WO2021232567A1 - Ai technology-based smart operation and maintenance knowledge analysis method - Google Patents

Ai technology-based smart operation and maintenance knowledge analysis method Download PDF

Info

Publication number
WO2021232567A1
WO2021232567A1 PCT/CN2020/102157 CN2020102157W WO2021232567A1 WO 2021232567 A1 WO2021232567 A1 WO 2021232567A1 CN 2020102157 W CN2020102157 W CN 2020102157W WO 2021232567 A1 WO2021232567 A1 WO 2021232567A1
Authority
WO
WIPO (PCT)
Prior art keywords
maintenance
analysis
data
fault
knowledge
Prior art date
Application number
PCT/CN2020/102157
Other languages
French (fr)
Chinese (zh)
Inventor
陈俊桦
夏鸣
吴雪峰
Original Assignee
江苏南工科技集团有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 江苏南工科技集团有限公司 filed Critical 江苏南工科技集团有限公司
Publication of WO2021232567A1 publication Critical patent/WO2021232567A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G06F16/243—Natural language query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Definitions

  • the invention relates to the technical field of operation and maintenance management, in particular to a method for analyzing intelligent operation and maintenance knowledge based on AI technology.
  • Operation and maintenance usually refers to the Internet operation and maintenance, which belongs to the technical department. It is essentially the operation and maintenance of each stage of the life cycle of the network, server, and service. It has reached a consensus and acceptable state in terms of cost, stability, and efficiency.
  • the current operation The maintenance method is performed by the operation and maintenance personnel after discovering the abnormal operation and resource consumption of the service, and then manually analyze and deal with it.
  • In the operation and maintenance management there are often many repeated faults, and these faults can be dealt with through a fixed solution. Manually handling these repetitive faults each time greatly wastes the time of operation and maintenance personnel and reduces the processing efficiency. For this reason, we propose a smart operation and maintenance knowledge analysis method based on AI technology to solve the above problems.
  • the purpose of the present invention is to provide a smart operation and maintenance knowledge analysis method based on AI technology to solve the problems raised in the background art.
  • an AI technology-based intelligent operation and maintenance knowledge analysis method including the following steps:
  • the AI analysis engine generates a fault handling plan, and feeds the handling plan back to the knowledge base, enriching knowledge base data;
  • the execution unit executes the operation and maintenance process according to the fault handling plan
  • step S1 the monitoring system continuously collects real-time load data of the device through collection devices such as sensors, and judges whether the device is overloaded according to the device load threshold.
  • the knowledge base includes a fault database, a solution database, a collection module, and a judgment module.
  • the fault data in the fault database corresponds to the solution data in the solution database, so
  • the collection module is used to collect the fault information and solutions processed by the operation and maintenance personnel in the past, and the judgment module determines whether the identified fault data is consistent with the implementation of the solution.
  • the AI analysis engine is connected to a manual intervention system, and the manual intervention system includes a display and an input unit for detecting the rationality of the processing plan generated by the AI analysis engine , And can actively input processing instructions through the input unit or make a selection of multiple processing schemes.
  • the AI analysis engine includes an analysis unit model for analyzing the fault data and selecting a processing plan based on the data stored in the knowledge base.
  • the method for generating the analysis unit model is as follows: constructing AI Learning framework, using historical manual operation and maintenance data as the training set of the AI learning framework to train the machine learning framework to obtain the analysis unit model, and use the parsed solution text and the answer corresponding to the input text before analysis as the AI learning.
  • the training set of the framework trains the AI learning framework and improves the analytical unit model.
  • the answer is corrected according to the statistical probability and the feedback mechanism.
  • the number of times the answer is selected is obtained, and the answer is determined.
  • the answer that has been selected the most times is the standard answer, which is stored in the analytical unit model and the knowledge base.
  • the AI analysis engine further includes a storage unit and an update training unit, the storage unit is used to store the parsed input text and answers corresponding to the fault data, and the update training unit is used to use the parsed input text The input text and answers of the analytic unit model are trained.
  • the present invention has the beneficial effects of establishing an AI analysis engine and a knowledge base, collecting the operation and maintenance data of the past operation and maintenance personnel through the analytical unit model, and performing fault data and processing solutions through the knowledge base.
  • the AI analysis engine analyzes the fault information, and then selects the corresponding processing plan from the database according to the analysis result, which greatly saves the workload of the operation and maintenance personnel, and the processing when repeated faults occur Efficiency is improved.
  • FIG. 1 is a flowchart of the present invention
  • Figure 2 is a block diagram of the knowledge base structure in the present invention.
  • an AI technology-based intelligent operation and maintenance knowledge analysis method including the following steps:
  • the AI analysis engine generates a fault handling plan, and feeds the handling plan back to the knowledge base, enriching knowledge base data;
  • the execution unit executes the operation and maintenance process according to the fault handling plan
  • step S1 the monitoring system continuously collects real-time load data of the device through collection devices such as sensors, and judges whether the device is overloaded according to the device load threshold.
  • the knowledge base includes a fault database, a solution database, a collection module, and a judgment module.
  • the fault data in the fault database corresponds to the solution data in the solution database, and the collection module is used to compare
  • the operation and maintenance personnel collects the fault information and plans that have been processed in the past, and the judgment module judges whether the identified fault data is consistent with the plan implementation.
  • the AI analysis engine is connected to the manual intervention system.
  • the manual intervention system includes a display and an input unit for detecting the rationality of the processing scheme generated by the AI analysis engine, and can pass The input unit actively inputs processing instructions or selects the best for multiple processing schemes.
  • the AI analysis engine includes an analysis unit model for analyzing the fault data and selecting a processing plan based on the data stored in the knowledge base.
  • the method for generating the analysis unit model is as follows: construct an AI learning framework to Historical manual operation and maintenance data is used as the training set of the AI learning framework to train the machine learning framework, and the analytical unit model is obtained, and the parsed plan text and the answer corresponding to the input text before the analysis are used as the training set of the AI learning framework to AI
  • the learning framework is trained to improve the analytical unit model.
  • a preferred implementation case is that after the analytical unit model parses the answer, the answer is corrected according to the statistical probability and feedback mechanism.
  • the number of times the answer is selected is obtained, and the number of times the answer is selected is determined to be the most.
  • the answer is the standard answer, which is stored in the analytical unit model and the knowledge base.
  • the AI analysis engine further includes a storage unit and an update training unit.
  • the storage unit is used to store the parsed input text and answers corresponding to the fault data
  • the update training unit is used to use the parsed input text and answer pairs. Analyze the unit model for training.
  • the invention collects the operation and maintenance data of the past operation and maintenance personnel through the analysis unit model by establishing an AI analysis engine and a knowledge base, and corresponds the fault data and the processing plan through the knowledge base, so that when repeated faults occur, the AI
  • the analysis engine analyzes the fault information, and selects the corresponding processing plan from the database according to the analysis result, which greatly saves the workload of operation and maintenance personnel and improves the processing efficiency when repeated faults occur.

Abstract

An AI technology-based smart operation and maintenance knowledge analysis method comprises the following steps: S1, detecting, in real-time and by means of a detection system, an apparatus operation state and load data, and if an apparatus operation failure occurs or a load becomes too large, collecting a failure signal, and transmitting the signal to an AI analysis engine; S2, parsing and analyzing the failure signal by means of the AI analysis engine, and performing, according to a parsing result, a matching operation against operation and maintenance data in a knowledge database; S3, the AI analysis engine generating a failure response solution, and feeding back the response solution to the knowledge database to increase data of the knowledge database; S4, an execution unit performing an operation and maintenance process according to the failure response solution; and S5, generating an operation and maintenance report after the operation and maintenance process is performed. When repeated failures occur, the invention uses the AI analysis engine to analyze failure information, and in turn selects, according to an analysis result, a corresponding response solution from a database, thereby reducing the workload of operation and maintenance staff, and improving response efficiency for repeated failures.

Description

一种基于AI技术的智慧运维知识分析方法A knowledge analysis method for smart operation and maintenance based on AI technology 技术领域Technical field
本发明涉及运维管理技术领域，具体为一种基于AI技术的智慧运维知识分析方法。The invention relates to the technical field of operation and maintenance management, in particular to a method for analyzing intelligent operation and maintenance knowledge based on AI technology.
背景技术Background technique
运维，通常指互联网运维，属于技术部门，本质上是对网络、服务器、服务的生命周期各个阶段的运营与维护，在成本、稳定性、效率上达成一致可接受的状态，目前的运维方式都是通过运维人员发现服务的运行异常和资源消耗情况后，人工进行分析和处理，在运维管理中，常常会出现许多重复的故障，这些故障可以通过固定的处理方案进行处理，每次都通过人工处理这些重复故障大大浪费了运维人员的时间，且降低了处理效率，为此我们提出一种基于AI技术的智慧运维知识分析方法用于解决上述问题。Operation and maintenance, usually refers to the Internet operation and maintenance, which belongs to the technical department. It is essentially the operation and maintenance of each stage of the life cycle of the network, server, and service. It has reached a consensus and acceptable state in terms of cost, stability, and efficiency. The current operation The maintenance method is performed by the operation and maintenance personnel after discovering the abnormal operation and resource consumption of the service, and then manually analyze and deal with it. In the operation and maintenance management, there are often many repeated faults, and these faults can be dealt with through a fixed solution. Manually handling these repetitive faults each time greatly wastes the time of operation and maintenance personnel and reduces the processing efficiency. For this reason, we propose a smart operation and maintenance knowledge analysis method based on AI technology to solve the above problems.
发明内容Summary of the invention
本发明的目的在于提供一种基于AI技术的智慧运维知识分析方法，以解决上述背景技术中提出的问题。The purpose of the present invention is to provide a smart operation and maintenance knowledge analysis method based on AI technology to solve the problems raised in the background art.
为实现上述目的，本发明提供如下技术方案：一种基于AI技术的智慧运维知识分析方法，包括如下步骤：In order to achieve the above objective, the present invention provides the following technical solution: an AI technology-based intelligent operation and maintenance knowledge analysis method, including the following steps:
S1、通过检测系统实时检测设备运行状态和负载数据，当设备运行发生故障或负载过大时，将故障信号收集并传输至AI分析引擎；S1. Real-time detection of equipment operating status and load data through the detection system. When equipment fails or the load is too large, the fault signal is collected and transmitted to the AI analysis engine;
S2、通过AI分析引擎对故障信号进行解析分析，并根据解析结果与知识库内的运维数据相匹配；S2. Analyze the fault signal through the AI analysis engine, and match the analysis result with the operation and maintenance data in the knowledge base;
S3、AI分析引擎生成故障处理方案，并将处理方案反向回馈至知识库，丰 富知识库数据；S3. The AI analysis engine generates a fault handling plan, and feeds the handling plan back to the knowledge base, enriching knowledge base data;
S4、执行单元根据故障处理方案执行运维流程；S4. The execution unit executes the operation and maintenance process according to the fault handling plan;
S5、执行运维流程后生成运维报告。S5. Generate an operation and maintenance report after executing the operation and maintenance process.
优选的一种实施案例，步骤S1中，所述监测系统通过传感器等采集设备不间断收集设备实时的负载数据，并根据设备负载阈值判断设备是否超负载运行。In a preferred implementation case, in step S1, the monitoring system continuously collects real-time load data of the device through collection devices such as sensors, and judges whether the device is overloaded according to the device load threshold.
优选的一种实施案例，步骤S2和步骤S3中，所述知识库包括故障数据库、方案数据库、收集模块和判断模块，所述故障数据库内的故障数据与方案数据库内的方案数据相互对应，所述收集模块用于对运维人员过往处理的故障信息和方案进行收集，所述判断模块判断识别故障数据与方案实施是否一致。In a preferred implementation case, in step S2 and step S3, the knowledge base includes a fault database, a solution database, a collection module, and a judgment module. The fault data in the fault database corresponds to the solution data in the solution database, so The collection module is used to collect the fault information and solutions processed by the operation and maintenance personnel in the past, and the judgment module determines whether the identified fault data is consistent with the implementation of the solution.
优选的一种实施案例，步骤S2和步骤S3中，所述AI分析引擎连接人工介入系统，所述人工介入系统包括显示器和输入单元，用于对AI分析引擎生成的处理方案进行合理性进行检测，并可通过输入单元主动输入处理指令或对多个处理方案进行择优选择。In a preferred implementation case, in step S2 and step S3, the AI analysis engine is connected to a manual intervention system, and the manual intervention system includes a display and an input unit for detecting the rationality of the processing plan generated by the AI analysis engine , And can actively input processing instructions through the input unit or make a selection of multiple processing schemes.
优选的一种实施案例，步骤S2中，所述AI分析引擎包括解析单元模型，用于对故障数据进行解析并根据知识库内存储数据选取处理方案，所述解析单元模型生成方法如下：构建AI学习框架，以历史人工运维数据作为AI学习框架的训练集对所述机器学习框架进行训练，得到解析单元模型，并以解析后的方案文本和与解析前的输入文本对应的答案作为AI学习框架的训练集对AI学习框架进行训练，提高解析单元模型。In a preferred implementation case, in step S2, the AI analysis engine includes an analysis unit model for analyzing the fault data and selecting a processing plan based on the data stored in the knowledge base. The method for generating the analysis unit model is as follows: constructing AI Learning framework, using historical manual operation and maintenance data as the training set of the AI learning framework to train the machine learning framework to obtain the analysis unit model, and use the parsed solution text and the answer corresponding to the input text before analysis as the AI learning The training set of the framework trains the AI learning framework and improves the analytical unit model.
优选的一种实施案例，所述解析单元模型解析得到答案之后，根据统计概率和反馈机制校正答案，当所述解析后的文本输入得出多个答案时，获取答案被选择的次数，确定所述被选择的次数最多的答案为标准答案，存于解析单元模型和知识库中。In a preferred implementation case, after the analysis unit model obtains the answer, the answer is corrected according to the statistical probability and the feedback mechanism. When multiple answers are obtained from the parsed text input, the number of times the answer is selected is obtained, and the answer is determined. The answer that has been selected the most times is the standard answer, which is stored in the analytical unit model and the knowledge base.
优选的一种实施案例，所述AI分析引擎还包括存储单元和更新训练单元，所述存储单元用于存储故障数据对应的解析后的输入文本和答案，所述更新训练单元用于利用解析后的输入文本和答案对解析单元模型进行训练。In a preferred implementation case, the AI analysis engine further includes a storage unit and an update training unit, the storage unit is used to store the parsed input text and answers corresponding to the fault data, and the update training unit is used to use the parsed input text The input text and answers of the analytic unit model are trained.
与现有技术相比，本发明的有益效果是：通过建立AI分析引擎和知识库，通过解析单元模型对过往运维人员的运维数据进行收集，并通过知识库将故障数据和处理方案进行相互对应，从而在发生重复故障时，通过AI分析引擎分析故障信息，从而根据分析结果从数据库内选取对应处理方案，从而极大的节省了运维人员的工作量，且发生重复故障时的处理效率得到提高。Compared with the prior art, the present invention has the beneficial effects of establishing an AI analysis engine and a knowledge base, collecting the operation and maintenance data of the past operation and maintenance personnel through the analytical unit model, and performing fault data and processing solutions through the knowledge base. Corresponding to each other, so that when repeated faults occur, the AI analysis engine analyzes the fault information, and then selects the corresponding processing plan from the database according to the analysis result, which greatly saves the workload of the operation and maintenance personnel, and the processing when repeated faults occur Efficiency is improved.
附图说明Description of the drawings
图1为本发明流程框图；Figure 1 is a flowchart of the present invention;
图2为本发明中知识库结构框图。Figure 2 is a block diagram of the knowledge base structure in the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
请参阅图1-2，本发明提供一种技术方案：一种基于AI技术的智慧运维知识分析方法，包括如下步骤：Please refer to Figure 1-2, the present invention provides a technical solution: an AI technology-based intelligent operation and maintenance knowledge analysis method, including the following steps:
S1、通过检测系统实时检测设备运行状态和负载数据，当设备运行发生故障或负载过大时，将故障信号收集并传输至AI分析引擎；S1. Real-time detection of equipment operating status and load data through the detection system. When equipment fails or the load is too large, the fault signal is collected and transmitted to the AI analysis engine;
S2、通过AI分析引擎对故障信号进行解析分析，并根据解析结果与知识库内的运维数据相匹配；S2. Analyze the fault signal through the AI analysis engine, and match the analysis result with the operation and maintenance data in the knowledge base;
S3、AI分析引擎生成故障处理方案，并将处理方案反向回馈至知识库，丰 富知识库数据；S3. The AI analysis engine generates a fault handling plan, and feeds the handling plan back to the knowledge base, enriching knowledge base data;
S4、执行单元根据故障处理方案执行运维流程；S4. The execution unit executes the operation and maintenance process according to the fault handling plan;
S5、执行运维流程后生成运维报告。S5. Generate an operation and maintenance report after executing the operation and maintenance process.
优选的一种实施案例，步骤S1中，监测系统通过传感器等采集设备不间断收集设备实时的负载数据，并根据设备负载阈值判断设备是否超负载运行。In a preferred implementation case, in step S1, the monitoring system continuously collects real-time load data of the device through collection devices such as sensors, and judges whether the device is overloaded according to the device load threshold.
优选的一种实施案例，步骤S2和步骤S3中，知识库包括故障数据库、方案数据库、收集模块和判断模块，故障数据库内的故障数据与方案数据库内的方案数据相互对应，收集模块用于对运维人员过往处理的故障信息和方案进行收集，判断模块判断识别故障数据与方案实施是否一致。In a preferred implementation case, in steps S2 and S3, the knowledge base includes a fault database, a solution database, a collection module, and a judgment module. The fault data in the fault database corresponds to the solution data in the solution database, and the collection module is used to compare The operation and maintenance personnel collects the fault information and plans that have been processed in the past, and the judgment module judges whether the identified fault data is consistent with the plan implementation.
优选的一种实施案例，步骤S2和步骤S3中，AI分析引擎连接人工介入系统，人工介入系统包括显示器和输入单元，用于对AI分析引擎生成的处理方案进行合理性进行检测，并可通过输入单元主动输入处理指令或对多个处理方案进行择优选择。In a preferred implementation case, in step S2 and step S3, the AI analysis engine is connected to the manual intervention system. The manual intervention system includes a display and an input unit for detecting the rationality of the processing scheme generated by the AI analysis engine, and can pass The input unit actively inputs processing instructions or selects the best for multiple processing schemes.
优选的一种实施案例，步骤S2中，AI分析引擎包括解析单元模型，用于对故障数据进行解析并根据知识库内存储数据选取处理方案，解析单元模型生成方法如下：构建AI学习框架，以历史人工运维数据作为AI学习框架的训练集对机器学习框架进行训练，得到解析单元模型，并以解析后的方案文本和与解析前的输入文本对应的答案作为AI学习框架的训练集对AI学习框架进行训练，提高解析单元模型。In a preferred implementation case, in step S2, the AI analysis engine includes an analysis unit model for analyzing the fault data and selecting a processing plan based on the data stored in the knowledge base. The method for generating the analysis unit model is as follows: construct an AI learning framework to Historical manual operation and maintenance data is used as the training set of the AI learning framework to train the machine learning framework, and the analytical unit model is obtained, and the parsed plan text and the answer corresponding to the input text before the analysis are used as the training set of the AI learning framework to AI The learning framework is trained to improve the analytical unit model.
优选的一种实施案例，解析单元模型解析得到答案之后，根据统计概率和反馈机制校正答案，当解析后的文本输入得出多个答案时，获取答案被选择的次数，确定被选择的次数最多的答案为标准答案，存于解析单元模型和知识库中。A preferred implementation case is that after the analytical unit model parses the answer, the answer is corrected according to the statistical probability and feedback mechanism. When multiple answers are obtained from the parsed text input, the number of times the answer is selected is obtained, and the number of times the answer is selected is determined to be the most. The answer is the standard answer, which is stored in the analytical unit model and the knowledge base.
优选的一种实施案例，AI分析引擎还包括存储单元和更新训练单元，存储单元用于存储故障数据对应的解析后的输入文本和答案，更新训练单元用于利用解析后的输入文本和答案对解析单元模型进行训练。In a preferred implementation case, the AI analysis engine further includes a storage unit and an update training unit. The storage unit is used to store the parsed input text and answers corresponding to the fault data, and the update training unit is used to use the parsed input text and answer pairs. Analyze the unit model for training.
本发明通过建立AI分析引擎和知识库，通过解析单元模型对过往运维人员的运维数据进行收集，并通过知识库将故障数据和处理方案进行相互对应，从而在发生重复故障时，通过AI分析引擎分析故障信息，从而根据分析结果从数据库内选取对应处理方案，从而极大的节省了运维人员的工作量，且发生重复故障时的处理效率得到提高。The invention collects the operation and maintenance data of the past operation and maintenance personnel through the analysis unit model by establishing an AI analysis engine and a knowledge base, and corresponds the fault data and the processing plan through the knowledge base, so that when repeated faults occur, the AI The analysis engine analyzes the fault information, and selects the corresponding processing plan from the database according to the analysis result, which greatly saves the workload of operation and maintenance personnel and improves the processing efficiency when repeated faults occur.
尽管已经示出和描述了本发明的实施例，对于本领域的普通技术人员而言，可以理解在不脱离本发明的原理和精神的情况下可以对这些实施例进行多种变化、修改、替换和变型，本发明的范围由所附权利要求及其等同物限定。Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, and substitutions can be made to these embodiments without departing from the principle and spirit of the present invention. And variations, the scope of the present invention is defined by the appended claims and their equivalents.

Claims (7)

  1. 一种基于AI技术的智慧运维知识分析方法，其特征在于，包括如下步骤：A method for analyzing intelligent operation and maintenance knowledge based on AI technology, which is characterized in that it includes the following steps:
    S1、通过检测系统实时检测设备运行状态和负载数据，当设备运行发生故障或负载过大时，将故障信号收集并传输至AI分析引擎；S1. Real-time detection of equipment operating status and load data through the detection system. When equipment fails or the load is too large, the fault signal is collected and transmitted to the AI analysis engine;
    S2、通过AI分析引擎对故障信号进行解析分析，并根据解析结果与知识库内的运维数据相匹配；S2. Analyze the fault signal through the AI analysis engine, and match the analysis result with the operation and maintenance data in the knowledge base;
    S3、AI分析引擎生成故障处理方案，并将处理方案反向回馈至知识库，丰富知识库数据；S3. The AI analysis engine generates a fault handling plan, and feeds the handling plan back to the knowledge base to enrich the data of the knowledge base;
    S4、执行单元根据故障处理方案执行运维流程；S4. The execution unit executes the operation and maintenance process according to the fault handling plan;
    S5、执行运维流程后生成运维报告。S5. Generate an operation and maintenance report after executing the operation and maintenance process.
  2. 根据权利要求1所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：步骤S1中，所述监测系统通过传感器等采集设备不间断收集设备实时的负载数据，并根据设备负载阈值判断设备是否超负载运行。The intelligent operation and maintenance knowledge analysis method based on AI technology according to claim 1, characterized in that: in step S1, the monitoring system continuously collects real-time load data of the equipment through collection equipment such as sensors, and according to the equipment load The threshold value determines whether the device is overloaded.
  3. 根据权利要求1所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：步骤S2和步骤S3中，所述知识库包括故障数据库、方案数据库、收集模块和判断模块，所述故障数据库内的故障数据与方案数据库内的方案数据相互对应，所述收集模块用于对运维人员过往处理的故障信息和方案进行收集，所述判断模块判断识别故障数据与方案实施是否一致。An AI technology-based knowledge analysis method for intelligent operation and maintenance according to claim 1, characterized in that: in step S2 and step S3, the knowledge base includes a fault database, a solution database, a collection module, and a judgment module. The fault data in the fault database corresponds to the plan data in the plan database. The collection module is used to collect the fault information and plans processed by the operation and maintenance personnel in the past, and the judgment module judges whether the identified fault data is consistent with the plan implementation.
  4. 根据权利要求1所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：步骤S2和步骤S3中，所述AI分析引擎连接人工介入系统，所述人工介入系统包括显示器和输入单元，用于对AI分析引擎生成的处理方案进行合理性进行检测，并可通过输入单元主动输入处理指令或对多个处理方案进行择优选择。The AI technology-based intelligent operation and maintenance knowledge analysis method according to claim 1, wherein in step S2 and step S3, the AI analysis engine is connected to an artificial intervention system, and the artificial intervention system includes a display and an input The unit is used to check the rationality of the processing plan generated by the AI analysis engine, and can actively input processing instructions through the input unit or make a selection of multiple processing plans.
  5. 根据权利要求1所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：步骤S2中，所述AI分析引擎包括解析单元模型，用于对故障数据进行解析并根据知识库内存储数据选取处理方案，所述解析单元模型生成方法如下：构建AI学习框架，以历史人工运维数据作为AI学习框架的训练集对所述机器学习框架进行训练，得到解析单元模型，并以解析后的方案文本和与解析前的输入文本对应的答案作为AI学习框架的训练集对AI学习框架进行训练，提高解析单元模型。An AI technology-based knowledge analysis method for smart operation and maintenance according to claim 1, wherein in step S2, the AI analysis engine includes an analysis unit model for analyzing fault data and analyzing fault data according to the knowledge base The storage data selection processing scheme, the analytical unit model generation method is as follows: construct an AI learning framework, use historical manual operation and maintenance data as the training set of the AI learning framework to train the machine learning framework to obtain the analytical unit model, and analyze The latter program text and the answer corresponding to the input text before the analysis are used as the training set of the AI learning framework to train the AI learning framework and improve the analysis unit model.
  6. 根据权利要求5所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：所述解析单元模型解析得到答案之后，根据统计概率和反馈机制校正答案，当所述解析后的文本输入得出多个答案时，获取答案被选择的次数，确定所述被选择的次数最多的答案为标准答案，存于解析单元模型和知识库中。The AI technology-based intelligent operation and maintenance knowledge analysis method according to claim 5, characterized in that: after the analysis unit model parses and obtains the answer, the answer is corrected according to the statistical probability and the feedback mechanism, and when the parsed text When multiple answers are obtained by input, the number of times the answer is selected is obtained, and the answer with the most selected times is determined to be the standard answer, which is stored in the analysis unit model and the knowledge base.
  7. 根据权利要求5所述的一种基于AI技术的智慧运维知识分析方法，其特征在于：所述AI分析引擎还包括存储单元和更新训练单元，所述存储单元用于存储故障数据对应的解析后的输入文本和答案，所述更新训练单元用于利用解析后的输入文本和答案对解析单元模型进行训练。The intelligent operation and maintenance knowledge analysis method based on AI technology according to claim 5, characterized in that: the AI analysis engine further comprises a storage unit and an update training unit, and the storage unit is used to store analysis corresponding to the fault data After the input text and answer, the update training unit is used to train the parsing unit model by using the parsed input text and answer.
PCT/CN2020/102157 2020-05-20 2020-07-15 Ai technology-based smart operation and maintenance knowledge analysis method WO2021232567A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010431974.0 2020-05-20
CN202010431974.0A CN111597204A (en) 2020-05-20 2020-05-20 AI technology-based intelligent operation and maintenance knowledge analysis method

Publications (1)

Publication Number Publication Date
WO2021232567A1 true WO2021232567A1 (en) 2021-11-25

Family

ID=72186084

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/102157 WO2021232567A1 (en) 2020-05-20 2020-07-15 Ai technology-based smart operation and maintenance knowledge analysis method

Country Status (2)

Country Link
CN (1) CN111597204A (en)
WO (1) WO2021232567A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115018095A (en) * 2022-05-26 2022-09-06 平安银行股份有限公司 Equipment fault processing method, device, equipment and storage medium
CN116506321A (en) * 2023-04-28 2023-07-28 杭州富阳海康保泰安防技术服务有限公司 Operation and maintenance intelligent terminal based on data analysis
CN116743603A (en) * 2023-08-16 2023-09-12 广州海晟科技有限公司 Safe operation and maintenance method and system for private cloud platform information system
CN116882966A (en) * 2023-06-27 2023-10-13 广州慧云网络科技有限公司 Fault judging method and device for inspection result of operation and maintenance equipment
CN116932148A (en) * 2023-09-19 2023-10-24 山东浪潮数据库技术有限公司 Problem diagnosis system and method based on AI
CN116882966B (en) * 2023-06-27 2024-04-19 广东慧云科技股份有限公司 Fault judging method and device for inspection result of operation and maintenance equipment

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112579391A (en) * 2020-12-14 2021-03-30 浪潮云信息技术股份公司 Distributed database automatic operation and maintenance method and system based on artificial intelligence
CN113591952A (en) * 2021-07-19 2021-11-02 湖南汉拓物联科技有限公司 Artificial intelligence operation and maintenance system and method based on data stream of Internet of things
CN114710391B (en) * 2022-03-22 2023-06-23 中国电子科技集团公司第五十四研究所 Intelligent fault perception analysis processing method suitable for special communication system
CN114637654B (en) * 2022-03-30 2022-12-02 北京国信网联科技有限公司 Fault monitoring and analyzing method based on AIOps intelligent operation center
CN115858324B (en) * 2023-02-02 2023-05-12 北京神州光大科技有限公司 AI-based IT equipment fault processing method, apparatus, equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104679828A (en) * 2015-01-19 2015-06-03 云南电力调度控制中心 Rules-based intelligent system for grid fault diagnosis
CN109218114A (en) * 2018-11-12 2019-01-15 西安微电子技术研究所 A kind of server failure automatic checkout system and detection method based on decision tree
CN109800127A (en) * 2019-01-03 2019-05-24 众安信息技术服务有限公司 A kind of system fault diagnosis intelligence O&M method and system based on machine learning
US20190306011A1 (en) * 2018-03-27 2019-10-03 Cisco Technology, Inc. Deep fusion reasoning engine (dfre) for prioritizing network monitoring alerts
CN110932899A (en) * 2019-11-28 2020-03-27 杭州东方通信软件技术有限公司 Intelligent fault compression research method and system applying AI
WO2020081245A1 (en) * 2018-10-17 2020-04-23 Cisco Technology, Inc. Device health assessment data summarization using machine learning

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5944839A (en) * 1997-03-19 1999-08-31 Symantec Corporation System and method for automatically maintaining a computer system
CN105844416A (en) * 2016-03-28 2016-08-10 国网江苏省电力公司电力科学研究院 Integrated date management system for analyzing fault defects of substation equipment
CN109117959A (en) * 2018-06-20 2019-01-01 中译语通科技（青岛）有限公司 A kind of artificial intelligence automatic recognition system and method based on intelligent operation platform

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104679828A (en) * 2015-01-19 2015-06-03 云南电力调度控制中心 Rules-based intelligent system for grid fault diagnosis
US20190306011A1 (en) * 2018-03-27 2019-10-03 Cisco Technology, Inc. Deep fusion reasoning engine (dfre) for prioritizing network monitoring alerts
WO2020081245A1 (en) * 2018-10-17 2020-04-23 Cisco Technology, Inc. Device health assessment data summarization using machine learning
CN109218114A (en) * 2018-11-12 2019-01-15 西安微电子技术研究所 A kind of server failure automatic checkout system and detection method based on decision tree
CN109800127A (en) * 2019-01-03 2019-05-24 众安信息技术服务有限公司 A kind of system fault diagnosis intelligence O&M method and system based on machine learning
CN110932899A (en) * 2019-11-28 2020-03-27 杭州东方通信软件技术有限公司 Intelligent fault compression research method and system applying AI

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115018095A (en) * 2022-05-26 2022-09-06 平安银行股份有限公司 Equipment fault processing method, device, equipment and storage medium
CN116506321A (en) * 2023-04-28 2023-07-28 杭州富阳海康保泰安防技术服务有限公司 Operation and maintenance intelligent terminal based on data analysis
CN116506321B (en) * 2023-04-28 2023-11-24 杭州富阳海康保泰安防技术服务有限公司 Operation and maintenance intelligent terminal based on data analysis
CN116882966A (en) * 2023-06-27 2023-10-13 广州慧云网络科技有限公司 Fault judging method and device for inspection result of operation and maintenance equipment
CN116882966B (en) * 2023-06-27 2024-04-19 广东慧云科技股份有限公司 Fault judging method and device for inspection result of operation and maintenance equipment
CN116743603A (en) * 2023-08-16 2023-09-12 广州海晟科技有限公司 Safe operation and maintenance method and system for private cloud platform information system
CN116743603B (en) * 2023-08-16 2023-10-20 广州海晟科技有限公司 Safe operation and maintenance method and system for private cloud platform information system
CN116932148A (en) * 2023-09-19 2023-10-24 山东浪潮数据库技术有限公司 Problem diagnosis system and method based on AI
CN116932148B (en) * 2023-09-19 2024-01-19 山东浪潮数据库技术有限公司 Problem diagnosis system and method based on AI
CN117764422B (en) * 2024-02-22 2024-04-26 北京洁禹通环保科技有限公司 Intelligent energy-saving operation and maintenance management cloud platform

Also Published As

Publication number Publication date
CN111597204A (en) 2020-08-28

Similar Documents

Publication Publication Date Title
WO2021232567A1 (en) Ai technology-based smart operation and maintenance knowledge analysis method
CN111047082B (en) Early warning method and device of equipment, storage medium and electronic device
CN111209131A (en) Method and system for determining fault of heterogeneous system based on machine learning
CN109501834B (en) Method and device for predicting fault of turnout switch machine
CN103062862A (en) Remote fault processing method for intelligent air conditioner
CN110674189A (en) Method for monitoring secondary state and positioning fault of intelligent substation
CN110825768B (en) Remote television exception handling method and system based on cloud analysis
CN110865924B (en) Health degree diagnosis method and health diagnosis framework for internal server of power information system
US11714403B2 (en) Method for learning and detecting abnormal part of device through artificial intelligence
CN102147816A (en) System for counting cases and analyzing tendency
CN108959037A (en) A kind of data center's automatic detecting method and device
KR20220073314A (en) A System and Method for Monitoring Manufacturing Process
CN104794771B (en) One kind patrols inspection automatic planning and a device
CN114647525A (en) Diagnostic method, diagnostic device, terminal and storage medium
CN111767193A (en) Server data anomaly detection method and device, storage medium and equipment
CN112084220A (en) Method and device for diagnosing abnormity of electric energy metering device and readable storage medium
CN113157521B (en) Monitoring method and monitoring system for block chain full life cycle
CN112803587A (en) Intelligent inspection method for state of automatic equipment based on diagnosis decision library
CN105072056A (en) Switch automatic inspection system and inspection method thereof
CN112269673A (en) Intelligent operation and maintenance management system and method for data center
Avolio et al. Applications of advanced data analysis and expert system technologies in the ATLAS Trigger-DAQ Controls framework
CN116861189A (en) Method for constructing equipment fault diagnosis maintenance knowledge base based on large language model
CN116448234A (en) Power transformer running state voiceprint monitoring method and system
CN115222181B (en) Robot operation state monitoring system and method
CN116150692A (en) Power grid fault diagnosis method and system based on cloud platform and improved isolated forest

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20936765

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20936765

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20936765

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC 29.06.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20936765

Country of ref document: EP

Kind code of ref document: A1