MEC cloud pool data-oriented automatic verification method and device

Abstract

The invention discloses an automatic verification method and device for MEC cloud pool data. The method comprises the following steps: firstly, acquiring CMDB data of the distributed cloud; acquiring real-time data of the distributed cloud; comparing the CMDB data with the real-time data to obtain a comparison result; and automatically synchronizing the real-time data to the CMDB data, which is inconsistent with the real-time data, in the comparison result, so as to obtain CMDB synchronous data, then detecting the CMDB synchronization data to obtain a detection result; and according to the real-time data, carrying out automatic restoration on an abnormal value in the detection result to obtain CMDB restoration data, and finally, integrating the CMDB synchronous data and the CMDB repair data to obtain CMDB automatic check data. According to the method, automatic verification of the CMDB data is realized, and the efficiency of resource management in the cloud pool and the accuracy of the data are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to an automated verification method and device for MEC cloud pool data. Background Art

[0002] With the continuous dynamic changes of MEC (Multi-access Edge Computing) cloud pool resources and configurations, computing resources such as virtual machines and containers are frequently created, deleted, and migrated, and the network topology is also constantly adjusted and optimized, resulting in an increasing demand for real-time reflection of resource and network status. However, the existing CMDB (Configuration Management Database) mainly relies on manual entry or periodic synchronization mechanisms, making it difficult to capture and reflect these changes in a timely manner, leading to a disconnect between the data and the actual situation, thus affecting the accuracy and efficiency of management and operation and maintenance. At the same time, the data verification in CMDB mainly relies on manual inspection and review, which cannot quickly identify or correct deviations. This verification method requires manual checking of resource information one by one, with cumbersome operations, low efficiency, and is prone to omission or error, seriously restricting the efficiency of data resource management and the accuracy of data in the MEC cloud pool. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to propose an automated verification method and device for MEC cloud pool data in view of the above deficiencies of the prior art. This method realizes the automated verification of CMDB data, effectively improving the efficiency of resource management and the accuracy of data in the cloud pool.

[0004] In a first aspect, the present invention provides an automated verification method for MEC cloud pool data, the method comprising the following steps:

[0005] Obtain the CMDB data of the distributed cloud; and obtain the real-time data of the distributed cloud;

[0006] Compare the CMDB data with the real-time data to obtain a comparison result; and automatically synchronize the real-time data to the CMDB data that is inconsistent with the real-time data in the comparison result to obtain CMDB synchronized data;

[0007] Detect the CMDB synchronized data to obtain a detection result; and automatically repair the outliers in the detection result according to the real-time data to obtain CMDB repaired data;

[0008] Integrate the CMDB synchronized data and the CMDB repaired data to obtain CMDB automatically verified data, thereby completing the automated verification of MEC cloud pool data.

[0009] Further, the obtaining of the CMDB data of the distributed cloud specifically includes the following steps:

[0010] Simulate a user to perform an automatic login operation; the simulation of the user performing an automatic login operation is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials;

[0011] According to the authentication information corresponding to the user email credentials, simulate the user to grab the resource list in the MEC cloud pool from the CMDB system, so as to obtain the CMDB data of the distributed cloud;

[0012] Among them, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices, and security devices.

[0013] Further, the real-time data includes the configuration data of virtual machines, the status data of containers, the network topology data, and the allocation data of storage resources;

[0014] The obtaining of the real-time data of the distributed cloud is obtained by periodic polling or event-driven mechanism and interacting with the MEC cloud pool management platform using API interfaces or data adapters.

[0015] Further, after obtaining the CMDB automatic verification data, the method further includes the steps of:

[0016] Generate a report on the CMDB automatic verification data and send it to the operation and maintenance personnel.

[0017] Further, detecting the CMDB synchronization data to obtain a detection result, specifically including the following steps:

[0018] Preprocess the CMDB data; the preprocessing includes normalization, feature extraction, and denoising;

[0019] Use an unsupervised anomaly detection model to detect the preprocessed CMDB synchronization data to obtain a first detection value; and use a supervised anomaly detection model to detect the preprocessed CMDB synchronization data to obtain a second detection value;

[0020] Compare the first detection value with a preset first threshold to obtain a first anomaly value; and compare the second detection value with a preset second threshold to obtain a second anomaly value;

[0021] Summarize the first detection value, the first anomaly value, the second detection value, and the second anomaly value to obtain a detection result.

[0022] Further, the unsupervised anomaly detection model is an isolation forest model; the supervised anomaly detection model is an XGBoost model or a LightGBM model;

[0023] Before detecting the preprocessed CMDB synchronization data, the method further includes the steps of: constructing an isolation forest model; and constructing an XGBoost model or a LightGBM model.

[0024] In a second aspect, the present invention provides an automated verification device for MEC cloud pool data, and the device includes:

[0025] An acquisition unit, configured to acquire CMDB data of a distributed cloud and real-time data of the distributed cloud;

[0026] A comparison unit, connected to the acquisition unit, configured to compare the CMDB data and the real-time data to obtain a comparison result;

[0027] A synchronization unit, connected to the comparison unit, configured to automatically synchronize the real-time data to the CMDB data that is inconsistent with the real-time data in the comparison result to obtain CMDB synchronization data;

[0028] A detection unit, connected to the synchronization unit, configured to detect the CMDB synchronization data to obtain a detection result;

[0029] A repair unit, connected to the detection unit, configured to automatically repair the outliers in the detection result according to the real-time data to obtain CMDB repair data;

[0030] An integration unit, respectively connected to the synchronization unit and the repair unit, configured to integrate the CMDB synchronization data and the CMDB repair data to obtain CMDB automatic verification data, thereby completing the automated verification of the MEC cloud pool data.

[0031] Further, the acquisition unit includes a first acquisition unit and a second acquisition unit, the first acquisition unit is configured to acquire CMDB data of a distributed cloud, and the second acquisition unit is configured to acquire real-time data of the distributed cloud;

[0032] The first acquisition unit includes:

[0033] A login module, configured to simulate a user to perform an automatic login operation; the operation of simulating a user to perform an automatic login is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials;

[0034] The scraping module, connected to the login module, is used to simulate a user to scrape the resource list in the MEC cloud pool from the CMDB system according to the authentication information corresponding to the user email credential, so as to obtain the CMDB data of the distributed cloud;

[0035] Among them, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices, and security devices.

[0036] Further, the device further includes:

[0037] The generation unit, connected to the integration unit, generates a report from the CMDB automatic verification data and sends it to the operation and maintenance personnel.

[0038] Further, the detection unit includes:

[0039] The preprocessing unit is used to preprocess the CMDB data; the preprocessing includes normalization, feature extraction, and denoising;

[0040] The first detection module, connected to the preprocessing unit, is used to detect the preprocessed CMDB synchronization data using an unsupervised anomaly detection model to obtain a first detection value;

[0041] The second detection module, connected to the preprocessing unit, is used to detect the preprocessed CMDB synchronization data using a supervised anomaly detection model to obtain a second detection value;

[0042] The first comparison module, connected to the first detection module, is used to compare the first detection value with a preset first threshold to obtain a first anomaly value;

[0043] The second comparison module, connected to the second detection module, is used to compare the second detection value with a preset second threshold to obtain a second anomaly value;

[0044] The summarization module is respectively connected to the first comparison module and the second comparison module, and is used to summarize the first detection value, the first anomaly value, the second detection value, and the second anomaly value to obtain a detection result.

[0045] Through automatically synchronizing or automatically repairing the CMDB data, the present invention realizes the automatic verification of the CMDB data, effectively improving the efficiency of resource management in the cloud pool and the accuracy of the data. The specific beneficial effects are as follows:

[0046] 1. Significantly improving the accuracy and consistency of the data: The present invention uses automatic detection and correction technologies to effectively reduce human errors, ensuring that the data in the CMDB is true and reliable, providing a solid foundation for decision-making.

[0047] 2. Enhance real-time monitoring and rapid response capabilities: Relying on real-time data collection and automatic verification mechanisms, it can quickly capture changes and anomalies in resource status, improving the system's response speed and fault handling efficiency.

[0048] 3. Greatly improve operation and maintenance efficiency and reduce operating costs: By automating processes to reduce manual intervention, lower labor input, and at the same time increase data processing speed, reducing the burden on operation and maintenance personnel.

[0049] 4. Optimize resource management and configuration: Relying on accurate data analysis, it supports more reasonable resource scheduling and allocation, improving the utilization rate of computing, storage, and network resources in the cloud pool, and achieving the optimal configuration of resources.

[0050] 5. Improve data stability: Continuously and automatically detect and correct abnormal data, ensuring the continuity and reliability of data in the system, and enhancing the stable operation ability of the overall system.

[0051] 6. Enhance system security: By automatically monitoring potential security hazards and violations, effectively warning and preventing security threats, and ensuring the security level of the cloud pool environment. Description of the Drawings

[0052] Figure 1 It is a schematic diagram of the automated verification method for MEC cloud pool data in the embodiments of the present invention;

[0053] Figure 2 It is a framework diagram of the automated verification for MEC cloud pool data in the embodiments of the present invention;

[0054] Figure 3 It is a flowchart of the automated verification for MEC cloud pool data in the embodiments of the present invention;

[0055] Figure 4 It is a schematic diagram of the automated verification device for MEC cloud pool data in the embodiments of the present invention.

[0056] Reference numerals: 10, acquisition unit; 20, comparison unit; 30, synchronization unit; 40, detection unit; 50, repair unit; 60, integration unit. Detailed Embodiments

[0057] To enable those skilled in the art to better understand the technical solutions of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0058] It can be understood that the specific embodiments and drawings described herein are only for explaining the present invention, rather than limiting the present invention.

[0059] It can be understood that, without conflict, the various embodiments in the present invention and the features in the embodiments can be combined with each other.

[0060] It is understood that, for the convenience of description, only the parts related to the present invention are shown in the drawings of the present invention, while the parts unrelated to the present invention are not shown in the drawings.

[0061] It is understood that each unit and module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures. Alternatively, multiple units and modules may also be integrated into one entity structure.

[0062] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in a different order from that marked in the drawings.

[0063] It is understood that in the flowcharts and block diagrams of the present invention, the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the embodiments of the present invention are shown. Among them, each block in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart may be implemented by a hardware-based system for implementing the specified function, or may be implemented by a combination of hardware and computer instructions.

[0064] It is understood that the units and modules involved in the embodiments of the present invention may be implemented in software or in hardware. For example, the units and modules may be located in the processor.

[0065] Embodiment 1:

[0066] This embodiment provides an automated verification method for MEC cloud pool data. This method can be applied to real-time monitoring and management of the status of MEC edge computing resources, ensuring the accuracy, consistency, and integrity of resource information, helping to quickly discover and eliminate faults, improving the stability and security of the network, while supporting automated operation and maintenance processes, optimizing resource allocation, and improving service quality, so as to meet diverse edge computing requirements and promote the innovation of intelligent applications and the digital transformation of the industry.

[0067] As Figure 1 shown, the automated verification method for MEC cloud pool data includes the following steps:

[0068] 1. Obtain the CMDB data of the distributed cloud; and, obtain the real-time data of the distributed cloud.

[0069] The obtaining of the CMDB data of the distributed cloud specifically includes the following steps:

[0070] Simulate a user to perform an automatic login operation; the simulation of the user performing an automatic login operation is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials;

[0071] According to the authentication information corresponding to the user email credentials, simulate the user to grab the resource list in the MEC cloud pool from the CMDB system, so as to obtain the CMDB data of the distributed cloud;

[0072] Among them, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices and security devices.

[0073] The real-time data includes the configuration data of virtual machines, the status data of containers, the network topology structure data, and the allocation data of storage resources;

[0074] The acquisition of the real-time data of the distributed cloud is obtained by means of timed polling or event-driven mechanism and interacting with the MEC cloud pool management platform using an API interface or a data adapter.

[0075] 2. Compare the CMDB data and the real-time data to obtain a comparison result; and, automatically synchronize the real-time data to the CMDB data that is inconsistent with the real-time data in the comparison result to obtain CMDB synchronization data. Specifically, in implementation, automatic synchronization can synchronize all real-time data to the CMDB, or only perform partial synchronization for the inconsistent parts, that is, update the CMDB data that is inconsistent with the real-time data to the real-time data.

[0076] 3. Detect the CMDB synchronization data to obtain a detection result; and, according to the real-time data, automatically repair the outliers in the detection result to obtain CMDB repair data.

[0077] As a specific implementation manner, detecting the CMDB synchronization data to obtain a detection result specifically includes the following steps:

[0078] Preprocess the CMDB data; the preprocessing includes normalization, feature extraction, and denoising;

[0079] Use an unsupervised anomaly detection model to detect the preprocessed CMDB synchronization data to obtain a first detection value; and, use a supervised anomaly detection model to detect the preprocessed CMDB synchronization data to obtain a second detection value;

[0080] Compare the first detection value with a preset first threshold to obtain a first outlier; and, compare the second detection value with a preset second threshold to obtain a second outlier;

[0081] Summarize the first detection value, the first outlier value, the second detection value, and the second outlier value to obtain a detection result.

[0082] As a specific implementation, the unsupervised anomaly detection model is an isolation forest model; the supervised anomaly detection model is an XGBoost model or a LightGBM model.

[0083] Before detecting the preprocessed CMDB synchronization data, the method further includes steps of: constructing an isolation forest model; and constructing an XGBoost model or a LightGBM model. The construction processes of the isolation forest model, the XGBoost model, or the LightGBM model are all constructed using mature methods in the prior art.

[0084] 4. Integrate the CMDB synchronization data and the CMDB repair data to obtain CMDB automatic verification data, thereby completing the automatic verification of data for the MEC cloud pool.

[0085] As a specific implementation, after obtaining the CMDB automatic verification data, the method further includes steps of:

[0086] Generate a report on the CMDB automatic verification data and send it to the operation and maintenance personnel.

[0087] As Figure 2 shown, the method of this embodiment is implemented through an MEC cloud pool data verification system, which mainly consists of the following key modules: The data collection module is responsible for collecting status data in real time from various resources in the MEC cloud pool (such as virtual machines, containers, physical devices, and network devices, etc.), interacting with each management platform (such as virtualization platforms, container management platforms, and operation and maintenance platforms, etc.) through API interfaces or data adapters to obtain the latest device configuration information; the data scraping module simulates logging into the CMDB system manually, and under the premise of ensuring account security and authentication, scrapes the resource lists of physical servers, logical hosts, network devices, and security devices, etc.; the data verification module compares the data in the CMDB with the collected real-time data according to preset verification rules to detect inconsistent, missing, or incorrect situations; the data synchronization module synchronizes the real-time data to the CMDB when it is found that the CMDB does not match the actual resources, ensuring that the configuration items in the database always reflect the actual resource status; the anomaly handling module issues an alarm to the operation and maintenance personnel or automatically generates repair suggestions when detecting anomalies, and triggers an automatic repair process when necessary to achieve fast handling of faults; in addition, the report generation module will regularly generate a detailed verification report, recording the entire verification process and results, helping the operation and maintenance personnel analyze the system health status and conduct tracking management.

[0088] As Figure 3As shown, the specific workflow of this embodiment includes the following steps:

[0089] Step S1: Data collection and data scraping:

[0090] The data collection module interacts with each management platform in the MEC cloud pool through the API interface or data adapter to obtain the latest status information of all resources in real time. This data includes the configuration information of virtual machines, container status, network topology, storage resource allocation, etc. The collection method can be in the form of regular polling or event triggering. At the same time, the data scraping module simulates manual login to the CMDB system. The program connects to the POP3 server through email credentials (such as application-specific passwords or OAuth tokens) to obtain authentication information such as verification codes. After completing the login, the program analyzes the response data, extracts authentication information such as session tokens and user IDs, and simulates manual operations to extract the resource list in the CMDB, including physical servers, logical hosts, network devices, and security devices.

[0091] Step S2: Data verification:

[0092] The system compares the real-time resource data collected in step S1 with the corresponding data in the CMDB according to the predetermined verification rules. The verification module checks the configuration information of each resource item by item to identify differences between the data, such as inconsistencies, omissions, or errors. The verification rules can be customized according to specific requirements, such as checking whether the physical hardware configuration, virtual machine running status, or network device parameters meet the requirements.

[0093] Step S3: Anomaly detection:

[0094] Based on data verification, the system uses the Isolation Forest algorithm to detect anomalies in time series data such as virtual machine traffic, container resource consumption, and network device CPU utilization. For example, when the memory usage rate of a virtual machine suddenly deviates from the historical range, the Isolation Forest model can quickly identify this anomaly. First, preprocess the collected real-time data and CMDB data, including normalization, feature extraction, and noise reduction, to ensure data quality and consistency. Subsequently, use the trained machine learning models (such as XGBoost, LightGBM, etc.) to analyze the historical data distribution and establish an anomaly detection model. During actual operation, input the real-time data into the model. If an index is detected to exceed the set threshold, it is determined as an anomaly.

[0095] Step S4: Data synchronization and repair:

[0096] If the verification finds that the configuration information in the CMDB does not match the actual resource status, the data synchronization module will be started to synchronize the latest real-time data to the CMDB, ensuring that the information in the database reflects the latest resource status. The synchronization can be performed in a full-volume or incremental manner according to specific configuration rules. When the system detects data anomalies (such as missing or misconfigured), the anomaly handling module will immediately respond, send an alert to the operation and maintenance personnel (through multiple channels such as email, SMS or system notifications), and at the same time automatically generate repair suggestions to help quickly solve the problem. For some anomalies that can be automatically repaired, the system can also directly trigger an automatic repair process to adjust the resource configuration items to ensure the stability and consistency of the system.

[0097] Step S5: Report generation:

[0098] After each verification is completed, the report generation module will generate a detailed verification report, the content of which includes the verification time, the resource items involved, the detected anomalies and the repair measures taken. These reports can be sent to the relevant operation and maintenance personnel via email or archived for subsequent auditing and tracking.

[0099] Through the above process, it is possible to realize the real-time verification, automatic synchronization and repair of the CMDB data in the MEC cloud pool, effectively reduce manual intervention, improve the accuracy and consistency of the data, and thus ensure the efficient management and stable operation and maintenance of the cloud pool resources.

[0100] The automated verification method for MEC cloud pool data in this embodiment aims to achieve real-time monitoring and efficient management of edge computing resources, ensure the accuracy and integrity of resource information, and improve the stability and security of the network. The method includes automatically capturing the resource list (i.e., CMDB data) of the distributed cloud by simulating user login and regularly collecting real-time data through the API from the management platform, and then comparing the two to detect inconsistencies. The system uses unsupervised models such as Isolation Forest and supervised models such as XGBoost to detect anomalies in the comparison results and automatically repair related problems. Finally, a detailed report of the verification results is generated and fed back to the operation and maintenance personnel. On the basis of ensuring the timeliness and consistency of the data, the entire process realizes automatic synchronization and fault repair, significantly reduces manual intervention, improves the accuracy of the data and management efficiency, helps the efficient operation and maintenance of edge computing resources and the digital transformation of the industry, and meets the diverse intelligent application requirements.

[0101] Embodiment 2:

[0102] As Figure 4 shown, the present invention provides an automated verification device for MEC cloud pool data, and the device includes:

[0103] An acquisition unit 10, configured to acquire the CMDB data of the distributed cloud and the real-time data of the distributed cloud;

[0104] A comparison unit 20, connected to the acquisition unit 10, for comparing the CMDB data and the real-time data to obtain a comparison result;

[0105] A synchronization unit 30, connected to the comparison unit 20, for automatically synchronizing the real-time data to the CMDB data that is inconsistent with the real-time data in the comparison result to obtain CMDB synchronization data;

[0106] A detection unit 40, connected to the synchronization unit 30, for detecting the CMDB synchronization data to obtain a detection result;

[0107] A repair unit 50, connected to the detection unit 40, for automatically repairing the abnormal values in the detection result according to the real-time data to obtain CMDB repair data;

[0108] An integration unit 60, respectively connected to the synchronization unit 30 and the repair unit 50, for integrating the CMDB synchronization data and the CMDB repair data to obtain CMDB automatic verification data, thereby completing the automatic verification of data for the MEC cloud pool.

[0109] As a specific implementation manner, the acquisition unit 10 includes a first acquisition unit and a second acquisition unit. The first acquisition unit is used to acquire the CMDB data of the distributed cloud, and the second acquisition unit is used to acquire the real-time data of the distributed cloud;

[0110] The first acquisition unit includes:

[0111] A login module, used to simulate a user to perform an automatic login operation; the operation of simulating a user to perform an automatic login is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials;

[0112] A scraping module, connected to the login module, for simulating a user to scrape the resource list in the MEC cloud pool from the CMDB system according to the authentication information corresponding to the user email credentials, thereby obtaining the CMDB data of the distributed cloud;

[0113] Among them, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices, and security devices.

[0114] As a specific implementation manner, the device further includes:

[0115] A generation unit, connected to the integration unit, for generating a report on the CMDB automatic verification data and sending it to the operation and maintenance personnel.

[0116] As a specific implementation manner, the detection unit 40 includes:

[0117] A preprocessing unit for preprocessing CMDB data; the preprocessing includes normalization, feature extraction, and denoising;

[0118] A first detection module, connected to the preprocessing unit, for detecting the preprocessed CMDB synchronization data using an unsupervised anomaly detection model to obtain a first detection value;

[0119] A second detection module, connected to the preprocessing unit, for detecting the preprocessed CMDB synchronization data using a supervised anomaly detection model to obtain a second detection value;

[0120] A first comparison module, connected to the first detection module, for comparing the first detection value with a preset first threshold to obtain a first anomaly value;

[0121] A second comparison module, connected to the second detection module, for comparing the second detection value with a preset second threshold to obtain a second anomaly value;

[0122] A summarization module, respectively connected to the first comparison module and the second comparison module, for summarizing the first detection value, the first anomaly value, the second detection value, and the second anomaly value to obtain a detection result.

[0123] The device in this embodiment can implement the method in Embodiment 1.

[0124] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principle of the present invention, and the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. An automated verification method for MEC cloud pool data, characterized in that The method includes the following steps: Obtain the CMDB data of the distributed cloud; and obtain the real-time data of the distributed cloud; Compare the CMDB data and the real-time data to obtain a comparison result; and automatically synchronize the real-time data to the CMDB data that is inconsistent with the real-time data in the comparison result to obtain CMDB synchronized data; Detect the CMDB synchronized data to obtain a detection result; and automatically repair the outliers in the detection result according to the real-time data to obtain CMDB repaired data; Integrate the CMDB synchronized data and the CMDB repaired data to obtain CMDB automatic verification data, thereby completing the automatic verification of data for the MEC cloud pool.

2. The automatic verification method for data for the MEC cloud pool according to claim 1, wherein The obtaining of the CMDB data of the distributed cloud specifically includes the following steps: Simulate a user to perform an automatic login operation; the simulation of the user performing an automatic login operation is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials; According to the authentication information corresponding to the user email credentials, simulate the user to grab the resource list in the MEC cloud pool from the CMDB system, thereby obtaining the CMDB data of the distributed cloud; Wherein, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices, and security devices.

3. The automatic verification method for data for the MEC cloud pool according to claim 1, wherein The real-time data includes the configuration data of virtual machines, the status data of containers, the network topology structure data, and the allocation data of storage resources; The obtaining of the real-time data of the distributed cloud is obtained by means of periodic polling or event-driven mechanism and interacting with the MEC cloud pool management platform using an API interface or a data adapter.

4. The automatic verification method for data for the MEC cloud pool according to claim 1, wherein After obtaining the CMDB automatic verification data, the method further includes the step of Generating a report from the CMDB automatic verification data and sending it to the operation and maintenance personnel.

5. The automatic verification method for data for the MEC cloud pool according to any one of claims 1 to 4, wherein The detecting of the CMDB synchronized data to obtain a detection result specifically includes the following steps: Preprocess the CMDB synchronized data; the preprocessing includes normalization, feature extraction, and denoising; Use an unsupervised anomaly detection model to detect the preprocessed CMDB synchronized data to obtain a first detection value; And use a supervised anomaly detection model to detect the preprocessed CMDB synchronized data to obtain a second detection value; Compare the first detection value with a preset first threshold to obtain a first outlier; And compare the second detection value with a preset second threshold to obtain a second outlier; Summarize the first detection value, the first outlier, the second detection value, and the second outlier to obtain a detection result.

6. The automated verification method for MEC cloud pool data according to claim 5, wherein: The unsupervised anomaly detection model is an isolation forest model; the supervised anomaly detection model is an XGBoost model or a LightGBM model; Before detecting the preprocessed CMDB synchronization data, the method further includes the steps of: constructing an isolation forest model; and constructing an XGBoost model or a LightGBM model.

7. An automated verification device for MEC cloud pool data, characterized in that, Including: An acquisition unit, configured to acquire CMDB data of a distributed cloud and real-time data of the distributed cloud; A comparison unit, connected to the acquisition unit, configured to compare the CMDB data and the real-time data to obtain a comparison result; A synchronization unit, connected to the comparison unit, configured to automatically synchronize the real-time data to the CMDB data inconsistent with the real-time data in the comparison result to obtain CMDB synchronization data; A detection unit, connected to the synchronization unit, configured to detect the CMDB synchronization data to obtain a detection result; A repair unit, connected to the detection unit, configured to automatically repair the outliers in the detection result according to the real-time data to obtain CMDB repair data; An integration unit, respectively connected to the synchronization unit and the repair unit, configured to integrate the CMDB synchronization data and the CMDB repair data to obtain CMDB automatic verification data, thereby completing the automated verification of the MEC cloud pool data.

8. The automated verification device for MEC cloud pool data according to claim 7, wherein: The acquisition unit includes a first acquisition unit and a second acquisition unit. The first acquisition unit is configured to acquire CMDB data of the distributed cloud, and the second acquisition unit is configured to acquire real-time data of the distributed cloud; The first acquisition unit includes: A login module, configured to simulate a user to perform an automatic login operation; the simulation of the user to perform an automatic login operation is to access the login page of the CMDB system through an automated program and obtain authentication using pre-configured user email credentials; A scraping module, connected to the login module, configured to simulate a user to scrape a resource list in the MEC cloud pool from the CMDB system according to the authentication information corresponding to the user email credentials, so as to obtain CMDB data of the distributed cloud; Wherein, the resource list in the MEC cloud pool includes physical servers, logical hosts, network devices and security devices.

9. The automated verification device for MEC cloud pool data according to claim 7, wherein It further includes: A generation unit, connected to the integration unit, configured to generate a report from the CMDB automatic verification data and send it to the operation and maintenance personnel.

10. The automated verification device for MEC cloud pool data according to any one of claims 7 to 9, wherein: The detection unit includes: A preprocessing unit, configured to preprocess the CMDB synchronization data; the preprocessing includes normalization, feature extraction, and denoising; A first detection module, connected to the preprocessing unit, configured to use an unsupervised anomaly detection model to detect the preprocessed CMDB synchronization data to obtain a first detection value; The second detection module, connected to the preprocessing unit, is used to detect the preprocessed CMDB synchronization data using a supervised anomaly detection model to obtain a second detection value; The first comparison module, connected to the first detection module, is used to compare the first detection value with a preset first threshold to obtain a first anomaly value; The second comparison module, connected to the second detection module, is used to compare the second detection value with a preset second threshold to obtain a second anomaly value; The summarization module, respectively connected to the first comparison module and the second comparison module, is used to summarize the first detection value, the first anomaly value, the second detection value, and the second anomaly value to obtain a detection result.

Images