An IT asset intelligent supervision platform based on networking

Abstract

The application relates to the technical field of IT asset intelligent supervision platforms, and discloses an IT asset intelligent supervision platform based on a network of numbers, which comprises a data acquisition module, a data fusion module, an analysis module, a resource scheduling module and a self-healing module; the data acquisition module is used for deploying edge computing nodes on each IT asset, collecting equipment state data, network traffic data and user behavior data; a data preprocessing module is used for preliminarily cleaning and formatting the data to generate a preprocessed data packet. The IT asset intelligent supervision platform based on the network of numbers collects the equipment state data, the network traffic data and the user behavior data by deploying the edge computing nodes on each IT asset, realizes comprehensive monitoring of the IT assets, reduces the delay of data transmission in the deployment mode, improves the data collection efficiency, simultaneously reduces the burden of the central server, makes the whole system more efficient and stable, and has the advantages of high efficiency, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy, high safety, high security, high convenience, high intelligence, high compatibility, high expansibility, high stability, high reliability, high accuracy

Description

Technical Field

[0001] This invention relates to the field of intelligent IT asset monitoring platform technology, specifically an intelligent IT asset monitoring platform based on the Internet of Things. Background Technology

[0002] An intelligent IT asset monitoring platform is a system based on Internet of Things (IoT) technology, designed to comprehensively monitor and manage an enterprise's IT assets. However, existing systems often rely on simple data merging methods for data integration, lacking effective data consistency and integrity verification, resulting in low-quality merged data and affecting the accuracy of analysis results. Furthermore, existing systems typically rely on traditional statistical methods for intelligent analysis, lacking advanced time series forecasting and classification regression capabilities, making it impossible to promptly identify and predict potential problems. In addition, existing systems usually adopt static resource allocation strategies for resource scheduling, failing to dynamically adjust resource allocation based on system load and forecast results, leading to low resource utilization and unstable system performance. Summary of the Invention

[0003] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An intelligent IT asset monitoring platform based on the Internet of Things (IoT) includes a data acquisition module, a data fusion module, an analysis module, a resource scheduling module, and a self-healing module. The data acquisition module deploys edge computing nodes on various IT assets to collect device status data, network traffic data, and user behavior data. The data preprocessing module performs preliminary cleaning and formatting of the data, generating preprocessed data packets, which are then transmitted to a central server via a communication protocol. The data fusion module verifies data integrity and consistency after the central server receives the data packets, using a graph model-based data fusion algorithm to fuse data from different data sources, and stores the fused data. The distributed database includes an intelligent analysis module that extracts historical data, performs feature engineering, uses deep learning models for time series prediction, employs ensemble learning methods for classification and regression tasks, and develops a real-time monitoring system that combines anomaly detection algorithms to analyze the data. The resource scheduling module uses reinforcement learning algorithms to dynamically adjust resource allocation, optimizing resource allocation strategies based on current system load and prediction results. The self-healing module periodically scans the system status to detect potential faults. Upon detection, the self-healing system automatically initiates a repair procedure to attempt service recovery. If automatic repair fails, the system generates a work order to notify maintenance personnel for manual intervention.

[0006] As a further aspect of the present invention: the step of deploying edge computing nodes on various IT assets to collect device status data, network traffic data, and user behavior data is as follows: deploying edge computing nodes on each IT asset, wherein the edge computing nodes include a data acquisition unit, a data preprocessing unit, and a data transmission unit; and collecting device status data, network traffic data, and user behavior data.

[0007] As a further aspect of the present invention: the preliminary cleaning and formatting of the data to generate preprocessed data packets, which are then transmitted to the central server via a secure communication protocol, specifically involves the following steps: checking the validity of the data and removing null, erroneous, and outlier values; normalizing different types of data to the same scale; converting the normalized data into a consistent structured format; packaging the structured data into data packets, each containing a timestamp and a set of data records; compressing the data packets; and transmitting the data packets to the central server using the secure communication protocol TLS.

[0008] As a further aspect of the present invention: after the central server receives the data packet, it verifies the data integrity and consistency. A graph-based data fusion algorithm is used to fuse data from different data sources, and the fused data is stored in a distributed database. Specifically, the central server receives data packets from edge computing nodes via the secure communication protocol TLS; verifies the integrity of the data packets; and after verification, compares data packets from different data sources within the same time period, using the following expression:

[0009] ;

[0010] in, Score the data consistency. For the first One data packet, For the first One data packet, For the k-th normalized data record in the i-th data packet, For the k-th normalized data record in the j-th data packet, The total number of data records;

[0011] A graph-based data fusion algorithm is used to fuse data from different data sources. The expression is as follows:

[0012] ;

[0013] ;

[0014] in, For the merged data, For the first Normalized data records from each data source. The total number of data sources, For the first The weight of each data source, For the first Data consistency score between the data source and the reference data source The data packet serves as a reference data source.

[0015] As a further aspect of this invention: the steps of extracting historical data from the database, performing feature engineering, using a deep learning model for time series prediction, using ensemble learning methods for classification and regression tasks, and simultaneously developing a real-time monitoring system, combined with anomaly detection algorithms, to analyze the data, are as follows: Extracting historical data from a distributed database, including device status data, network traffic data, and user behavior data; performing feature extraction and transformation on the extracted historical data to generate feature vectors suitable for model input; using a Long Short-Term Memory (LSTM) network for time series prediction, training an LSTM model using historical data to generate a prediction model; using a random forest for classification and regression tasks, training a random forest model using historical data to generate classification and regression models; employing a monitoring system to read the latest data from the database, monitoring device status, network traffic, and user behavior; and using an isolated forest for anomaly detection.

[0016] As a further aspect of the present invention: the use of a Long Short-Term Memory (LSTM) network for time series prediction involves training an LSTM model using historical data to generate a prediction model, the expression of which is:

[0017] ;

[0018] in, For time The predicted value, For activation function, Here is the weight matrix of the hidden state. For time The hidden state, The input weight matrix, For time The input feature vector, This is a bias term.

[0019] As a further aspect of the present invention: the random forest is used for classification and regression tasks, and a random forest model is trained using historical data to generate classification and regression models, the expressions of which are:

[0020] ;

[0021] in, For the classification results, For the input feature vector, For the number of decision trees, For the first The predicted categories of a decision tree. For category labels, This is an indicator function.

[0022] As a further aspect of the present invention: the method of dynamically adjusting resource allocation using a reinforcement learning algorithm, and optimizing the resource allocation strategy based on the current system load and prediction results, specifically involves the following steps: collecting various state data of the current system, including CPU utilization, memory utilization, disk I / O, and network bandwidth; representing the collected state data as a state vector; setting an initial resource allocation strategy; defining an action space to represent the resource allocation actions that can be taken; defining a reward function to evaluate the system performance after taking an action in a given state; and updating the resource allocation strategy using a reinforcement learning algorithm, with the expression:

[0023] ;

[0024] in, The state-action value function For learning rate, The discount factor represents the weight of future rewards. In order to take action The new state after that, Actions in the new state.

[0025] As a further aspect of the present invention: the system status is periodically scanned to detect potential faults. Once a fault is detected, the self-healing system automatically initiates a repair program to attempt to restore service. If the automatic repair fails, the system generates a work order to notify maintenance personnel for manual intervention. The specific steps are as follows: a scheduled task is set to periodically scan the system's status data, including CPU utilization, memory utilization, disk I / O, and network bandwidth; the latest status data is collected from various IT assets and aggregated to the central server; anomaly detection algorithms are used to detect anomalies in the system status data; an anomaly threshold is set, and if the anomaly score exceeds the threshold, the system is considered to have a fault; the specific location and type of the fault are located based on the feature with the highest anomaly score; a preset self-healing program is initiated to attempt to automatically repair the fault; if the self-healing program fails to repair the fault, fault information is recorded, including the fault time, fault type, and fault location; a work order is generated, and the fault information is sent to maintenance personnel to notify them for manual intervention.

[0026] As a further aspect of the present invention: an anomaly threshold is set; if the anomaly score exceeds the threshold, the system is considered to have a fault, expressed as:

[0027] ;

[0028] in, This is a fault indicator; 1 indicates a fault, and 0 indicates normal operation. For abnormal scores, This is the abnormal threshold.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] By deploying edge computing nodes on various IT assets, comprehensive monitoring of IT assets is achieved by collecting device status data, network traffic data, and user behavior data. This deployment method reduces data transmission latency, improves data collection efficiency, and also reduces the burden on the central server, making the entire system more efficient and stable. After receiving data packets, the central server verifies data integrity and consistency. A graph-based data fusion algorithm is used to merge data from different data sources, and the merged data is stored in a distributed database. This achieves efficient fusion and management of multi-source data. The fusion method not only improves data utilization but also enhances data accuracy and integrity, providing a solid foundation for subsequent intelligent analysis. The use of a distributed database further improves data storage and access efficiency, ensuring high availability and scalability of the system. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the module connections of an intelligent IT asset monitoring platform based on the Internet of Things. Detailed Implementation

[0032] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0033] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0035] Example 1

[0036] Please see Figure 1This is the first embodiment of the present invention, which provides an intelligent IT asset monitoring platform based on the Internet of Things, including a data acquisition module, a data fusion module, an analysis module, a resource scheduling module, and a self-healing module. The data acquisition module is used to deploy edge computing nodes on various IT assets to collect device status data, network traffic data, and user behavior data. The data preprocessing module is used to perform preliminary cleaning and formatting of the data, generating preprocessed data packets, which are then transmitted to the central server via a communication protocol. The data fusion module is used to verify data integrity and consistency after the central server receives the data packets, using a graph model-based data fusion algorithm to fuse data from different data sources and... The merged data is stored in a distributed database. The intelligent analysis module extracts historical data from the database, performs feature engineering, uses deep learning models for time series prediction, and uses ensemble learning methods for classification and regression tasks. It also develops a real-time monitoring system and combines anomaly detection algorithms to analyze the data. The resource scheduling module uses reinforcement learning algorithms to dynamically adjust resource allocation, optimizing resource allocation strategies based on current system load and prediction results. The self-healing module periodically scans the system status to detect potential faults. Once a fault is detected, the self-healing system automatically initiates a repair procedure to attempt service recovery. If automatic repair fails, the system generates a work order to notify maintenance personnel for manual intervention.

[0037] Specifically, edge computing nodes are deployed on various IT assets to collect device status data, network traffic data, and user behavior data. The specific steps are as follows: deploy an edge computing node on each IT asset. The edge computing node includes a data acquisition unit, a data preprocessing unit, and a data transmission unit; collect device status data, network traffic data, and user behavior data.

[0038] It should be noted that the data acquisition module can not only collect data in real time, but also dynamically adjust the data acquisition strategy according to the preset acquisition frequency and conditions to ensure the comprehensiveness and timeliness of the data. By dynamically adjusting the data acquisition strategy, the data acquisition module can flexibly collect data in different time periods and under different conditions to ensure the comprehensiveness and timeliness of the data. The dynamic adjustment mechanism not only improves the flexibility of data acquisition, but also reduces unnecessary data acquisition, reduces the consumption of system resources, and improves the overall efficiency of the system.

[0039] Specifically, the data undergoes initial cleaning and formatting to generate preprocessed data packets, which are then transmitted to the central server via a secure communication protocol. The specific steps are as follows: checking the validity of the data and removing null, erroneous, and outlier values; normalizing different types of data to the same scale; converting the normalized data into a consistent structured format; packaging the structured data into data packets, each containing a timestamp and a set of data records; compressing the data packets; and transmitting the data packets to the central server using the secure communication protocol TLS.

[0040] It should be noted that the data preprocessing module also includes a data encryption function to ensure the security of data during transmission. The data preprocessing module encrypts the data before transmission to ensure that the data is not stolen or tampered with during transmission. The data encryption function greatly improves the security of data transmission, protects the security of sensitive data, and enhances the security of the system.

[0041] Specifically, after the central server receives data packets, it verifies data integrity and consistency. A graph-based data fusion algorithm is used to merge data from different data sources, and the merged data is stored in a distributed database. The specific steps are as follows: the central server receives data packets from edge computing nodes via the secure communication protocol TLS; it verifies the integrity of the data packets; after verification, it compares data packets from different data sources within the same time period, using the following expression:

[0042] ;

[0043] in, Score the data consistency. For the first One data packet, For the first One data packet, For the k-th normalized data record in the i-th data packet, For the k-th normalized data record in the j-th data packet, The total number of data records;

[0044] A graph-based data fusion algorithm is used to fuse data from different data sources. The expression is as follows:

[0045] ;

[0046] ;

[0047] in, For the merged data, For the first Normalized data records from each data source. The total number of data sources, For the first The weight of each data source, For the first Data consistency score between the data source and the reference data source The data packet serves as a reference data source.

[0048] It should be noted that the data fusion module also includes a data quality assessment function, which periodically assesses the quality of the fused data and generates a quality report. By periodically assessing the quality of the fused data, the data fusion module ensures the accuracy and reliability of the data. The quality report can help maintenance personnel understand the data quality status in a timely manner and take necessary measures to optimize it. The data quality assessment function not only improves the credibility of the data, but also provides data support for the continuous optimization of the system, ensuring the long-term stable operation of the system.

[0049] Specifically, historical data is extracted from the database, feature engineering is performed, a deep learning model is used for time series prediction, and ensemble learning methods are used for classification and regression tasks. Simultaneously, a real-time monitoring system is developed, combined with anomaly detection algorithms, to analyze the data. The specific steps are as follows: Historical data, including device status data, network traffic data, and user behavior data, is extracted from the distributed database; features are extracted and transformed from the extracted historical data to generate feature vectors suitable for model input; a Long Short-Term Memory (LSTM) network is used for time series prediction, and a LSTM model is trained using historical data to generate the prediction model; a Random Forest model is used for classification and regression tasks, and a Random Forest model is trained using historical data to generate classification and regression models; a monitoring system is used to read the latest data from the database to monitor device status, network traffic, and user behavior; anisotropic forests are used for anomaly detection; and a Long Short-Term Memory (LSTM) network is used for time series prediction, and a LSTM model is trained using historical data to generate the prediction model, the expression of which is:

[0050] ;

[0051] in, For time The predicted value, For activation function, Here is the weight matrix of the hidden state. For time The hidden state, The input weight matrix, For time The input feature vector, This is the bias term; Random forest is used for classification and regression tasks. The random forest model is trained using historical data to generate the classification and regression models, expressed as:

[0052] ;

[0053] in, For the classification results, For the input feature vector, For the number of decision trees, For the first The predicted categories of a decision tree. For category labels, This is an indicator function.

[0054] It should be noted that the intelligent analysis module also includes a data visualization function, which intuitively displays the analysis results in the form of charts and dashboards. Through the data visualization function, the intelligent analysis module can intuitively display complex analysis results in the form of charts and dashboards, helping operation and maintenance personnel to quickly understand and make decisions. The data visualization function not only improves the understandability of data analysis results, but also simplifies the workflow of operation and maintenance personnel and improves work efficiency.

[0055] Specifically, reinforcement learning algorithms are used to dynamically adjust resource allocation. Based on the current system load and prediction results, the resource allocation strategy is optimized. The specific steps are as follows: Collect various state data of the current system, including CPU utilization, memory utilization, disk I / O, and network bandwidth; represent the collected state data as a state vector; set an initial resource allocation strategy; define an action space representing the possible resource allocation actions; define a reward function to evaluate the system performance after taking an action in a given state; and update the resource allocation strategy using a reinforcement learning algorithm, with the expression:

[0056] ;

[0057] in, The state-action value function For learning rate, The discount factor represents the weight of future rewards. In order to take action The new state after that, Actions in the new state.

[0058] It should be noted that the resource scheduling module also includes a real-time monitoring function for resource usage, which displays the current resource usage of the system in real time. Through the real-time monitoring function, the resource scheduling module displays the current resource usage of the system in real time, helping operation and maintenance personnel to understand the system load status in a timely manner and make dynamic adjustments to resources. The real-time monitoring function for resource usage not only improves the accuracy of resource scheduling, but also reduces problems caused by insufficient or excessive allocation of resources, thereby improving the overall performance of the system.

[0059] Specifically, the system periodically scans its status to detect potential faults. Once a fault is detected, the self-healing system automatically initiates a repair procedure to attempt service recovery. If automatic repair fails, the system generates a work order to notify operations personnel for manual intervention. The specific steps are as follows: 1. Set up a scheduled task to periodically scan the system's status data, including CPU utilization, memory utilization, disk I / O, and network bandwidth; 2. Collect the latest status data from various IT assets and aggregate this data to the central server; 3. Use anomaly detection algorithms to detect anomalies in the system status data; 4. Set an anomaly threshold; if the anomaly score exceeds the threshold, the system is considered to have a fault; 5. Based on the characteristics of the highest anomaly score, locate the specific location and type of the fault; 6. Initiate a preset self-healing procedure to attempt automatic fault repair; 7. If the self-healing procedure fails to repair the fault, record the fault information, including the fault time, fault type, and fault location; 8. Generate a work order and send the fault information to operations personnel to notify them for manual intervention; 9. Set an anomaly threshold; if the anomaly score exceeds the threshold, the system is considered to have a fault, expressed as:

[0060] ;

[0061] in, This is a fault indicator; 1 indicates a fault, and 0 indicates normal operation. For abnormal scores, This is the abnormal threshold.

[0062] It should be noted that the self-healing module also includes a fault prediction function, which uses machine learning algorithms to predict potential faults and perform preventative maintenance in advance. The self-healing module uses machine learning algorithms to analyze historical data, predict potential faults, and perform preventative maintenance in advance to reduce the occurrence of faults. The fault prediction function not only improves the reliability of the system, but also reduces service interruptions caused by sudden faults, thereby improving the stability of the system and the user experience.

[0063] In summary, by deploying edge computing nodes on various IT assets to collect device status data, network traffic data, and user behavior data, comprehensive monitoring of IT assets is achieved. This deployment method reduces data transmission latency, improves data collection efficiency, and also alleviates the burden on the central server, making the entire system more efficient and stable. After receiving data packets, the central server verifies data integrity and consistency. A graph-based data fusion algorithm is used to merge data from different data sources, and the merged data is stored in a distributed database. This achieves efficient fusion and management of multi-source data. The fusion method not only improves data utilization but also enhances data accuracy and integrity, providing a solid foundation for subsequent intelligent analysis. The use of a distributed database further improves data storage and access efficiency, ensuring high availability and scalability of the system.

[0064] Example 2

[0065] Please refer to Table 1 for the second embodiment of the present invention.

[0066] To verify the effectiveness and superiority of the data network-based intelligent IT asset monitoring platform, this embodiment underwent a practical test in a large enterprise data center. This data center has 100 servers, each with an edge computing node deployed to collect device status data, network traffic data, and user behavior data. The entire testing process consisted of the following steps:

[0067] S1. Data Acquisition Module Deployment: Edge computing nodes are deployed on each server. Each edge computing node includes a data acquisition unit, a data preprocessing unit, and a data transmission unit. The data acquisition unit is responsible for collecting device status data (such as CPU utilization, memory utilization, disk I / O, and network bandwidth), network traffic data, and user behavior data. The data preprocessing unit performs preliminary cleaning on the collected data, removing null values, error values, and outliers, and normalizing different types of data to the same scale. The data transmission unit converts the normalized data into a unified structured format, packages it into data packets, and each data packet contains a timestamp and a set of data records. Then, the data packets are transmitted to the central server using the secure communication protocol TLS.

[0068] S2. Data Fusion Module Processing: The central server receives data packets from edge computing nodes via the secure communication protocol TLS, verifies the integrity of the data packets to ensure data integrity and consistency, and uses a graph model-based data fusion algorithm to fuse data from different data sources. The specific steps include comparing data packets from different data sources within the same time period, calculating data consistency scores, and then performing data fusion based on the scores. The fused data is stored in a distributed database for subsequent intelligent analysis.

[0069] S3 Intelligent Analysis Module Applications: Extracts historical data from a distributed database, including device status data, network traffic data, and user behavior data. Performs feature extraction and transformation on the extracted historical data to generate feature vectors suitable for model input. Uses Long Short-Term Memory (LSTM) networks for time series prediction. Trains an LSTM model using historical data to generate a prediction model. Uses random forests for classification and regression tasks. Trains a random forest model using historical data to generate classification and regression models. Develops a real-time monitoring system that reads the latest data from the database to monitor device status, network traffic, and user behavior. Uses isolated forests for anomaly detection to promptly identify anomalies in the system.

[0070] S4. Resource Scheduling Module Optimization: Collect various status data of the current system, including CPU utilization, memory utilization, disk I / O, and network bandwidth. Represent the collected status data as a state vector, set an initial resource allocation strategy, define an action space to represent the resource allocation actions that can be taken, define a reward function to evaluate the system performance after taking actions in a given state, use reinforcement learning algorithms to update the resource allocation strategy, and dynamically adjust resource allocation based on the current system load and prediction results to optimize the resource allocation strategy.

[0071] S5. Self-Healing Module Test: Set up a scheduled task to periodically scan the system's status data, including CPU utilization, memory utilization, disk I / O, and network bandwidth. Collect the latest status data from various IT assets and aggregate this data to the central server. Use anomaly detection algorithms to detect anomalies in the system status data. Set an anomaly threshold. If the anomaly score exceeds the threshold, the system is considered to have a fault. Based on the characteristics of the highest anomaly score, locate the specific location and type of the fault, and start the preset self-healing program to attempt to automatically repair the fault. If the self-healing program fails to repair the fault, record the fault information, including the fault time, fault type, and fault location, generate a work order, and notify the operations and maintenance personnel to intervene manually.

[0072] sheet:

[0073] Table 1: Comparison of existing technologies and the present invention in data center performance.

[0074]

[0075] By comparing the data in the table above, it is clear that the present invention has significant advantages over the prior art in many aspects:

[0076] This invention effectively reduces CPU utilization, decreases system load, and improves overall system performance through intelligent resource scheduling and optimization. The lowest CPU utilization of this invention is 68%, while the highest in the prior art is 78%.

[0077] This invention reduces memory usage and improves memory resource utilization by optimizing memory management and resource allocation, thereby reducing the risk of memory overflow. The memory usage of this invention is as low as 73%, while the highest in the prior art is 82%.

[0078] This invention reduces network bandwidth usage, improves network transmission efficiency, and reduces the possibility of network congestion by preprocessing and compressing data. The minimum network bandwidth of this invention is 88 Mbps, while the maximum of existing technologies is 105 Mbps.

[0079] This invention significantly improves the accuracy of fault detection through advanced anomaly detection algorithms and self-healing modules, enabling timely detection and handling of potential faults, thereby enhancing the reliability and stability of the system. The fault detection rate of this invention is up to 96%, while the highest rate of existing technologies is only 62%.

[0080] This invention dynamically adjusts resource allocation through reinforcement learning algorithms, optimizing resource usage and increasing resource utilization from 70% to 87%, significantly improving the overall performance and resource utilization efficiency of the system. The resource utilization rate of this invention is up to 87%, while the highest in the prior art is only 72%.

[0081] In summary, by deploying edge computing nodes on various IT assets to collect device status data, network traffic data, and user behavior data, comprehensive monitoring of IT assets is achieved. This deployment method reduces data transmission latency, improves data collection efficiency, and also alleviates the burden on the central server, making the entire system more efficient and stable. After receiving data packets, the central server verifies data integrity and consistency. A graph-based data fusion algorithm is used to merge data from different data sources, and the merged data is stored in a distributed database. This achieves efficient fusion and management of multi-source data. The fusion method not only improves data utilization but also enhances data accuracy and integrity, providing a solid foundation for subsequent intelligent analysis. The use of a distributed database further improves data storage and access efficiency, ensuring high availability and scalability of the system.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An IT asset intelligent supervision platform based on a network of numbers, characterized in that, The application relates to an IT asset management system based on edge computing and deep learning. The application comprises a data collection module, a data fusion module, an analysis module, a resource scheduling module and a self-healing module. The data collection module is used for deploying edge computing nodes on each IT asset to collect device state data, network traffic data and user behavior data. The data preprocessing module is used for preliminarily cleaning and formatting the data, generating preprocessed data packets and transmitting the data packets to a central server through a communication protocol. The data fusion module is used for verifying the data integrity and consistency after the central server receives the data packets, fusing the data from different data sources by using a graph model-based data fusion algorithm and storing the fused data in a distributed database. The analysis module is used for extracting historical data from the database, performing feature engineering, using a deep learning model to perform time series prediction, using an ensemble learning method to perform classification and regression tasks, developing a real-time monitoring system and combining an anomaly detection algorithm to analyze the data. The resource scheduling module is used for dynamically adjusting resource allocation by using a reinforcement learning algorithm, optimizing resource allocation strategies according to the current system load and prediction results. The self-healing module is used for periodically scanning the system state, detecting potential faults, automatically starting a repair program to attempt to restore services once a fault is found, and generating a work order to notify operation and maintenance personnel for manual intervention if the automatic repair fails. 2.The IT asset intelligent monitoring platform based on a network of numbers according to claim 1, characterized in that: The edge computing nodes are deployed on each IT asset to collect device state data, network traffic data and user behavior data, and the specific steps include: Deploying edge computing nodes on each IT asset, wherein the edge computing nodes comprise a data collection unit, a data preprocessing unit and a data transmission unit; Collecting device state data, network traffic data and user behavior data. 3.The IT asset intelligent monitoring platform based on a cyber network according to claim 1, characterized in that: The data is preliminarily cleaned and formatted, preprocessed data packets are generated and the data packets are transmitted to a central server through a secure communication protocol, and the specific steps include: Checking the validity of the data and removing null values, error values and abnormal values; Normalizing different types of data to the same scale; Converting the normalized data into a consistent structured format; Packing the structured data into data packets, wherein each data packet contains a timestamp and a set of data records; Compressing the data packets and transmitting the data packets to the central server through a secure communication protocol TLS. 4.The IT asset intelligent monitoring platform based on a network of numbers according to claim 1, characterized in that: After the central server receives the data packets, the data integrity and consistency are verified, the data from different data sources is fused by using a graph model-based data fusion algorithm and the fused data is stored in a distributed database, and the specific steps include: The central server receives the data packets from the edge computing nodes through a secure communication protocol TLS; Performing integrity verification on the data packets; After verification, the data packets from different data sources in the same time period are compared, and the expression is as follows: ; wherein, is a data consistency score, is a first data packet, is a first data packet, is a first data packet, is a first data packet, is a kth normalized data record in an ith data packet, is a kth normalized data record in a jth data packet, is a total number of data records; The data from different data sources is fused by using a graph model-based data fusion algorithm, and the expression is as follows: ; ; wherein, is the normalized data record of the i-th data source, is the total number of data sources, is the normalized data record of the i-th data source, is the total number of data sources, is the weight of the i-th data source, is the weight of the i-th data source, is the data consistency score between the i-th data source and the reference data source, is the data consistency score between the i-th data source and the reference data source, is the data packet of the reference data source. 5.The IT asset intelligent monitoring platform based on a cyber network according to claim 1, wherein: The method comprises the following steps: extracting historical data from the database, performing feature engineering, using a deep learning model to perform time series prediction, using an ensemble learning method to perform classification and regression tasks, developing a real-time monitoring system, and analyzing data using an anomaly detection algorithm. Extract historical data from the distributed database, including device status data, network traffic data, and user behavior data. Perform feature extraction and transformation on the extracted historical data to generate feature vectors suitable for model input. Use a long short-term memory network to perform time series prediction, train an LSTM model using historical data, and generate a prediction model. Use a random forest to perform classification and regression tasks, train a random forest model using historical data, and generate classification and regression models. Use a monitoring system to read the latest data in the database and monitor device status, network traffic, and user behavior. And use an isolation forest for anomaly detection. 6.The IT asset intelligent monitoring platform based on a cyber network according to claim 5, wherein: The long short-term memory network is used to perform time series prediction, the LSTM model is trained using historical data, and the prediction model is generated, which is expressed as: ; wherein, is a prediction value for time , is an activation function, is a weight matrix for hidden state, is a hidden state for time , is a weight matrix for input, is an input feature vector for time , is a bias term. 7.The IT asset intelligent monitoring platform based on a cyber network according to claim 5, wherein: The random forest is used to perform classification and regression tasks, the random forest model is trained using historical data, and the classification and regression models are generated, which are expressed as: ; wherein, is the classification result, is the input feature vector, is the number of decision trees, is the prediction class of the th decision tree, is the class label, is the indicator function. 8.The IT asset intelligent monitoring platform based on a cyber network according to claim 1, wherein: The reinforcement learning algorithm is used to dynamically adjust resource allocation, the current system load and prediction results are used to optimize the resource allocation strategy, and the specific steps include: Collect the status data of the current system, including CPU usage, memory usage, disk I / O, and network bandwidth. Express the collected status data as a state vector. Set an initial resource allocation strategy. Define the action space to represent the resource allocation actions that can be taken. Define a reward function to evaluate the system performance after taking actions in a state. Update the resource allocation strategy using the reinforcement learning algorithm, which is expressed as: ; in, For state-action value function, For learning rate, The discount factor represents the weight of future rewards. In order to take action The new state after that, Actions in the new state. 9.The IT asset intelligent monitoring platform based on a cyber network according to claim 1, wherein: Periodically scan the system status to detect potential faults. Once a fault is found, the self-healing system automatically starts the repair program to try to restore the service. If the automatic repair fails, the system will generate a work order to notify the operation and maintenance personnel for manual intervention. The specific steps include: Set a timing task to periodically scan the system status data, including CPU usage, memory usage, disk I / O, and network bandwidth. Collect the latest status data from each IT asset and aggregate these data to the central server. Use an anomaly detection algorithm to detect abnormal points in the system status data. Set an anomaly threshold. If the anomaly score exceeds the threshold, it is considered that the system has a fault. Locate the specific location and type of the fault based on the feature with the highest anomaly score. Start the pre-set self-healing program to try to automatically repair the fault. If the self-healing program fails to repair the fault, record the fault information, including the fault time, fault type, and fault location. Generate a work order to send the fault information to the operation and maintenance personnel to notify them of manual intervention. 10.The IT asset intelligent monitoring platform based on a network of numbers according to claim 9, characterized in that: Set an anomaly threshold. If the anomaly score exceeds the threshold, it is considered that the system has a fault, which is expressed as: ; wherein, is a fault flag, 1 indicates a fault exists, 0 indicates normal, is an anomaly score, is an anomaly threshold.

Images