WO2021143483A1 - System maintenance method and apparatus, device, and storage medium - Google Patents

Abstract

The present application provides a system maintenance method and apparatus, a device, and a storage medium. The system maintenance method comprises: acquiring real-time operation data of a system; under the condition that a system maintenance condition is satisfied, determining a maintenance operation instruction on the basis of the acquired first operation data and a preset decision model; and executing the maintenance operation instruction, wherein the maintenance operation instruction being used for instructing the system to perform health maintenance.

Description

Translated fromChinese

系统维护方法、装置、设备和存储介质System maintenance method, device, equipment and storage medium

本申请要求在2020年01月17日提交中国专利局、申请号为202010054511.7的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office with an application number of 202010054511.7 on January 17, 2020. The entire content of this application is incorporated into this application by reference.

技术领域Technical field

本申请涉及无线通信系统技术领域，例如涉及一种系统维护方法、装置、设备和存储介质。This application relates to the technical field of wireless communication systems, for example, to a system maintenance method, device, equipment, and storage medium.

背景技术Background technique

移动通信技术已经进入了第五代移动通信技术(The 5th Generation Mobile Communication Technology，5G)时代，5G系统的自动化管理是网络管理功能的一个重要需求。然而，如何实现5G系统的自动化管理和维护是一个亟待解决的问题。Mobile communication technology has entered the era of the 5th Generation Mobile Communication Technology (5G), and the automated management of 5G systems is an important requirement for network management functions. However, how to realize the automated management and maintenance of the 5G system is an urgent problem to be solved.

发明内容Summary of the invention

本申请提供用于系统维护方法、装置、系统和存储介质。This application provides methods, devices, systems, and storage media for system maintenance.

提供一种系统维护方法，包括：Provide a system maintenance method, including:

采集系统实时运行数据；Collect real-time operating data of the system;

在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；When the system maintenance conditions are met, the maintenance operation instruction is determined based on the collected first operation data and the preset decision model;

执行所述维护操作指令，其中，所述操作指令用于指示系统进行健康维护。Execute the maintenance operation instruction, wherein the operation instruction is used to instruct the system to perform health maintenance.

还提供一种系统维护装置，包括：A system maintenance device is also provided, including:

采集模块，被配置为采集系统实时运行数据；The acquisition module is configured to collect real-time operating data of the system;

确定模块，被配置为在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；The determining module is configured to determine the maintenance operation instruction based on the collected first operating data and the preset decision model when the system maintenance conditions are met;

执行模块，被配置为执行所述维护操作指令。The execution module is configured to execute the maintenance operation instruction.

还提供一种设备，包括：A device is also provided, including:

一个或多个处理器；One or more processors;

存储器，用于存储一个或多个程序；Memory, used to store one or more programs;

当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多 个处理器实现如本申请实施例中的任意一种方法。When the one or more programs are executed by the one or more processors, the one or more processors implement any method as in the embodiments of the present application.

还提供了一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本申请实施例中的任意一种方法。A storage medium is also provided, the storage medium stores a computer program, and when the computer program is executed by a processor, any one of the methods in the embodiments of the present application is implemented.

附图说明Description of the drawings

图1是本申请提供的3GPP网络自动化总体框架的结构示意图；Figure 1 is a schematic structural diagram of the overall framework of 3GPP network automation provided by this application;

图2为本申请提供的一种系统维护方法的流程示意图；Figure 2 is a schematic flowchart of a system maintenance method provided by this application;

图3是本申请提供的一种系统健康维护方法的流程图；Figure 3 is a flowchart of a system health maintenance method provided by the present application;

图4是本申请提供的一种系统健康维护方法的流程图；Figure 4 is a flowchart of a system health maintenance method provided by the present application;

图5为本申请提供的一种系统维护装置的结构示意图；FIG. 5 is a schematic structural diagram of a system maintenance device provided by this application;

图6是本申请实施例提供的一种设备的结构示意图。Fig. 6 is a schematic structural diagram of a device provided by an embodiment of the present application.

具体实施方式Detailed ways

下文中将结合附图对本申请的实施例进行详细说明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互任意组合。Hereinafter, the embodiments of the present application will be described in detail with reference to the accompanying drawings. It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other arbitrarily if there is no conflict.

在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行。并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。The steps shown in the flowcharts of the drawings may be executed in a computer system such as a set of computer-executable instructions. And, although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.

移动通信技术已经进入了5G时代，而网络切片(Network Slice)是5G的一个重要组成部分。所述网络切片，主要是指由一组网络功能组成的具有特定的网络特性的实例化的完整的逻辑网络，该逻辑网络用于满足某一类特定网络业务的需求。所述网络特性的例子有超低延时、超高可靠性等。其中，所述网络功能包括支持该网络功能的网络资源。Mobile communication technology has entered the 5G era, and Network Slice is an important part of 5G. The network slicing mainly refers to an instantiated complete logical network with specific network characteristics composed of a set of network functions, and the logical network is used to meet the requirements of a certain type of specific network service. Examples of the network characteristics include ultra-low latency, ultra-high reliability, and so on. Wherein, the network function includes network resources supporting the network function.

当一个网络切片比较复杂时，为了便于管理，网络切片可以分解为子切片(Network Slice Subnet)，子切片是指一组网络功能及支持所述网络功能的网络资源组成的具有特定的网络特性的一个逻辑网络。一个网络切片可以包含0个、1个或多个子切片。对于子切片的管理和编排，由子切片管理功能(Network Slice Subnet Management Function，NSSMF)完成。NSSMF根据子切片蓝图的定义完成子切片的实例化及其生命周期的控制管理。When a network slice is more complex, in order to facilitate management, the network slice can be decomposed into sub-slices (Network Slice Subnet), a sub-slice refers to a group of network functions and network resources that support the network functions and have specific network characteristics. A logical network. A network slice can contain zero, one, or multiple sub-slices. For the management and arrangement of sub-slices, the sub-slice management function (Network Slice Subnet Management Function, NSSMF) is completed. NSSMF completes the instantiation of the sub-slice and the control and management of its life cycle according to the definition of the sub-slice blueprint.

在5G技术中，5G网络管理自动化是非常重要的一个网络管理功能的需求，网络管理自动化相关技术，主要包括自组织网络(Self-Organized Nerwork，SON)、意图驱动网络等。在5G网络系统中，还会引入人工智能(Artificial Intelligence，AI)技术及大数据技术。基于上述技术，5G网络系统将具有智能分析及决策能力，如果智能分析及决策结果能够被自动执行，则基本实现5G网络的自动化管理。In 5G technology, 5G network management automation is a very important requirement for network management functions. Network management automation related technologies mainly include self-organized networks (Self-Organized Nerwork, SON), intent-driven networks, etc. In the 5G network system, artificial intelligence (AI) technology and big data technology will also be introduced. Based on the above technology, the 5G network system will have intelligent analysis and decision-making capabilities. If the results of intelligent analysis and decision-making can be automatically executed, the automatic management of the 5G network will basically be realized.

欧洲电信标准化研究所(European Telecommunications Standards Institute，ETSI)进行了自动化管理的研究，其给出了一个自动化闭环管理系统，所述闭环管理系统包括数据采集、数据分析、基于数据分析及人工智能的决策、决策结果的执行。而在第三代合作伙伴项目(the 3rd Generation Partnership Project，3GPP)的研究中，也体现了数据分析对于系统自动化管理和运行的重要性。因此，在3GPP中也提出了网络数据分析功能(Network data analytics function，NWDAF)和管理数据分析功能(Management data analytics function，MDAF)的概念，并研究如何利用上述功能进行系统性能优化、故障排除、系统资源预测等。The European Telecommunications Standards Institute (ETSI) has conducted research on automated management, and it provides an automated closed-loop management system that includes data collection, data analysis, and decision-making based on data analysis and artificial intelligence , Implementation of decision-making results. In the 3rd Generation Partnership Project (the 3rd Generation Partnership Project, 3GPP) research, it also reflects the importance of data analysis for the automated management and operation of the system. Therefore, in 3GPP, the concepts of network data analysis function (NWDAF) and management data analysis function (MDAF) are also proposed, and how to use the above functions to optimize system performance, troubleshoot, System resource prediction, etc.

图1是本申请提供的3GPP网络自动化总体框架的结构示意图；如图1所示，NWDAF能够从运营商操作维护管理(Operation Administration and Maintenance，OAM)、应用层功能(Application Function，AF)和3GPP网络功能中采集数据。对于OAM数据的采集，NWDAF可以复用3GPP定义的现有机制和接口。AF可以根据网络部署情况，通过网络暴露功能(Network Exposure Function，NEF)与NWDAF进行信息交互，或者使用基于业务的接口直接访问NWDAF。NWDAF可以从数据存储库访问网络数据，如统一数据库(Unified Data Repository，UDR)。对于3GPP的NF，NWDAF利用基于3GPP定义的业务的接口通信获取网络数据。基于上述数据采集，NWDAF进行数据分析，并将数据分析结果提供给3GPP中的网络功能NF、AF和OAM。Figure 1 is a schematic structural diagram of the overall framework of 3GPP network automation provided by this application; as shown in Figure 1, NWDAF can operate and maintain from operators (Operation Administration and Maintenance, OAM), application layer functions (Application Function, AF) and 3GPP Collect data in the network function. For OAM data collection, NWDAF can reuse existing mechanisms and interfaces defined by 3GPP. AF can exchange information with NWDAF through the Network Exposure Function (NEF) according to the network deployment situation, or directly access NWDAF using a service-based interface. NWDAF can access network data from data repositories, such as Unified Data Repository (UDR). For the 3GPP NF, NWDAF uses the interface communication based on the service defined by 3GPP to obtain network data. Based on the above data collection, NWDAF performs data analysis and provides the data analysis results to the network functions NF, AF, and OAM in 3GPP.

其中主要的3GPP的网络功能(Network Function，NF)包括但不限于下列各种网络功能类型：The main 3GPP network functions (Network Function, NF) include but are not limited to the following types of network functions:

接入管理功能(Access Management Function，AMF)属于核心网内的公共控制面功能，终结所有用户与网络之间的非接入层(Non-Access-Stratum，NAS)消息，负责用户移动性管理，用户设备(User Equipment，UE)状态(如可达性)管理等。Access Management Function (AMF) is a common control plane function in the core network, terminating all non-access-stratum (NAS) messages between users and the network, and is responsible for user mobility management, User equipment (User Equipment, UE) status (such as reachability) management, etc.

会话管理功能(Session Management Function，SMF)，负责会话建立、修改、删除，控制策略控制功能(Policy Control Function，PCF)收费和策略的执行等功能。Session Management Function (SMF), responsible for session establishment, modification, deletion, control policy control function (Policy Control Function, PCF) charging and policy execution functions.

PCF负责根据用户的签约、UE当前的位置、应用相关的信息为终端制定策略，包括路由策略、服务质量策略、计费策略等。The PCF is responsible for formulating strategies for the terminal according to the user's contract, the current location of the UE, and application-related information, including routing strategies, service quality strategies, and charging strategies.

统一数据管理功能(Unified Data Management，UDM)具有统一数据管理功能，用户签约数据的永久存放等功能；The unified data management function (Unified Data Management, UDM) has functions such as unified data management and permanent storage of user contract data;

UDR主要用于存储UDM和PCF管理的用户签约数据、策略数据等。UDR is mainly used to store user subscription data and policy data managed by UDM and PCF.

用户平面功能(User Plane Function，UPF)属于核心网内用户面的功能，是核心网用户面的锚点，是与外部网络(Data Network，DN)数据传输的接口，执行用户面部分PCF策略规则的执行等。User Plane Function (UPF) belongs to the function of the user plane in the core network, is the anchor point of the user plane of the core network, is the data transmission interface with the external network (Data Network, DN), and executes the user plane part of the PCF policy rules The implementation of etc.

NEF用于暴露3GPP网络功能(network functions，NFs)的能力和事件给其他NF或者外部应用AF，提供AF预配置3GPP NFs能力，实现3GPP网络和外部网络信息映射等。NEF is used to expose 3GPP network functions (network functions, NFs) capabilities and events to other NFs or external applications AF, provide AF pre-configured 3GPP NFs capabilities, and implement 3GPP network and external network information mapping.

AF指接入3GPP的应用。AF refers to applications that access 3GPP.

网络存储功能(Network Repository Function，NRF)维护NF文件夹(NF文件夹包括NF实体和其所支持的业务描述)，支持业务发现功能等。The network storage function (Network Repository Function, NRF) maintains the NF folder (the NF folder includes the NF entity and the service description it supports), and supports the service discovery function.

NWDAF支持从NF、AF、OAM收集数据，业务注册和元数据暴露给NF和/或AF，分析结果暴露给NF和/或AF和/或OAM；NWDAF supports data collection from NF, AF, and OAM, business registration and metadata are exposed to NF and/or AF, and analysis results are exposed to NF and/or AF and/or OAM;

OAM可以是核心网的OAM，和/或接入网(Radio Access Network，RAN)的OAM。The OAM may be the OAM of the core network and/or the OAM of the access network (Radio Access Network, RAN).

在实际应用中，利用网络数据分析功能和管理数据分析功能，还可以进行故障的预测和预防，即通过对系统性能、故障相关数据的分析，可以预测可能发生故障的网络功能，并提出解除故障隐患的操作建议或操作指令，通过执行相关操作指令，可以有效解除故障隐患，提高系统的健壮性。In practical applications, the use of network data analysis functions and management data analysis functions can also be used to predict and prevent failures, that is, through the analysis of system performance and failure-related data, network functions that may malfunction can be predicted and proposed to resolve the failure Operating suggestions or operating instructions for hidden dangers can effectively eliminate hidden troubles and improve the robustness of the system by executing relevant operating instructions.

图2为本申请提供的一种系统维护方法的流程示意图。该方法可以适用于对5G网络系统中的故障进行预测，并有效解除故障隐患的情况。该方法可以由本申请提供的系统维护装置来执行，该系统维护装置可以由软件和/或硬件实现。Fig. 2 is a schematic flowchart of a system maintenance method provided by this application. This method can be suitable for predicting the fault in the 5G network system and effectively removing the hidden trouble of the fault. The method can be executed by the system maintenance device provided by the present application, and the system maintenance device can be implemented by software and/or hardware.

如图2所示，本申请实施例提供的系统维护方法主要包括步骤S21、S22和S23。As shown in Figure 2, the system maintenance method provided by the embodiment of the present application mainly includes steps S21, S22, and S23.

S21、采集系统实时运行数据。S21. Collect real-time operating data of the system.

S22、在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令。S22. When the system maintenance condition is satisfied, the maintenance operation instruction is determined based on the collected first operation data and the preset decision model.

S23、执行所述维护操作指令，其中，所述操作指令用于指示系统进行健康维护。S23. Execute the maintenance operation instruction, where the operation instruction is used to instruct the system to perform health maintenance.

在本实施例中，通过NWDAF持续采集系统实时运行数据。NWDAF能够从运营商OAM、AF和3GPP网络功能中采集数据。对于OAM数据的采集，NWDAF可以复用3GPP定义的现有机制和接口。NWDAF还可以从数据存储库访问系统运行数据，如统一数据库(Unified Data Repository，UDR)。对于3GPP的NF，NWDAF利用基于3GPP定义的业务的接口通信获取网络数据。In this embodiment, real-time operating data of the system is continuously collected through NWDAF. NWDAF can collect data from operators' OAM, AF and 3GPP network functions. For OAM data collection, NWDAF can reuse existing mechanisms and interfaces defined by 3GPP. NWDAF can also access system operating data from a data repository, such as a unified database (Unified Data Repository, UDR). For the 3GPP NF, NWDAF uses the interface communication based on the service defined by 3GPP to obtain network data.

需要说明的是，本实施例进行系统运行数据采集的方式进行说明，而非限定，可以根据实际情况选择或者设计其他运行数据采集方式。It should be noted that the method of collecting system operation data in this embodiment is described without limitation, and other operation data collection methods can be selected or designed according to actual conditions.

在另一个实施例中，通过管理数据分析功能MDAF持续采集系统实时运行数据。MDAF还可以从数据存储库访问系统运行数据，如统一数据库(Unified Data Repository，UDR)、网管数据库等。对于3GPP的NF，MDAF利用基于3GPP定义的业务的接口通信获取网络数据。In another embodiment, MDAF continuously collects real-time operating data of the system through the management data analysis function. MDAF can also access system operating data from data repositories, such as Unified Data Repository (UDR) and network management databases. For 3GPP's NF, MDAF uses interface communication based on services defined by 3GPP to obtain network data.

在一个示例性的实施方式中，所述满足系统维护条件，包括如下一个或多个：In an exemplary implementation, the meeting the system maintenance condition includes one or more of the following:

数据采集时长达到预设系统维护时长；The data collection time reaches the preset system maintenance time;

检测到系统发生预设故障事件；A preset failure event is detected in the system;

检测到系统维护事件被触发。A system maintenance event was detected to be triggered.

在本实施例中，可以通过获取采集数据的时间信息确定数据采集时长。所述预设系统维护时长可以理解为系统健康维护周期T2。数据采集时长达到系统健康维护周期T2的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令。In this embodiment, the data collection time can be determined by acquiring time information of the collected data. The preset system maintenance duration can be understood as the system health maintenance period T2. When the data collection time reaches the system health maintenance period T2, the maintenance operation instruction is determined based on the collected first operation data and the preset decision model.

在检测到系统发生预设故障事件或系统维护事件被触发的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令。In the case of detecting that a preset failure event of the system or a system maintenance event is triggered, the maintenance operation instruction is determined based on the collected first operating data and the preset decision model.

预设故障事件可以由工作人员进行预先设定，本申请中不对故障事件进行限定。The preset failure event can be pre-set by the staff, and the failure event is not limited in this application.

系统维护事件被触发可以理解为工作人员通过维护设备的输入装置输入维护指令。具体输入方式本申请不进行限定。A system maintenance event is triggered, which can be understood as a worker inputting a maintenance instruction through the input device of the maintenance equipment. The specific input method is not limited in this application.

在一个示例性的实施方式中，在所述采集系统运行数据之前，还包括：采集系统的历史运行数据、网络位置信息和历史维护信息；基于采集到的所述历史运行数据、所述网络位置信息和所述历史维护信息进行训练，生成预设决策模型。在数据采集时长达到模型更新时长的情况下，基于采集到的第二运行数 据对预设决策模型进行训练更新，得到新的预设决策模型。In an exemplary embodiment, before the collecting system operation data, the method further includes: collecting historical operation data, network location information, and historical maintenance information of the system; based on the collected historical operation data, the network location Information and the historical maintenance information are trained to generate a preset decision model. In the case that the data collection time reaches the model update time, the preset decision model is trained and updated based on the collected second running data to obtain a new preset decision model.

在本实施例中，模型更新时长可以理解为决策模型更新周期。In this embodiment, the model update duration can be understood as the decision model update period.

所述运行数据包括如下一种或多种：系统性能数据、系统故障数据、执行配置操作的情况下生成的日志数据、执行维护操作的情况下生成的日志数据；其中，The operating data includes one or more of the following: system performance data, system failure data, log data generated when configuration operations are performed, and log data generated when maintenance operations are performed; among them,

所述系统性能数据包括如下一种或多种：性能测量数据、关键性能指标(Key Performance Indicator，KPI)数据、最小化路测(Minimization of DriveTests，MDT)数据；The system performance data includes one or more of the following: performance measurement data, Key Performance Indicator (KPI) data, and Minimization of Drive Tests (MDT) data;

所述故障数据包括如下一种或多种：告警数据、告警恢复数据、修复操作数据、修复效果数据。The fault data includes one or more of the following: alarm data, alarm recovery data, repair operation data, and repair effect data.

基于采集到的第一运行数据和预设决策模型确定维护操作指令，包括如下一个或多个：The maintenance operation instructions are determined based on the collected first operating data and the preset decision model, including one or more of the following:

基于所述预设决策模型对所述第一运行数据中的系统性能数据进行分析，得到指令执行时间段；Analyzing the system performance data in the first operating data based on the preset decision model to obtain an instruction execution time period;

基于所述预设决策模型对所述第一运行数据中的系统故障数据和执行维护操作的情况下生成的日志数据进行分析，得到故障避免操作指令；Analyzing the system failure data in the first operating data and the log data generated in the case of performing maintenance operations based on the preset decision model to obtain a failure avoidance operation instruction;

基于所述预设决策模型对所述第一运行数据中的执行配置操作的情况下生成的日志数据进行分析，得到系统优化指令。Based on the preset decision model, the log data generated in the case of performing the configuration operation in the first operating data is analyzed to obtain a system optimization instruction.

所述维护操作指令包括如下之一：The maintenance operation instruction includes one of the following:

重启指令，所述重启指令用于指示系统在第一预设时间重启某个网络功能；A restart instruction, where the restart instruction is used to instruct the system to restart a certain network function at a first preset time;

清理指令，所述清理指令用于指示系统在第二预设时间清理某个网络功能的运行系统；A cleaning instruction, where the cleaning instruction is used to instruct the system to clean the operating system of a certain network function at a second preset time;

升级指令，所述升级指令用于指示系统在第三预设时间对某个网络功能进行软件升级；An upgrade instruction, where the upgrade instruction is used to instruct the system to upgrade the software of a certain network function at a third preset time;

建议指令，所述建议指令用于指示对某个网络功能软件版本升级的建议。The suggestion instruction is used to indicate a suggestion for upgrading a certain network function software version.

在一个应用性实例中，本申请提供一种系统健康维护方法。图3是本申请提供的一种系统健康维护方法的流程图，如图3所示，本实施例中提供的系统健康维护方法主要包括步骤S31、S32、S33和S34。In an application example, this application provides a system health maintenance method. Fig. 3 is a flowchart of a system health maintenance method provided by the present application. As shown in Fig. 3, the system health maintenance method provided in this embodiment mainly includes steps S31, S32, S33, and S34.

S31、管理数据分析功能持续采集系统实时运行数据。S31. The management data analysis function continuously collects real-time operating data of the system.

其中，系统运行数据包括但不限于：系统性能数据、系统故障数据、配置 操作的日志数据、其它系统维护功能执行日志数据。Among them, the system operation data includes but is not limited to: system performance data, system failure data, configuration operation log data, and other system maintenance function execution log data.

所述系统性能数据包括但不限于性能测量数据、关键性能指标KPI数据、MDT数据等。The system performance data includes, but is not limited to, performance measurement data, key performance indicator KPI data, MDT data, and the like.

所述系统故障数据包括但不限于告警数据、告警恢复数据、信令跟踪数据、为解除故障采取的修复操作及修复的效果。The system failure data includes, but is not limited to, alarm data, alarm recovery data, signaling tracking data, repair operations taken to resolve the failure, and repair effects.

所述其它系统维护功能包括但不限于SON、自修复等。The other system maintenance functions include but are not limited to SON, self-repair and so on.

采集的系统运行数据还应包括时间信息。The collected system operation data should also include time information.

S32、对采集到的运行数据进行分析。S32. Analyze the collected operating data.

在本实施例中，对运行数据进行分析的方法包括人工智能和/或机器学习算法。本实施例仅对分析方法进行说明，而非限定。In this embodiment, the method for analyzing the operating data includes artificial intelligence and/or machine learning algorithms. This embodiment only illustrates the analysis method, but does not limit it.

对运行数据进行分析的同时，除了上述从系统采集的运行数据外，还包括但不限于如下信息：While analyzing the operating data, in addition to the above-mentioned operating data collected from the system, it also includes but is not limited to the following information:

整个通信网络的位置信息，系统维护的经验信息。The location information of the entire communication network, and the experience information of system maintenance.

运行数据分析分为两种，一种是对历史数据进行分析，基于历史运行数据、网络位置信息和历史维护信息更新决策模型。另一种是对实时数据进行分析，得到需要执行的操作指令。两种数据分析是同时进行，决策模型更新和实时运行数据分析的频度可能不一样，即决策模型更新和实时运行数据分析的周期是不同的。There are two types of operating data analysis. One is to analyze historical data and update the decision model based on historical operating data, network location information, and historical maintenance information. The other is to analyze real-time data to get the operating instructions that need to be executed. The two types of data analysis are carried out at the same time, and the frequency of decision model update and real-time operation data analysis may be different, that is, the cycle of decision model update and real-time operation data analysis is different.

决策模型更新需要的历史数据分析的采集周期为决策模型更新周期T1，主要是使用人工智能和/或机器学习算法对采集的历史数据进行分析，更新决策模型。每隔决策模型更新周期T1执行一次。The collection cycle of historical data analysis required for the update of the decision model is the decision model update cycle T1, which mainly uses artificial intelligence and/or machine learning algorithms to analyze the collected historical data and update the decision model. Execute once every decision model update cycle T1.

例如：具体的分析场景可以包括但不限于：For example: specific analysis scenarios can include but are not limited to:

根据性能测量数据、MDT数据、系统位置信息等分析得出不同的区域的业务高峰时间和业务低谷时间。为确定最好的维护操作时段做好准备，以使系统的健康维护对用户的影响减到最小。本实施例中选择业务低估时间作为维护操作时段。According to the analysis of performance measurement data, MDT data, system location information, etc., business peak hours and business valley times in different regions can be obtained. Make preparations for determining the best maintenance operation period to minimize the impact of system health maintenance on users. In this embodiment, the business underestimation time is selected as the maintenance operation period.

根据系统故障数据及SON、自愈等功能的操作日志进行分析，找出避免各类故障的最佳操作及相应的参数和时间。Analyze the system fault data and the operation log of SON and self-healing functions to find out the best operation and corresponding parameters and time to avoid various faults.

根据配置操作日志归纳各类操作对系统的影响，找出维护系统健康的可用操作及相关的参数和操作时间。Summarize the impact of various operations on the system according to the configuration operation log, and find out the available operations to maintain the health of the system and related parameters and operation time.

对实时运行数据进行分析时，实时运行数据采集周期为系统健康维护周期 T2，主要是运用上述产生的决策模型对实时数据进行分析，给出具体的系统健康维护的建议或指令。When analyzing real-time operation data, the real-time operation data collection period is the system health maintenance period T2, which mainly uses the decision model generated above to analyze real-time data and give specific suggestions or instructions for system health maintenance.

一般是每隔系统健康维护周期T2执行一次，但也可以在特定事件发生时立即执行。其中，特定事件发生包括但不限于特定故障发生、管理人员人工触发。It is generally executed once every system health maintenance period T2, but it can also be executed immediately when a specific event occurs. Among them, the occurrence of a specific event includes, but is not limited to, the occurrence of a specific fault and manual triggering by management personnel.

S33、根据数据分析结果，给出系统健康维护操作建议或操作指令。S33. According to the data analysis result, provide system health maintenance operation suggestions or operation instructions.

所述操作建议或操作指令一般应该包括具体操作的时间；给出的操作建议或操作指令包括但不限于：The operating suggestions or operating instructions should generally include the time of the specific operation; the operating suggestions or operating instructions given include but are not limited to:

在规定的时间重启某个网络功能；Restart a certain network function at the specified time;

在规定的时间清理优化某个网络功能的运行系统；Clean and optimize the operating system of a certain network function at the specified time;

在规定的时间对某个网络功能进行软件升级；Upgrade the software of a certain network function at the specified time;

给出某个或某类网络功能后续版本软件的升级建议，例如，所述升级建议包括对某个功能进行增强等。An upgrade suggestion for the subsequent version software of a certain or certain type of network function is given. For example, the upgrade suggestion includes enhancement of a certain function.

S34、根据健康维护操作建议或操作指令执行相关操作。S34. Perform related operations according to health maintenance operation suggestions or operation instructions.

在根据给出的健康维护操作建议或操作指令执行相关操作后，继续重复执行步骤S31、S32、S33和S34，以持续维护系统的健康。After performing related operations according to the given health maintenance operation suggestions or operation instructions, continue to repeat steps S31, S32, S33, and S34 to continuously maintain the health of the system.

本申请实施例通过不断更新的历史数据的分析、学习，更新、优化决策模型，从而使得给出的操作建议或操作指令更加准确、高效。The embodiment of the present application updates and optimizes the decision-making model through continuously updated historical data analysis, learning, so as to make the given operation suggestions or operation instructions more accurate and efficient.

本实施例中提供的系统健康维护方法解决了还没有通过对系统的数据进行分析以预测系统的故障隐患并提出相应解决故障隐患的操作指令的方法的问题。通过提出一种基于网络数据分析功能和管理数据分析功能对系统的故障隐患进行预测并给出相应的操作建议或操作指令的方案，以实现自动化的系统健康维护。The system health maintenance method provided in this embodiment solves the problem that the method for predicting the hidden trouble of the system by analyzing the data of the system and proposing corresponding operation instructions for solving the hidden trouble has not been solved. By proposing a scheme based on the network data analysis function and management data analysis function to predict the hidden danger of the system and give the corresponding operation suggestions or instructions, in order to realize the automatic system health maintenance.

在一个应用性实例中，本申请提供一种系统健康维护方法。图4是本申请提供的一种系统健康维护方法的流程图，如图4所示，本实施例中提供的系统健康维护方法主要包括步骤S41、S42、S43、S44、S45和S46。In an application example, this application provides a system health maintenance method. Fig. 4 is a flowchart of a system health maintenance method provided by the present application. As shown in Fig. 4, the system health maintenance method provided in this embodiment mainly includes steps S41, S42, S43, S44, S45, and S46.

S41、采集系统历史运行数据。S41. Collect historical operating data of the system.

其中，采集的持续时间需大于或等于决策模型更新周期T1。Among them, the duration of collection needs to be greater than or equal to the decision model update cycle T1.

S42、根据已经采集的系统运行历史数据进行分析，生成决策模型。S42. Analyze the collected historical data of system operation to generate a decision model.

S43、采集系统实时运行数据。S43. Collect real-time operating data of the system.

S44、在达到系统健康维护周期的情况下，基于系统健康维护周期内采集的实时运行数据更新决策模型。S44. When the system health maintenance cycle is reached, the decision model is updated based on the real-time operation data collected during the system health maintenance cycle.

S45、在达到系统健康维护周期的情况下，基于最新的决策模型和系统健康维护周期T2内采集的运行数据进行分析，对系统的健康状态进行分析，找出潜在的健康隐患，并给出消除健康隐患的健康维护指令。S45. When the system health maintenance cycle is reached, analyze based on the latest decision model and the operating data collected in the system health maintenance cycle T2, analyze the health status of the system, find out potential health hazards, and provide solutions to eliminate them Health maintenance instructions for hidden health hazards.

S46、根据给出的健康维护指令执行相关操作。S46. Perform related operations according to the given health maintenance instruction.

在执行相关操作之后，持续采集系统运行数据，并判断是否已到决策模型更新周期T1或系统健康维护周期T2。如果已经到了一个新的决策模型更新周期T1的开始时间，则执行S44；如果已经到了一个新的系统健康维护周期T2的开始时间，则执行S45。After performing related operations, continue to collect system operating data, and determine whether it has reached the decision model update cycle T1 or the system health maintenance cycle T2. If the start time of a new decision model update period T1 has been reached, S44 is executed; if the start time of a new system health maintenance period T2 has been reached, S45 is executed.

需要说明的是，上述步骤S43、S44、S45、S46可以并行执行，本实施例中并不限定上述步骤的执行顺序。It should be noted that the foregoing steps S43, S44, S45, and S46 can be executed in parallel, and the execution order of the foregoing steps is not limited in this embodiment.

图5为本申请提供的一种系统维护装置的结构示意图。该方法可以适用于对5G网络系统中的故障进行预测，并有效解除故障隐患的情况。该系统维护装置可以由软件和/或硬件实现。Fig. 5 is a schematic structural diagram of a system maintenance device provided by this application. This method can be suitable for predicting the fault in the 5G network system and effectively removing the hidden trouble of the fault. The system maintenance device can be implemented by software and/or hardware.

如图5所示，本申请实施例提供的系统维护装置主要包括采集模块51、确定模块52和执行模块53。As shown in FIG. 5, the system maintenance device provided by the embodiment of the present application mainly includes acollection module 51, adetermination module 52, and anexecution module 53.

采集模块51，被配置为采集系统实时运行数据；Thecollection module 51 is configured to collect real-time operating data of the system;

确定模块51，被配置为在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；The determiningmodule 51 is configured to determine a maintenance operation instruction based on the collected first operating data and a preset decision model when the system maintenance condition is met;

执行模块51，被配置为执行所述维护操作指令。Theexecution module 51 is configured to execute the maintenance operation instruction.

在一个示例性的实施方式中，所述满足系统维护条件，包括如下一个或多个：In an exemplary implementation, the meeting the system maintenance condition includes one or more of the following:

数据采集时长达到预设系统维护时长；The data collection time reaches the preset system maintenance time;

检测到系统发生预设故障事件；A preset failure event is detected in the system;

检测到系统维护事件被触发。A system maintenance event was detected to be triggered.

在一个示例性的实施方式中，所述装置还包括：In an exemplary embodiment, the device further includes:

模型更新模块，被配置为在数据采集时长达到模型更新时长的情况下，基于采集到的第二运行数据对预设决策模型进行训练更新，得到新的预设决策模型。The model update module is configured to train and update the preset decision model based on the collected second operating data when the data collection time period reaches the model update time period to obtain a new preset decision model.

在一个示例性的实施方式中，采集模块51，被配置为采集系统的历史运行数据、网络位置信息和历史维护信息；In an exemplary embodiment, thecollection module 51 is configured to collect historical operating data, network location information, and historical maintenance information of the system;

所述装置还包括；模型生成模块，被配置为基于采集到的所述历史运行数据、所述网络位置信息和所述历史维护信息进行训练，生成预设决策模型。The device further includes; a model generation module configured to perform training based on the collected historical operation data, the network location information, and the historical maintenance information to generate a preset decision model.

所述运行数据包括如下一种或多种：系统性能数据、系统故障数据、执行配置操作的情况下生成的日志数据、执行维护操作的情况下生成的日志数据；其中，The operating data includes one or more of the following: system performance data, system failure data, log data generated when configuration operations are performed, and log data generated when maintenance operations are performed; among them,

所述系统性能数据包括如下一种或多种：性能测量数据、关键性能指标KPI数据、最小化路测MDT数据；The system performance data includes one or more of the following: performance measurement data, key performance index KPI data, and minimized drive test MDT data;

所述故障数据包括如下一种或多种：告警数据、告警恢复数据、修复操作数据、修复效果数据。The fault data includes one or more of the following: alarm data, alarm recovery data, repair operation data, and repair effect data.

确定模块52，被配置为执行如下一个或多个操作：The determiningmodule 52 is configured to perform one or more of the following operations:

基于所述预设决策模型对所述第一运行数据中的系统性能数据进行分析，得到指令执行时间段；Analyzing the system performance data in the first operating data based on the preset decision model to obtain an instruction execution time period;

基于所述预设决策模型对所述第一运行数据中的系统故障数据和执行维护操作的情况下生成的日志数据进行分析，得到故障避免操作指令；Analyzing the system failure data in the first operating data and the log data generated in the case of performing maintenance operations based on the preset decision model to obtain a failure avoidance operation instruction;

基于所述预设决策模型对所述第一运行数据中的执行配置操作的情况下生成的日志数据进行分析，得到系统优化指令。Based on the preset decision model, the log data generated in the case of performing the configuration operation in the first operating data is analyzed to obtain a system optimization instruction.

所述维护操作指令包括如下之一：The maintenance operation instruction includes one of the following:

重启指令，所述重启指令用于指示系统在第一预设时间重启某个网络功能；A restart instruction, where the restart instruction is used to instruct the system to restart a certain network function at a first preset time;

清理指令，所述清理指令用于指示系统在第二预设时间清理某个网络功能的运行系统；A cleaning instruction, where the cleaning instruction is used to instruct the system to clean the operating system of a certain network function at a second preset time;

升级指令，所述升级指令用于指示系统在第三预设时间对某个网络功能进行软件升级；An upgrade instruction, where the upgrade instruction is used to instruct the system to upgrade the software of a certain network function at a third preset time;

建议指令，所述建议指令用于指示对某个网络功能软件版本升级的建议。The suggestion instruction is used to indicate a suggestion for upgrading a certain network function software version.

本实施例中提供的系统维护装置可执行本发明任意实施例所提供的系统维护方法，具备执行该方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明任意实施例所提供的系统维护方法。The system maintenance device provided in this embodiment can execute the system maintenance method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. For technical details that are not described in detail in this embodiment, please refer to the system maintenance method provided by any embodiment of the present invention.

值得注意的是，上述系统维护装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的具体名称也只是为了便于相互区分， 并不用于限制本申请的保护范围。It is worth noting that in the embodiment of the system maintenance device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, each The specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of this application.

图6是本申请实施例提供的一种设备的结构示意图，如图6所示，该设备包括处理器610、存储器620、输入装置630和输出装置640；设备中处理器610的数量可以是一个或多个，图6中以一个处理器610为例；设备中的处理器610、存储器620、输入装置630和输出装置640可以通过总线或其他方式连接，图6中以通过总线连接为例。FIG. 6 is a schematic structural diagram of a device provided by an embodiment of the present application. As shown in FIG. 6, the device includes aprocessor 610, amemory 620, aninput device 630, and anoutput device 640; the number ofprocessors 610 in the device may be one Or more, oneprocessor 610 is taken as an example in FIG. 6; theprocessor 610, thememory 620, theinput device 630, and theoutput device 640 in the device may be connected by a bus or other means.

存储器620作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序以及模块，如本申请实施例中的系统维护方法对应的程序指令/模块(例如，系统维护装置中的采集模块51、确定模块52和执行模块53)。处理器610通过运行存储在存储器620中的软件程序、指令以及模块，从而执行设备的各种功能应用以及数据处理，即实现本申请实施例提供的任一方法。As a computer-readable storage medium, thememory 620 can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the system maintenance method in the embodiment of the present application (for example, the collection module in the system maintenance device). 51. Thedetermination module 52 and the execution module 53). Theprocessor 610 executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in thememory 620, that is, implements any method provided in the embodiments of the present application.

存储器620可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据设备的使用所创建的数据等。此外，存储器620可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器620可包括相对于处理器610远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。Thememory 620 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the device, and the like. In addition, thememory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some examples, thememory 620 may include a memory remotely provided with respect to theprocessor 610, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

输入装置630可用于接收输入的数字或字符信息，以及产生与设备的用户设置以及功能控制有关的键信号输入。输出装置640可包括显示屏等显示设备。Theinput device 630 may be used to receive inputted numeric or character information, and generate key signal input related to user settings and function control of the device. Theoutput device 640 may include a display device such as a display screen.

本领域技术人员可以理解，处理器610还可以实现本申请任意实施例所提供的系统维护方法的技术方案。该设备的硬件结构以及功能可参见本实施例的内容解释。Those skilled in the art can understand that theprocessor 610 may also implement the technical solution of the system maintenance method provided by any embodiment of the present application. For the hardware structure and function of the device, please refer to the content explanation of this embodiment.

本申请实施例还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种系统维护方法，所述方法包括：An embodiment of the present application also provides a storage medium containing computer-executable instructions, which are used to perform a system maintenance method when the computer-executable instructions are executed by a computer processor, and the method includes:

采集系统实时运行数据；Collect real-time operating data of the system;

在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；When the system maintenance conditions are met, the maintenance operation instruction is determined based on the collected first operation data and the preset decision model;

执行所述维护操作指令，其中，所述操作指令用于指示系统进行健康维护。Execute the maintenance operation instruction, wherein the operation instruction is used to instruct the system to perform health maintenance.

本申请实施例所提供的一种包含计算机可执行指令的存储介质，其计算机可执行指令不限于如上所述的方法操作，还可以执行本申请任意实施例所提供的系统维护方法中的相关操作。An embodiment of the application provides a storage medium containing computer-executable instructions. The computer-executable instructions are not limited to the method operations described above, and can also perform related operations in the system maintenance method provided in any embodiment of the application. .

通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到，本申请可借助软件及必需的通用硬件来实现，也可以通过硬件实现。基于这样的理解，本申请的技术方案可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、闪存(FLASH)、硬盘或光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。Through the above description of the implementation manners, those skilled in the art can clearly understand that the present application can be implemented by software and necessary general-purpose hardware, or can be implemented by hardware. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), Random Access Memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including several instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute each implementation of this application The method described in the example.

以上所述，仅为本申请的示例性实施例而已，并非用于限定本申请的保护范围。The above are only exemplary embodiments of the present application, and are not used to limit the protection scope of the present application.

本领域内的技术人员应明白，术语用户终端涵盖任何适合类型的无线用户设备，例如移动电话、便携数据处理装置、便携网络浏览器或车载移动台。Those skilled in the art should understand that the term user terminal encompasses any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser, or a vehicle-mounted mobile station.

一般来说，本申请的多种实施例可以在硬件或专用电路、软件、逻辑或其任何组合中实现。例如，一些方面可以被实现在硬件中，而其它方面可以被实现在可以被控制器、微处理器或其它计算装置执行的固件或软件中，尽管本申请不限于此。In general, the various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the present application is not limited thereto.

本申请的实施例可以通过移动装置的数据处理器执行计算机程序指令来实现，例如在处理器实体中，或者通过硬件，或者通过软件和硬件的组合。计算机程序指令可以是汇编指令、指令集架构(Industry Subversive Alliance，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码。The embodiments of the present application may be implemented by executing computer program instructions by a data processor of a mobile device, for example, in a processor entity, or by hardware, or by a combination of software and hardware. Computer program instructions can be assembly instructions, Industry Subversive Alliance (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or written in any combination of one or more programming languages Source code or object code.

本申请附图中的任何逻辑流程的框图可以表示程序步骤，或者可以表示相互连接的逻辑电路、模块和功能，或者可以表示程序步骤与逻辑电路、模块和功能的组合。计算机程序可以存储在存储器上。存储器可以具有任何适合于本地技术环境的类型并且可以使用任何适合的数据存储技术实现，例如但不限于只读存储器(ROM)、随机访问存储器(RAM)、光存储器装置和系统(数码多功能光碟(Digital Video Disk，DVD)或便携式紧凑磁盘(Compact Disc，CD))等。计算机可读介质可以包括非瞬时性存储介质。数据处理器可以是任何适合于本地技术环境的类型，例如但不限于通用计算机、专用计算机、微处理器、 数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑器件(Field Programmable Gate Array，FPGA)以及基于多核处理器架构的处理器。The block diagram of any logic flow in the drawings of the present application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions. The computer program can be stored on the memory. The memory can be of any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read only memory (ROM), random access memory (RAM), optical memory devices and systems (digital multi-function optical discs) (Digital Video Disk, DVD) or portable compact disk (Compact Disc, CD)), etc. Computer-readable media may include non-transitory storage media. The data processor can be any type suitable for the local technical environment, such as but not limited to general-purpose computers, special-purpose computers, microprocessors, digital signal processors (DSP), application specific integrated circuits (ASICs) ), programmable logic devices (Field Programmable Gate Array, FPGA), and processors based on multi-core processor architecture.

Claims (10)

Translated fromChinese

一种系统维护方法，包括：A system maintenance method, including:采集系统的实时运行数据；Collect real-time operating data of the system;在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；When the system maintenance conditions are met, the maintenance operation instruction is determined based on the collected first operation data and the preset decision model;执行所述维护操作指令，其中，所述维护操作指令用于指示所述系统进行健康维护。The maintenance operation instruction is executed, wherein the maintenance operation instruction is used to instruct the system to perform health maintenance.根据权利要求1所述的方法，其中，所述满足系统维护条件，包括如下至少一个：The method according to claim 1, wherein the satisfying the system maintenance condition includes at least one of the following:数据采集时长达到预设系统维护时长；The data collection time reaches the preset system maintenance time;检测到系统发生预设故障事件；A preset failure event is detected in the system;检测到系统维护事件被触发。A system maintenance event was detected to be triggered.根据权利要求1所述的方法，其中，在所述采集系统的实时运行数据之后，还包括：The method according to claim 1, wherein, after the real-time operating data of the system is collected, the method further comprises:在数据采集时长达到模型更新时长的情况下，基于采集到的第二运行数据对所述预设决策模型进行训练更新，得到新的预设决策模型。In the case that the data collection duration reaches the model update duration, the preset decision-making model is trained and updated based on the collected second operating data to obtain a new preset decision-making model.根据权利要求1所述的方法，其中，在所述采集系统的实时运行数据之前，还包括：The method according to claim 1, wherein before collecting real-time operating data of the system, the method further comprises:采集所述系统的历史运行数据、网络位置信息和历史维护信息；Collect historical operation data, network location information and historical maintenance information of the system;基于采集到的所述历史运行数据、所述网络位置信息和所述历史维护信息进行训练，生成所述预设决策模型。Training is performed based on the collected historical operation data, the network location information, and the historical maintenance information to generate the preset decision model.根据权利要求1-4中任一项所述的方法，其中，所述运行数据包括如下至少一种：系统性能数据、系统故障数据、执行配置操作的情况下生成的日志数据、执行维护操作的情况下生成的日志数据；其中，The method according to any one of claims 1 to 4, wherein the operating data includes at least one of the following: system performance data, system failure data, log data generated when configuration operations are performed, and maintenance operations performed Log data generated under the circumstances; among them,所述系统性能数据包括如下至少一种：性能测量数据、关键性能指标KPI数据、最小化路测MDT数据；The system performance data includes at least one of the following: performance measurement data, key performance indicator KPI data, and minimized drive test MDT data;所述系统故障数据包括如下至少一种：告警数据、告警恢复数据、修复操作数据、修复效果数据。The system failure data includes at least one of the following: alarm data, alarm recovery data, repair operation data, and repair effect data.根据权利要求1所述的方法，其中，所述基于采集到的第一运行数据和预设决策模型确定维护操作指令，包括如下至少一个：The method according to claim 1, wherein the determining a maintenance operation instruction based on the collected first operation data and a preset decision model includes at least one of the following:基于所述预设决策模型对所述第一运行数据中的系统性能数据进行分析， 得到指令执行时间段；Analyzing the system performance data in the first operating data based on the preset decision model to obtain an instruction execution time period;基于所述预设决策模型对所述第一运行数据中的系统故障数据和执行维护操作的情况下生成的日志数据进行分析，得到故障避免操作指令；Analyzing the system failure data in the first operating data and the log data generated in the case of performing maintenance operations based on the preset decision model to obtain a failure avoidance operation instruction;基于所述预设决策模型对所述第一运行数据中的执行配置操作的情况下生成的日志数据进行分析，得到系统优化指令。Based on the preset decision model, the log data generated in the case of performing the configuration operation in the first operating data is analyzed to obtain a system optimization instruction.根据权利要求1所述的方法，其中，所述维护操作指令包括如下之一：The method according to claim 1, wherein the maintenance operation instruction includes one of the following:重启指令，所述重启指令用于指示所述系统在第一预设时间重启一个网络功能；A restart instruction, where the restart instruction is used to instruct the system to restart a network function at a first preset time;清理指令，所述清理指令用于指示所述系统在第二预设时间清理一个网络功能的运行系统；A cleaning instruction, where the cleaning instruction is used to instruct the system to clean an operating system of a network function at a second preset time;升级指令，所述升级指令用于指示所述系统在第三预设时间对一个网络功能进行软件升级；An upgrade instruction, where the upgrade instruction is used to instruct the system to upgrade the software of a network function at a third preset time;建议指令，所述建议指令用于指示对一个网络功能软件版本升级的建议。The suggestion instruction is used to indicate a suggestion for upgrading a network function software version.一种系统维护装置，包括：A system maintenance device, including:采集模块，被配置为采集系统的实时运行数据；The collection module is configured to collect the real-time operating data of the system;确定模块，被配置为在满足系统维护条件的情况下，基于采集到的第一运行数据和预设决策模型确定维护操作指令；The determining module is configured to determine the maintenance operation instruction based on the collected first operating data and the preset decision model when the system maintenance conditions are met;执行模块，被配置为执行所述维护操作指令，其中，所述维护操作指令用于指示所述系统进行健康维护。The execution module is configured to execute the maintenance operation instruction, wherein the maintenance operation instruction is used to instruct the system to perform health maintenance.一种设备，包括：A device that includes:一个或多个处理器；One or more processors;存储器，设置为存储一个或多个程序；Memory, set to store one or more programs;所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一项所述的系统维护方法。The one or more programs are executed by the one or more processors, so that the one or more processors implement the system maintenance method according to any one of claims 1-7.一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1-7中任一项所述的系统维护方法。A storage medium storing a computer program, and when the computer program is executed by a processor, the system maintenance method according to any one of claims 1-7 is realized.

Images