Artificial intelligence-based server operation supervision method and system, and storage medium

Abstract

The application relates to the technical field of server operation supervision, in particular to a server operation supervision method and system based on artificial intelligence and a storage medium, the system comprising an operation supervision center, an identification matching unit, a dynamic evaluation unit, a time period image unit, an output supervision unit and a supervision feedback unit; the application preliminarily analyzes the time period operation state of a target server, reasonably performs operation supervision according to different operation states, analyzes operation risk supervision according to standby and operation work through an information feedback mode, makes targeted improvement measures for the target server according to the information feedback situation, analyzes the operation risk of the target server from the perspective of image processing, so as to increase the range of operation supervision analysis data of the target server, and deeply performs joint interactive analysis on the feedback information, so as to ensure the consistency of supervision feedback information from different angles and improve the operation supervision efficiency of the target server.

Description

Technical Field

[0001] This invention relates to the field of server operation monitoring technology, and in particular to server operation monitoring methods, systems and storage media based on artificial intelligence. Background Technology

[0002] In today's digital age, servers are like a super brain, supporting all kinds of network services. If this "brain" malfunctions, it can be disastrous, potentially causing major problems such as websites becoming inaccessible or data loss. Just like a core machine in a large factory suddenly breaking down, the entire production process can be affected. Therefore, monitoring the server's operating status is of paramount importance.

[0003] Currently, when monitoring the operating status of computers, it is impossible to reasonably analyze and accurately assess the current state of the server, making it difficult to achieve precise operation supervision. This hinders the accurate judgment of the server's operating status and makes it impossible to analyze the consistency of the output results, which is not conducive to timely adjustments to the server operation supervision plan. Consequently, the operation supervision error increases, reducing the efficiency of server operation supervision.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an artificial intelligence-based server operation monitoring method, system, and storage medium to address the aforementioned technical deficiencies. This invention initially analyzes the target server's operational status over a specific time period, implementing reasonable operation monitoring based on different operational states. It then conducts operational risk monitoring analysis from both standby and operational perspectives through information feedback. Based on the feedback, targeted improvement measures are implemented for the target server to ensure its safe, stable, and efficient operation. Furthermore, it analyzes the target server's operational risks from an image processing perspective to broaden the scope of operational monitoring analysis data. Simultaneously, it conducts in-depth joint interactive analysis of feedback information to adjust the current operational monitoring scheme for the target server, ensuring consistency of feedback information from different perspectives and improving the credibility and efficiency of operational monitoring.

[0006] The objective of this invention can be achieved through the following technical solution: an artificial intelligence-based server operation monitoring system, including an operation monitoring center, an identification and matching unit, a dynamic evaluation unit, a time period image unit, an output monitoring unit, and a monitoring feedback unit;

[0007] The operation monitoring center is used to retrieve the status information of the target server and send the status information to the identification and matching unit for operation status identification and analysis to obtain standby monitoring signals or operation monitoring signals.

[0008] When a standby monitoring signal is generated, the collected standby operation evaluation results are analyzed to obtain a stable signal or an abnormal signal. When an operation monitoring signal is generated, the dynamic evaluation unit is used to perform status risk assessment and feedback analysis on the collected off-work performance data and on-space performance data to obtain a normal performance signal or an abnormal performance signal.

[0009] When a standby monitoring signal or an operation monitoring signal is generated, the time period image unit is used to perform time period operation status monitoring and evaluation analysis on the infrared thermal feature image of the target server to obtain a status stability signal or a status risk signal. The output monitoring unit is used to perform operation monitoring defect analysis on the time period operation evaluation results of the target server to obtain a consistency signal or a deviation signal.

[0010] Preferably, the operation status identification and analysis process is as follows: the power-on period of the target server is collected, and the power-on period of the target server is set as a time threshold. The status information of the target server within the time threshold is obtained. The status information includes standby status and running status. The status information of the target server is then processed for discrimination: if the status information of the target server is standby status, a standby monitoring signal is generated; if the status information of the target server is running status, a running monitoring signal is generated.

[0011] Preferably, the process of discriminant analysis of the standby operation evaluation results is as follows: the standby operation evaluation results of the target server within the time threshold are obtained, the standby operation evaluation results include stable operation and abnormal operation, and the standby operation evaluation results of the target server are analyzed to obtain a stable signal or an abnormal signal;

[0012] Analysis process for stable and abnormal operation: Obtain the monitoring parameters of the target server within the time threshold, perform discrimination processing on the monitoring parameters of the target server, obtain the number of qualified discrimination output results corresponding to the monitoring parameters of the target server, and compare and analyze the number of qualified discrimination output results corresponding to the monitoring parameters of the target server. If the number of qualified discrimination output results corresponding to the monitoring parameters of the target server is equal to the preset threshold, the target server is determined to be operating stably. If the number of qualified discrimination output results corresponding to the monitoring parameters of the target server is not equal to the preset threshold, the target server is determined to be operating abnormally.

[0013] Preferably, the state risk assessment feedback analysis process is as follows: obtaining the target server's external performance data and spatial performance data within the time threshold;

[0014] The performance data within the space includes the CPU utilization and memory utilization of the target server. The performance data is processed to identify the number of parameters in the performance data that meet the preset requirements, and these are set as the performance values ​​within the operation. The performance data outside the operation includes the data processing capability value and the operation smoothness evaluation value of the target server.

[0015] Preferably, historical performance data and environmental information of the target server are retrieved, and the historical performance data and environmental information are preprocessed. A health status scoring model is then constructed based on the preprocessed historical performance information and environmental information.

[0016] Off-duty performance data is input into the health status assessment model to obtain the output health status score. A health status score change curve is constructed, and the maximum peak value and minimum peak value are obtained from the health status score change curve. Based on the maximum peak value and minimum peak value, a health status interval A is constructed, and a discriminant analysis is performed on the health status interval A and the performance value during operation to obtain a normal performance signal or an abnormal performance signal.

[0017] Preferably, the process for monitoring, evaluating, and analyzing the operational status during the specified time period is as follows:

[0018] Infrared thermal feature images of the target server within a time threshold are obtained, and the infrared thermal feature images are sorted based on the time series. The sorted infrared thermal feature images are then preprocessed.

[0019] The sorted infrared thermal feature images are converted to grayscale. The grayscale images are then divided into i sub-regions, where i is a natural number greater than zero. The grayscale value range corresponding to each sub-region is obtained, and the grayscale value range is compared with the corresponding preset range. If the grayscale value range is contained within the corresponding preset range, a normal signal for the region is generated. The number of normal signals generated is obtained, and the number of normal signals generated is compared with the total number of sub-regions. If the number of normal signals generated is the same as the total number of sub-regions, the corresponding infrared thermal feature image is deemed qualified. The number of qualified infrared thermal feature images is obtained, and the number of qualified infrared thermal feature images is compared and analyzed to obtain a stable state signal or a risk state signal.

[0020] Preferably, the operational monitoring defect analysis process is as follows: the time period operation evaluation results of the target server within the time threshold are obtained. The time period operation evaluation results include the operation security evaluation status and the operation risk evaluation status. If the time period operation evaluation result of the target server is the operation security evaluation status, a consistency signal is generated. If the time period operation evaluation result of the target server is the operation risk evaluation status, a deviation signal is generated.

[0021] The beneficial effects of this invention are as follows:

[0022] (1) The present invention initially analyzes the time period operation status of the target server, divides the target server into standby state and running state, and performs reasonable operation supervision based on different operation states. The operation risk supervision analysis is carried out from the standby and running states through information feedback to judge the operation risk of the target server. At the same time, targeted improvement measures are made for the target server based on the information feedback to ensure the safe, stable and efficient operation of the computer.

[0023] (2) This invention analyzes the operational risks of the target server from the perspective of image processing, so as to increase the scope of the data for the operation monitoring analysis of the target server. At the same time, it conducts in-depth joint interactive analysis of the feedback information in order to adjust the current operation monitoring scheme of the target server, so as to ensure the consistency of the monitoring feedback information from different perspectives, thereby improving the credibility and efficiency of the operation monitoring of the target server. Attached Figure Description

[0024] The invention will now be further described with reference to the accompanying drawings;

[0025] Figure 1 This is a flowchart of the system of the present invention;

[0026] Figure 2 This is a reference diagram of the method of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1:

[0028] Please see Figures 1 to 2 As shown, the present invention is a server operation monitoring system based on artificial intelligence, including an operation monitoring center, an identification and matching unit, a dynamic evaluation unit, a time period image unit, an output monitoring unit, and a monitoring feedback unit. The operation monitoring center and the identification and matching unit have a one-way communication connection. The identification and matching unit has a one-way communication connection with the dynamic evaluation unit, the time period image unit, and the output monitoring unit. The dynamic evaluation unit and the time period image unit have a one-way communication connection with the output monitoring unit and the monitoring feedback unit. The output monitoring unit has a one-way communication connection with the monitoring feedback unit.

[0029] The operation monitoring center is used to retrieve the status information of the target server and send the status information to the identification and matching unit. The identification and matching unit performs operation status identification and classification analysis on the received status information, so as to carry out reasonable operation monitoring analysis based on different operation statuses. The specific operation status identification and classification analysis process is as follows:

[0030] The system collects the power-on period of the target server and sets the power-on period of the target server as a time threshold. It then obtains the status information of the target server within the time threshold, including standby status and running status. The system then performs discrimination processing on the status information of the target server: if the status information of the target server is standby, a standby monitoring signal is generated; if the status information of the target server is running, a running monitoring signal is generated.

[0031] When a standby monitoring signal is generated, the standby operation evaluation results of the target server within the time threshold are obtained. The standby operation evaluation results include stable operation and abnormal operation. The standby operation evaluation results of the target server are analyzed. If the standby operation evaluation result of the target server is stable, a stable signal is generated. If the standby operation evaluation result of the target server is abnormal, an abnormal signal is generated. The stable signal or abnormal signal is sent to the monitoring feedback unit. After receiving the stable signal or abnormal signal, the monitoring feedback unit immediately controls the warning light on the target server to respond to the warning light corresponding to the stable signal or abnormal signal, so as to perform early warning management of the target server in standby state and improve the operational stability of the target server.

[0032] Analysis process for stable and abnormal operation: Obtain monitoring parameters of the target server within the time threshold. The monitoring parameters include operation information, characteristic information, environmental information, etc. Operation information includes standby power consumption, standby power, etc. Characteristic information includes standby vibration amplitude, standby noise value, etc. Environmental information includes the internal temperature value and internal humidity value of the target server, etc.

[0033] The monitoring parameters of the target server are processed to determine the number of qualified output results corresponding to the monitoring parameters of the target server. The number of qualified output results corresponding to the monitoring parameters of the target server is compared and analyzed. If the number of qualified output results corresponding to the monitoring parameters of the target server is equal to the preset threshold, the target server is determined to be running stably. If the number of qualified output results corresponding to the monitoring parameters of the target server is not equal to the preset threshold, the target server is determined to be running abnormally.

[0034] The output results are classified as qualified or unqualified: if the values ​​of the information in the monitoring parameters all meet the preset requirements, the corresponding information is judged as qualified; otherwise, the corresponding information is judged as unqualified. Example 2:

[0035] When a monitoring signal is generated, a joint analysis is performed on both the external performance and internal characteristics of the target server to determine whether the target server is operating normally. This allows for targeted management of the target server to improve its operational security and stability. The dynamic evaluation unit performs status risk assessment and feedback analysis on the collected external and internal performance data. The specific status risk assessment and feedback analysis process is as follows:

[0036] Obtain the target server's out-of-work performance data and spatial performance data within the time threshold;

[0037] The performance data within the space includes the CPU utilization and memory utilization of the target server. The performance data is processed to identify the number of parameters in the performance data that meet the preset requirements, and these are set as the performance values ​​within the runtime.

[0038] Off-duty performance data includes the target server's data processing capability value, operational smoothness evaluation value, etc.

[0039] Among them, the data processing capability value represents the amount of data or number of tasks that the target server can process per unit of time, and the operation smoothness evaluation value represents the average time from when the target server receives the instruction from the operator to when the instruction is completed.

[0040] Retrieve historical performance data and environmental information of the target server, including the target server's external temperature and humidity, and preprocess the historical performance data and environmental information, including cleaning and enhancement, and build a health status scoring model based on the preprocessed historical performance information and environmental information.

[0041] Off-duty performance data is input into a health status assessment model to obtain an output health status score. A health status score change curve is constructed, and the maximum peak value and minimum peak value are obtained from the health status score change curve. Based on the maximum peak value and minimum peak value, a health status interval A is constructed, and a discriminant analysis is performed on health status interval A and the on-duty performance value.

[0042] If the health status interval A is contained within the preset health status interval and the performance value during operation is equal to the preset threshold, then a normal performance signal is generated.

[0043] If the health status interval A is not included in the preset health status interval, or the in-operation performance value is not equal to the preset threshold, an abnormal performance signal is generated, and the normal performance signal or the abnormal performance signal is sent to the supervision feedback unit. After receiving the normal performance signal or the abnormal performance signal, the supervision feedback unit immediately performs the preset warning operation corresponding to the normal performance signal or the abnormal performance signal, which is beneficial for the management personnel to take timely targeted improvement measures to ensure the safe, stable and efficient operation of the computer. Embodiment III:

[0044] When generating a standby supervision signal or an operation supervision signal, the time-period image unit is used to perform time-period operation status supervision and evaluation analysis on the infrared thermal characteristic image of the target server collected, so as to manage the target server from the perspective of image processing feedback to improve the operation safety of the target server. The specific time-period operation status supervision and evaluation analysis process is as follows:

[0045] Obtain the infrared thermal characteristic image of the target server within the time threshold, sort the infrared thermal characteristic images based on the time series, and preprocess the sorted infrared thermal characteristic images. The preprocessing includes cleaning, denoising, etc.;

[0046] Perform grayscale processing on the sorted infrared thermal characteristic images, divide the grayscale processed infrared thermal characteristic images into i sub-region blocks, where i is a natural number greater than zero, obtain the gray value intervals corresponding to each sub-region block, and compare and analyze the gray value intervals with the corresponding preset intervals. If the gray value interval is included in the corresponding preset interval, a normal region block signal is generated, obtain the number of generated normal region block signals, and compare and analyze the number of generated normal region block signals with the total number of sub-region blocks. If the number of generated normal region block signals is the same as the total number of sub-region blocks, it is determined that the corresponding infrared thermal characteristic image is qualified, obtain the number corresponding to the qualified infrared thermal characteristic image, and compare and analyze the number corresponding to the qualified infrared thermal characteristic image:

[0047] If the number corresponding to the qualified infrared thermal characteristic image is equal to the total number of infrared thermal characteristic images, a stable state signal is generated;

[0048] If the number corresponding to the qualified infrared thermal characteristic image is not equal to the total number of infrared thermal characteristic images, a state risk signal is generated, and the obtained stable state signal or state risk signal is sent to the supervision feedback unit. After receiving the stable state signal or state risk signal, the supervision feedback unit immediately performs the preset warning operation corresponding to the stable state signal or state risk signal, so as to manage the target server from the perspective of image processing feedback to improve the operation safety of the target server;

[0049] When a standby monitoring signal or an operational monitoring signal is generated, the output monitoring unit is used to perform operational monitoring defect analysis on the collected time-period operational evaluation results of the target server. The specific operational monitoring defect analysis process is as follows:

[0050] The system obtains the time-period operation evaluation results of the target server within the time threshold. The time-period operation evaluation results include the operation safety evaluation status and the operation risk evaluation status. If the time-period operation evaluation result of the target server is the operation safety evaluation status, a consistency signal is generated. If the time-period operation evaluation result of the target server is the operation risk evaluation status, a deviation signal is generated. The obtained consistency signal or deviation signal is sent to the monitoring feedback unit. After receiving the consistency signal or deviation signal, the monitoring feedback unit immediately displays the preset warning text corresponding to the consistency signal or deviation signal so as to adjust the current operation monitoring plan of the target server and ensure the consistency of monitoring feedback information from different perspectives, thereby improving the credibility and efficiency of the operation monitoring of the target server.

[0051] The operational safety assessment status is represented by generating a stable status signal and a stable signal, or a stable status signal and a normal performance signal, or a risk status signal and an abnormal signal, or a risk status signal and an abnormal performance signal.

[0052] The operational risk assessment status indicates the generation of stable and abnormal status signals, or risk and stable status signals, or stable and abnormal status signals, or risk and normal status signals. Example 4:

[0053] An AI-based method for monitoring server operation includes the following steps:

[0054] Step 1: Target server status identification and classification operation, that is, to perform operational status identification and classification analysis on the status information to understand whether the target server is in standby or operational state, and at the same time generate standby monitoring signals or operational monitoring signals;

[0055] Step 2: Standby operation evaluation and processing based on standby monitoring signals, that is, judging the standby operation evaluation results of the target server and outputting the obtained stable signal or abnormal signal as feedback;

[0056] Step 3: Based on the status risk assessment and feedback analysis process under the operation monitoring signal, that is, to conduct status risk assessment and feedback analysis on the target server's external performance data and internal performance data, to conduct discriminant analysis on the obtained health status interval A and the internal performance value, and to output the obtained normal performance signal or abnormal performance signal as feedback.

[0057] Step 4: Based on information feedback, conduct time-period operation status monitoring and assessment analysis from the perspective of image processing. This involves analyzing the infrared thermal feature images of the target server collected during the time period, comparing and analyzing the number of qualified infrared thermal feature images, and outputting the obtained status stability signal or status risk signal as feedback.

[0058] Step 5: Conduct operational monitoring defect analysis based on information feedback and interactive comparison, that is, process the time period operation evaluation results of the target server and output the obtained consistent or deviation signals as feedback;

[0059] A computer-readable storage medium storing a computer program that, when executed by a processor, implements an artificial intelligence-based server operation monitoring method.

[0060] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods.

[0061] In summary, this invention initially analyzes the target server's operational status over time, dividing it into standby and operational states. Based on these different states, it implements reasonable operational monitoring. Through information feedback, it analyzes operational risks from both standby and operational perspectives to assess the target server's operational risks. Based on the feedback, it implements targeted improvement measures to ensure the computer's safe, stable, and efficient operation. Furthermore, it analyzes operational risks from an image processing perspective to broaden the scope of operational monitoring data. In-depth joint interactive analysis of feedback information allows for adjustments to the current operational monitoring scheme, ensuring consistency of feedback information from different perspectives and improving the credibility and efficiency of operational monitoring.

[0062] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0063] The size of the coefficient is a specific value obtained by quantifying each parameter to facilitate subsequent comparison. The size of the coefficient depends on the amount of sample data and the corresponding operating coefficient initially set by those skilled in the art for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0064] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A server operation monitoring system based on artificial intelligence, characterized in that, It includes an operation monitoring center, an identification and matching unit, a dynamic evaluation unit, a time-period image unit, an output monitoring unit, and a monitoring feedback unit; The operation monitoring center is used to retrieve the status information of the target server and send the status information to the identification and matching unit for operation status identification and analysis to obtain standby monitoring signals or operation monitoring signals. When a standby monitoring signal is generated, the collected standby operation evaluation results are analyzed to obtain a stable signal or an abnormal signal. When an operation monitoring signal is generated, the dynamic evaluation unit is used to perform status risk assessment and feedback analysis on the collected off-work performance data and on-space performance data to obtain a normal performance signal or an abnormal performance signal. When a standby monitoring signal or an operation monitoring signal is generated, the time period image unit is used to perform time period operation status monitoring and evaluation analysis on the infrared thermal feature image of the target server to obtain a status stability signal or a status risk signal. The output monitoring unit is used to perform operation monitoring defect analysis on the time period operation evaluation results of the target server to obtain a consistency signal or a deviation signal. The state risk assessment feedback analysis process is as follows: Obtain the target server's external performance data and spatial performance data within the time threshold; The performance data within the space includes the CPU utilization and memory utilization of the target server. The performance data is processed to identify the number of parameters in the performance data that meet the preset requirements, and these are set as the performance values ​​within the runtime. The performance data outside the work includes the data processing capability value and the operation smoothness evaluation value of the target server. The process of monitoring, evaluating, and analyzing the operational status during the specified time period is as follows: Infrared thermal feature images of the target server within a time threshold are obtained, and the infrared thermal feature images are sorted based on the time series. The sorted infrared thermal feature images are then preprocessed. The sorted infrared thermal feature images are converted to grayscale. The grayscale images are then divided into i sub-regions, where i is a natural number greater than zero. The grayscale value range corresponding to each sub-region is obtained, and the grayscale value range is compared with the corresponding preset range. If the grayscale value range is contained within the corresponding preset range, a normal signal for the region is generated. The number of normal signals generated is obtained, and the number of normal signals generated is compared with the total number of sub-regions. If the number of normal signals generated is the same as the total number of sub-regions, the corresponding infrared thermal feature image is deemed qualified. The number of qualified infrared thermal feature images is obtained, and the number of qualified infrared thermal feature images is compared and analyzed to obtain a stable state signal or a risk state signal.

2. The server operation monitoring system based on artificial intelligence according to claim 1, characterized in that, The operation status identification and analysis process is as follows: The power-on period of the target server is collected, and the power-on period of the target server is set as a time threshold. The status information of the target server within the time threshold is obtained. The status information includes standby status and running status. The status information of the target server is then processed for discrimination: if the status information of the target server is standby status, a standby monitoring signal is generated; if the status information of the target server is running status, a running monitoring signal is generated.

3. The server operation monitoring system based on artificial intelligence according to claim 1, characterized in that, The process of discriminant analysis of the standby operation evaluation results is as follows: the standby operation evaluation results of the target server within the time threshold are obtained. The standby operation evaluation results include stable operation and abnormal operation. The standby operation evaluation results of the target server are analyzed to obtain stable signals or abnormal signals. Analysis process for stable and abnormal operation: Obtain the monitoring parameters of the target server within the time threshold, perform discrimination processing on the monitoring parameters of the target server, obtain the number of qualified discrimination output results corresponding to the monitoring parameters of the target server, and compare and analyze the number of qualified discrimination output results corresponding to the monitoring parameters of the target server. If the number of qualified discrimination output results corresponding to the monitoring parameters of the target server is equal to the preset threshold, the target server is determined to be operating stably. If the number of qualified discrimination output results corresponding to the monitoring parameters of the target server is not equal to the preset threshold, the target server is determined to be operating abnormally.

4. The server operation monitoring system based on artificial intelligence according to claim 1, characterized in that, Retrieve historical performance data and environmental information of the target server, preprocess the historical performance data and environmental information, and construct a health status scoring model based on the preprocessed historical performance information and environmental information; Off-duty performance data is input into the health status assessment model to obtain the output health status score. A health status score change curve is constructed, and the maximum peak value and minimum peak value are obtained from the health status score change curve. Based on the maximum peak value and minimum peak value, a health status interval A is constructed, and a discriminant analysis is performed on the health status interval A and the performance value during operation to obtain a normal performance signal or an abnormal performance signal.

5. The server operation monitoring system based on artificial intelligence according to claim 1, characterized in that, The operational monitoring defect analysis process is as follows: Obtain the time period operation evaluation results of the target server within the time threshold. The time period operation evaluation results include the operation security evaluation status and the operation risk evaluation status. If the time period operation evaluation result of the target server is the operation security evaluation status, a consistency signal is generated. If the time period operation evaluation result of the target server is the operation risk evaluation status, a deviation signal is generated.

6. A server operation monitoring method based on artificial intelligence, wherein the method is applied to the server operation monitoring system based on artificial intelligence as described in any one of claims 1-5, characterized in that, Includes the following steps: Step 1: Target server status identification and classification operation, that is, to perform operational status identification and classification analysis on the status information to understand whether the target server is in standby or operational state, and at the same time generate standby monitoring signals or operational monitoring signals; Step 2: Standby operation evaluation and processing based on standby monitoring signals, that is, judging the standby operation evaluation results of the target server and outputting the obtained stable signal or abnormal signal as feedback; Step 3: Based on the status risk assessment and feedback analysis process under the operation monitoring signal, that is, to conduct status risk assessment and feedback analysis on the target server's external performance data and internal performance data, to conduct discriminant analysis on the obtained health status interval A and the internal performance value, and to output the obtained normal performance signal or abnormal performance signal as feedback. Step 4: Based on information feedback, conduct time-period operation status monitoring and assessment analysis from the perspective of image processing. This involves analyzing the infrared thermal feature images of the target server collected during the time period, comparing and analyzing the number of qualified infrared thermal feature images, and outputting the obtained status stability signal or status risk signal as feedback. Step 5: Conduct operational monitoring defect analysis based on information feedback and interactive comparison, that is, process the evaluation results of the target server's operation over a period of time, and output the obtained consistent or deviation signals as feedback.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in claim 6.

Images