Database operation and maintenance method, electronic equipment, storage medium and program product

Abstract

The invention discloses a database operation and maintenance method, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a user intention matched with an operation and maintenance demand problem of a user; if the intention is a general operation and maintenance knowledge acquisition demand, performing retrieval in a knowledge base according to an operation and maintenance demand problem, and generating a first response result for feedback; if the intention is an actual operation and maintenance scene knowledge acquisition demand, real-time operation data of a database is acquired through a database monitoring module, retrieval is performed in a knowledge base according to the real-time operation data and an operation and maintenance demand problem, and a second response result is generated for feedback; and if the intention is to execute the target operation and maintenance task, retrieving an operation and maintenance instruction set matched with the target operation and maintenance task in the knowledge base, and issuing the operation and maintenance instruction set to an operation and maintenance task execution module, so that the operation and maintenance task execution module arranges and executes the target operation and maintenance task according to the task priority. According to the embodiment of the invention, the workload of operation and maintenance personnel is reduced while the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence (AI) technology, and in particular to a database operation and maintenance method, electronic equipment, storage medium, and program product. Background Art

[0002] Currently, database operations and management are primarily performed manually or through traditional automated operations and maintenance tools. Manual operations and maintenance primarily involve operators manually performing various operations and maintenance tasks, such as daily database inspections, backups, and restores, using the graphical user interface (GUI) or command-line tools provided by the database management system. Traditional automated operations and maintenance tools primarily execute pre-written scheduled task scripts to automatically perform the database operations defined in the scripts.

[0003] During the implementation of this invention, the inventors discovered the following deficiencies in the existing technology: During manual operation and maintenance, operators must troubleshoot and diagnose faults based on real-time error messages. This approach is highly dependent on the operator's experience and skill level. Different operators may have different approaches and efficiency for the same problem. Furthermore, complex issues can take a long time to resolve, potentially disrupting normal business operations. Traditional automated operation and maintenance tools have relatively limited flexibility and intelligence. They can only operate according to pre-set rules, making them less adaptable to complex and dynamically changing database operation and maintenance scenarios. Summary of the Invention

[0004] The embodiments of the present invention provide a database operation and maintenance method, electronic device, storage medium and program product to provide a new database operation and maintenance method based on AI dialogue, which greatly reduces the workload of operation and maintenance personnel while improving operation and maintenance efficiency and accuracy.

[0005] According to one aspect of an embodiment of the present invention, a database operation and maintenance method is provided, which is performed by an AI dialogue robot in a database operation and maintenance system. The method includes:

[0006] In response to an operation and maintenance requirement question input by a user, determining a user intent that matches the operation and maintenance requirement question;

[0007] If the user intends to obtain general operation and maintenance knowledge, the knowledge base will be searched according to the operation and maintenance requirements, and the first response result that matches the search result will be generated for feedback;

[0008] If the user intention is actual operation and maintenance scene knowledge acquisition requirement, real-time running data of the database is acquired through a database monitoring module in the database operation and maintenance system, and the real-time running data and the operation and maintenance demand question are searched in the knowledge base to generate a second response result matched with the search result for feedback.

[0009] If the user intention is to execute a target operation and maintenance task, an operation and maintenance instruction set matched with the target operation and maintenance task is searched in the knowledge base, and the operation and maintenance instruction set is issued to an operation and maintenance task execution module in the database operation and maintenance system for the operation and maintenance task execution module to execute the target operation and maintenance task according to a task priority.

[0010] According to another aspect of the embodiment of the present application, a database operation and maintenance device configured in an AI dialogue robot in a database operation and maintenance system is further provided, and the device comprises:

[0011] A user intention determination module configured to determine a user intention matched with an operation and maintenance demand question in response to the operation and maintenance demand question input by a user;

[0012] A first response result feedback module configured to search in the knowledge base according to the operation and maintenance demand question to generate a first response result matched with a search result for feedback if the user intention is general operation and maintenance knowledge acquisition requirement;

[0013] A second response result feedback module configured to acquire real-time running data of the database through a database monitoring module in the database operation and maintenance system, and search in the knowledge base according to the real-time running data and the operation and maintenance demand question to generate a second response result matched with a search result for feedback if the user intention is actual operation and maintenance scene knowledge acquisition requirement;

[0014] An operation and maintenance instruction set issuing module configured to search in the knowledge base an operation and maintenance instruction set matched with a target operation and maintenance task, and issue the operation and maintenance instruction set to an operation and maintenance task execution module in the database operation and maintenance system for the operation and maintenance task execution module to execute the target operation and maintenance task according to a task priority if the user intention is to execute the target operation and maintenance task.

[0015] According to another aspect of the embodiment of the present application, an electronic device is further provided, and the electronic device comprises:

[0016] at least one processor; and

[0017] a memory connected with the at least one processor in communication; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the database operation and maintenance method according to any one of the embodiments of the present application.

[0019] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores computer instructions for causing a processor to implement the database operation and maintenance method according to any of the embodiments of the present application when executed.

[0020] According to another aspect of the embodiments of the present application, a computer program product is also provided, which comprises a computer program for implementing the steps of the database operation and maintenance method according to any of the embodiments of the present application when executed by a processor.

[0021] The technical solution of the embodiments of the present application provides a new database operation and maintenance method based on AI conversation mode, which can realize automatic operation and maintenance management of the database, improve operation and maintenance efficiency and accuracy, reduce operation and maintenance cost, and provide more convenient and efficient working mode for operation and maintenance personnel.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0024] Figure 1 is a flowchart of a database operation and maintenance method according to an embodiment of the present application;

[0025] Figure 2 is a flowchart of another database operation and maintenance method according to an embodiment of the present application;

[0026] Figure 3 is an architecture diagram of a database operation and maintenance system according to an embodiment of the present application;

[0027] Figure 4This is a schematic diagram of the structure of a database operation and maintenance device provided according to the third embodiment of the present invention;

[0028] Figure 5 It is a structural diagram of an electronic device for implementing the database operation and maintenance method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a database operation and maintenance method provided in Example 1 of the present invention. This embodiment can be applied to situations where an AI dialogue robot is used to conduct one or more rounds of dialogue with the user to accurately respond to the user's actual operation and maintenance needs. The method can be executed by a database operation and maintenance device, which can be implemented in the form of hardware and / or software and can generally be configured in an electronic device equipped with an AI dialogue robot.

[0033] Among them, the AI ​​dialogue robot can be understood as a human-computer dialogue software that is pre-packaged with a pre-trained AI large model. For example, the human-computer dialogue software can be set up separately as an independent software, or it can be integrated into a web page in the form of a web plug-in, such as an AI assistant set up in a web page. The AI ​​large model can be understood as a pre-trained large language model (Large Language Model, LLM) based on a deep neural network architecture with a large number of model parameters (for example, more than 1 billion). The AI ​​large model can be a generative AI system, that is, after training with massive data, it can realize natural language understanding, generation and reasoning to obtain new content for multi-source input data such as text, images, audio and video. Typically, the AI ​​large model can be an autoregressive language model that supports setting context size, etc.

[0034] Furthermore, in this embodiment, the AI ​​conversational robot is a system element in a database operation and maintenance system. The database operation and maintenance system can be understood as a collection of system elements used to perform operation and maintenance operations on a given database. In addition to the AI ​​conversational robot, the database operation and maintenance system further includes: a knowledge base, a database monitoring module, and an operation and maintenance task execution module.

[0035] Correspondingly, such as Figure 1 As shown, the method includes:

[0036] S110 : In response to an operation and maintenance requirement question input by a user, determining a user intention that matches the operation and maintenance requirement question.

[0037] Among them, after the user triggers the AI ​​dialogue robot, he can send operation and maintenance requirements to the AI ​​dialogue machine through various input devices, such as keyboard or microphone.

[0038] This operation and maintenance requirement question can be understood as a question used to obtain general operation and maintenance knowledge, such as "how to implement database backup", or a question used to obtain knowledge of actual operation and maintenance scenarios, such as "the current database performance suddenly deteriorates, possible reasons and solutions", or it can also be a question used to trigger the execution of set operation and maintenance tasks, such as "back up the database immediately".

[0039] In other words, users may have different user intentions when raising different O&M requirements. Continuing with the previous example, user intentions can include: general O&M knowledge acquisition needs, actual O&M scenario knowledge acquisition needs, and executing target O&M tasks.

[0040] In this embodiment, a user intent recognition model may be pre-trained, and the user intent recognition model may be obtained by training a set machine learning model using training samples that are pre-labeled with different user intents.

[0041] S120: If the user intends to acquire general operation and maintenance knowledge, a search is performed in the knowledge base according to the operation and maintenance requirement question, and a first response result matching the search result is generated for feedback.

[0042] In this embodiment, when the user intends to obtain general operation and maintenance knowledge, it means that the operation and maintenance requirement entered by the user does not need to be closely integrated with the current actual database operation scenario. Only some general database operation and maintenance knowledge is needed. For example, an operation and maintenance requirement such as "How to check the database version number" can be directly searched in the knowledge base.

[0043] Furthermore, after accurately retrieving one or more pieces of knowledge data that match the operation and maintenance demand problem from the knowledge base, the above retrieval results can be directly used as the first response results for user feedback. Alternatively, the knowledge summary and induction capabilities of the AI ​​large model can be used to generate knowledge induction results that match the retrieved knowledge data, and the knowledge induction results can be used as the first response results for user feedback.

[0044] Optionally, in this knowledge base, a combination of relational databases and document databases can be used to store database operation and maintenance knowledge. Specifically, a relational database can be used to store structured knowledge data, such as solutions to common problems, detailed procedures for operation and maintenance steps, etc., to facilitate accurate queries and association analysis; and a document database can be used to store unstructured knowledge, such as operation and maintenance experience articles or technical documents, to better preserve the original format and contextual information of the knowledge. For example, the database failure type, corresponding symptoms, and solutions can be stored in a relational database in a table format, while detailed troubleshooting cases and analysis processes can be stored in a document database in a document format.

[0045] In this embodiment, the AI ​​dialogue robot can generate a corresponding first response result only for the currently input operation and maintenance demand question, or the AI ​​dialogue robot can also generate a corresponding first response result based on one or more historical questions raised by the user before inputting the current operation and maintenance demand question. This embodiment does not limit this.

[0046] S130. If the user intends to acquire knowledge for actual operation and maintenance scenarios, the real-time operation data of the database is obtained through the database monitoring module in the database operation and maintenance system, and a search is performed in the knowledge base based on the real-time operation data and operation and maintenance requirements, and a second response result matching the search result is generated for feedback.

[0047] The need for knowledge acquisition in actual operation and maintenance scenarios can be understood as the need for knowledge acquisition tailored to the actual operational status of the current database. For example, if a user notices a sudden increase in the database's response latency to data bureau queries, or experiences multiple crashes within a short period of time, they might ask the AI ​​conversational robot questions such as, "What's going on with the sudden drop in database performance?" or "What should I do if the database suddenly experiences multiple crashes?" These user-generated questions represent the need for knowledge acquisition in actual operation and maintenance scenarios.

[0048] When users seek knowledge for actual operation and maintenance scenarios, the actual operating status of the database may differ from normal operation in some dimensions. In this case, real-time database operating data can be obtained and combined with this data to provide users with a more targeted or accurate second response.

[0049] In this embodiment, real-time database operation data can be obtained through the database monitoring module in the database operation and maintenance system. Furthermore, the database monitoring module can collect database operation data through various methods, including using the database system's built-in monitoring interface to obtain performance indicator data such as CPU usage, memory usage, disk I / O speed, and network bandwidth usage; or, various database log analysis tools can be used to collect database operation logs and error logs to understand the database's operation history and failure conditions.

[0050] After obtaining the real-time operation data of the database, one or more abnormal monitoring indicators can be identified in the real-time operation data, such as memory occupancy or CPU usage, etc. Then, based on the degree of match between the abnormal monitoring indicator and the user's actual operation and maintenance scenario knowledge acquisition needs, one or more knowledge data associated with the above two can be obtained in the knowledge base, and second response data can be generated based on the above one or more knowledge data for user feedback.

[0051] S140. If the user intends to execute the target operation and maintenance task, the operation and maintenance instruction set that matches the target operation and maintenance task is retrieved from the knowledge base, and the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, so that the operation and maintenance task execution module can arrange and execute the target operation and maintenance task according to the task priority.

[0052] In this embodiment, if the operation and maintenance personnel hope that the database operation and maintenance system can automatically trigger the execution of the set operation and maintenance task, the target operation and maintenance task can be issued in the form of human-computer dialogue with the AI dialogue robot, for example, "start database backup at 9 o'clock" or "automatically revoke the rights of service accounts that have not been used for 90 days". At this time, the user intention of the operation and maintenance demand problem is to execute the target operation and maintenance task.

[0053] In this embodiment, when it is determined that the user intention is to execute the target operation and maintenance task, the operation and maintenance instruction set for realizing the target operation and maintenance task can be retrieved and acquired in the knowledge base. The operation and maintenance instruction set can be understood as one or more sequentially arranged operation and maintenance instructions, and when the operation and maintenance task execution module sequentially executes each operation and maintenance instruction in the operation and maintenance instruction set, the execution of the target operation and maintenance task can be completed.

[0054] Among them, the operation and maintenance task execution module can be understood as an operation and maintenance instruction execution module, and the operation and maintenance task execution module executes specific database operation and maintenance operations by interacting with the database. Optionally, the operation and maintenance task execution module has multiple operation execution modes, including calling the command line tool provided by the database management system, executing the pre-written script, and performing related operations by calling the database API (Application Programming Interface, application programming interface).

[0055] Further, after the AI dialogue robot issues the operation and maintenance instruction set to the operation and maintenance task execution module, the operation and maintenance task execution module reasonably arranges, schedules and manages the target operation and maintenance task according to the priority (urgency) of the task. For example, when the target operation and maintenance task is an urgent database fault repair task, it is arranged to be executed first; when the target operation and maintenance task is a periodic database optimization task, it can be scheduled according to the preset time plan. At the same time, the operation and maintenance task execution module can record the execution state and history of the task, so as to facilitate subsequent auditing and analysis.

[0056] In an optional implementation manner of this embodiment, the AI dialogue robot can directly acquire the standard operation and maintenance instruction template set from the knowledge base, and by adding some personalized information (for example, the specific time of performing database backup) extracted from the operation and maintenance demand problem to a specific position in the standard operation and maintenance instruction template set, the operation and maintenance instruction set for realizing the target operation and maintenance task can be correspondingly constructed.

[0057] Further, if the knowledge base does not store a standard operation and maintenance instruction template set that precisely matches the operation and maintenance demand problem, one or more similar standard operation and maintenance instruction template sets associated with the operation and maintenance demand problem can be obtained in order from high to low matching degree. Then, the one or more similar standard operation and maintenance instruction template sets are fused by the pre-constructed operation and maintenance instruction set migration model to generate a standard operation and maintenance instruction template set that precisely matches the operation and maintenance demand problem. Alternatively, the one or more similar standard operation and maintenance instruction template sets can be directly pushed to the operation and maintenance personnel, and a standard operation and maintenance instruction template set that precisely matches the operation and maintenance demand problem can be obtained by manual modification of the operation and maintenance personnel.

[0058] The technical solution of the embodiment of the application provides a new database operation and maintenance manner realized based on an AI conversation manner. The database operation and maintenance manner realizes automatic operation and maintenance management of a database, improves operation and maintenance efficiency and accuracy, reduces operation and maintenance cost, and provides a more convenient and efficient working manner for operation and maintenance personnel.

[0059] On the basis of the above-mentioned embodiments, after the operation and maintenance instruction set is issued to the operation and maintenance task execution module in the database operation and maintenance system, the following can be further included:

[0060] During execution of the operation and maintenance instruction set by the operation and maintenance task execution module, if abnormal operation information reported by the database monitoring module is detected, an abnormal processing strategy that matches the abnormal operation information is retrieved from the knowledge base;

[0061] According to the execution level of the abnormal processing strategy, a processing suggestion that matches the abnormal processing strategy is selected to be fed back to the user, or the abnormal processing strategy is directly triggered to be executed.

[0062] In the embodiment, when the operation and maintenance task execution module receives the operation and maintenance instruction set that matches the target operation and maintenance task, the target operation and maintenance task is executed according to a preset execution plan, and when a preset execution time point is reached, each operation and maintenance instruction included in the operation and maintenance instruction set is executed in sequence. For example, when a database backup task is executed, a command line interface of a database backup tool is called, and corresponding parameters such as a backup target path, a backup mode (full backup or incremental backup), etc. are transmitted to complete a data backup operation. When database optimization is performed, an optimization script is executed to adjust indexes, storage structures, etc. of the database.

[0063] At the same time, the operation and maintenance task execution module will also send a task start execution notification instruction to the AI ​​dialogue robot at the execution time of the target operation and maintenance task, so that the AI ​​dialogue robot will be informed of the database starting to execute the target operation and maintenance task based on this notification instruction. At this time, the AI ​​dialogue robot can obtain abnormal operation information reported by the database monitoring module in real time, such as the CPU usage rate exceeding 80% for 10 consecutive minutes. When receiving abnormal operation information, it is likely that the abnormal operation information is caused by the execution of the target operation and maintenance task. At this time, the abnormal operation information and the execution information of the target operation and maintenance task can be searched in the knowledge base to obtain an exception handling strategy.

[0064] Among them, the exception handling strategy can also carry an execution level, for example, immediate execution, execution after review, or suspended execution, etc. Based on the execution level, you can choose to build a processing suggestion that matches the exception handling strategy for user feedback, or choose to directly trigger the execution of the exception handling strategy.

[0065] Through the above settings, the execution status of operation and maintenance tasks can be grasped in real time during the automated execution of operation and maintenance tasks, and corresponding exception handling strategies can be adopted for abnormal execution status, thereby minimizing business losses caused by failures or anomalies, thereby indirectly reducing operation and maintenance costs.

[0066] Furthermore, based on the above embodiments, after the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, the following steps may be further included:

[0067] When receiving the task execution result fed back by the operation and maintenance task execution module for the target operation and maintenance task, result description information is generated according to the task execution result, and the result description information is fed back to the user.

[0068] Furthermore, after the operation and maintenance task execution module completes the execution of the target operation and maintenance task, it can first verify the execution results to ensure the correctness and effectiveness of the task execution. For example, after the database backup is completed, the integrity and availability of the backup file are verified, and the data consistency is ensured by comparing the hash value of the backup file with the hash value of the source data. If the task execution is found to have failed or the result does not meet expectations, a timely retry or appropriate remedial measures are taken to correct the loopholes or errors that occurred during the execution of the target operation and maintenance task. After the entire processing of the target operation and maintenance task is finally completed, the corresponding task execution results are generated and provided to the AI ​​dialogue robot.

[0069] Accordingly, the task execution results may specifically include various operation logs generated by the operation and maintenance task execution module during the execution of the target task, as well as execution status records. Based on the task execution results, the AI ​​conversational robot can further invoke the data induction, reasoning, and summary capabilities of the AI ​​large model to obtain result description information that matches the task execution results, such as whether the execution was smooth, any problems encountered, solutions, and subsequent execution suggestions.

[0070] Through the above settings, operation and maintenance personnel can optimize the natural language processing methods of operation and maintenance tasks, accumulate more operation and maintenance knowledge that adapts to various actual scenarios, and further improve the execution efficiency of database operation and maintenance work.

[0071] Example 2

[0072] Figure 2 This is a flowchart of another database operation and maintenance method provided in Example 2 of the present invention. This example is optimized based on the above examples. In this example, the specific implementation method for generating the first response result and the second response result is specified when the user intends to obtain general operation and maintenance knowledge or to obtain knowledge for actual operation and maintenance scenarios.

[0073] Correspondingly, such as Figure 2 As shown, the method includes:

[0074] S210. In response to the operation and maintenance requirement question input by the user, determine the user intention that matches the operation and maintenance requirement question: if the user intention is a general operation and maintenance knowledge acquisition requirement, execute S220; if the user intention is an actual operation and maintenance scenario knowledge acquisition requirement, execute S260; if the user intention is to execute the target operation and maintenance task, execute S290.

[0075] S220: Tracing back at least one historical operation and maintenance issue raised by the user based on the sending time of the operation and maintenance requirement issue.

[0076] In this embodiment, when a user's intent is to acquire general operational knowledge, the AI ​​conversational robot can interact with the user appropriately based on the context of the conversation. When the user asks a series of related questions, the AI ​​conversational robot can remember the previous conversation content, avoid repeatedly asking for the same information, and provide coherent solutions.

[0077] Accordingly, whenever the AI ​​conversational robot receives an O&M request, it can trace back one or more previous O&M requests that were asked before the O&M request was sent, based on the time the request was sent. Furthermore, the time difference between the time the question was asked and the time the question was sent should be within a preset time difference range, for example, two or three hours.

[0078] S230 , detecting whether there is at least one consistency issue in each historical operation and maintenance issue that belongs to the same operation and maintenance scenario as the operation and maintenance requirement issue: if so, executing S240 ; otherwise, executing S250 .

[0079] Among them, coherence questions can understand multiple questions with time or logical correlation. For example, the user first asked about the database backup method and then asked for recommendations on backup frequency. The AI ​​dialogue robot can understand that these are questions in the same operation and maintenance scenario.

[0080] In this embodiment, a data operation and maintenance knowledge graph can be established in the knowledge base, and association relationships between different knowledge points can be established in the knowledge graph. For example, in the data operation and maintenance knowledge graph, under the knowledge point of database backup, the backup frequency selection knowledge point, the backup granularity selection knowledge point, and the backup location selection knowledge point can be connected by directed arrows.

[0081] Accordingly, after obtaining the operation and maintenance requirement question and at least one historical operation and maintenance question, the corresponding knowledge data can be extracted from each of these questions and mapped to the data operation and maintenance knowledge graph in the knowledge base. If it is determined that the knowledge point corresponding to the operation and maintenance requirement question is directly connected to the knowledge point corresponding to a historical operation and maintenance question in the data operation and maintenance knowledge graph, or is connected only through a relay knowledge point, the historical operation and maintenance question can be determined to be a coherence question belonging to the same operation and maintenance scenario as the operation and maintenance requirement question.

[0082] S240: Search the knowledge base based on the operation and maintenance requirement question and the historical response results corresponding to each consistency question, and generate a first response result that matches the search result for feedback.

[0083] In this embodiment, if one or more consistency issues are obtained, the historical response results generated by the AI ​​big model for the consistency issues can be retrieved together with the operation and maintenance demand issues in the knowledge base, and then the first response results that are closer to the user's actual needs can be generated for feedback.

[0084] In an optional implementation of this embodiment, searching the knowledge base based on the operation and maintenance requirement question and the historical response results corresponding to each consistency question, generating a first response result matching the search result for feedback, may include:

[0085] S2401. Search the knowledge base based on the operation and maintenance requirement questions and the historical response results corresponding to each consistency question to obtain target search knowledge.

[0086] S2402: Detect whether the target retrieval knowledge includes multiple branch knowledge determined by a combination of multiple alternative values ​​of multiple target database status information.

[0087] It's understandable that the target knowledge retrieved from a knowledge base might not only be a single piece of explicit knowledge data, but also multiple branches of knowledge based on various assumptions. For example, the target knowledge retrieved for the aforementioned "database backup frequency recommendations" might include: "Backup frequency recommendations in high-concurrency scenarios...", "Backup frequency recommendations in low-latency scenarios...", "Backup recommendations under high storage costs...", and so on.

[0088] Accordingly, the target database state information can be understood as a hypothesis entry in the hypothesis conditions corresponding to the branch knowledge, and each hypothesis entry can correspond to one or more alternative values. For example, the target database state information can include a database operating scenario, and the alternative values ​​corresponding to the database operating scenario can include: high concurrency scenario and low latency scenario. Alternatively, the target database state information can also include: database storage cost, and the alternative values ​​corresponding to the database storage cost can include: high, medium, and low.

[0089] By extracting the target database state information from the target retrieval knowledge, the target retrieval knowledge can be split into multiple branches of knowledge corresponding to specific assumptions. For example, branch knowledge 1 is when target database state information 1 = value a1 and target database state information 2 = value b1; branch knowledge 2 is when target database state information 1 = value a2 and target database state information 2 = value b2, and so on.

[0090] S2403: If yes, when the amount of branch knowledge is greater than or equal to a preset threshold, construct a value acquisition problem corresponding to the multiple target database state information, and provide user feedback on the value acquisition problem.

[0091] It is understandable that if the number of branches of knowledge ultimately split out is not too large, such as 2-4, the first response result can be directly constructed based on the above branches of knowledge for feedback. However, when the number of branches of knowledge ultimately split out is too large, it will be very difficult for users to extract the knowledge they actually need from the large amount of branches of knowledge. In this case, the user can be further asked about the values ​​they consider for each target database status information in the actual database scenario. Then, the AI ​​dialogue robot can effectively screen the large amount of branches of knowledge.

[0092] For example, a value acquisition question such as "Is the database backup scenario applicable to a high-concurrency scenario or a low-latency scenario" can be constructed, and the value acquisition question can be provided to users for feedback.

[0093] S2404, according to the target value provided by the user for the value acquisition question, the branch knowledge contained in the target retrieval knowledge is screened, and the screened target branch knowledge is fed back as the first response result.

[0094] S250, only according to the operation and maintenance demand question, the knowledge base is searched, and the first response result matched with the search result is generated and fed back.

[0095] S260, the real-time running data of the plurality of monitoring indexes in the database is obtained from the database monitoring module, and at least one candidate monitoring index is screened from the monitoring indexes according to the historical running trend data of each monitoring index.

[0096] In this embodiment, when the user's intention is to acquire the actual operation and maintenance scene knowledge, the real-time running data of the plurality of monitoring indexes in the database can be obtained from the database monitoring module. The monitoring index can be understood as a parameter that affects the performance of the database during the running of the database, for example, CPU usage, memory occupancy, network bandwidth, and number of requests per unit time.

[0097] By comparing the real-time running data of the above-mentioned monitoring indexes with the matched historical running trend data, the monitoring indexes whose running state fluctuates (or deviates from the average running level) can be obtained, and these monitoring indexes are screened as candidate monitoring indexes.

[0098] S270, each candidate monitoring index is matched with the operation and maintenance demand question, and a target monitoring index is screened from each candidate monitoring index according to the matching result.

[0099] In an optional implementation of this embodiment, matching each candidate monitoring index with the operation and maintenance demand question and screening a target monitoring index from each candidate monitoring index according to the matching result can include:

[0100] S2701, at least one database state description keyword is extracted from the operation and maintenance demand question.

[0101] The database state description keyword can be understood as a keyword that describes the running state of the current actual database. For example, when the operation and maintenance demand question is "what causes the sudden response request jam of the database, and how to improve it", the database state description keyword "request response jam" can be extracted from the operation and maintenance demand question.

[0102] Optionally, a database state description keyword extraction template can be constructed, or a keyword extraction model can be pre-trained to extract at least one database state description keyword from the operation and maintenance demand question, and this embodiment does not limit this.

[0103] S2702: Match the database state description keyword with a pre-established attribution rule set to obtain at least one state influencing factor that matches the database state description keyword.

[0104] In this embodiment, an attribution rule set can be further established, which stores mappings between different database states and the state influencing factors that affect the database state. For example, the attribution rules in the attribution rule set can be: "Request response delay: CPU usage is too high, the number of requests per unit time is too large;" or "CPU usage is too high: the current limiting policy fails or the current number of parallel threads is too large."

[0105] In this embodiment, by constructing an attribution chain, various state influencing factors that match the database state description keywords can be obtained step by step. For example, the above-mentioned state influencing factors can be obtained through an attribution chain in the form of "request response lag - CPU usage is too high - current limiting strategy failure - balancing server abnormality".

[0106] Optionally, since there may be multiple status influencing factors that affect the status of each database, multiple attribution chains can be constructed by combining the status influencing factors.

[0107] S2703. Screen the candidate monitoring indicators according to the status influencing factors to obtain the target monitoring indicators.

[0108] Furthermore, after obtaining the above-mentioned multiple state influencing factors, each state influencing factor can be compared with the fluctuation or deviation from the normal value of each alternative monitoring indicator, and the alternative monitoring indicator with consistent comparison can be determined as the target monitoring indicator.

[0109] S280: Search the knowledge base based on the real-time operation data of the target monitoring indicators and the operation and maintenance requirements, and generate a second response result that matches the search result for feedback.

[0110] S290. Retrieve an operation and maintenance instruction set that matches the target operation and maintenance task from the knowledge base, and send the operation and maintenance instruction set to the operation and maintenance task execution module in the database operation and maintenance system, so that the operation and maintenance task execution module can arrange and execute the target operation and maintenance task according to the task priority.

[0111] The technical solution of the embodiment of the present invention can provide targeted answers to operation and maintenance demand questions raised by users with general operation and maintenance knowledge acquisition needs in combination with the context, so that the response results are more targeted and have a higher hit rate for the user's actual needs. In addition, for operation and maintenance demand questions raised by users with actual operation and maintenance scenario knowledge acquisition needs, targeted replies can be made in combination with the real-time operation data of the actual database. Through simple one or several interactions, users can quickly locate various sudden problems that occur during the database operation and maintenance process, thereby improving the database exception response speed and effectively improving the database operation and maintenance efficiency.

[0112] Specific application scenarios

[0113] Figure 3 This is an architecture diagram of a database operation and maintenance system applicable to the embodiment of the present invention. Figure 3 As shown, the database operation and maintenance system can specifically include four system elements: an AI conversational robot, a database monitoring module, an operation and maintenance task execution module, and a knowledge base (also called a knowledge database). Each system element is now described from the perspective of the function it implements.

[0114] 1) AI conversational robots:

[0115] Advanced natural language processing technologies, including a deep learning-based semantic understanding model, are employed to better capture the semantic information and contextual relationships within text, enabling efficient and accurate understanding of natural language input from users. This model is trained on a large amount of text data related to database operations, including frequently asked questions, operation and maintenance instructions, and fault reports, to continuously refine its understanding of the language specific to database operations.

[0116] This AI conversational robot is equipped with an intelligent question-and-answer system that not only understands user questions but also generates clear and accurate responses based on the type and complexity of the question. For simple FAQs, such as "How do I view the database version number?", it can quickly retrieve and return answers directly from the knowledge database. For complex questions, such as "Database performance suddenly degraded, possible causes and solutions," it comprehensively analyzes the real-time data provided by the database monitoring module and the relevant empirical knowledge in the knowledge database to provide users with detailed analysis and suggestions. For example, it may be due to the recent rapid growth in data volume, resulting in reduced indexing efficiency, and it is recommended to re-evaluate and optimize the index structure.

[0117] Furthermore, the AI ​​chatbot integrates conversation management capabilities, enabling appropriate interactions based on the context of the conversation. When a user asks a series of related questions, it can remember previous conversations, avoid repeated requests for the same information, and provide coherent solutions. For example, if a user first asks about database backup methods and then asks for backup frequency recommendations, the chatbot will understand that these questions fall within the same operational and maintenance scenario. Based on the previous discussion about backups, it will recommend an appropriate backup frequency and can further inquire about factors such as database usage and data importance to provide more personalized recommendations.

[0118] 2) Database monitoring module:

[0119] From the perspective of the functions realized by the database monitoring module, the database monitoring module can be specifically divided into three software functional sub-modules: real-time data acquisition sub-module, data analysis and processing sub-module, and early warning and notification sub-module.

[0120] 1. Real-time Data Collection Submodule: This module collects database operational data through various methods, including using the database system's built-in monitoring interface to obtain performance metrics such as CPU usage, memory utilization, disk I / O speed, and network bandwidth usage. It also utilizes database log analysis tools to collect database operation logs, error logs, and other information to understand the database's operational history and failure conditions. For example, for relational databases, you can use the provided performance analysis plug-in to obtain detailed performance data and identify potential problems by parsing error log files.

[0121] 2. Data Analysis and Processing Submodule: This module performs real-time analysis and processing of collected data. Data mining algorithms and machine learning techniques, such as cluster analysis and anomaly detection algorithms, are used to analyze performance data and promptly identify anomalies and potential performance bottlenecks. For example, cluster analysis can be used to categorize database performance indicators and identify normal operating and abnormal patterns. When new data points deviate from the normal pattern, anomaly detection algorithms can be used to promptly issue alerts. Furthermore, database operation logs are analyzed to collect statistics on frequently executed queries and operations, providing a basis for optimization. For example, if certain queries are found to be executed too frequently and take too long, optimization may be necessary.

[0122] 3. Warning and Notification Submodule: When anomalies or potential risks are detected in the database, a warning message is promptly sent to the AI ​​conversational robot based on pre-set rules and thresholds. Operations and maintenance personnel can also be notified via various means, such as email, SMS, and system pop-up windows. For example, if the database CPU usage exceeds 80% for 10 consecutive minutes, the operation and maintenance personnel will be notified via email and SMS, and an alert window will pop up on the system interface, prompting them to take prompt action.

[0123] 3) Operation and maintenance task execution module:

[0124] From the perspective of the functions realized by the operation and maintenance task execution module, the database monitoring module can be specifically divided into three software functional sub-modules: task scheduling and management sub-module, operation execution sub-module, and result feedback and verification sub-module.

[0125] 1. Task Scheduling and Management Submodule: This module receives operational and maintenance task instructions from the AI ​​conversational robot module and schedules and manages them appropriately based on factors such as task priority and urgency. For example, urgent database troubleshooting tasks are prioritized, while regular database optimization tasks can be scheduled according to a pre-set schedule. Task execution status and history are also recorded for subsequent auditing and analysis.

[0126] 2. Operation Execution Submodule: This module interacts with the database system to perform specific operation and maintenance tasks. It offers multiple operation execution methods, including calling command-line tools provided by the database management system, executing pre-written scripts, and operating through the database API. For example, when performing a database backup task, the command-line interface of the database backup tool is called, and the corresponding parameters, such as the backup target path and backup mode (full or incremental), are passed in to complete the data backup operation. When optimizing the database, the optimization script is executed to adjust the database's indexes, storage structure, and other aspects.

[0127] 3. Result Feedback and Verification Submodule: After the operation and maintenance task is completed, the execution results are fed back to the AI ​​conversational robot module for display to the user. At the same time, the execution results are verified to ensure the correctness and effectiveness of the task execution. For example, after a database backup is completed, the integrity and availability of the backup file are verified, and data consistency is ensured by comparing the backup file's hash value with the source data's hash value. If a task execution fails or the result does not meet expectations, a retry is performed promptly or appropriate remedial measures are taken, and relevant feedback is provided to the AI ​​conversational robot module and the operation and maintenance personnel.

[0128] 4) Knowledge database (also known as knowledge base):

[0129] The knowledge database uses a combination of relational and document-based databases to store database operation and maintenance knowledge. Relational databases are used to store structured knowledge data, such as solutions to common problems and detailed procedures for operation and maintenance procedures, facilitating precise queries and correlation analysis. Document-based databases are used to store unstructured knowledge, such as articles on operation and maintenance experience and technical documentation, to better preserve the knowledge's original format and context. For example, database fault types, corresponding symptoms, and solutions are stored in a table format in a relational database, while detailed troubleshooting cases and analysis processes are stored in a document-based database.

[0130] Furthermore, database operation and maintenance knowledge and technical developments are updated through data upload, including official database documentation updates, industry technical forums, professional books and journals. New knowledge is screened, organized, and verified before being updated to the knowledge database. Simultaneously, existing knowledge is revised and improved based on actual operation and maintenance experience and user feedback. For example, when a new version of the database system is released and new operation and maintenance features are introduced, relevant information is promptly obtained and updated to the knowledge database to ensure that the knowledge provided to users is up-to-date and accurate.

[0131] Furthermore, this knowledge database provides efficient knowledge retrieval services for AI conversational robots. When the AI ​​conversational robot module needs to query relevant knowledge, it uses keyword matching, semantic similarity calculation, and other techniques based on the user's question and context to quickly retrieve relevant knowledge content from the knowledge database. Simultaneously, based on the user's historical operations and question records, machine learning algorithms are used for analysis to recommend knowledge and solutions that may be of interest to the user, improving operational efficiency and user experience. For example, after a user repeatedly inquires about database performance optimization, the system proactively recommends relevant advanced optimization techniques and the latest industry practice cases.

[0132] Further, such as Figure 3 As shown in the figure, the workflow of the data operation and maintenance method based on the database operation and maintenance system, which is led by the AI ​​dialogue robot, is as follows:

[0133] First, the user sends an operation and maintenance request to the AI ​​conversational robot through an input device (such as a keyboard or voice input device), such as "query the current performance indicators of the database" or "back up the database." After receiving the user's request, the AI ​​conversational robot performs semantic analysis and understanding to determine the user's intent. Then, based on the user's intent, it queries the knowledge database module for relevant solutions or operational instructions. If a specific operation and maintenance task needs to be performed, the AI ​​conversational robot sends the corresponding instruction to the operation and maintenance task execution module. After receiving the instruction, the operation and maintenance task execution module interacts with the database system and performs the corresponding operation, such as querying performance indicators or performing a database backup.

[0134] Meanwhile, the database monitoring module continuously monitors the database's operational status throughout the entire process. If any anomalies are detected, the AI ​​chatbot promptly reports these anomalies to the AI ​​chatbot. Based on these anomalies, the AI ​​chatbot retrieves appropriate solutions from its knowledge database and provides recommendations or automatically takes appropriate action. Finally, the AI ​​chatbot provides the user with operational and maintenance results or related information, allowing them to perform further operations or inquire based on these responses.

[0135] Through the above implementation, the technical solution of the embodiment of the present invention brings the following beneficial effects:

[0136] 1) Improved Operation and Maintenance Efficiency: Automated operation and maintenance tasks and rapid problem response significantly shorten operation and maintenance time and improve work efficiency. AI conversational robots can process user requests in real time, eliminating the need for human input and can handle multiple operation and maintenance tasks simultaneously, effectively improving overall operation and maintenance efficiency.

[0137] 2) Provide convenient operation and maintenance methods: Users can complete various complex database operation and maintenance operations by simply interacting with the AI ​​dialogue robot through simple natural language, without having to master professional database management knowledge and skills. This lowers the threshold for operation and maintenance work and improves the user experience.

[0138] 3) Reduced Operation and Maintenance Costs: This reduces reliance on manual operation and maintenance, lowering labor costs. Furthermore, the ability to promptly identify and resolve problems avoids business losses caused by failures, indirectly reducing operation and maintenance costs.

[0139] 4) Improved Operation and Maintenance Efficiency: Automated operation and maintenance tasks and rapid problem response significantly shorten operation and maintenance time and improve work efficiency. AI conversational robots can process user requests in real time, eliminating the need for human input and can handle multiple operation and maintenance tasks simultaneously, effectively improving overall operation and maintenance efficiency.

[0140] Example 3

[0141] Figure 4A structural schematic diagram of a database operation and maintenance device provided for Embodiment Three of the present application. The device is configured in an AI dialogue robot in a database operation and maintenance system. As shown in the figure, the device comprises a user intention determination module 410, a first response result feedback module 420, a second response result feedback module 430, and an operation and maintenance instruction set issuing module 440, wherein: Figure 4

[0142] The user intention determination module 410 is configured to determine a user intention matched with the operation and maintenance demand question in response to the operation and maintenance demand question input by the user.

[0143] The first response result feedback module 420 is configured to perform retrieval in the knowledge base according to the operation and maintenance demand question, generate a first response result matched with the retrieval result, and feed back the first response result if the user intention is a general operation and maintenance knowledge acquisition demand.

[0144] The second response result feedback module 430 is configured to acquire real-time running data of the database through a database monitoring module in the database operation and maintenance system, perform retrieval in the knowledge base according to the real-time running data and the operation and maintenance demand question, generate a second response result matched with the retrieval result, and feed back the second response result if the user intention is an actual operation and maintenance scene knowledge acquisition demand.

[0145] The operation and maintenance instruction set issuing module 440 is configured to retrieve an operation and maintenance instruction set matched with the target operation and maintenance task in the knowledge base if the user intention is to execute the target operation and maintenance task, and issue the operation and maintenance instruction set to an operation and maintenance task execution module in the database operation and maintenance system, so that the operation and maintenance task execution module executes the target operation and maintenance task according to the task priority.

[0146] The technical scheme of the embodiment of the present application responds to the operation and maintenance demand question input by the user in the manner of one or more rounds of dialogue between the AI dialogue robot in the database operation and maintenance system and the user, determines a user intention matched with the operation and maintenance demand question, accurately executes an operation and maintenance service matched with the user intention according to different types of user intentions in combination with the database monitoring module, the operation and maintenance task execution module, and the knowledge base included in the database operation and maintenance system, and provides a new database operation and maintenance mode realized based on the AI dialogue mode. The technical scheme of the embodiment of the present application realizes automatic operation and maintenance management of the database, improves operation and maintenance efficiency and accuracy, reduces operation and maintenance cost, and provides a more convenient and efficient working mode for operation and maintenance personnel.

[0147] On the basis of the above-mentioned embodiments, the first response result feedback module 420 can specifically comprise:

[0148] ​a consistency problem detection unit, configured to trace back at least one historical operation and maintenance problem raised by the user based on the time point of sending the operation and maintenance requirement problem, and detect whether there is at least one consistency problem in each historical operation and maintenance problem that belongs to the same operation and maintenance scenario as the operation and maintenance requirement problem;

[0149] The first response result feedback subunit is used to search the knowledge base according to the operation and maintenance demand problem and the historical response results corresponding to each consistency problem, and generate a first response result matching the search result for feedback.

[0150] Based on the above embodiments, the first response result feedback subunit can be specifically used to:

[0151] Search the knowledge base based on the operation and maintenance requirements and the historical response results corresponding to each consistency issue to obtain the target retrieval knowledge;

[0152] Detecting whether the target retrieval knowledge contains multiple branch knowledge determined by a combination of multiple alternative values ​​of multiple target database state information;

[0153] If so, when the amount of branch knowledge is greater than or equal to a preset threshold, construct a value acquisition problem corresponding to the multiple target database state information, and provide user feedback on the value acquisition problem;

[0154] According to the target value provided by the user for the value acquisition problem, the branch knowledge contained in the target retrieval knowledge is filtered, and the filtered target branch knowledge is fed back as the first response result.

[0155] Based on the above embodiments, the second response result feedback module 430 may specifically include:

[0156] The candidate monitoring indicator acquisition unit is used to obtain real-time operating data of multiple monitoring indicators in the database from the database monitoring module, and select at least one candidate monitoring indicator from each monitoring indicator based on the historical operating trend data of each monitoring indicator;

[0157] The target monitoring indicator screening unit is used to match each candidate monitoring indicator with the operation and maintenance demand problem, and screen the target monitoring indicator from each candidate monitoring indicator according to the matching result;

[0158] The second response result feedback subunit is used to search the knowledge base according to the real-time operation data of the target monitoring indicators and the operation and maintenance demand issues, and generate a second response result that matches the search result for feedback.

[0159] Based on the above embodiments, the target monitoring indicator screening unit can be specifically used to:

[0160] Extract at least one database status description keyword from the operation and maintenance requirement question;

[0161] Matching the database state description keywords with a pre-established attribution rule set to obtain at least one state influencing factor that matches the database state description keywords;

[0162] The candidate monitoring indicators are screened according to the status influencing factors to obtain the target monitoring indicators.

[0163] Based on the above embodiments, an exception handling module may be further included, which is used to:

[0164] After the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, during the process of the operation and maintenance task execution module executing the operation and maintenance instruction set, if abnormal operation information reported by the database monitoring module is detected, an exception handling strategy matching the abnormal operation information is retrieved from the knowledge base;

[0165] According to the execution level of the exception handling strategy, you can choose to build a processing suggestion that matches the exception handling strategy for user feedback, or choose to directly trigger the execution of the exception handling strategy.

[0166] Based on the above embodiments, a result description information feedback module may be further included, which is used to:

[0167] After the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, when the task execution result feedback for the target operation and maintenance task is received from the operation and maintenance task execution module, result description information is generated according to the task execution result, and the result description information is fed back to the user.

[0168] The database operation and maintenance device provided in the embodiment of the present invention can execute the database operation and maintenance method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0169] In the technical solutions of the embodiments of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information complies with relevant laws and regulations and does not violate public order and good morals. Users are given the option to authorize or deny the collection of personal information. Furthermore, users are provided with a corresponding entry point for agreeing to or denying automated decision-making. If the user chooses to deny, the expert decision-making process begins.

[0170] =

[0171] Example 4

[0172] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0173] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0174] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0175] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as executing the database operation and maintenance method performed by the AI ​​dialogue robot in the database operation and maintenance system as described in any embodiment of the present invention. That is:

[0176] In response to the user inputted operation and maintenance demand question, a user intention matched with the operation and maintenance demand question is determined;

[0177] If the user intention is a general operation and maintenance knowledge acquisition demand, a search is performed in the knowledge base according to the operation and maintenance demand question, a first response result matched with the search result is generated, and the first response result is fed back;

[0178] If the user intention is an actual operation and maintenance scene knowledge acquisition demand, real-time running data of a database is acquired through a database monitoring module in a database operation and maintenance system, a search is performed in the knowledge base according to the real-time running data and the operation and maintenance demand question, a second response result matched with the search result is generated, and the second response result is fed back;

[0179] If the user intention is to execute a target operation and maintenance task, an operation and maintenance instruction set matched with the target operation and maintenance task is searched in the knowledge base, and the operation and maintenance instruction set is issued to an operation and maintenance task execution module in the database operation and maintenance system, so that the operation and maintenance task execution module executes the target operation and maintenance task according to a task priority.

[0180] In some embodiments, the database operation and maintenance method performed by the AI dialogue robot in the database operation and maintenance system as described in any embodiment of the present application can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the database operation and maintenance method performed by the AI dialogue robot in the database operation and maintenance system as described in any embodiment of the present application can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the database operation and maintenance method performed by the AI dialogue robot in the database operation and maintenance system as described in any embodiment of the present application by any other appropriate means (for example, by means of firmware).

[0181] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0182] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented on the computer or other programmable apparatus. The computer programs can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0183] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0184] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0185] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0186] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0187] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0188] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A database operation and maintenance method, characterized in that: The method is executed by an AI dialogue robot in the database operation and maintenance system, and includes: In response to an operation and maintenance requirement question input by a user, determining a user intent that matches the operation and maintenance requirement question; If the user intends to obtain general operation and maintenance knowledge, the knowledge base will be searched according to the operation and maintenance requirements, and the first response result that matches the search result will be generated for feedback; If the user intends to acquire knowledge for actual operation and maintenance scenarios, the database monitoring module in the database operation and maintenance system will be used to obtain real-time operation data of the database, and the knowledge base will be searched based on the real-time operation data and operation and maintenance requirements. A second response result matching the search result will be generated for feedback. If the user intends to execute the target operation and maintenance task, the operation and maintenance instruction set that matches the target operation and maintenance task will be retrieved from the knowledge base, and the operation and maintenance instruction set will be sent to the operation and maintenance task execution module in the database operation and maintenance system, so that the operation and maintenance task execution module can arrange and execute the target operation and maintenance task according to the task priority.

2. The method according to claim 1, characterized in that Search the knowledge base based on the operation and maintenance requirements, and generate the first response results that match the search results for feedback, including: Based on the sending time of the operation and maintenance requirement question, trace back at least one historical operation and maintenance question raised by the user, and detect whether there is at least one coherence question in each historical operation and maintenance question that belongs to the same operation and maintenance scenario as the operation and maintenance requirement question; If so, a search is performed in the knowledge base based on the operation and maintenance requirement questions and the historical response results corresponding to each consistency question, and a first response result matching the search result is generated for feedback.

3. The method according to claim 2, characterized in that Search the knowledge base based on the operation and maintenance requirements and the historical response results corresponding to each consistency issue, and generate the first response result that matches the search results for feedback, including: Search the knowledge base based on the operation and maintenance requirements and the historical response results corresponding to each consistency issue to obtain the target retrieval knowledge; Detecting whether the target retrieval knowledge contains multiple branch knowledge determined by a combination of multiple alternative values ​​of multiple target database state information; If so, when the amount of branch knowledge is greater than or equal to a preset threshold, construct a value acquisition problem corresponding to the multiple target database state information, and provide user feedback on the value acquisition problem; According to the target value provided by the user for the value acquisition problem, the branch knowledge contained in the target retrieval knowledge is filtered, and the filtered target branch knowledge is fed back as the first response result.

4. The method according to claim 1, wherein The database monitoring module in the database operation and maintenance system obtains real-time operation data of the database, searches the knowledge base based on the real-time operation data and operation and maintenance requirements, and generates a second response result that matches the search result for feedback, including: Acquire real-time operating data of multiple monitoring indicators in the database from the database monitoring module, and select at least one candidate monitoring indicator from each monitoring indicator based on historical operating trend data of each monitoring indicator; Match each candidate monitoring indicator with the operation and maintenance requirements, and select the target monitoring indicator from the candidate monitoring indicators based on the matching results; According to the real-time operation data of the target monitoring indicators and the operation and maintenance requirements, the knowledge base is searched and a second response result matching the search result is generated for feedback.

5. The method according to claim 4, characterized in that Match each candidate monitoring indicator with the operation and maintenance requirements, and select the target monitoring indicators from the candidate monitoring indicators based on the matching results, including: Extract at least one database status description keyword from the operation and maintenance requirement question; Matching the database state description keywords with a pre-established attribution rule set to obtain at least one state influencing factor that matches the database state description keywords; The candidate monitoring indicators are screened according to the status influencing factors to obtain the target monitoring indicators.

6. The method according to any one of claims 1 to 5, characterized in that After the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, the following steps are also included: During the process of the operation and maintenance task execution module executing the operation and maintenance instruction set, if abnormal operation information reported by the database monitoring module is detected, an abnormality handling strategy matching the abnormal operation information is retrieved from the knowledge base; According to the execution level of the exception handling strategy, you can choose to build a processing suggestion that matches the exception handling strategy for user feedback, or choose to directly trigger the execution of the exception handling strategy.

7. The method according to any one of claims 1 to 5, characterized in that After the operation and maintenance instruction set is sent to the operation and maintenance task execution module in the database operation and maintenance system, the following steps are also included: When receiving the task execution result fed back by the operation and maintenance task execution module for the target operation and maintenance task, result description information is generated according to the task execution result, and the result description information is fed back to the user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the database operation and maintenance method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the database operation and maintenance method according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the database operation and maintenance method according to any one of claims 1 to 7.

Images