Computer monitoring system one-key inspection method and system
The one-key inspection method and system addresses compatibility and data processing issues in computer monitoring by identifying platform and hardware architecture, configuring edge nodes, and using deep learning for anomaly detection, enhancing data collection and maintenance efficiency.
Patent Information
- Application Number
- CN202410940421.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-12-03
AI Technical Summary
Existing computer monitoring systems face challenges in compatibility, data processing, and intelligence, particularly in heterogeneous environments, leading to incomplete and inaccurate data collection and increased system risks.
A one-key inspection method and system that utilizes LLDP network communication technology to identify platform type and hardware architecture, configures edge computing nodes via MQTT, executes tasks with AI algorithms, and employs deep learning for anomaly detection, generating optimization and repair strategies.
The system achieves accurate and efficient data collection, rapid anomaly detection, and intelligent decision-making, significantly reducing operation and maintenance costs while improving response speed and troubleshooting efficiency.
Smart Images

Figure CN119065918A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of computer monitoring system management, in particular to a one-key inspection method and system for a computer monitoring system. Background Art
[0002] Computer monitoring systems are crucial in modern information technology infrastructure, ensuring the stable operation of various network environments. In the early days, they relied on manual inspections, which were inefficient and prone to missing problems. In recent years, automated monitoring technology has emerged to improve operation and maintenance efficiency, but it still faces challenges in compatibility, data processing, and intelligence. Especially in heterogeneous environment monitoring, it is difficult to achieve accurate and efficient adaptation analysis;
[0003] Existing solutions are restricted by specific platforms or hardware architectures, and have limited data transmission and processing capabilities, resulting in incomplete and inaccurate data collection. When processing massive amounts of data, there is a lack of efficient data cleaning and anomaly identification mechanisms, which increases system risks. Therefore, the market urgently needs a computer monitoring system that is cross-platform, has strong hardware adaptability, and integrates deep learning technology to optimize data processing and accurate anomaly detection. It can simplify the process with one-click operation, improve monitoring intelligence and efficiency, and fill the gaps in existing technologies. Summary of the invention
[0004] In view of the above existing problems, the present invention is proposed.
[0005] Therefore, the present invention provides a one-key inspection method and system for a computer monitoring system to solve compatibility limitations, insufficient data processing and intelligence, efficiency and real-time performance, automated and intelligent decision-making, and resource optimization and management problems.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In the first aspect, an embodiment of the present invention provides a one-key inspection method for a computer monitoring system, which includes identifying the platform type and hardware architecture of the monitored system through LLDP network communication technology and selecting a corresponding adapter interface; configuring and activating edge computing nodes according to the adapted interface, and receiving inspection tasks through the MQTT data transmission protocol; executing inspection tasks and dividing them, and issuing task instructions to each edge node for data collection; cleaning, processing and analyzing monitoring data based on the data collected by the edge nodes through a deep learning model to obtain abnormal data; uploading the abnormal data to the central console and integrating the analysis data to generate an inspection report; based on the inspection report results, the central console generates optimization and repair strategies.
[0008] As a preferred solution of the one-key inspection method for a computer monitoring system of the present invention, wherein: the LLDP network communication technology is used to identify the platform type and hardware architecture of the monitored system and select the corresponding adapter interface, the specific steps are:
[0009] Enable LLDP network communication technology, deploy an LLDP monitoring program in the monitoring system, monitor LLDP messages in the network, and obtain the original data set;
[0010] Use Chassis ID TLV device unique identification information, Port ID TLV port location information, SystemName TLV device name information and System Description TLV device to parse the key information fields of LLDP packets;
[0011] Extract key information fields and parse them to identify keywords of platform type and hardware architecture;
[0012] According to the identified platform type and hardware architecture keywords, the application mapping function selects the most appropriate monitoring adapter interface, which is expressed as:
[0013] I = S × A + 5;
[0014] Among them, I represents the output variable of the final adaptation interface, S represents the platform type of the monitored device, A represents the hardware architecture, S×A represents the combined effect of the platform type and the hardware architecture, and +5 represents a fixed basic configuration.
[0015] As a preferred solution of the one-key inspection method of the computer monitoring system of the present invention, wherein: the edge computing node is configured and activated according to the adapted interface, and the inspection task is received through the MQTT data transmission protocol, and the specific steps are:
[0016] Based on the calculated adaptation interface I, the script is called from the adaptation interface to generate the processing function Script(I), which is expressed as:
[0017] Script (I) = (I) 2-D;
[0018] I is the adapter interface, and D is a constant representing the value subtracted from the square of I. The specific value is determined according to the actual application scenario;
[0019] Based on the processing function Script(I), the network settings, data collection configuration, data processing logic, resource management strategy, security settings, log and monitoring configuration proprietary mode are extracted from the database according to the value of I, and the script C for edge computing node configuration is constructed;
[0020] Use the MQTT data transmission protocol to configure MQTT client parameters for edge nodes, and interconnect and be compatible with the MQTT server of the central monitoring system through API application programming interface rules;
[0021] Then, upload the configured script C to the edge node through the SSH protocol and execute the script to activate it;
[0022] After activation, the tested data set is sent to the central monitoring system MQTT server and edge node monitoring is deployed;
[0023] The MQTT client on the edge computing node continuously listens and subscribes to a set of rule topics to receive initial task instructions;
[0024] Based on a set of subscription rules, the MQTT client program of the edge node automatically subscribes to the topic;
[0025] Using the API rules provided by the MQTT client library, initiate a subscription request to the central monitoring system MQTT server to receive and execute inspection tasks.
[0026] As a preferred solution of the one-key inspection method of the computer monitoring system of the present invention, the specific steps of executing the inspection task and dividing it and sending the task instruction to each edge node for data collection are as follows:
[0027] Start executing inspection tasks and analyze them with the help of integrated AI algorithms;
[0028] Based on the analyzed key resource types and levels, the ARS adaptive resource scheduling algorithm is used to automatically adjust hardware resources;
[0029] After adjustment, resource allocation is performed, and the formula is:
[0030]
[0031] Among them, Ealloc represents the resource allocation efficiency, U represents the task urgency, Rreq represents the amount of resources required for the task, Rtotal represents the total available resources, and C1 reflects the resource tension index;
[0032] Based on resource allocation decisions, the ONVIF protocol is remotely configured for cameras and sensors to adjust camera resolution and sensor sampling rate;
[0033] After adjusting the camera resolution and sensor adoption rate, the multi-path transmission MP-TCP protocol is dynamically enabled according to the network connection quality to achieve network bandwidth aggregation and fault switching;
[0034] Based on the requirements, select suitable high-definition cameras, various environmental sensors, ONVIF-compatible device management software, and sensor drivers to deploy the data acquisition platform on the edge nodes;
[0035] Connect all multi-source data to the collection platform and configure corresponding parameters through the provided API rules;
[0036] Then use the NTP protocol synchronization mechanism to calibrate the time synchronization of all data sources;
[0037] After time synchronization calibration, all data sources are instructed to start data collection at the same time. The video stream is transmitted through the network control RTSP protocol, and the sensor data is sent through the MQTT data transmission protocol.
[0038] At the edge node, each frame of video and each piece of sensor data received is accurately timestamped, and the timestamp is used as the key field for data alignment to complete data collection.
[0039] As a preferred solution of the one-key inspection method of the computer monitoring system of the present invention, wherein: the data collected based on the edge node is cleaned and processed by the deep learning model to analyze the monitoring data to obtain abnormal data, and the specific steps are:
[0040] All collected numerical data sets are normalized and cleaned, and the expression is:
[0041]
[0042] Where X is the original data value, min(x) is the minimum value of all values in the data set, max(x) is the maximum value of all values in the data set, and nm is the data value after normalization.
[0043] The missing values after normalization and cleaning are filled with K nearest neighbor interpolation method;
[0044] Divide the preprocessed and cleaned data set into training set, validation set and test set;
[0045] Use the deep learning PyTorch model to build a sparse autoencoder model;
[0046] A multi-layer fully connected neural network is constructed for the encoder, and sparsity is encouraged through the regularization term L1 in the loss function;
[0047] The loss function expression is:
[0048]
[0049] Among them, Ltotal loss function is the loss function, is the error term, measuring the model prediction output The difference between the actual output x, λΣ i ∣w i∣ is the L1 regularization term, λ is a hyperparameter, ∑ is the summation symbol, and w i Represents the weight w i The absolute value of , i is the index variable;
[0050] Another series of multi-layer fully connected networks is constructed for the decoder to reconstruct the original input data from the low-dimensional features generated by the encoder;
[0051] Use the Adam optimizer to iterate and update the model parameters on the training set multiple times through the back propagation algorithm and gradient descent algorithm;
[0052] At the end of a complete pass through the training dataset, the performance of the deep learning sparse autoencoder model is evaluated on the test set, and the reconstruction error distribution on the validation set is analyzed;
[0053] Input the new edge node monitoring data into the trained model and calculate the reconstruction error of this data.
[0054] When the error exceeds the preset threshold, the data point is marked as abnormal, the abnormal data is analyzed, feedback is given, and corresponding measures are taken.
[0055] As a preferred solution of the one-key inspection method of the computer monitoring system of the present invention, wherein: uploading the abnormal data to the central control console and integrating and analyzing the data to generate an inspection report, the specific steps are:
[0056] Obtain data points marked as abnormal from the anomaly detection module of the edge node, and encapsulate this information into structured data packets. Each data packet follows a unified data format.
[0057] Use TLS / SSL protocol to encrypt the encapsulated abnormal data packets;
[0058] After the central console receives the data, it decrypts it through the TLS / SSL protocol, selects a deserializer to convert the serialized data back to its original data structure and verifies its data;
[0059] The decrypted abnormal data is persistently stored in a distributed database system, and the association rule learning algorithm is used to conduct in-depth analysis of the abnormal data, find potential connections between abnormal events, and identify abnormal patterns and frequent abnormal sequences;
[0060] Based on the analysis results of abnormal data and combined with the historical inspection report template, the inspection report is automatically generated using the automated report generation tool;
[0061] Based on the analysis results, data visualization tools are used to convert the analysis results into charts and dashboards to intuitively display abnormal distribution, trends and correlations.
[0062] As a preferred solution of the one-key inspection method for a computer monitoring system of the present invention, wherein: according to the inspection report results, the central control console generates an optimization and repair strategy, and the specific steps are:
[0063] The central control console uses the random forest algorithm to classify abnormal events. According to the severity, impact range and repetitiveness of the abnormalities, it automatically divides them into different levels of emergency, important and minor. The expression is:
[0064]
[0065] Among them, Class represents the final classification result, argmax is a mathematical operator that finds the element that maximizes the function value in the brackets, c∈C is the set of all possible categories, which means the accumulation of the prediction results of T decision trees, Treet(Se) represents the classification prediction of the tth decision tree for a specific sample, and I is an indicator function;
[0066] For each type of exception, the system uses natural language processing (NLP) technology to parse the exception description, accurately match the solution template, and reduce the risk of human misjudgment;
[0067] Based on exception handling requirements, the most suitable operation and maintenance team and automated repair tools are intelligently allocated using genetic algorithms;
[0068] Enable real-time monitoring to track key indicators during the process. Using real-time data visualization tools, the central console can clearly view the progress of all ongoing repair tasks, and promptly identify and intervene in progress delays or resource bottlenecks;
[0069] During the processing, the system uses reinforcement learning algorithms to dynamically adjust the solution based on real-time feedback and emerging data;
[0070] After each exception is processed, the central console collects the processing results, time consumption, resource consumption and other data. Through a closed-loop feedback mechanism, the actual operation experience and results are fed back to the solution knowledge base and resource scheduling algorithm to continuously optimize future decisions.
[0071] Regularly review and analyze the abnormal events that have been handled, and use the root cause analysis (RCA) method to deeply explore the deep-seated reasons for the occurrence of abnormalities.
[0072] In the second aspect, the present invention provides a one-key inspection system for a computer monitoring system, comprising an interface adapter module, a configuration module, an acquisition module, a processing module, a generation module, and an optimization module; the interface adapter module is used to identify the platform type and hardware architecture of the monitored system through LLDP network communication technology and select the corresponding adapter interface; the configuration module is used to configure and activate the edge computing node according to the adapted interface, and receive the inspection task through the MQTT data transmission protocol; the acquisition module is used to execute the inspection task and divide it, and send task instructions to each edge node for data collection; the processing module is used to clean, process and analyze the monitoring data based on the data collected by the edge node through a deep learning model to obtain abnormal data; the generation module is used to upload the abnormal data to the central console and integrate the analysis data to generate an inspection report.
[0073] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the one-key inspection method and system for a computer monitoring system as described in the first aspect of the present invention is implemented.
[0074] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the one-key inspection method and system for a computer monitoring system as described in the first aspect of the present invention is implemented.
[0075] The beneficial effects of the present invention are as follows: the present invention automatically identifies the type and hardware architecture of the monitored system through LLDP network communication technology, selects the best adapter interface, realizes accurate matching of monitoring strategies, greatly simplifies the configuration process, and improves the pertinence and efficiency of monitoring; the efficient configuration and activation of edge computing nodes, combined with the MQTT data transmission protocol, ensures the rapid issuance of inspection tasks and real-time data collection, and maintains the stability of communication and the integrity of data even in an environment with restricted network conditions; overall, the present invention significantly reduces the operation and maintenance costs through automated and intelligent means, improves the response speed and troubleshooting efficiency of the monitoring system, and lays a solid foundation for building a stable, efficient and secure IT operation and maintenance environment; through continuous data analysis and optimization, the system can continuously learn and adapt, gradually improve its own intelligent decision-making capabilities, and bring revolutionary changes to the field of IT operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0077] Figure 1 This is a flow chart of the one-key inspection method for a computer monitoring system in Example 1.
[0078] Figure 2 This is a flow chart of integrating and analyzing data to generate an inspection report in Example 1. DETAILED DESCRIPTION
[0079] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0080] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0081] 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0082] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a one-key inspection method for a computer monitoring system, comprising the following steps:
[0083] S1. Identify the platform type and hardware architecture of the monitored system through LLDP network communication technology and select the corresponding adapter interface.
[0084] Furthermore, LLDP network communication technology is enabled, and an LLDP monitoring program is deployed in the monitoring system to monitor LLDP messages in the network and obtain the original data set;
[0085] LLDP messages include: management address, system description, system name, and device capability information;
[0086] Use Chassis ID TLV device unique identification information, Port ID TLV port location information, SystemName TLV device name information and System Description TLV device to parse the key information fields of LLDP packets;
[0087] Chassis ID TLV: unique physical or logical identifier used to identify the device sending the LLDP message; helps the network management system identify and track specific devices in the network, especially in large networks, which is helpful for asset management and fault location;
[0088] Port ID TLV: It is the identifier of the network interface that sends the LLDP message. It provides the precise location information of the message source, so that the administrator can know exactly which specific port the network traffic enters and exits from. It is very important for diagnosing network problems and understanding network topology.
[0089] System Name TLV: is the system name of the sending device, usually a friendly name for the device, which is convenient for human identification and differentiation of devices in network management. Especially when the system description information may contain a lot of technical details, the system name provides a concise identifier;
[0090] System Description TLV: provides more detailed description information of the sending device. It is the main source of information for identifying the device type, platform, and hardware architecture. It is essential for automated system identification, configuration management, and troubleshooting. By analyzing this field, you can learn the detailed functions of the device.
[0091] Match the parsed information with a pre-built database of characteristic strings of known system types and hardware architectures;
[0092] Extract key information fields and parse them to identify keywords of platform type and hardware architecture;
[0093] The platform type refers to the operating system, which determines the system's basic operating environment, supported applications, system call methods, and management interfaces. It is crucial for monitoring systems because it directly affects the selection of monitoring tools, compatibility settings, and how to interpret and process the data collected from the system;
[0094] Hardware architecture refers to the physical structure and organization of a computer system, including processor type, memory architecture, and bus structure. Different hardware architectures affect the way software is compiled and run. The monitoring system needs to select appropriate monitoring agents, drivers, or tools based on the hardware architecture to ensure efficient and accurate data collection.
[0095] According to the identified platform type and hardware architecture keywords, the application mapping function selects the most appropriate monitoring adapter interface, which is expressed as:
[0096] I = S × A + 5;
[0097] Among them, I represents the output variable of the final adaptation interface, S represents the platform type of the monitored device, A represents the hardware architecture, S×A represents the combined effect of the platform type and the hardware architecture, and +5 represents a fixed basic configuration;
[0098] It should be noted that this step uses LLDP network communication technology combined with intelligent analysis and matching strategies, which significantly improves the automation and intelligence level of the monitoring system. It not only simplifies the management and monitoring of network equipment, but also optimizes resource allocation and improves the efficiency of data collection and analysis, providing strong support for building an efficient and stable network monitoring system.
[0099] S2. Configure and activate the edge computing node according to the adapted interface, and receive the inspection task through the MQTT data transmission protocol.
[0100] Furthermore, based on the calculated adaptation interface I, a script is called from the adaptation interface to generate a processing function Script(I), which is expressed as:
[0101] Script (I) = (I) 2-D;
[0102] I is the adapter interface, and D is a constant representing the value subtracted from the square of I. The specific value is determined according to the actual application scenario;
[0103] Based on the processing function Script(I), the network settings, data collection configuration, data processing logic, resource management strategy, security settings, log and monitoring configuration proprietary mode are extracted from the database according to the value of I, and the script C for edge computing node configuration is constructed;
[0104] Use the MQTT data transmission protocol to configure MQTT client parameters for edge nodes, and interconnect and be compatible with the MQTT server of the central monitoring system through API application programming interface rules;
[0105] The MQTT data transmission protocol is a lightweight messaging protocol suitable for resource-constrained devices and low-bandwidth, high-latency, and unreliable network environments.
[0106] API is a bridge between software and software. It enables different software applications to communicate and interact with each other, share data and functions, without knowing each other's internal implementation details.
[0107] MQTT client parameters include: server address, port, client ID, user name and password, etc.
[0108] Then, upload the configured script C to the edge node through the SSH protocol and execute the script to activate it;
[0109] First, use the SSH client in the central management system to establish a secure remote connection to the target edge node;
[0110] After connecting to the edge node, use the SCP command to transfer the locally generated configuration script C to the specified directory of the edge node;
[0111] Then run the command through the SSH session to ensure that the script can execute script C on the edge node to activate the specific functions and configurations of the edge node;
[0112] SSH protocol is a network security protocol used to provide secure remote login and other network services on an insecure network.
[0113] After activation, a simple functional test is performed and the tested data set is sent to the central monitoring system MQTT server to verify whether the data can be transmitted normally and ensure that the edge node monitoring system is ready;
[0114] The MQTT client on the edge computing node continuously listens and subscribes to a set of rule topics to receive initial task instructions;
[0115] Functional testing includes: network connectivity testing, data transmission verification, configuration validity check, resource management and performance testing, security function verification, log and monitoring system verification;
[0116] Based on a set of subscription rules, the MQTT client program of the edge node automatically subscribes to specific topics as needed.
[0117] Using the API rules provided by the MQTT client library, initiate a subscription request to the central monitoring system MQTT server to receive and execute inspection tasks;
[0118] It should be noted that edge computing nodes can be effectively configured, activated and put into operation, maintaining close contact with the central monitoring system to ensure the security of data transmission and the efficiency of task execution.
[0119] S3: Execute inspection tasks and divide them, and send task instructions to each edge node for data collection.
[0120] Going a step further, it starts to perform inspection tasks and analyzes them with the help of integrated AI algorithms to identify the types and levels of key resources required;
[0121] Based on the analysis results, the ARS adaptive resource scheduling algorithm is used to automatically adjust hardware resources;
[0122] ARS adaptive resource scheduling algorithm: is an intelligent resource management strategy designed to optimize the allocation and use of computing resources, especially in edge computing, cloud computing or data center environments;
[0123] Hardware resources include: dynamically adjusting the number of GPU cores, adjusting service quality parameters based on network conditions, and using prediction models to plan storage usage in advance;
[0124] After adjustment, resource allocation is performed, and the formula is:
[0125]
[0126] Ealloc represents resource allocation efficiency. represents square root, U represents task urgency, Rreq represents the amount of resources required for the task, Rtotal represents the total available resources, and C1 is the resource tension index, which is used to measure the tension level when allocating resources;
[0127] Based on resource allocation decisions, the ONVIF protocol is used to remotely configure cameras and sensors.
[0128] Adjust camera resolution and sensor sampling rate;
[0129] The ONVIF protocol is an open network video interface standard designed to promote interoperability between video surveillance devices and management systems produced by different manufacturers;
[0130] After adjusting the camera resolution and sensor adoption rate, the multi-path transmission MP-TCP protocol is dynamically enabled according to the network connection quality to achieve network bandwidth aggregation and fault switching;
[0131] The multi-path transmission MP-TCP protocol uses multiple network paths to transmit data simultaneously, thereby improving transmission performance, reliability and fault tolerance. Even if there is congestion or link failure in the network, MPTCP can automatically bypass the problem path to ensure the continuity and efficiency of data transmission;
[0132] Based on the needs, select suitable high-definition cameras, various environmental sensors, ONVIF-compatible device management software, and sensor drivers to deploy data acquisition platforms on edge nodes, support multi-source data access, and configure time synchronization NTP servers to ensure that the time base of all devices is consistent;
[0133] The data collection platform is an integrated system that includes: data source integration, data processing and conversion, data storage, real-time and batch processing, data transmission, API and integration, security and compliance, monitoring and management, scalability, data visualization and analysis;
[0134] Data source integration: the ability to connect and integrate data sources from different devices, sensors, systems or services, whether it is an IoT device, database or API interface;
[0135] Data processing and conversion: The platform provides processing functions such as data cleaning, filtering, format conversion, aggregation and standardization to ensure the quality and consistency of data, making it more suitable for subsequent analysis and storage;
[0136] Data storage: The platform can store the collected data in a suitable database or file system, including relational databases, NoSQL databases, Hadoop HDFS, and cloud storage services;
[0137] Real-time and batch processing: supports the processing of real-time data streams, and can also handle batch loading and analysis of historical data;
[0138] Data transmission: using various communication protocols, such as MQTT, AMQP, HTTP(S), etc., to ensure data is transmitted securely and efficiently from the data source to the data storage or analysis system;
[0139] API and Integration: Provide API interfaces to enable external applications and services to interact with the data collection platform to obtain data or control data flow;
[0140] Security and compliance: Ensure the security of data transmission and storage, and comply with relevant data protection regulations and standards, such as GDPR and HIPAA;
[0141] Monitoring and management: The platform has built-in monitoring tools to monitor the status of data flow and ensure the stability and reliability of the data collection process;
[0142] Scalability: The ability to easily expand its processing power and storage capacity as data volumes grow and needs change;
[0143] Data visualization and analysis: Some platforms also provide data visualization and basic analysis tools to help users understand and use the collected data;
[0144] Multi-source data includes: visual data, audio data, text data, sensor data, physiological signal data, location data, and behavioral data;
[0145] Connect all multi-source data to the collection platform and configure corresponding parameters through the provided API rules;
[0146] Then use the NTP protocol synchronization mechanism to calibrate the time synchronization of all data sources to ensure that the time error is within an acceptable range and does not exceed the millisecond level;
[0147] NTP protocol is an application layer protocol used to synchronize computer system clocks on the network. Its main goal is to improve the accuracy and reliability of time synchronization to ensure that all devices in the distributed network can maintain time consistency.
[0148] After time synchronization calibration, all data sources are instructed to start data collection at the same time. The video stream is transmitted through the network control RTSP protocol, and the sensor data is sent through the MQTT data transmission protocol.
[0149] The RTSP protocol is an application layer protocol used to control the transmission of real-time media data streams. Its purpose is to achieve one-to-many multimedia data stream transmission on IP networks, and is particularly suitable for real-time applications.
[0150] At the edge node, each frame of video and each piece of sensor data received is accurately timestamped, and the timestamp is used as the key field for data alignment to complete data collection;
[0151] It should be noted that through intelligent resource scheduling, efficient data collection and transmission, and deep learning analysis, the automated execution of inspection tasks and the rapid identification of abnormal data have been achieved, greatly improving the data processing efficiency and accuracy in the edge computing environment.
[0152] S4: The data collected from the edge nodes is cleaned, processed and analyzed through a deep learning model to obtain abnormal data.
[0153] Furthermore, all collected numerical data sets are normalized and cleaned so that they fall between 0 and 1. The expression is:
[0154]
[0155] Where X is the original data value, min(x) is the minimum value of all values in the data set, max(x) is the maximum value of all values in the data set, and xnorm is the data value after normalization.
[0156] The missing values after normalization and cleaning are filled with K nearest neighbor interpolation method;
[0157] The preprocessed and cleaned data set is divided into 80% training set, 10% validation set and 10% test set;
[0158] Use the deep learning PyTorch model to build a sparse autoencoder model, which includes: encoder and decoder;
[0159] A multi-layer fully connected neural network is constructed for the encoder, and sparsity is encouraged through the regularization term L1 in the loss function, so that the model only relies on a small part of the key feature data of the input data for decision-making, ignoring unimportant information, thereby achieving the effect of feature data selection and improving the generalization ability of the model;
[0160] The multi-layer fully connected neural network includes: input layer, hidden layer, and output layer;
[0161] Input layer: It is the first layer of the neural network. Its main responsibility is to receive raw data. It serves as the entrance for data to enter the network and converts the actual numerical data into a form that the network can process, preparing for subsequent processing and feature learning.
[0162] Hidden layer: The hidden layer is located between the input layer and the output layer. There can be one or more hidden layers. In the autoencoder, the hidden layer plays a core role in data encoding and decoding. The hidden layer of the encoder is responsible for data feature extraction. It maps the input data to a low-dimensional space through nonlinear transformation, aiming to capture the key features of the data. The hidden layer of the decoder performs the inverse process and tries to reconstruct the original data from the compressed representation.
[0163] Output layer: The output layer is the final stage of the neural network. Its task is to generate the final output of the model. By minimizing the difference between the reconstructed data and the original data, the network learns how to encode and decode the data effectively, while maintaining the simplicity and generalization ability of the model through regularization terms.
[0164] The loss function expression is:
[0165]
[0166] Among them, Ltotal loss function is the loss function, is the error term, measuring the model prediction output The difference between the actual output x, λ∑ i |w i | is the L1 regularization term, λ is a hyperparameter, ∑ is the summation symbol, wi represents the absolute value of the weight wi, and i is the variable that should be indexed;
[0167] Another series of multi-layer fully connected networks is constructed for the decoder to reconstruct the original input data from the low-dimensional features generated by the encoder;
[0168] Use the Adam optimizer to iteratively update the model parameters on the training set through the back-propagation algorithm and the gradient descent algorithm to reduce the loss function value;
[0169] At the end of a complete traversal of the training dataset, the performance of the deep learning sparse autoencoder model is evaluated on the test set, the reconstruction error distribution on the validation set is analyzed, and a reasonable threshold is determined to distinguish normal data from abnormal data;
[0170] Input the new edge node monitoring data into the trained model and calculate the reconstruction error of the data. When the error exceeds the preset threshold, the data point is marked as abnormal, and the abnormal data is analyzed, fed back and countermeasures are taken.
[0171] It should be noted that deep learning technology is used for data cleaning, feature learning and anomaly detection, and the autoencoder model is used to effectively identify anomalies in the edge node monitoring data, thereby improving the monitoring efficiency and response speed of the system.
[0172] S5. Upload the abnormal data to the central console and integrate and analyze the data to generate an inspection report.
[0173] Furthermore, the anomaly detection module of the edge node obtains data points that have been marked as abnormal, and encapsulates this information into structured data packets. Each data packet follows a unified data format, which is convenient for the central console to parse;
[0174] Use TLS / SSL protocol to encrypt the encapsulated abnormal data packets to ensure the security and integrity of the data during the upload process;
[0175] The TLS / SSL protocol is a protocol used to provide security in network communications. It uses digital certificates and public key infrastructure (PKI) to ensure the identities of both parties in communication, ensure that data is sent to the correct recipient, and that the recipient is also sure of the sender's identity. Before data transmission, the TLS / SSL protocol allows the client and server to securely exchange encryption keys. After the exchange is completed, the client and server will use these keys to encrypt and decrypt data transmission to ensure that even if the data is intercepted, it cannot be read. The message authentication code (MAC) is used to verify that the data has not been tampered with during transmission to ensure data integrity.
[0176] After the central console receives the data, it will decrypt it through the TLS / SSL protocol;
[0177] After decryption, the console parses the data, determines the format used by the data, selects a deserializer to convert the serialized data back to its original data structure and validates the data to ensure that all necessary fields exist and conform to the expected format;
[0178] Serialized data is a form of expression that converts a data structure or object state into a format that can be stored or transmitted. Deserialization is the reverse process of serialization, which is to convert the serialized data stream back to its original data structure or object state so that the data can be interpreted and used by the program.
[0179] The decrypted abnormal data is persistently stored in the distributed database system;
[0180] Then, we use association rule learning algorithms to conduct in-depth analysis of abnormal data, find potential connections between abnormal events, and identify abnormal patterns and frequent abnormal sequences;
[0181] Association rule learning is a data mining technique used to discover associations in a data set;
[0182] Based on the analysis results of abnormal data and combined with the historical inspection report template, the inspection report is automatically generated using the automated report generation tool;
[0183] Inspection reports should include: abnormal overview, key abnormal events, trend analysis, early warning suggestions, and correlation analysis;
[0184] Then, based on the analysis results, data visualization tools are used to convert the analysis results into charts and dashboards to intuitively display abnormal distribution, trends, and associations;
[0185] It should be noted that this process ensures the safe transmission, effective analysis and clear reporting of abnormal data, providing strong support for system operation and maintenance.
[0186] S6. Based on the inspection report results, the central control console generates optimization and repair strategies.
[0187] Furthermore, the central control console uses the random forest algorithm to classify abnormal events, automatically classifying them into different levels of emergency, major, and minor according to the severity, scope of impact, and repetitiveness of the abnormalities. The expression is:
[0188]
[0189] Class represents the final classification result, that is, the category to which the sample belongs according to the prediction of random forest. argmax is a mathematical operator used to find the element that maximizes the function value in the brackets. c∈C is the set of all possible categories, and c is an element in this set, indicating that element c is a member of set C. is a summation operator, which means to accumulate the prediction results of T to T decision trees. Treet(Sample) represents the classification prediction of the t-th decision tree for a specific sample. I(·) is an indicator function.
[0190] For emergency abnormal data processing: the system should automatically trigger an alarm immediately, notify the relevant operation and maintenance personnel or team, and initiate an emergency response process, such as automatic shutdown and isolation of the affected system or service to prevent further damage;
[0191] Furthermore, for important abnormal data processing: the system will send warning emails and SMS to designated technicians and automatically execute mitigation measures;
[0192] For minor abnormal data processing: These abnormalities may have a small impact on the system and can be repaired through automatic repair scripts;
[0193] The random forest algorithm is an ensemble learning method based on multiple decision trees;
[0194] For each type of exception, the system uses natural language processing (NLP) technology to parse the exception description, accurately match the solution template, and reduce the risk of human misjudgment;
[0195] Natural Language Processing (NLP) technology: It is an important branch of artificial intelligence (AI), focusing on enabling computers to understand, interpret, process and generate human natural language;
[0196] Based on exception handling requirements, the most suitable operation and maintenance team and automated repair tools are intelligently allocated using genetic algorithms;
[0197] Genetic algorithm is a heuristic search algorithm designed to solve optimization and search problems. It finds the optimal solution or approximate optimal solution by imitating the processes of inheritance, mutation, natural selection and hybridization in natural evolution.
[0198] Enable real-time monitoring to track key indicators during the process. Using real-time data visualization tools, the central console can clearly view the progress of all ongoing repair tasks, and promptly identify and intervene in progress delays or resource bottlenecks;
[0199] During the processing, the system uses reinforcement learning algorithms to dynamically adjust the solution based on real-time feedback and emerging data;
[0200] Reinforcement learning algorithms are a type of machine learning method that allows an agent to learn how to take actions to maximize a certain cumulative reward while interacting with its environment;
[0201] After each exception is processed, the central console collects the processing results, time consumption, resource consumption and other data. Through a closed-loop feedback mechanism, the actual operation experience and results are fed back to the solution knowledge base and resource scheduling algorithm to continuously optimize future decisions.
[0202] Regularly review and analyze the abnormal events that have been handled, and use the root cause analysis (RCA) method to deeply explore the deep-seated causes of the abnormalities;
[0203] Root Cause Analysis (RCA) is a systematic problem-solving approach used to identify the causes of a problem, not just the symptoms, by digging deeper into the real causes behind the problem, so as to develop effective corrective actions to prevent similar problems from happening again in the future.
[0204] It should be noted that this strategy system makes full use of modern AI technologies, including random forests, NLP, genetic algorithms, real-time data visualization, reinforcement learning, and RCA, to achieve intelligent classification, precise processing, and continuous optimization of abnormal events, greatly improving system maintenance efficiency and reliability.
[0205] The present embodiment also provides a one-key inspection system for a computer monitoring system, comprising an interface adapter module, a configuration module, an acquisition module, a processing module, a generation module, and an optimization module; the interface adapter module is used to identify the platform type and hardware architecture of the monitored system through LLDP network communication technology to select a corresponding adapter interface; the configuration module is used to configure and activate edge computing nodes according to the adapted interface, and receive inspection tasks through the MQTT data transmission protocol; the acquisition module is used to execute inspection tasks and divide them, and issue task instructions to each edge node for data collection; the processing module is used to clean, process and analyze monitoring data based on the data collected by the edge nodes through a deep learning model to obtain abnormal data; the generation module is used to upload the abnormal data to the central console and integrate the analysis data to generate an inspection report; the optimization module is used for the central console to generate optimization and repair strategies based on the inspection report results.
[0206] This embodiment also provides a computer device, which is suitable for the one-key inspection method and system of a computer monitoring system, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the one-key inspection method and system of a computer monitoring system proposed in the above embodiment.
[0207] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0208] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the one-key inspection method and system for a computer monitoring system proposed in the above embodiment are implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0209] In summary, the present invention realizes the monitoring and understanding of user behavior through the analysis of user file operation behavior, can accurately capture the user's operation habits and behavior patterns, provide basic data for the subsequent generation of encryption strategies, and also help the system to detect and prevent abnormal behaviors; predict the user's future operations according to the user's behavior habits, so as to formulate encryption strategies more intelligently; more accurately protect user privacy, reduce the risk of data leakage, and improve the data security and confidentiality of the system; the present invention better adapts to the user's operation habits and needs, improves the intelligence level of the encryption algorithm and user experience, and enhances the flexibility and adaptability of the system.
[0210] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of a one-key inspection method for a computer monitoring system is provided.
[0211] Two similar network monitoring systems were set up, named Innovative System and Traditional System. Both systems were deployed in the same network environment, including the same network devices, servers and edge nodes. The same number and types of monitoring devices were deployed in both systems, including high-definition cameras, temperature sensors and traffic monitors. The Innovative System and Traditional System were used to collect network monitoring data for one week. The Innovative System adopted LLDP network communication technology, deep learning model and association rule learning algorithm for data processing and anomaly detection, while the traditional system used rule-based anomaly detection method and manual data processing process. The performance indicators of the two systems were compared in terms of data collection efficiency, anomaly detection accuracy, resource utilization and processing delay.
[0212] The details are shown in the following table:
[0213] Table 1 Experimental record table
[0214]
[0215] According to the data analysis of the above table, it can be clearly seen that the effectiveness and superiority of the inventive method of the present invention. The innovative system (120Mbps) is 50% higher than the traditional system (80Mbps), which is attributed to the use of LLDP network communication technology and intelligent resource scheduling algorithm; the anomaly detection accuracy of the innovative system reaches 98%, while the traditional system is only 82%. This shows that the deep learning model and association rule learning algorithm significantly improve the accuracy and efficiency of anomaly detection; the innovative system has achieved 85% in resource utilization, which is 25 percentage points higher than the 60% of the traditional system, reflecting the effectiveness of the intelligent resource scheduling algorithm; the processing delay of the innovative system is only 5ms, which is much lower than the 20ms of the traditional system, which shows the superiority of the deep learning model and ARs adaptive resource scheduling algorithm in processing speed.
[0216] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A one-key inspection method for a computer monitoring system, characterized in that: include: Identify the platform type and hardware architecture of the monitored system through LLDP network communication technology and select the corresponding adapter interface; Configure and activate edge computing nodes according to the adapted interface, and receive inspection tasks through the MQTT data transmission protocol; Execute inspection tasks and divide them, and send task instructions to each edge node for data collection; The data collected from edge nodes is cleaned, processed and analyzed through deep learning models to obtain abnormal data. Upload abnormal data to the central console and integrate and analyze the data to generate inspection reports; Based on the inspection report results, the central console generates optimization and repair strategies.
2. The one-key inspection method for a computer monitoring system according to claim 1, characterized in that: The specific steps of identifying the platform type and hardware architecture of the monitored system and selecting the corresponding adapter interface through the LLDP network communication technology are as follows: Enable LLDP network communication technology, deploy an LLDP monitoring program in the monitoring system, monitor LLDP messages in the network, and obtain the original data set; Use Chassis ID TLV device unique identification information, PortID TLV port location information, System Name TLV device name information and System Description TLV device to parse the key information fields of LLDP packets; Extract key information fields and parse them to identify keywords of platform type and hardware architecture; According to the identified platform type and hardware architecture keywords, the application mapping function selects the most appropriate monitoring adapter interface, which is expressed as: I = S × A + 5; Among them, I represents the output variable of the final adaptation interface, S represents the platform type of the monitored device, A represents the hardware architecture, S×A represents the combined effect of the platform type and the hardware architecture, and +5 represents a fixed basic configuration.
3. The one-key inspection method for a computer monitoring system as claimed in claim 2, characterized in that: The edge computing node is configured and activated according to the adapted interface, and the inspection task is received through the MQTT data transmission protocol. The specific steps are as follows: Based on the calculated adaptation interface I, the script is called from the adaptation interface to generate the processing function Script(I), which is expressed as: Script (I) = (I) 2-D; I is the adapter interface, and D is a constant representing the value subtracted from the square of I. The specific value is determined according to the actual application scenario; Based on the processing function Script(I), the network settings, data collection configuration, data processing logic, resource management strategy, security settings, log and monitoring configuration proprietary mode are extracted from the database according to the value of I, and the script C for edge computing node configuration is constructed; Use the MQTT data transmission protocol to configure MQTT client parameters for edge nodes, and interconnect and be compatible with the MQTT server of the central monitoring system through API application programming interface rules; Then, upload the configured script C to the edge node through the SSH protocol and execute the script to activate it; After activation, the tested data set is sent to the central monitoring system MQTT server and edge node monitoring is deployed; The MQTT client on the edge computing node continuously listens and subscribes to a set of rule topics to receive initial task instructions; Based on a set of subscription rules, the MQTT client program of the edge node automatically subscribes to the topic; Using the API rules provided by the MQTT client library, initiate a subscription request to the central monitoring system MQTT server to receive and execute inspection tasks.
4. The one-key inspection method and system for a computer monitoring system as claimed in claim 3, characterized in that: The inspection tasks are executed and divided, and task instructions are sent to each edge node for data collection. The specific steps are as follows: Start executing inspection tasks and analyze them with the help of integrated AI algorithms; Based on the analyzed key resource types and levels, the ARS adaptive resource scheduling algorithm is used to automatically adjust hardware resources; After adjustment, resource allocation is performed, and the formula is: Among them, Ealloc represents the resource allocation efficiency, U represents the task urgency, Rreq represents the amount of resources required for the task, Rtotal represents the total available resources, and C1 reflects the resource tension index; Based on resource allocation decisions, the ONVIF protocol is remotely configured for cameras and sensors to adjust camera resolution and sensor sampling rate; After adjusting the camera resolution and sensor adoption rate, the multi-path transmission MP-TCP protocol is dynamically enabled according to the network connection quality to achieve network bandwidth aggregation and fault switching; Based on the requirements, select suitable high-definition cameras, various environmental sensors, ONVIF-compatible device management software, and sensor drivers to deploy the data acquisition platform on the edge nodes; Connect all multi-source data to the collection platform and configure corresponding parameters through the provided API rules; Then use the NTP protocol synchronization mechanism to calibrate the time synchronization of all data sources; After time synchronization calibration, all data sources are instructed to start data collection at the same time. The video stream is transmitted through the network control RTSP protocol, and the sensor data is sent through the MQTT data transmission protocol. At the edge node, each frame of video and each piece of sensor data received is accurately timestamped, and the timestamp is used as the key field for data alignment to complete data collection.
5. The one-key inspection method and system for a computer monitoring system as claimed in claim 4, characterized in that: The data collected based on the edge node is cleaned, processed and analyzed by the deep learning model to obtain abnormal data. The specific steps are as follows: All collected numerical data sets are normalized and cleaned, and the expression is: Where X is the original data value, min(x) is the minimum value of all values in the data set, max(x) is the maximum value of all values in the data set, and nm is the data value after normalization. The missing values after normalization and cleaning are filled with K nearest neighbor interpolation method; Divide the preprocessed and cleaned data set into training set, validation set and test set; Use the deep learning PyTorch model to build a sparse autoencoder model; A multi-layer fully connected neural network is constructed for the encoder, and sparsity is encouraged through the regularization term L1 in the loss function; The loss function expression is: Among them, Ltotal loss function is the loss function, is the error term, measuring the model prediction output The difference between the actual output x and λΣ i ∣w i ∣ is the L1 regularization term, λ is a hyperparameter, ∑ is the summation symbol, and w i Represents the weight w i The absolute value of , i is the index variable; Another series of multi-layer fully connected networks is constructed for the decoder to reconstruct the original input data from the low-dimensional features generated by the encoder; Use the Adam optimizer to iterate and update the model parameters on the training set multiple times through the back propagation algorithm and gradient descent algorithm; At the end of a complete pass through the training dataset, the performance of the deep learning sparse autoencoder model is evaluated on the test set, and the reconstruction error distribution on the validation set is analyzed; Input the new edge node monitoring data into the trained model and calculate the reconstruction error of this data. When the error exceeds the preset threshold, the data point is marked as abnormal, the abnormal data is analyzed, feedback is given, and corresponding measures are taken.
6. The one-key inspection method and system for a computer monitoring system as claimed in claim 5, characterized in that: The specific steps of uploading abnormal data to the central console and integrating and analyzing the data to generate an inspection report are as follows: Obtain data points marked as abnormal from the anomaly detection module of the edge node, and encapsulate this information into structured data packets. Each data packet follows a unified data format. Use TLS / SSL protocol to encrypt the encapsulated abnormal data packets; After the central console receives the data, it decrypts it through the TLS / SSL protocol, selects a deserializer to convert the serialized data back to its original data structure and verifies its data; The decrypted abnormal data is persistently stored in a distributed database system, and the association rule learning algorithm is used to conduct in-depth analysis of the abnormal data, find potential connections between abnormal events, and identify abnormal patterns and frequent abnormal sequences; Based on the analysis results of abnormal data and combined with the historical inspection report template, the inspection report is automatically generated using the automated report generation tool; Based on the analysis results, data visualization tools are used to convert the analysis results into charts and dashboards to intuitively display abnormal distribution, trends and correlations.
7. The one-key inspection method and system for a computer monitoring system as claimed in claim 6, characterized in that: According to the inspection report results, the central control console generates an optimization and repair strategy, the specific steps are: The central control console uses the random forest algorithm to classify abnormal events. According to the severity, impact range and repetitiveness of the abnormalities, it automatically divides them into different levels of emergency, important and minor. The expression is: Among them, Class represents the final classification result, argmax is a mathematical operator that finds the element that maximizes the function value in the brackets, c∈C is the set of all possible categories, which means the accumulation of the prediction results of T decision trees, Treet(Se) represents the classification prediction of the tth decision tree for a specific sample, and I is an indicator function; For each type of exception, the system uses natural language processing (NLP) technology to parse the exception description, accurately match the solution template, and reduce the risk of human misjudgment; Based on exception handling requirements, the most suitable operation and maintenance team and automated repair tools are intelligently allocated using genetic algorithms; Enable real-time monitoring to track key indicators during the process. Using real-time data visualization tools, the central console can clearly view the progress of all ongoing repair tasks, and promptly identify and intervene in progress delays or resource bottlenecks; During the processing, the system uses reinforcement learning algorithms to dynamically adjust the solution based on real-time feedback and emerging data; After each exception is processed, the central console collects the processing results, time consumption, resource consumption and other data. Through a closed-loop feedback mechanism, the actual operation experience and results are fed back to the solution knowledge base and resource scheduling algorithm to continuously optimize future decisions. Regularly review and analyze the abnormal events that have been handled, and use the root cause analysis (RCA) method to deeply explore the deep-seated reasons for the occurrence of abnormalities.
8. A one-key inspection system for a computer monitoring system, based on the one-key inspection method and system for a computer monitoring system according to any one of claims 1 to 7, characterized in that: include: Interface adaptation module, configuration module, acquisition module, processing module, generation module, optimization module; The interface adapter module is used to identify the platform type and hardware architecture of the monitored system through LLDP network communication technology and select the corresponding adapter interface; The configuration module is used to configure and activate the edge computing node according to the adapted interface, and receive the inspection task through the MQTT data transmission protocol; The acquisition module is used to execute inspection tasks and divide them, and issue task instructions to each edge node for data collection; The processing module is used to clean, process and analyze the monitoring data through a deep learning model based on the data collected by the edge node to obtain abnormal data; The generation module is used to upload abnormal data to the central control console and integrate and analyze the data to generate an inspection report; The optimization module is used for the central control console to generate optimization and repair strategies according to the inspection report results.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the one-key inspection method and system for a computer monitoring system according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the one-key inspection method and system for a computer monitoring system described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Management method and platform of digital intelligent technology and software and hardware integration service, and storage medium
CN119496805A
Data processing method and device for semiconductor equipment, equipment and storage medium
CN120630838A
Data processing methods, apparatus, devices, and storage media for semiconductor devices
CN120630838B
Monitoring method, device and equipment for crane operation and storage medium
CN121125764A
