WO2024131445A1 - 一种基于分布式灾备演练场景的数据分析及预警的方法 - Google Patents
一种基于分布式灾备演练场景的数据分析及预警的方法 Download PDFInfo
- Publication number
- WO2024131445A1 WO2024131445A1 PCT/CN2023/134295 CN2023134295W WO2024131445A1 WO 2024131445 A1 WO2024131445 A1 WO 2024131445A1 CN 2023134295 W CN2023134295 W CN 2023134295W WO 2024131445 A1 WO2024131445 A1 WO 2024131445A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- disaster recovery
- business
- drill
- data
- model
- Prior art date
Links
- 238000011084 recovery Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000007405 data analysis Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 45
- 230000008569 process Effects 0.000 claims abstract description 12
- 230000002776 aggregation Effects 0.000 claims abstract description 5
- 238000004220 aggregation Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims abstract description 3
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 9
- 230000007704 transition Effects 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000004931 aggregating effect Effects 0.000 claims 1
- 238000005553 drilling Methods 0.000 abstract 1
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 2
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
-
- 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
- G06F16/23—Updating
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Definitions
- the present invention belongs to the technical field of disaster recovery drills, and in particular relates to a data analysis and early warning method based on a distributed disaster recovery drill scenario.
- the disaster recovery drill business process information of existing IT business systems is incomplete, and there are problems such as the impact of privacy data of edge nodes in various places on the central model shadow training.
- the technical problem to be solved by the present invention is to provide a method for data analysis and early warning based on distributed disaster recovery drill scenarios in view of the deficiencies of the above-mentioned prior art.
- the present invention provides a method for data analysis and early warning based on distributed disaster recovery drill scenarios.
- the present IT business system's disaster recovery drill business process information is incomplete, and there are problems such as the influence of privacy data of edge nodes in various places on the training of the central model.
- the present invention adopts distributed data convergence and uses edge nodes in various local networks to train the central model, thereby optimizing the central training model and greatly reducing the training load of the central model.
- the drill data is collected and analyzed by edge nodes in various places, and the data is classified by event reporting, disaster assessment, and disaster declaration, and the probability of a real disaster occurring during the training process of this disaster recovery drill is obtained through data statistics, which can effectively overcome the model bias problem and reduce the computational complexity.
- the technical solution adopted by the present invention is:
- a method for data analysis and early warning based on a distributed disaster recovery drill scenario comprising:
- Step 1 Distributed training of the central warning model and aggregation of privacy data
- Step 2 Put the data from step 1 into the model for training. Obtain the local disaster recovery drill warning model through training. Submit the disaster recovery drill warning model data from various places to the central server to update the disaster recovery drill warning model, and update the headquarters drill result database to store the updated indicators after each training. At the same time, update the business identifier and store it in the database as the initial business identifier for the next disaster recovery scenario of the same type, and command the central server program to re-execute a new round of model training to complete the entire process.
- step 1 The specific steps of the above step 1 are as follows:
- the central server program deployed at the headquarters executes the first round of central model training start instructions, and sends the instructions to the local disaster recovery drill edge node servers;
- the node server accesses the model training identification field flag deployed in the local exercise database. If the flag is not 0, it means that it is not the first training, and the privacy data analysis and calculation will continue. If it is 0, it will send a central warning model instruction to the central server. After receiving the request instruction, the central server will send the central warning model to the edge node server;
- the edge node server aggregates the privacy data.
- the drill scenarios include data-level disaster recovery drills, application-level disaster recovery drills, single-system drills, and overall switching of data centers.
- the modeling elements of the above-mentioned central architecture include data center coordinates, buildings, floors, identification information, and a list of business systems included;
- the modeling elements of the disaster recovery system architecture include the data center, rack, cabinet location, server information, network information, and deployment application status;
- the modeling elements of the switching operation are used to model the specific switching steps and configure the business systems that the business system depends on.
- the business system association relationship is mapped to the association identifier: business system###configuration id.
- the elements of the switching operation include the business system server IP, password, execution script, and script return value.
- the above S2 automatically generates a business switching flow chart according to the association relationship configured by the business system, and generates corresponding VR tasks and situation interaction elements according to the maintenance personnel configured by the database of the business system or the application server; automatically generates multiple Hierarchical business architecture diagram, including business system, business group, and data center level; the business architecture diagram is mapped as an associated identifier: business system architecture diagram###configuration id; the switching flowchart is mapped as an associated identifier: switching flowchart###configuration id###business association relationship ID.
- P represents the one-step transition probability matrix
- the present invention highlights the advantages of artificial intelligence in the process of disaster recovery drills, effectively solves the protection of privacy data of existing distributed edge nodes in the network without affecting the effect of central model training, and greatly reduces the central model training load.
- comprehensive data training is performed on the disaster recovery drill business process information corresponding to the edge node, so as to obtain the alarm probability of disaster recovery drills in the edge node area.
- the present invention can effectively overcome the model deviation problem and reduce the computational complexity.
- FIG1 is a flow chart of the method of the present invention.
- a method for data analysis and early warning based on a distributed disaster recovery drill scenario includes:
- Step 1 Distributed training of the [central warning model] and aggregation of privacy data.
- the data collection module includes three parts: exercise result database, local exercise database, and exercise association database:
- the central server deploys the [exercise result database] and [exercise association database], and the local server deploys the [local Party Exercise Database].
- the present invention executes the first round of central model training start instructions through the central server program deployed at the headquarters, and sends the instructions to the local disaster recovery drill edge node server, referred to as the edge node server.
- the node server accesses the model training identification field flag deployed in the local exercise database. If it is not 0, it means that it is not the first training and continues to analyze and calculate the privacy data. If it is 0, it sends the [central warning model] instruction to the central server. After receiving the request instruction, the central server sends the [central warning model] to the edge node server.
- the edge node server aggregates the privacy data.
- the specific steps are as follows:
- S1 Classify and aggregate the data in the local drill database and the database related to the drill to form real and effective privacy analysis data. If this is not the first time to conduct this type of disaster recovery drill, the disaster recovery scenario of S2 is constructed according to the initial business identification stored in the database. Otherwise, the business identification is created through S2.
- the modeling elements of the center architecture include data center coordinates, buildings, floors, identification information, and a list of business systems included.
- the modeling elements of the disaster recovery system architecture include the data center, rack, cabinet location, server information, network information, and deployed applications (database, web service, DNS, etc.).
- the modeling elements of the switching operation are used to model the specific switching steps.
- the elements include the business system server IP, password, execution script, script return value, and the business system on which the configuration business system depends.
- the business system association relationship is mapped to the association identifier: business system 1###configuration id.
- the business switching flowchart is automatically generated, and the corresponding VR tasks and situation interaction elements are generated according to the maintenance personnel of the business system database or application server configuration.
- business architecture diagram is mapped to the associated identifier: business system architecture diagram 1###configuration id;
- the switching flowchart is mapped to the association identifier: switching flowchart 1###configuration id###business association relationship ID.
- Step 2 [Central Early Warning Module]: Put the data from step 1 into the model for training, and obtain the local [disaster recovery drill early warning model] through training. Finally, submit the data of the [disaster recovery drill early warning model] from various places to the central server to update the [disaster recovery drill early warning model], and update the headquarters drill result database to store the updated indicators after each training. At the same time, update the business identifier and store it in the database as the initial business identifier for the next disaster recovery scenario of this type. Command the central server program to re-execute a new round of model training, thus completing the entire process.
- P represents the one-step transfer probability matrix
- the probability of abnormal to normal transition of the threshold value in this model training is [0.6, 0.4]
- the normal to abnormal transition probability of this model training threshold is [0.3, 0.7]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Alarm Systems (AREA)
- Computer And Data Communications (AREA)
Abstract
本发明公开了一种基于分布式灾备演练场景的数据分析及预警的方法,包括:步骤一:分布式训练中央预警模型并进行隐私数据聚合;步骤二:将步骤一数据放入模型进行训练,通过训练获得本地灾备演练预警模型,将各地灾备演练预警模型数据提交到中央服务器更新灾备演练预警模型,并更新总部演练结果数据库,存储每次训练后的更新指标;同时,更新业务标识并存储到数据库做为下一次同类型灾备场景的初始业务标识,命令中央服务器程序则重新执行新一轮模型训练,从而完成整个流程,得出灾备演练的训练过程发生真实灾难的概率。本发明可有效地克服模型偏差问题,降低计算复杂度。
Description
本发明属于灾备演练技术领域,具体涉及一种基于分布式灾备演练场景的数据分析及预警的方法。
随着数字化发展的逐渐深入,网络安全已经成为社会发展的重要保证,使得灾备演练更加具有参考价值,灾备数据信息的收集和处理是灾备演练中的一个重要环节。信息收集全面,数据准确能够保证灾备演练的各任务正常执行。演练的处理过程是高度接近真实灾难发生时的处理过程,确保了灾备演练能够对工作起到作用,从而使灾备自动演练对数据维护起到参考作用。
现有IT业务系统的灾备演练业务流程信息表现不完整,存在各地边缘节点隐私数据对中央模型影训练影响等问题。
发明内容
本发明所要解决的技术问题是针对上述现有技术的不足,提供一种基于分布式灾备演练场景的数据分析及预警的方法,对现有IT业务系统的灾备演练业务流程信息表现不完整,存在各地边缘节点隐私数据对中央模型影训练影响等问题,综合采用分布式数据收敛及利用各地组网内边缘节点训练中央模型,从而优化中央训练模型,并大幅度减小中央模型训练负载。通过各地边缘节点进行演练数据收集和分析,通过对数据按事件上报、灾害评估、灾难宣告分类,进行数据统计得出本次灾备演练的训练过程发生真实灾难的概率,可有效地克服模型偏差问题,降低计算复杂度。
为实现上述技术目的,本发明采取的技术方案为:
一种基于分布式灾备演练场景的数据分析及预警的方法,包括:
步骤一:分布式训练中央预警模型并进行隐私数据聚合;
步骤二:将步骤一数据放入模型进行训练,通过训练获得本地灾备演练预警模型,将各地灾备演练预警模型数据提交到中央服务器更新灾备演练预警模型,并更新总部演练结果数据库,存储每次训练后的更新指标;同时,更新业务标识并存储到数据库做为下一次同类型灾备场景的初始业务标识,命令中央服务器程序则重新执行新一轮模型训练,从而完成整个流程。
为优化上述技术方案,采取的具体措施还包括:
上述的步骤一具体步骤如下:
首先,通过部署在总部的中央服务器程序执行第一轮中央模型训练开始指令,将指令下发到地方灾备演练边缘节点服务器;
其次,节点服务器收到指令后,访问部署在地方演练数据库的模型训练标识字段flag,flag如果不为0则说明是非第一次训练,继续进行隐私数据分析及计算,如果为0则向中央服务器发送下发中央预警模型指令,中央服务器收到请求指令后将中央预警模型下发到边缘节点服务器;
然后,边缘节点服务器收到中央预警模型后,进行隐私数据聚合。
上述的隐私数据聚合具体步骤如下:
S1、对地方演练数据库和与演练关联关系数据库数据进行分类聚合,形成真实有效的隐私分析数据;
S2、解析初始业务标识,根据‘###’相邻的参数值实现数据中心架构,灾备系统架构,切换操作的要素建模,或进行业务标识创建。
如果是非第一次进行该类型灾备演练,根据数据库存储的初始业务标识进行S2的灾备场景构建;
反之,通过S2进行业务标识创建。
上述的业务标识为:
场景所在边缘节点###演练场景###一级分类_二级分类###业务系统1###配置id###切换流程图###配置id###业务关联关系ID;
演练场景包括数据级灾备演练、应用级灾备演练、单系统演练、数据中心整体切换。
上述的中心架构的建模要素包括数据中心坐标,建筑物,楼层,标识信息,所含业务系统列表;
灾备系统架构的建模要素包括所属数据中心,机架,机柜位置,服务器信息,网络信息,部署应用情况;
切换操作的建模要素用于对具体切换步骤进行建模并配置业务系统依赖的业务系统,业务系统关联关系映射为关联标识:业务系统###配置id,切换操作的要素包括业务系统服务器IP,口令,执行脚本,脚本返回值。
上述的S2根据业务系统配置的关联关系,自动生成业务切换流程图,并根据业务系统的数据库或者应用服务器配置的维护人员,生成相应的VR任务及情况交互要素;自动生成多
层次的业务架构图,包括业务系统,业务群,数据中心级;业务架构图映射为关联标识:业务系统架构图###配置id;切换流程图映射为关联标识:切换流程图###配置id###业务关联关系ID。
上述的灾备演练预警模型的模型公式为:
X(k+1)=X(k)×P
X(k+1)=X(k)×P
式中:X(k)表示趋势分析与预测对象在t=k时刻的状态向量,P表示一步转移概率矩阵,X(k+1)表示趋势分析与预测对象在t=k+1时刻的状态向量。
本发明具有以下有益效果:
本发明突出了人工智能在灾备演练过程中的优势,有效解决现有组网分布式边缘节点隐私数据的保护且不影响中央模型训练的效果,并大幅度减小中央模型训练负载。同时对边缘节点对应的灾备演练业务流程信息进行综合数据训练,从而得到边缘节点区域的灾备演练的发生告警概率。本发明可有效地克服模型偏差问题,降低计算复杂度。
图1为本发明方法流程图。
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。
本发明中的步骤虽然用标号进行了排列,但并不用于限定步骤的先后次序,除非明确说明了步骤的次序或者某步骤的执行需要其他步骤作为基础,否则步骤的相对次序是可以调整的。可以理解,本文中所使用的术语“和/或”涉及且涵盖相关联的所列项目中的一者或一者以上的任何和所有可能的组合。
如图1所示,一种基于分布式灾备演练场景的数据分析及预警的方法,包括:
步骤一:分布式训练【中央预警模型】并进行隐私数据聚合。
对地方演练数据和与演练关联关系数据库进行分类聚合,形成真实有效的隐私分析数据。如果是非第一次进行该类型灾备演练,根据数据库存储的初始业务标识进行S2的灾备场景构建。反之,通过S2进行业务标识创建。
数据采集模块包含演练结果数据库和地方演练数据库、演练关联关系数据库三部分:
中央服务器部署【演练结果数据库】和【演练关联关系数据库】,地方服务器部署【地
方演练数据库】。
具体描述如下:
首先,本发明通过部署在总部的中央服务器程序执行第一轮中央模型训练开始指令,将指令下发到地方灾备演练边缘节点服务器,简称边缘节点服务器。
其次,节点服务器收到指令后,访问部署在地方演练数据库的模型训练标识字段flag,如果不为0则说明是非第一次训练,继续进行隐私数据分析及计算。如果为0则向中央服务器发送下发【中央预警模型】指令,中央服务器收到请求指令后将【中央预警模型】下发到边缘节点服务器。
然后,边缘节点服务器收到【中央预警模型】后,进行隐私数据聚合。具体步骤如下:
S1、对地方演练数据库和与演练关联关系数据库数据进行分类聚合,形成真实有效的隐私分析数据。如果是非第一次进行该类型灾备演练,根据数据库存储的初始业务标识进行S2的灾备场景构建。反之,通过S2进行业务标识创建。
S2、解析初始业务标识,根据‘###’相邻的参数值实现数据中心架构,灾备系统架构,切换操作等要素建模和标识。
首先,对灾备演练确认的场景进行数据补充和映射。
1、中心架构的建模要素包括数据中心坐标,建筑物,楼层,标识信息,所含业务系统列表。
2、灾备系统架构的建模要素包括所属数据中心,机架,机柜位置,服务器信息,网络信息,部署应用情况(数据库、web服务,DNS等)。
3、切换操作的建模要素用于对具体切换步骤进行建模,要素包括业务系统服务器IP,口令,执行脚本,脚本返回值,配置业务系统依赖的业务系统,业务系统关联关系映射为关联标识:业务系统1###配置id。
4、根据业务系统配置的关联关系,自动生成业务切换流程图,并根据业务系统的数据库或者应用服务器配置的维护人员,生成相应的VR任务及情况交互要素。
自动生成多层次的业务架构图,包括业务系统,业务群,数据中心级。
业务架构图映射为关联标识:业务系统架构图1###配置id;
切换流程图映射为关联标识:切换流程图1###配置id###业务关联关系ID。
业务标识:场景所在边缘节点###演练场景(例如数据级灾备演练、应用级灾备演练、单系统演练、数据中心整体切换等)###一级分类_二级分类###业务系统1###配置id###切换流程图1###配置id###业务关联关系ID。
步骤二:【中央预警模块】:将步骤一数据放入模型进行训练,通过训练获得本地【灾备演练预警模型】,最后,将各地【灾备演练预警模型】数据提交到中央服务器更新【灾备演练预警模型】,并更新总部演练结果数据库,存储每次训练后的更新指标。同时,更新业务标识并存储到数据库做为下一次该类型灾备场景的初始业务标识。命令中央服务器程序则重新执行新一轮模型训练,从而完成整个流程。
【灾备演练预警模型】
模型公式:X(k+1)=X(k)×P
公式中:X(k)表示趋势分析与预测对象在t=k时刻的状态向量,P表示一步转移概率矩阵,X(k+1)表示趋势分析与预测对象在t=k+1时刻的状态向量。
上次模型训练阈值转移概率【0.3、0.7】
本次模型训练阈值异常转正常转移概率【0.6、0.4】
本次模型训练阈值正常转异常转移概率【0.3、0.7】
通过模型计算得出:X(k+1)=X(k)×P
下次模型训练正常转异常概率:
0.3x0.6+0.3x0.7=0.39
0.3x0.6+0.3x0.7=0.39
下次模型训练异常转正常概率:
0.3x0.4+7x0.7=0.61
0.3x0.4+7x0.7=0.61
最后,下次模型训练阈值转移概率【0.39 0.61】
对于本领域技术人员而言,显然本发明不限于上述示范性实施例的细节,而且在不背离本发明的精神或基本特征的情况下,能够以其他的具体形式实现本发明。因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本发明的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化囊括在本发明内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。
此外,应当理解,虽然本说明书按照实施方式加以描述,但并非每个实施方式仅包含一个独立的技术方案,说明书的这种叙述方式仅仅是为清楚起见,本领域技术人员应当将说明书作为一个整体,各实施例中的技术方案也可以经适当组合,形成本领域技术人员可以理解的其他实施方式。
Claims (8)
- 一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,包括:步骤一:分布式训练中央预警模型并进行隐私数据聚合;步骤二:将步骤一数据放入模型进行训练,通过训练获得本地灾备演练预警模型,将各地灾备演练预警模型数据提交到中央服务器更新灾备演练预警模型,并更新总部演练结果数据库,存储每次训练后的更新指标;同时,更新业务标识并存储到数据库做为下一次同类型灾备场景的初始业务标识,命令中央服务器程序则重新执行新一轮模型训练,得出灾备演练的训练过程发生真实灾难的概率。
- 根据权利要求1所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述步骤一具体步骤如下:首先,通过部署在总部的中央服务器程序执行第一轮中央模型训练开始指令,将指令下发到地方灾备演练边缘节点服务器;其次,节点服务器收到指令后,访问部署在地方演练数据库的模型训练标识字段flag,flag如果不为0则说明是非第一次训练,继续进行隐私数据分析及计算,如果为0则向中央服务器发送下发中央预警模型指令,中央服务器收到请求指令后将中央预警模型下发到边缘节点服务器;然后,边缘节点服务器收到中央预警模型后,进行隐私数据聚合。
- 根据权利要求2所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述隐私数据聚合具体步骤如下:S1、对地方演练数据库和与演练关联关系数据库数据进行分类聚合,形成真实有效的隐私分析数据;S2、解析初始业务标识,根据‘###’相邻的参数值实现数据中心架构,灾备系统架构,切换操作的要素建模,或进行业务标识创建。
- 根据权利要求3所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,如果是非第一次进行该类型灾备演练,根据数据库存储的初始业务标识进行S2的灾备场景构建;反之,通过S2进行业务标识创建。
- 根据权利要求3所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述业务标识为:场景所在边缘节点###演练场景###一级分类二级分类###业务系统1###配置id###切换流程图###配置id###业务关联关系ID;演练场景包括数据级灾备演练、应用级灾备演练、单系统演练、数据中心整体切换。
- 根据权利要求3所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述中心架构的建模要素包括数据中心坐标,建筑物,楼层,标识信息,所含业务系统列表;灾备系统架构的建模要素包括所属数据中心,机架,机柜位置,服务器信息,网络信息,部署应用情况;切换操作的建模要素用于对具体切换步骤进行建模并配置业务系统依赖的业务系统,业务系统关联关系映射为关联标识:业务系统###配置id,切换操作的要素包括业务系统服务器IP,口令,执行脚本,脚本返回值。
- 根据权利要求6所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述S2根据业务系统配置的关联关系,自动生成业务切换流程图,并根据业务系统的数据库或者应用服务器配置的维护人员,生成相应的VR任务及情况交互要素;自动生成多层次的业务架构图,包括业务系统,业务群,数据中心级;业务架构图映射为关联标识:业务系统架构图###配置id;切换流程图映射为关联标识:切换流程图###配置id###业务关联关系ID。
- 根据权利要求1所述的一种基于分布式灾备演练场景的数据分析及预警的方法,其特征在于,所述灾备演练预警模型的模型公式为:
X(k+1)=X(k)×P式中:X(k)表示趋势分析与预测对象在t=k时刻的状态向量,P表示一步转移概率矩阵,X(k+1)表示趋势分析与预测对象在t=k+1时刻的状态向量。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211643163.2A CN116010163A (zh) | 2022-12-20 | 2022-12-20 | 一种基于分布式灾备演练场景的数据分析及预警的方法 |
CN202211643163.2 | 2022-12-20 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024131445A1 true WO2024131445A1 (zh) | 2024-06-27 |
Family
ID=86037239
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/134295 WO2024131445A1 (zh) | 2022-12-20 | 2023-11-27 | 一种基于分布式灾备演练场景的数据分析及预警的方法 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN116010163A (zh) |
WO (1) | WO2024131445A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116010163A (zh) * | 2022-12-20 | 2023-04-25 | 中电信数智科技有限公司 | 一种基于分布式灾备演练场景的数据分析及预警的方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115033464A (zh) * | 2022-05-31 | 2022-09-09 | 中电信数智科技有限公司 | 一种基于人工智能的分布式灾备演练数据预警方法及系统 |
CN115422302A (zh) * | 2022-08-25 | 2022-12-02 | 中电信数智科技有限公司 | 一种基于数据仓库的分布式灾备演练数据优化及预警方法 |
CN115460100A (zh) * | 2021-06-09 | 2022-12-09 | 华为技术有限公司 | 一种应用人工智能的通信方法及通信装置 |
CN116010163A (zh) * | 2022-12-20 | 2023-04-25 | 中电信数智科技有限公司 | 一种基于分布式灾备演练场景的数据分析及预警的方法 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109460322B (zh) * | 2018-11-14 | 2021-11-05 | 西安瑞蓝创软件科技有限公司 | 基于流程调度引擎技术的灾备切换演练系统及方法 |
CN113254279B (zh) * | 2021-07-14 | 2021-11-30 | 睿至科技集团有限公司 | 一种智能灾备管理平台系统 |
CN115204625A (zh) * | 2022-06-24 | 2022-10-18 | 中国建设银行股份有限公司 | 混合容灾场景切换方法及装置 |
-
2022
- 2022-12-20 CN CN202211643163.2A patent/CN116010163A/zh active Pending
-
2023
- 2023-11-27 WO PCT/CN2023/134295 patent/WO2024131445A1/zh unknown
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115460100A (zh) * | 2021-06-09 | 2022-12-09 | 华为技术有限公司 | 一种应用人工智能的通信方法及通信装置 |
CN115033464A (zh) * | 2022-05-31 | 2022-09-09 | 中电信数智科技有限公司 | 一种基于人工智能的分布式灾备演练数据预警方法及系统 |
CN115422302A (zh) * | 2022-08-25 | 2022-12-02 | 中电信数智科技有限公司 | 一种基于数据仓库的分布式灾备演练数据优化及预警方法 |
CN116010163A (zh) * | 2022-12-20 | 2023-04-25 | 中电信数智科技有限公司 | 一种基于分布式灾备演练场景的数据分析及预警的方法 |
Also Published As
Publication number | Publication date |
---|---|
CN116010163A (zh) | 2023-04-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10469320B2 (en) | Versioning system for network states in a software-defined network | |
CN110224894B (zh) | 一种智能变电站过程层网络监测管理系统 | |
WO2024131445A1 (zh) | 一种基于分布式灾备演练场景的数据分析及预警的方法 | |
CN108306756B (zh) | 一种基于电力数据网全息评估系统及其故障定位方法 | |
CN102752142B (zh) | 一种基于多维建模的信息系统的监控方法及监控系统 | |
CN102420700B (zh) | 网络故障诊断系统 | |
CN111885012A (zh) | 基于多种网络设备信息采集的网络态势感知方法及系统 | |
CN106371986A (zh) | 一种日志处理运维监控系统 | |
Wan et al. | Event-Based Anomaly Detection for Non-Public Industrial Communication Protocols in SDN-Based Control Systems. | |
CN108259202A (zh) | 一种ca监测预警方法和ca监测预警系统 | |
CN112559237B (zh) | 运维系统排障方法、装置、服务器和存储介质 | |
CN109150869A (zh) | 一种交换机信息采集分析系统及方法 | |
CN111935189B (zh) | 工控终端策略控制系统及工控终端策略控制方法 | |
CN107547228A (zh) | 一种基于大数据的安全运维管理平台的实现架构 | |
CN105867347B (zh) | 一种基于机器学习技术的跨空间级联故障检测方法 | |
CN111031000B (zh) | 一种业务风控系统的处理方法、装置、系统及存储介质 | |
CN115033450A (zh) | 一种基于分布式的贝叶斯集群监控预警分析方法 | |
CN117640544B (zh) | 一种分布式的服务调用治理系统及其方法 | |
CN109639475A (zh) | 基于关联图的网络自诊断故障定位方法 | |
WO2023231185A1 (zh) | 一种基于人工智能的分布式灾备演练数据预警方法及系统 | |
JP2006025434A (ja) | 大容量障害相関システム及び方法 | |
CN110399261B (zh) | 一种基于共现图的系统告警聚类分析方法 | |
CN107592234A (zh) | 业务链路故障定位的方法、系统和计算机可读存储介质 | |
Kiani et al. | Distributed rule anomaly detection in SDN-based IoT | |
CN112288566A (zh) | 基于深度神经网络的跨链交易异常检测和预警方法及系统 |
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: 23905613 Country of ref document: EP Kind code of ref document: A1 |