on the target device, so that information retrieval and expansion are performed through the preset large language model, providing a reference for the alarm processing user, thereby achieving the effect of improving the feasibility and adaptability of the operation and maintenance document and improving the efficiency of alarm processing.

[0089] Example 2

[0090] Figure 2 This is a schematic diagram of the structure of an intelligent operation and maintenance system provided by an embodiment of the present invention. Figure 2 As shown, it includes infrastructure layer, data collection layer, knowledge processing layer, intelligent application layer and user interaction layer.

[0091] The infrastructure layer is used to build an elastic resource pool based on a cloud-native architecture. This pool includes computing clusters, distributed storage, and networking equipment, supporting resource sharing with existing monitoring platforms. This elastically scalable hardware resource pool supports the system's core computing power and storage needs and can be shared with the monitoring and operations platform. This includes bare metal servers, microservices clusters, object storage, and communication equipment.

[0092] The data collection layer is used for global data collection and standardized processing, establishing a connection between the physical state of the equipment and the knowledge system. This layer includes: a document parser, a log collector, an alarm client, and an operation and maintenance scheduling engine. The document parser uses NLP+OCR technology to parse unstructured technical documents (an initial document sequence set) uploaded in advance by operation and maintenance personnel, automatically extracting knowledge elements and generating structured knowledge. The log collector collects device system logs in real time. The alarm client is responsible for implementing a standardized multi-source alarm conversion interface to parse alarm events, generating a unified alarm event stream through standardized protocol conversion to obtain the target alarm items. The operation and maintenance scheduling engine builds an instruction set repository to support the batch distribution of configuration instructions for devices across manufacturers. This layer is the system's sensory nerve, responsible for collecting device log information, alarm items, and text information from operation and maintenance documents (a candidate document sequence set), transmitting them to the knowledge processing layer for storage so that they can be accessed when an alarm occurs. Multi-threaded concurrent acquisition technology is used to achieve a data response within seconds, ensuring the integrity and timeliness of the input data to the knowledge processing layer.

[0093] The knowledge processing layer is used to extract, integrate, and dynamically update operational knowledge, building the core carrier of knowledge assets. This includes: knowledge graph engine, vector database, quality assessment model, etc.

[0094] The device digital twin warehouse in the data collection layer will store the basic information of all basic devices in all clusters, including device name, cabinet, cluster, device role, device IP, manufacturer, serial number, maintenance date, etc. The knowledge graph engine uses the basic information of the basic devices in the device warehouse to build a device topology relationship network (device topology network) based on the existing device digital twin warehouse, and implements association reasoning such as "switch A failure affects the business chain" through query language; a workflow engine is used to implement streaming orchestration of documents, and in the document orchestration module, alarm items (candidate alarm items) are bound to the orchestrated document set (candidate document sequence set) to form an automated document recommendation function; in addition, in the self-healing orchestration module, the operation and maintenance script ( Self-healing scripts also implement streaming orchestration, using the orchestration results as templates to associate with alarm information, forming an automated operation and maintenance process. The knowledge graph learns the associations between alarm self-healing through inference and builds operation and maintenance procedure models for alarm items not bound to self-healing scripts. The vector database stores document semantic vectors provided by the document collector in the data acquisition layer and supports thousand-dimensional vector similarity retrieval to respond to fuzzy requirements such as "network latency optimization solutions" or fuzzy requirements for alarm conditions corresponding to different alarm items. The quality assessment model integrates a document scoring algorithm to calculate document quality scores based on various quality assessment dimensions such as readability, feasibility, clarity, and standardization, and dynamically adjusts the weights of knowledge nodes in the operation and maintenance documents (candidate document sequence sets). This layer is the intelligent core of the system. Through a hybrid retrieval mechanism (exact retrieval + fuzzy semantic retrieval), it achieves breakthroughs in both knowledge query accuracy and coverage. This layer can generate operation and maintenance knowledge based on existing data in the system, regardless of whether an exact match exists for the target document sequence set. Specifically, if a target document sequence set with an exact match for the target alarm item exists, that set is preferred; if a target document sequence set without an exact match exists, the corresponding target document sequence set is determined through fuzzy matching inference.

[0095] The intelligent application layer is used to generate decision-making solutions and drive automated operations and maintenance. It is used for the management, invocation, and knowledge point feedback of generative / inferential models, thus achieving a closed-loop transformation from data to action. This includes: a generative question-answering engine, a model management center, an alarm rule management center, a document management and scheduling center, and a point incentive system. The generative question-answering engine serves as the middleware for the output of operation and maintenance knowledge, connecting the knowledge processing layer and the user interaction layer. Operation and maintenance personnel input natural language through the intelligent assistant dialog box provided by the front-end page, and input the natural language as a parameter into the API (Application Programming) provided by the generative question-answering engine. After receiving user query statements, the engine uses a query analyzer to determine the source of operation and maintenance knowledge. It then acquires knowledge based on the order of target documents recommended by the knowledge processing layer. The result fusion module then fuses these knowledge into multiple versions of operation and maintenance knowledge. The knowledge is then scored and ranked based on accuracy and relevance, with the highest-scoring knowledge returned to the front-end dialog box. The model management center manages generative and inference models, providing model switching and call functions for the generative question-answering engine. The alarm rule management center is primarily responsible for storing alarm trigger conditions and corresponding alarm items. Operation and maintenance personnel can associate alarm items with candidate document sequence sets to achieve the precise document recommendation function mentioned in the knowledge processing layer. The document management and scheduling center stores candidate document sequence sets uploaded by operation and maintenance personnel, which are used as knowledge sources and training corpus. The point incentive system uses the quality assessment model in the knowledge processing layer to score the document quality of the candidate document sequence sets uploaded by operation and maintenance personnel. This system then generates a subject quality assessment value for the operation and maintenance personnel, which is then used to categorize their ability levels and serve as a reference for assessing their operation and maintenance knowledge production capabilities.

[0096] The user interaction layer provides a natural human-machine collaborative interface for the system, improving operational efficiency and user experience. This layer includes: intelligent assistant, model management, alarm self-healing configuration, document management, and a smart dashboard. It supports natural language interaction and configuration between operators and models, provides alarm self-healing procedure configuration, document management, and a smart dashboard that includes, but is not limited to, a document contribution leaderboard. The intelligent assistant is a front-end component similar to a customer service dialog box. The back-end utilizes an API provided by the generative question-answering engine in the intelligent application layer, allowing users to select different models for communication, achieving a learning-while-conversation operational model. Model management, as the front-end module of the model management center in the intelligent application layer, provides functions such as model upload, configuration, update, training, and deletion. Alarm self-healing configuration provides a front-end module that links alarm items with operation and maintenance scripts into a streamlined operation. Document management corresponds to the document scheduling center in the intelligent application layer, responsible for implementing the addition, deletion, modification, and query of operation and maintenance documents and the streamlined orchestration of alarm item associations on the front-end interactive page. The smart dashboard displays document scoreboards, operator knowledge production rankings, and operational knowledge production capacity assessments.

[0097] The above system has a dual-mode knowledge engine, that is, a knowledge graph + vector database, which can achieve seamless connection between precise and fuzzy retrieval, and has a generative decision-making center. It combines the preset large language model to drive the generation of automated solutions, achieving a response speed of seconds. Moreover, it can fuse multi-source data, align device signals, documents, and logs in time and space, and eliminate information islands. It also has an immersive interactive design, which reduces cognitive load through dialogue / visual multimodal operations, has intelligent parsing capabilities, and can automatically extract parameters for unstructured documents to improve conversion efficiency. In terms of use, it has a closed-loop feedback mechanism, which can reversely optimize weights through document quality assessment values to form an automated system, and realize a contribution incentive ecosystem, quantify knowledge value (document quality assessment value and subject quality flatness value), and promote the output of high-quality documents.

[0098] Example 3

[0099] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 300 includes one or more processors 301 and a memory 302 .

[0100] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0101] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the intelligent operation and maintenance method of any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters and thresholds may also be stored in the computer-readable storage medium.

[0102] In one example, electronic device 300 may further include an input device 303 and an output device 304, which are interconnected via a bus system and / or other connection mechanisms (not shown). Input device 303 may include, for example, a keyboard, a mouse, etc. Output device 304 may output various information to the outside, including warning information, braking force, etc. Output device 304 may include, for example, a display, a speaker, a printer, a communication network, and remote output devices connected thereto.

[0103] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device 300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 300 may further include any other appropriate components according to specific application scenarios.

[0104] Example 4

[0105] In addition to the above methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the intelligent operation and maintenance method provided by any embodiment of the present invention.

[0106] The computer program product may be written in any combination of one or more programming languages to implement the operations of embodiments of the present invention, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0107] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the processor executes the steps of the intelligent operation and maintenance method provided by any embodiment of the present invention.

[0108] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0109] It should be noted that the terms used in the present invention are only for describing specific embodiments and are not intended to limit the scope of this application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "an", "a kind of" and / or "the" do not specifically refer to the singular and may also include the plural. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device comprising a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method or device comprising the elements.

[0110] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent operation and maintenance method, characterized in that: include: Obtaining a current alarm item, and determining a target alarm item corresponding to the current alarm item based on a pre-built device topology network; According to the target alarm item, determining whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set; In response to the existence of the target document sequence set, interpreting and processing the target document sequence set according to the subject quality evaluation value corresponding to the alarm processing user, and displaying it on the target device; In response to the absence of the target document sequence set, a target question and answer instruction is generated based on the target alarm item, and the target information corresponding to the target alarm item is determined based on the target question and answer instruction and a preset large language model, and the target information is displayed on the target device.

2. The method according to claim 1, characterized in that The step of interpreting the target document sequence set according to the subject quality evaluation value corresponding to the alarm processing user includes: Determining the capability level of the alarm processing user according to the subject quality assessment value of the alarm processing user; Determining each difficult information in the target document sequence set according to the ability level corresponding to the alarm processing user, and determining the explanation information corresponding to each difficult information according to each difficult information and the preset large language model; The target document sequence set is interpreted and processed according to the interpretation information corresponding to each piece of difficult information.

3. The method according to claim 1, characterized in that The step of judging, based on the target alarm item, whether there is a target document sequence set corresponding to the target alarm item in each candidate document sequence set includes: According to the target alarm item, determining whether there is at least one candidate document sequence set bound to the target alarm item; In response to the existence of a candidate document sequence set bound to the target alarm item, taking the candidate document sequence set bound to the target alarm item as the target document sequence set; In response to the absence of a candidate document sequence set bound to the target alarm item, determining the candidate matching degree corresponding to the target alarm item and each candidate document sequence set respectively according to the alarm triggering condition corresponding to the target alarm item and the alarm triggering condition corresponding to each candidate document sequence set; In response to the presence of at least one candidate matching degree being greater than or equal to a matching degree threshold, taking a candidate document sequence set corresponding to each candidate matching degree greater than or equal to the matching degree threshold as a reference document sequence set, and determining a target document sequence set corresponding to the target alarm item based on a document quality assessment value corresponding to each reference document sequence set and a preset reference quantity; In response to the absence of at least one candidate having a matching degree greater than or equal to the matching degree threshold, it is determined that there is no target document sequence set corresponding to the target alarm item in each candidate document sequence set.

4. The method according to claim 3, characterized in that The step of determining a target document sequence set corresponding to the target alarm item according to the document quality evaluation value corresponding to each reference document sequence set and a preset reference quantity includes: In response to the number of the reference document sequence sets being less than or equal to a preset reference number, each reference document sequence set is used as a target document sequence set corresponding to the target alarm item, and each target document sequence set is sorted from largest to smallest according to the corresponding document quality evaluation value; In response to the number of the reference document sequence sets being greater than the preset reference number, sorting the reference document sequence sets from largest to smallest according to their corresponding document quality assessment values; if at least two reference document sequence sets have the same document quality assessment values, sorting the at least two reference document sequence sets from largest to smallest according to their corresponding subject quality assessment values; selecting the sorted reference document sequence sets according to the preset reference number to determine a target document sequence set corresponding to the target alarm item; The subject quality evaluation value is determined according to the document quality evaluation values of each candidate document sequence set uploaded by the target user corresponding to the reference document sequence set.

5. The method according to claim 1, wherein Also includes: receiving an initial document sequence set uploaded by a target user and an initial alarm item corresponding to the initial document sequence set, performing structural processing on the initial document sequence set, and updating the initial document sequence set; Determining the dimension evaluation value of the initial document sequence set on each quality evaluation dimension according to the evaluation rules corresponding to each quality evaluation dimension; Determining the document quality evaluation value corresponding to the initial document sequence set based on the evaluation values of each dimension; In response to a document quality evaluation value corresponding to the initial document sequence set being less than a preset evaluation value, document modification information is generated, and the document modification information and the initial document sequence set are fed back to the target user. Upon receiving the initial document sequence set updated by the target user, the step of returning to the step of executing the evaluation rules corresponding to each quality evaluation dimension to determine the dimension evaluation value of the initial document sequence set in each quality evaluation dimension is performed. In response to a document quality evaluation value corresponding to the initial document sequence set being greater than or equal to the preset evaluation value, taking the initial document sequence set as a candidate document sequence set, and taking the initial alarm item as a candidate alarm item corresponding to the candidate document sequence set; For each target user, the subject quality evaluation value corresponding to the target user is determined according to the document quality evaluation values corresponding to each candidate document sequence set uploaded by the target user.

6. The method according to claim 5, characterized in that After the target documents are sequentially assembled and displayed on the target device in the order of the documents, the method further includes: In response to the candidate alarm item bound to the target document sequence set being the same as the target alarm item, receiving a processing result corresponding to the target document sequence set; In response to the processing result being successful, updating the document quality evaluation value corresponding to the target document sequence set according to the first preset incentive value; In response to the processing result being a processing failure, the document quality evaluation value corresponding to the target document sequence set is updated according to the second preset incentive value, and if the updated document quality evaluation value is less than the preset evaluation value, the target document sequence set is deleted.

7. The method according to claim 1, characterized in that Also includes: Obtain basic information of each basic device and build a device topology network based on the basic information; For each device node in the device topology network, determine an upstream node of the device node, and use the upstream node and each downstream node corresponding to the upstream node as an impact service chain corresponding to the device node; Accordingly, determining the target alarm item corresponding to the current alarm item based on the pre-built device topology network includes: Determining an alarm service chain according to the current alarm item; Determine at least one target service chain based on the alarm service chain and the impact service chains corresponding to each device node in the pre-built device topology network, and use the device node corresponding to the target service chain as the target node; The current alarm item corresponding to the target node is used as the target alarm item.

8. The method according to claim 1, characterized in that After determining the target alarm item corresponding to the current alarm item, the method further includes: In response to the existence of a target self-healing script corresponding to the target alarm item, executing the self-healing script and determining whether the target alarm item has been processed; In response to completion of processing of the target alarm item, the target document sequence set or the target information is canceled from being displayed on the target device.

9. An electronic device, characterized in that: The electronic device comprises: processor and memory; The processor is used to execute the steps of the intelligent operation and maintenance method according to any one of claims 1 to 8 by calling the program or instructions stored in the memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program or instruction, which enables a computer to execute the steps of the intelligent operation and maintenance method according to any one of claims 1 to 8.

Images