An integrated intelligent operation and maintenance control method and system

Abstract

The present invention relates to the field of equipment operation and maintenance technology, and in particular to an integrated intelligent operation and maintenance control method and system. The method comprises the following steps: acting on a target equipment group, acting on any target equipment in the target equipment group, performing multi-dimensional situational awareness collection on the target equipment, and obtaining equipment operation data, wherein the equipment operation data includes equipment operation status parameters, equipment temperature data, and equipment operation index data; performing historical fault time point statistics on the target equipment to obtain a number of historical fault time point data; performing operation status detection time window analysis on the target equipment based on a number of historical fault time point data to obtain detection time window data. The present invention can provide accurate equipment status information, discover potential faults in advance, fully understand the equipment operation status, improve the accuracy and timeliness of operation and maintenance decisions, and automate the intelligent operation and maintenance operation execution, thereby realizing intelligent equipment operation and maintenance control.

Description

Technical Field

[0001] The present invention relates to the field of equipment operation and maintenance technology, and in particular to an integrated intelligent operation and maintenance control method and system. Background Art

[0002] In the field of equipment operation and maintenance, traditional equipment operation and maintenance methods rely on manual inspections and manual intervention, resulting in low operation and maintenance efficiency and prone to omissions and errors. Operation and maintenance personnel need to spend a lot of time and energy to monitor the status of equipment, judge the operating status of equipment, and perform corresponding operations and maintenance. In addition, the existing equipment operation and maintenance control methods lack intelligent decision-making support and cannot make automated operation and maintenance strategy decisions based on the actual situation of the equipment. They rely on the experience and intuition of operation and maintenance personnel and are easily affected by subjective factors and misjudgments. In addition, traditional equipment operation and maintenance methods cannot effectively optimize the utilization of equipment resources, lack accurate data support and intelligent resource allocation strategies, resulting in resource waste and performance bottlenecks. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an integrated intelligent operation and maintenance control method and system to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, an integrated intelligent operation and maintenance control method includes the following steps:

[0005] Step S1: Perform multi-dimensional situation awareness collection on the target device to obtain device operation data, wherein the device operation data includes device operation status parameters, device temperature data and device operation index data;

[0006] Step S2: Perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device based on the several historical fault time point data to obtain detection time window data;

[0007] Step S3: Based on the detection time window data, the target device is analyzed for its operating status according to the device operating status parameters, the device temperature data and the device operating index data to obtain the device operating status data; based on the device operating status data, the target device is analyzed for manual intervention requirements to obtain manual intervention requirements data;

[0008] Step S4: Identify the service type processed by the target device to obtain data on the service type processed by the device;

[0009] Step S5: Make an operation and maintenance strategy decision for the target device according to the manual intervention demand data and the device processing business type data to obtain an operation and maintenance strategy decision plan; perform intelligent operation and maintenance operations on the target device according to the operation and maintenance strategy decision plan.

[0010] The present invention can acquire the operation data of the target device in real time through multi-dimensional situation awareness collection, including device operation status parameters, device temperature data and device operation index data. This can make analysis and decision based on accurate device status information, and improve the comprehensive understanding and monitoring of the device operation status. By counting the historical fault time points of the target device, several historical fault time point data can be obtained. By analyzing the detection time window of these data, an appropriate time window is determined to detect the operation status of the device. This helps to discover potential faults and problems in advance, reduce the impact of equipment failures on the business, and take measures to prevent and deal with them in time, thereby improving the availability and stability of the equipment. By analyzing the detection time window data, and combining the device operation status parameters, device temperature data and device operation index data, the operation status of the target device can be deeply analyzed. The operation and maintenance personnel can obtain detailed device operation status data and fully understand the operation status of the device. At the same time, by analyzing the manual intervention demand of the device operation status data, it is determined whether manual intervention operation is required, timely decision support is provided, the workload of the operation and maintenance personnel is reduced, and the accuracy and timeliness of the operation and maintenance decision are guaranteed. By identifying the type of business processed by the target device, the device processing business type data can be obtained. This helps to understand the current business environment and load conditions of the equipment, and provide more accurate information for subsequent operation and maintenance decisions. Based on the identification results of the business type, the intelligent operation and maintenance control method can formulate corresponding operation and maintenance strategies according to different business needs, and improve the flexibility and adaptability of operation and maintenance. By making operation and maintenance strategy decisions based on manual intervention demand data and equipment processing business type data, corresponding operation and maintenance strategy decision plans can be formulated. This can perform intelligent operation and maintenance operations according to the actual situation of the equipment, and improve operation and maintenance efficiency and accuracy. Finally, according to the operation and maintenance strategy decision plan, the intelligent operation and maintenance control method can automatically perform intelligent operation and maintenance operations, reduce errors and delays in manual operations, and improve the automation level and efficiency of operation and maintenance. In summary, the present invention can provide accurate equipment status information, detect potential faults in advance, fully understand the operating status of the equipment, improve the accuracy and timeliness of operation and maintenance decisions, and automate the execution of intelligent operation and maintenance operations, thereby realizing intelligent equipment operation and maintenance control.

[0011] Preferably, the present invention further provides an integrated intelligent operation and maintenance control system for executing the integrated intelligent operation and maintenance control method as described above, the integrated intelligent operation and maintenance control system comprising:

[0012] Intelligent collection module, used to collect multi-dimensional situation awareness of target equipment and obtain equipment operation data, where the equipment operation data includes equipment operation status parameters, equipment temperature data and equipment operation index data;

[0013] The abnormal detection cycle analysis module is used to perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device based on a number of historical fault time point data to obtain detection time window data;

[0014] The status analysis module is used to analyze the operation status of the target device based on the detection time window data according to the device operation status parameters, device temperature data and device operation index data to obtain the device operation status data; and to analyze the manual intervention demand of the target device according to the device operation status data to obtain the manual intervention demand data;

[0015] A service type identification module is used to identify the service type processed by the target device and obtain the service type data processed by the device;

[0016] The intelligent operation and maintenance decision module is used to make operation and maintenance strategy decisions for the target equipment based on the manual intervention demand data and the equipment processing business type data, and obtain an operation and maintenance strategy decision plan; and perform intelligent operation and maintenance operations on the target equipment according to the operation and maintenance strategy decision plan.

[0017] In the present invention, the intelligent acquisition module collects the equipment operation data of the target equipment through multi-dimensional situational awareness, including equipment operation status parameters, equipment temperature data and equipment operation index data, provides real-time equipment status information, and provides accurate data support for subsequent intelligent operation and maintenance decisions. The abnormal detection cycle analysis module analyzes the failure occurrence of the target equipment through historical fault time point statistics, and obtains several historical fault time point data. According to these data, the operation status detection time window analysis can be performed to determine the detection time window, so as to discover the abnormal state and potential faults of the equipment in advance. The state analysis module analyzes the operation status of the target equipment based on the detection time window data and the equipment operation data to obtain the equipment operation status data. These data can be used to judge the health status, performance and any abnormal situation of the equipment, and provide an accurate basis for subsequent operation and maintenance decisions and manual intervention demand analysis. According to the equipment operation status data, analyze whether the target equipment needs manual intervention, judge the equipment with problems or potential risks, and generate corresponding manual intervention demand data. This helps the operation and maintenance personnel to find equipment problems in time and take appropriate measures to avoid equipment failures and business interruptions. The business type identification module identifies the equipment processing business type of the target equipment, that is, determines the business type used by the equipment to process. This helps to better understand the operating environment and requirements of the equipment, and provides a more accurate basis for subsequent intelligent operation and maintenance decisions. The intelligent operation and maintenance decision module makes intelligent operation and maintenance strategy decisions for the target equipment based on the manual intervention demand data and the equipment processing business type data. This module can automatically formulate an operation and maintenance strategy decision plan that adapts to the current status of the equipment and the business type based on real-time data and business needs. According to the operation and maintenance strategy decision plan, perform intelligent operation and maintenance operations. This module can automatically perform operation and maintenance operations, including equipment maintenance, fault repair, performance optimization, etc., to improve operation and maintenance efficiency and reduce the risk of equipment failure and business interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0019] Figure 1 A schematic flow chart of the steps of an integrated intelligent operation and maintenance control method according to an embodiment is shown.

[0020] Figure 2 A detailed flow chart of step S5 of an embodiment is shown.

[0021] Figure 3 A detailed flowchart diagram of step S56 of an embodiment is shown. DETAILED DESCRIPTION

[0022] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides an integrated intelligent operation and maintenance control method, comprising the following steps:

[0026] Step S1: Perform multi-dimensional situation awareness collection on the target device to obtain device operation data, wherein the device operation data includes device operation status parameters, device temperature data and device operation index data;

[0027] Specifically, sensors, monitoring tools or device management systems can be used to monitor and collect data from target devices in real time. Collect device operating status parameters, such as CPU usage, memory usage, disk space, etc. Collect device temperature data, using temperature sensors or device internal temperature monitoring functions. Collect device operating indicator data, such as network traffic, request response time, etc.

[0028] Step S2: Perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device based on the several historical fault time point data to obtain detection time window data;

[0029] Specifically, you can use the fault management system, log records, or historical maintenance records to collect the fault time point data of the target device. Count and organize the fault time point data to obtain several historical fault time points. According to the historical fault time point data, determine the size or duration of the operation status detection time window. For example, you can select a time window of one hour before the fault occurs for analysis.

[0030] Step S3: Based on the detection time window data, the target device is analyzed for its operating status according to the device operating status parameters, the device temperature data and the device operating index data to obtain the device operating status data; based on the device operating status data, the target device is analyzed for manual intervention requirements to obtain manual intervention requirements data;

[0031] Specifically, the equipment operating status parameters, equipment temperature data, and equipment operating index data within the detection time window can be extracted. Use data analysis tools or algorithms to analyze, compare, and process the extracted data to determine the operating status of the equipment. For example, a threshold can be set to determine whether the equipment is in a normal, abnormal, or faulty state. Based on the equipment operating status data, identify the abnormality or fault of the equipment. Evaluate whether manual intervention is required based on factors such as the severity, scope of impact, and urgency of the abnormality or fault. Generate manual intervention demand data based on the evaluation results, including information such as the required intervention measures, intervention timing, and intervention priority.

[0032] Step S4: Identify the service type processed by the target device to obtain data on the service type processed by the device;

[0033] Specifically, the device's processing business data, such as tasks, requests, or operation records processed by the device, can be collected. The collected business data can be analyzed and processed using machine learning algorithms, text classification techniques, or pattern recognition methods. Based on the analysis results, the business type processed by the device can be identified, such as network routing, data storage, image processing, etc.

[0034] Step S5: Make an operation and maintenance strategy decision for the target device according to the manual intervention demand data and the device processing business type data to obtain an operation and maintenance strategy decision plan; perform intelligent operation and maintenance operations on the target device according to the operation and maintenance strategy decision plan.

[0035] Specifically, the data on manual intervention needs can be analyzed to understand the intervention measures, intervention timing, and intervention priority. Combined with the data on the types of business processed by the equipment, corresponding operation and maintenance strategies, such as fault recovery strategies and performance optimization strategies, can be formulated according to the business characteristics and requirements of the equipment. According to the operation and maintenance strategy decision plan, the specific operation and maintenance operations that need to be performed are determined, such as equipment restart, configuration modification, patch installation, etc. Use automated operation and maintenance tools, remote management tools, or equipment management systems to perform intelligent operation and maintenance operations on target devices. Monitor the execution process of the operation and maintenance operations to ensure the smooth completion of the operations, and record the execution results.

[0036] The present invention can acquire the operation data of the target device in real time through multi-dimensional situation awareness collection, including device operation status parameters, device temperature data and device operation index data. This can make analysis and decision based on accurate device status information, and improve the comprehensive understanding and monitoring of the device operation status. By counting the historical fault time points of the target device, several historical fault time point data can be obtained. By analyzing the detection time window of these data, an appropriate time window is determined to detect the operation status of the device. This helps to discover potential faults and problems in advance, reduce the impact of equipment failures on the business, and take measures to prevent and deal with them in time, thereby improving the availability and stability of the equipment. By analyzing the detection time window data, and combining the device operation status parameters, device temperature data and device operation index data, the operation status of the target device can be deeply analyzed. The operation and maintenance personnel can obtain detailed device operation status data and fully understand the operation status of the device. At the same time, by analyzing the manual intervention demand of the device operation status data, it is determined whether manual intervention operation is required, timely decision support is provided, the workload of the operation and maintenance personnel is reduced, and the accuracy and timeliness of the operation and maintenance decision are guaranteed. By identifying the type of business processed by the target device, the device processing business type data can be obtained. This helps to understand the current business environment and load conditions of the equipment, and provide more accurate information for subsequent operation and maintenance decisions. Based on the identification results of the business type, the intelligent operation and maintenance control method can formulate corresponding operation and maintenance strategies according to different business needs, and improve the flexibility and adaptability of operation and maintenance. By making operation and maintenance strategy decisions based on manual intervention demand data and equipment processing business type data, corresponding operation and maintenance strategy decision plans can be formulated. This can perform intelligent operation and maintenance operations according to the actual situation of the equipment, and improve operation and maintenance efficiency and accuracy. Finally, according to the operation and maintenance strategy decision plan, the intelligent operation and maintenance control method can automatically perform intelligent operation and maintenance operations, reduce errors and delays in manual operations, and improve the automation level and efficiency of operation and maintenance. In summary, the present invention can provide accurate equipment status information, detect potential faults in advance, fully understand the operating status of the equipment, improve the accuracy and timeliness of operation and maintenance decisions, and automate the execution of intelligent operation and maintenance operations, thereby realizing intelligent equipment operation and maintenance control.

[0037] Preferably, step S1 comprises the following steps:

[0038] Step S11: Monitor the target device in kernel mode to obtain device operation status parameters;

[0039] Specifically, you can run monitoring software on the target device, for example, use a performance monitoring tool such as the sar command under the Linux system. This tool can provide various system performance indicators, including CPU usage, memory usage, disk I / O, etc. Through the data collected by the monitoring software, you can obtain the operating status parameters of the device, such as CPU utilization, memory utilization, network traffic, etc.

[0040] Step S12: Perform thermal imaging monitoring on the target device to obtain device temperature data;

[0041] Specifically, an infrared thermal imager or thermal imaging camera can be used to perform thermal imaging monitoring on the target device. Aim the thermal imaging device at the surface of the target device to obtain a temperature distribution image of the device surface. Thermal imaging devices can detect the temperature of an object through infrared radiation and convert it into a visual image. By analyzing the thermal imaging image, temperature data of different areas of the device can be obtained.

[0042] Step S13: Perform workload analysis on the target device to obtain device operation index data; wherein the device operation state parameters, device temperature data and device operation index data constitute the device operation data.

[0043] Specifically, you can run performance monitoring tools such as sar and vmstat to monitor the device's CPU, memory, disk, network and other resources in real time. Through the data collected by the monitoring tools, you can obtain the device's operating status parameters, such as CPU utilization, memory utilization, disk I / O speed, and network traffic. Analyze the device's system log, application log, or other log files, such as syslog, log file analysis tools ELK (Elasticsearch, Logstash, and Kibana), etc. By analyzing log files, you can obtain the device's operating indicator data, such as error logs, warning logs, and application request volume.

[0044] The present invention can obtain the operating status parameters of the device in real time by performing kernel state monitoring on the target device, such as CPU utilization, memory usage, disk IO, etc. By monitoring these parameters, the operating status, resource utilization and performance of the device can be understood. By obtaining the temperature data of the device through thermal imaging monitoring, the thermal condition of the device can be understood in real time, and whether the device has overheating problems or temperature abnormalities. By analyzing the temperature data of the device, the area or component with abnormal temperature can be identified, thereby providing a basis for optimizing the heat dissipation design of the device, adjusting the device layout or improving the operating environment of the device. Through workload analysis and the composition of device operation data, the operating status of the device can be fully understood, including resource utilization, temperature conditions, and performance. By analyzing the workload and operation index data of the device, the scheduling and allocation of resources can be optimized, and the utilization and performance of the device can be improved.

[0045] Preferably, step S13 comprises the following steps:

[0046] Step S131: Perform workload perception on the target device to obtain device workload data, wherein the device workload data includes but is not limited to system call tracking data, process behavior monitoring data and resource utilization statistics data;

[0047] Specifically, you can use tools such as strace and dtrace to trace the system calls of applications on the target device. These tools can record the system call interaction process between the application and the operating system and generate corresponding logs or trace data. By analyzing the system call trace data, you can obtain the workload data of the device, such as the type, frequency and parameters of the system call. Use tools such as ps and top to monitor the processes running in the system. These tools can provide process status information, CPU and memory usage, etc. Through the data collected by the monitoring tools, you can obtain the workload data of the device, such as the number of processes, CPU utilization and memory usage. Use performance monitoring tools such as sar and vmstat to count the resource utilization of the device. These tools can provide data such as the CPU utilization, memory utilization, disk I / O status and network traffic of the device.

[0048] Step S132: performing semantic analysis on the system call tracing data to obtain workload semantic pattern data;

[0049] Specifically, you can use log analysis tools and machine learning techniques to perform semantic analysis on system call tracing data. You can use tools such as ELK (Elasticsearch, Logstash, and Kibana) to collect and analyze log data. Machine learning techniques such as natural language processing (NLP) and text classification algorithms can be used to analyze and process system call tracing data to extract semantic information and patterns. These semantic pattern data can be used to understand and describe the workload characteristics of the device.

[0050] Step S133: Acquire target device configuration information data and target device application dependency data;

[0051] Specifically, you can collect the configuration information of the target device, including hardware configuration and software configuration. You can use commands such as lshw and dmidecode to obtain hardware configuration information, and use commands such as lsb_release and uname to obtain software configuration information such as operating system and kernel version. Analyze the dependencies of applications running on the target device. You can use tools such as lsof and ldd to view the dependent libraries and files of the application. By analyzing the dependencies of the application, you can obtain the association and dependency between the applications on the target device.

[0052] Step S134: constructing a workload knowledge graph based on the workload semantic pattern data by combining the target device configuration information data and the target device application dependency data to obtain a workload knowledge graph;

[0053] Specifically, workload semantic pattern data, target device configuration information data, and target device application dependency data can be combined to build a knowledge graph to establish the association and feature description of the workload. Graph database tools such as Neo4j can be used to build and query the knowledge graph and represent it as a relationship network of nodes and edges.

[0054] Step S135: Using the workload knowledge graph, the process behavior monitoring data and resource utilization statistics are subjected to workload fingerprint recognition to obtain workload classification data;

[0055] Specifically, the workload knowledge graph can be used to match and associate process behavior monitoring data and resource utilization statistics with nodes and edges in the graph. By identifying and comparing workload features, workload data can be classified. This can be achieved using the query and matching functions provided by graph database tools.

[0056] Step S136: Perform dynamic load assessment on the target device according to the workload classification data and resource utilization statistics to obtain device performance pressure assessment data; wherein, the workload classification data and the device performance pressure assessment data constitute device operation data; wherein, the device operation status parameters, device temperature data and device operation index data constitute the device operation data.

[0057] Specifically, dynamic load assessment can be performed based on workload classification data and resource utilization statistics. According to the workload classification data and resource utilization statistics, appropriate features are selected to describe the load status of the device. For example, CPU utilization, memory usage, disk I / O rate, etc. can be selected as features. Using historical data sets, workload classification data and resource utilization statistics are used as input, and the performance pressure assessment data of the device is used as the target output to train the machine learning model. Regression models, classification models, or other appropriate models can be used for training. Use the trained model to predict and evaluate the current workload classification data and resource utilization statistics. The model will output the performance pressure assessment data of the device, such as the device load level, performance bottleneck indication, etc., based on the characteristics of the input data. According to the evaluation results, the performance pressure assessment data of the device can be obtained, which is used to judge the working status and performance status of the device.

[0058] The present invention can obtain the workload data of the device through workload perception, and deeply understand the processes running on the device, the usage of system calls and the utilization of resources. The resource utilization statistics in the device workload data can provide detailed information about the usage of device resources, such as CPU utilization, memory usage and disk IO, etc., which is of great significance for resource scheduling and optimization. Through semantic analysis of system call tracking data, abstract system calls can be converted into data with semantic patterns to better understand the behavior and operation of workloads. By analyzing the workload semantic pattern data, specific patterns in the workload can be accurately identified, such as common operation sequences, typical application behaviors, etc., which is helpful for subsequent workload optimization and resource scheduling. Obtaining the configuration information data of the target device helps to understand the hardware configuration and software environment of the device, and provides a basis for subsequent workload analysis and optimization. By obtaining the dependency data between applications on the target device, the interaction and dependence between applications can be understood, providing a basis for workload optimization and resource scheduling. Through the workload knowledge graph, the association patterns, characteristics and mutual influences in the workload can be revealed, helping to understand and analyze the behavior and optimization potential of the workload. The workload knowledge graph comprehensively represents the relationships among workload behaviors, device configurations, and application dependencies, providing a comprehensive understanding of the workload as a whole. The workload knowledge graph provides a basis for subsequent workload management and decision-making, such as resource allocation, load balancing, and capacity planning, improving the intelligence and automation of the system. Through workload fingerprinting, workload data can be classified, and similar workloads can be grouped together, which is helpful for subsequent resource scheduling and performance optimization. Workload classification data can provide a basis for load balancing and resource optimization, help allocate resources reasonably, and improve system performance and efficiency. Through dynamic load assessment, the load of the device can be understood, which helps make load balancing decisions, and the workload can be reasonably allocated to different devices to improve the overall performance and throughput of the system. Through dynamic load assessment, future performance requirements can be predicted, which helps with capacity planning and resource reservation, and avoids performance degradation or failures caused by excessive load.

[0059] Preferably, step S2 comprises the following steps:

[0060] Step S21: collecting historical logs of the target device to obtain a historical log data set;

[0061] Specifically, you can select appropriate log collection tools, such as ELK Stack (Elasticsearch, Logstash, Kibana), Splunk, Fluentd, etc., to collect historical log data from the target device. Configure the log collection tool and specify parameters such as the log file path and log format of the target device to ensure that historical log data is collected correctly. Start the log collection tool to start collecting historical logs of the target device. The tool will read the log files of the target device periodically or in real time according to the configured parameters, and send the log data to the specified storage location.

[0062] Step S22: filtering the historical log data set by device abnormality logs to obtain a historical abnormality log data set;

[0063] Specifically, you can define rules or patterns for device abnormal logs, such as specific error codes, keywords, abnormal behaviors, etc. These definitions will be used to filter and identify abnormal logs in historical log data. Use appropriate log data processing tools, such as grep, awk, sed, etc., to filter and filter abnormal logs in historical log data sets. According to the abnormal log definition, use the grep command to filter log lines containing abnormal keywords or patterns. Use the awk command to extract key fields or information for subsequent analysis and processing.

[0064] Step S23: performing historical fault time point statistics on the target device according to the historical abnormal log data set to obtain a number of historical fault time point data;

[0065] Specifically, you can perform time series analysis on the historical abnormal log data set to find the time point when the abnormal log occurred. Use clustering algorithms (such as K-means) or window sliding technology to classify adjacent abnormal time points into a fault time period. Perform statistical analysis based on the identified historical fault time point data to obtain data for several historical fault time points. You can count the duration, frequency, and time period of each fault time period.

[0066] Step S24: Visualize the timeline of several historical fault time point data to obtain fault timeline data;

[0067] Specifically, you can use Python's matplotlib library to create a timeline graph with time as the horizontal axis and the count of fault events as the vertical axis. Take the prepared fault time point data as input and draw the fault timeline graph based on the timestamp.

[0068] Step S25: performing time interval clustering analysis on the fault timeline data to obtain fault time interval pattern data;

[0069] Specifically, you can use Python's scikit-learn library and select a suitable clustering algorithm, such as the K-means algorithm. Take the prepared fault time interval data as input, set the parameters of the clustering algorithm, and perform cluster analysis. Extract fault time interval pattern data from the results of cluster analysis, such as the center of each cluster, the number and members of clusters, etc. These pattern data can be used for fault prediction and fault time interval identification.

[0070] Step S26: Performing an operation status detection time window analysis on the target device according to the fault timeline data and the fault time interval pattern data to obtain detection time window data.

[0071] Specifically, you can use Python's pandas library to create a sliding window object and set the length and interval of the time window. Take the fault timeline data as input and perform window analysis through the sliding window object, such as calculating the number of fault events and duration in each window. Extract the detection time window data from the results of the time window analysis, such as the start time and statistical indicators of each window. These data can be used for running status detection, fault prediction, and fault diagnosis.

[0072] The present invention obtains a historical log data set, which provides a record of the past operations and events of the equipment, and can be used as an important basis for fault diagnosis. By analyzing the historical log data, the pattern and law of equipment failure can be found, which helps to identify and locate potential problems. The historical abnormal log data set provides a record of abnormal conditions of the equipment. By analyzing the abnormal log, the abnormal behavior and abnormal pattern of the equipment can be found, which helps to quickly detect and identify the abnormal state of the equipment, and perform corresponding fault processing and maintenance. Through the statistics of historical fault time point data, the time distribution of equipment failure can be understood, which helps to predict and prevent possible future failures. At the same time, the law and trend of failure occurrence can be found, providing a basis for equipment maintenance and maintenance. Through the visualization of the fault timeline data, the trend and pattern of equipment failure can be intuitively observed, which helps to determine the frequency, cycle and duration of the failure. This helps to formulate more effective fault prevention and maintenance strategies and improve the reliability and availability of the equipment. Through time interval clustering analysis, the pattern and law of different fault time intervals can be found. This helps to optimize maintenance plans and resource scheduling. For example, common fault time interval patterns can be identified, so as to predict the time point when the equipment may fail in advance, take corresponding maintenance measures, and avoid the impact of equipment failure on production and operation. By detecting the time window data, the operating status of the equipment can be monitored in real time, including normal operation, abnormal operation and potential failures, etc. This helps to timely discover abnormal behavior of the equipment, conduct fault warning and maintenance planning, and improve the reliability and stability of the equipment.

[0073] Preferably, step S26 comprises the following steps:

[0074] Step S261: performing a fault rhythm analysis on the fault time interval pattern data to obtain fault rhythm pattern data;

[0075] Specifically, appropriate fault rhythm analysis tools, such as Fourier transform, wavelet transform, etc., can be selected to perform frequency domain or time-frequency domain analysis on fault time interval pattern data. Use Python's numpy library and scipy library to perform Fourier transform or wavelet transform. Take the fault time interval pattern data as input and perform frequency domain or time-frequency domain analysis through the corresponding transformation function. Extract fault rhythm pattern data from the results of fault rhythm analysis, such as spectral components, transformation coefficients, etc. These data can be used for fault prediction, fault diagnosis, and operation and maintenance decisions.

[0076] Step S262: performing frequency statistics on the fault rhythm pattern data to obtain fault rhythm frequency data;

[0077] Specifically, appropriate frequency statistics tools, such as histograms, probability density estimation, etc., can be selected to perform frequency analysis on fault rhythm pattern data. Use Python's matplotlib library or numpy library to create a histogram or perform probability density estimation. Take the fault rhythm pattern data as input and perform frequency analysis through the corresponding statistical function. Extract fault rhythm frequency data from the results of frequency statistics, such as frequency distribution, peak frequency, etc. These data can be used for fault prediction, fault diagnosis, and operation and maintenance decisions.

[0078] Step S263: Calculate the historical fault time intervals on the fault timeline data to obtain a number of fault time interval data;

[0079] Specifically, you can select an appropriate fault time interval calculation method, such as simple difference, sliding window, etc., to calculate the historical fault time interval data. Use Python's pandas library to create a time series object that contains the fault timeline data. Calculate the historical fault time interval data through the difference operation or sliding window operation of the time series object. Extract several fault time interval data from the result of the fault time interval calculation, such as the value and duration of each time interval.

[0080] Step S264: sorting the plurality of fault time interval data in ascending order to obtain sorted time interval data; dividing the sorted time interval data into time periods to obtain time period set data, wherein the time period set data includes a plurality of time period data;

[0081] Specifically, you can use Python sorting functions, such as sorted() or numpy.sort(), to sort the fault time interval data. Define the time window size of the time period, such as hourly, daily, or weekly. Use Python's pandas library to convert the sorted time interval data into a time series object. Use the resample() function of the time series object to divide the time period into the set time window size to obtain the time period collection data.

[0082] Step S265: Based on the fault rhythm frequency data and a plurality of fault time interval data, a time period in which the fault time interval with the highest fault rhythm frequency is located in the time period set data is selected as the detection time window data.

[0083] Specifically, the fault rhythm frequency data can be compared with the fault time interval data in the time period set data. The time period data corresponding to the fault time interval with the highest fault rhythm frequency is found. The fault time window data is extracted from the matched time period data, that is, the time period data where the fault time interval with the highest fault rhythm frequency is located. These data can be used for fault detection and operation and maintenance decisions.

[0084] The present invention can find the rhythm and law of equipment failure by analyzing the fault time interval pattern data. Identifying the rhythm pattern of the fault helps to predict the time point and frequency of future faults, further optimize the maintenance plan and resource scheduling, and improve the reliability and efficiency of the equipment. Through the statistics of the fault rhythm frequency data, the occurrence frequency of different fault rhythm patterns can be understood. This helps to identify and focus on the most common or most frequently occurring fault rhythm patterns, and provides a key reference for the maintenance and operation and maintenance strategy of the equipment. Through the calculation of the fault time interval data, the distribution of time intervals between equipment failures can be understood. This helps to evaluate the fault interval of the equipment, find the law and trend of the occurrence of faults, and provide a basis for fault prediction and maintenance planning. By sorting the division of time interval data and generating time period set data, the time range and duration of the occurrence of the fault can be better observed and analyzed. This helps to determine the occurrence mode and persistence of the fault, and provide more accurate information for fault prediction, maintenance planning and equipment operation and maintenance decisions. By selecting the time period where the fault time interval with the highest fault rhythm frequency is located as the detection time window data, fault detection and monitoring can be focused on the time period where the fault occurs most frequently. This helps to timely discover and respond to high-frequency faults, reduce the impact of faults on equipment performance and production efficiency, and improve the availability and operation efficiency of the equipment.

[0085] Preferably, step S3 comprises the following steps:

[0086] Step S31: collect the last detection timestamp of the target device to obtain the last detection timestamp data;

[0087] Specifically, the device status information, including the last detection timestamp, can be obtained by communicating with the target device. The last detection timestamp data of the target device can be obtained by using the device management system or API call. The collected last detection timestamp data can be sorted into an appropriate format, such as a date and time format or a timestamp format.

[0088] Step S32: Calculate the next detection time according to the detection time window data and the last detection timestamp data to obtain the next detection time data;

[0089] Specifically, the last detection timestamp data can be converted into a date and time format or a timestamp format. According to the fault time window length in the detection time window data, the last detection timestamp is added to the fault time window length to obtain the next detection time. The calculated next detection time data is sorted into an appropriate format, such as a date and time format or a timestamp format.

[0090] Step S33: extract the collection timestamp of the equipment operation status parameter to obtain the parameter collection timestamp; compare and judge the parameter collection timestamp with the next detection time data;

[0091] Specifically, the timestamp tag can be extracted from the equipment operation status parameter, and the next detection time data can be converted into a date and time format or a timestamp format. The parameter collection timestamp is compared with the next detection time to determine whether the next detection time has exceeded.

[0092] Step S34: If the parameter collection timestamp is earlier than the next detection time data, skip this detection and enter the next detection cycle; if the parameter collection timestamp is later than the next detection time data, execute the next step;

[0093] Specifically, the parameter collection timestamp and the next detection time data can be converted into a date and time format or a timestamp format. The parameter collection timestamp and the next detection time data are compared to determine whether the parameter timestamp is earlier or later than the next detection time. According to the result of the comparison and judgment, if the parameter collection timestamp is earlier than the next detection time data, skip this detection and enter the next detection cycle; if the parameter collection timestamp is later than the next detection time data, execute the next step.

[0094] Step S35: inputting the equipment operation status parameters, equipment temperature data and equipment operation index data into a preset operation status evaluation model to perform operation status scoring, thereby obtaining operation status scoring data;

[0095] Specifically, a preset operation status evaluation model can be established in advance, which can accept device operation status parameters, device temperature data, and device operation index data as input and output operation status score data. Arrange the device operation status parameters, device temperature data, and device operation index data into an appropriate format for input into the operation status evaluation model. Use a machine learning or deep learning framework, such as Scikit-learn, TensorFlow, or PyTorch, to load the preset operation status evaluation model. Take the device operation status parameters, device temperature data, and device operation index data as input and use the model to score the operation status.

[0096] Step S36: performing graded judgment on the operating status of the target device according to the operating status scoring data to obtain device operating status data;

[0097] Specifically, a set of grading standards may be set, such as being divided into excellent, good, medium and poor grades according to the scoring range. The running state of the target device is graded by comparing the running state scoring data with the grading standards.

[0098] Step S37: Perform manual intervention requirement analysis on the target device according to the device operation status data to obtain manual intervention requirement data.

[0099] Specifically, a set of standards or rules for manual intervention requirements may be set, such as determining whether manual intervention is required based on different levels of equipment operation status. Whether manual intervention is required is determined by comparing equipment operation status data with the standards or rules for manual intervention requirements.

[0100] The present invention can record the time point of the last detection of the device by collecting the timestamp data of the last detection. This helps to track the detection history of the device, understand the detection frequency and time interval of the device, and provide a basis for the calculation of the next detection time and the evaluation of the operation status. By calculating the next detection time data, the next detection time point of the device can be determined. This helps to formulate the detection plan of the equipment, reasonably arrange the maintenance and repair work of the equipment, and ensure the reliability and performance of the equipment. By extracting the acquisition timestamp data of the equipment operation status parameters, the time point of parameter acquisition can be understood, and the data of the equipment operation status can be time-correlated. This helps to establish the time series data of the equipment operation status, and provides a basis for subsequent operation status evaluation and analysis. Compare and judge according to the acquisition timestamp data of the parameters and the next detection time data. If the acquisition time of the parameters is earlier than the next detection time, it means that the parameters have been collected within the detection time window, and the current detection can be skipped and the next detection cycle can be entered. If the acquisition time of the parameters is later than the next detection time, it means that the next step of processing is required. By comparing the parameter acquisition timestamp with the next detection time data, it is possible to avoid repeated acquisition of the same parameter data in a short time, reduce unnecessary workload and resource consumption, and optimize the detection process. Through the operation status evaluation model, the operation status of the device can be objectively evaluated. The scoring data reflects the operating status of the equipment, including the rationality of parameters, temperature stability, and compliance with operating indicators. This helps to promptly detect abnormal conditions or failures of the equipment and provides a reference basis to help decision makers carry out corresponding maintenance and repair work. The operating status of the equipment can be classified by grading the operating status scoring data. This enables decision makers to have a clearer understanding of the operating status of the equipment and to clarify the health and risk level of the equipment. Different levels of operating status can trigger different treatment measures, which helps to take appropriate maintenance and intervention measures in a timely manner. Through manual intervention demand analysis, information on the manual intervention needs of the equipment can be provided to decision makers. According to different operating states, it can be determined whether manual intervention is required, as well as the method, timing and priority of intervention. This helps decision makers formulate corresponding intervention plans based on the actual situation and needs of the equipment to ensure the normal operation of the equipment and the efficient implementation of maintenance work.

[0101] Preferably, step S4 comprises the following steps:

[0102] Step S41: collecting service data flow of the target device to obtain device service data flow;

[0103] Specifically, you can use a network packet capture tool, such as Wireshark or tcpdump, to capture network communication data between the target device and other devices. Configure the packet capture tool to capture only the service data stream related to the target device. Start the service data stream collection tool and configure the packet capture filter to capture only the data stream related to the target device. Start capturing the service data stream and save the results to a file or database.

[0104] Step S42: sampling typical cases of the device service data flow to obtain a typical service data set;

[0105] Specifically, you can use data analysis tools, such as the pandas library in Python, to process and analyze business data streams. Prepare a set of sampling rules or methods for selecting typical business data. Read the device business data stream and load it into the data analysis tool. According to the sampling rules or methods, select typical business data for sampling. For example, you can select representative business traffic or business data for a specific time period. Save the sampled typical business data as a typical business data set.

[0106] Step S43: performing semantic mining and annotation on typical business data sets to obtain semantically annotated business data;

[0107] Specifically, you can use natural language processing (NLP) tool libraries, such as NLTK, spaCy, or StanfordCoreNLP, to perform text semantic mining and annotation. You can use pre-trained semantic role labeling models or named entity recognition models to assist in semantic annotation. Load a typical business data set into the semantic mining and annotation tool. Use the semantic mining and annotation functions provided by the tool to analyze and annotate the text in the business data set. For example, you can perform part-of-speech tagging, named entity recognition, syntactic analysis, etc. Save the results of semantic mining and annotation as semantically annotated business data.

[0108] Step S44: Determine the device processing service type of the semantically annotated service data to obtain device processing service type data.

[0109] Specifically, a machine learning or deep learning framework, such as Scikit-learn, TensorFlow, or PyTorch, can be used to build and train a device processing business type judgment model. Prepare a training data set that contains semantically annotated business data with the device processing business type labeled. Load the trained device processing business type judgment model. Use the semantically annotated business data as input and use the model to judge the device processing business type for each sample. For example, a classification model can be used to classify each semantically annotated data and divide it into different processing business types. Save the result of the device processing business type judgment as device processing business type data for subsequent analysis or application use.

[0110] The present invention can obtain detailed data generated by the device during operation by collecting the device business data stream. This helps to understand the actual operation of the device, business processes and data interactions, and provides a data basis for subsequent analysis and processing. By sampling typical cases of the device business data stream, representative typical business data can be selected. These data can reflect the typical operation of the device and business scenarios, which is helpful for subsequent analysis, modeling and decision-making. By performing semantic mining and annotation on typical business data sets, the data can be given richer semantic information. This helps to improve the ability to understand and utilize data, so that the data has higher value and application potential. By judging the device processing business type of semantically annotated business data, the data can be classified and categorized to determine the specific business type to which the data belongs. This helps to better understand and utilize data, and provide support and guidance for device processing business.

[0111] Preferably, step S5 comprises the following steps:

[0112] Step S51: if the manual intervention requirement data is data requiring manual intervention, start human-machine collaborative scheduling; if the manual intervention requirement data is data not requiring manual intervention, execute the next step;

[0113] Specifically, if it is determined that the demand data requires human intervention, human-machine collaborative scheduling is initiated. The identification of the target device that requires human intervention is sent to the appropriate human operator or team. The collaborative scheduling process is designed and implemented, including task allocation, progress tracking, etc.

[0114] Step S52: If the service type data processed by the device is user interaction service data, real-time traffic monitoring is performed on the target device to obtain a traffic time series data set;

[0115] Specifically, you can use network traffic analysis tools such as tshark, Suricata, or Bro to monitor and capture the network traffic of the target device. Configure the traffic monitoring tool to capture only the traffic for user interaction service data. Start the real-time traffic monitoring tool and configure the traffic filter to capture only the traffic related to user interaction service data. Start monitoring the real-time traffic of the target device and save the results as a traffic time series dataset.

[0116] Step S53: Scan the performance status of the target device to obtain performance status data;

[0117] Specifically, you can use a system performance monitoring tool, such as GKrellM, Windows Task Manager, or Linux top command, to monitor the performance status of the target device. Configure the performance monitoring tool to capture and record the performance indicators of the target device, such as CPU usage, memory usage, etc. Start the performance monitoring tool and select the target device for monitoring. Monitor and record the performance indicators of the target device, such as CPU usage, memory usage, etc. Save the recorded performance status data as a performance status data set.

[0118] Step S54: Counting the maximum freeze duration of the target device according to the performance status data to obtain the maximum freeze duration data;

[0119] Specifically, you can use a performance analysis tool, such as Windows Performance Recorder, Linux Perf, or Xcode Instruments, to analyze the performance status data and identify the jamming events. Configure the performance analysis tool to capture and analyze the performance status data and calculate the jamming duration. Load the performance status data into the performance analysis tool. Analyze the performance status data, identify the jamming events, and calculate the duration of each jamming event. Extract the maximum jamming duration, which is the longest duration among all the jamming events. Save the maximum jamming duration data as the maximum jamming duration data.

[0120] Step S55: Compare the maximum jamming duration data with the preset jamming threshold value. When the maximum jamming duration data is less than the preset jamming threshold value, perform a traffic regulation strategy on the target device based on the traffic time series data set to obtain an operation and maintenance strategy decision plan;

[0121] Specifically, the maximum jamming duration data and the preset jamming threshold can be obtained. The maximum jamming duration data is compared with the jamming threshold to determine whether it is less than the jamming threshold. When the maximum jamming duration data is less than the preset jamming threshold, a traffic regulation strategy is implemented for the target device based on the traffic time series data set. The traffic time series data set is analyzed to understand the traffic pattern and trend of the target device. Based on the analysis results, a traffic regulation strategy is formulated, such as increasing bandwidth, optimizing network routing, etc. Based on the traffic regulation strategy, an operation and maintenance strategy decision plan is generated.

[0122] Step S56: when the maximum jamming duration data is equal to or greater than the preset jamming threshold, optimizing and allocating resources for the target device based on the performance status data to obtain an operation and maintenance strategy decision plan;

[0123] Specifically, you can use resource management tools, such as Kubernetes, Docker, or VMware, to allocate and optimize resources. Configure resource management tools to optimize resource allocation based on performance status data. When the maximum jamming duration data is equal to or greater than the preset jamming threshold, optimize resource allocation for the target device based on the performance status data. Analyze the performance status data to understand the resource usage and bottlenecks of the target device. Based on the analysis results, adjust the resource allocation of the target device, such as increasing the number of CPU cores, adjusting memory allocation, etc. Generate an operation and maintenance strategy decision plan based on the resource optimization and allocation results.

[0124] Step S57: If the device processing business type data is enterprise internal business data, an operation and maintenance strategy decision is made for the target device based on the device operation data to obtain an operation and maintenance strategy decision solution;

[0125] Specifically, if the business type data processed by the equipment is for internal business data of the enterprise, analyze the equipment operation data to understand the equipment's operating status, performance status and potential problems. According to the analysis results, formulate targeted operation and maintenance strategies, such as adding backup strategies, optimizing database query statements, etc. According to the operation and maintenance strategy, generate an operation and maintenance strategy decision plan.

[0126] Step S58: Perform intelligent operation and maintenance operations on the target device according to the operation and maintenance strategy decision plan.

[0127] Specifically, you can use automated operation and maintenance tools, such as Ansible, SaltStack, or Puppet, to perform intelligent operation and maintenance operations. Configure the automated operation and maintenance tools to perform corresponding operations according to the operation and maintenance strategy decision plan. According to the operation and maintenance strategy decision plan, write corresponding automated operation and maintenance scripts or tasks. Use the automated operation and maintenance tools to apply the written scripts or tasks to the target devices. The automated operation and maintenance tools will perform corresponding intelligent operation and maintenance operations, such as configuration updates, service restarts, etc., according to the definition of the scripts or tasks.

[0128] The present invention determines whether it is necessary to start human-machine collaborative scheduling according to the situation of manual intervention demand data. When the manual intervention demand data requires manual intervention, starting human-machine collaborative scheduling can combine the advantages of manual and machine, and realize efficient task allocation and collaboration. This helps to improve processing efficiency, reduce manual workload, and ensure that tasks are processed and resolved within a reasonable time. For the device processing business type facing user interactive business data, by performing real-time traffic monitoring on the target device, the traffic situation of the device when processing user interactive business can be obtained. This helps to understand the load situation, traffic fluctuation trend and bottleneck problem of the device, and provides data support for subsequent traffic regulation strategy and operation and maintenance decision. By performing performance status scanning on the target device, various performance indicators of the device, such as CPU usage, memory occupancy, network delay, etc., can be obtained. This helps to understand the current performance status of the device, detect potential performance problems, and provide data basis for resource optimization and allocation and operation and maintenance decisions. By analyzing and calculating the performance status data, the maximum freeze duration of the device during operation is determined. This helps to evaluate the performance stability and user experience of the device, discover freeze problems and take corresponding optimization and adjustment measures. When the maximum jamming duration data is lower than the preset jamming threshold, the traffic regulation strategy for the target device based on the traffic time series data set can optimize the load balancing of the device, improve the response speed and user experience. This helps to maintain the normal operation of the device and improve the system performance and service quality. When the maximum jamming duration data exceeds the preset jamming threshold, the resource optimization and allocation of the target device based on the performance status data can adjust the resource allocation of the device and optimize the system configuration to improve the performance and stability of the device. This helps to solve the jamming problem of the device and improve the processing capacity and user satisfaction of the device. For the type of business processing of the device for internal business data of the enterprise, the appropriate operation and maintenance strategy can be formulated through analysis and decision-making based on the device operation data. This helps to improve the stability, security and reliability of the device and ensure the normal operation and service of the internal business of the enterprise. According to the operation and maintenance strategy decision plan, the intelligent operation and maintenance operation of the target device can be executed to automatically optimize, adjust and maintain the device. This helps to improve the operation and maintenance efficiency, reduce manual operation errors, and ensure the stability and availability of the device.

[0129] Preferably, step S56 includes the following steps:

[0130] Step S561: performing abnormal value detection on the equipment operation index data based on the equipment operation data to obtain abnormal equipment index data;

[0131] Specifically, the equipment operation index data can be statistically analyzed, such as calculating the mean value, standard deviation, etc. Anomaly detection algorithms, such as Z-score, box plot, etc., are used to detect outliers in the operation index data. According to the anomaly detection results, the abnormal operation index data is marked as equipment index abnormal data.

[0132] Step S562: Compare the device temperature data with a preset temperature threshold, and when the device temperature data is less than or equal to the preset temperature threshold, maintain the current device heat dissipation state;

[0133] Specifically, the device temperature data can be compared with the temperature threshold to determine whether it is less than or equal to the temperature threshold. If the device temperature data is less than or equal to the temperature threshold, the current device heat dissipation state is maintained; otherwise, subsequent steps are performed.

[0134] Step S563: when the device temperature data is greater than a preset temperature threshold, a temperature difference is calculated between the preset temperature threshold and the device temperature data to obtain temperature difference data;

[0135] Specifically, when the device temperature data is greater than a preset temperature threshold, the temperature difference between the device temperature data and the preset temperature threshold is calculated, for example, by subtraction operation, to obtain the temperature difference data, which can be used as an input for subsequent operations or recorded.

[0136] Step S564: making a heat dissipation adjustment decision according to the temperature difference data to obtain heat dissipation gear data; generating heat dissipation adjustment instruction data according to the heat dissipation gear data; and performing active heat dissipation operation on the target device according to the heat dissipation adjustment instruction data;

[0137] Specifically, the heat dissipation gear can be determined according to the temperature difference data based on a predefined heat dissipation strategy or algorithm. For example, different heat dissipation gears can be divided according to the size of the temperature difference. According to the heat dissipation gear data, a corresponding heat dissipation adjustment instruction is generated. For example, the heat dissipation gear can be mapped to a specific heat dissipation device working mode or parameter setting. The heat dissipation adjustment instruction is sent to the target device to trigger the corresponding heat dissipation operation. For example, the instruction can be sent through a remote management tool or a network communication protocol.

[0138] Step S565: Selecting a backup device type for the target device based on the device operation status parameters and the indicator abnormality data to obtain backup device type data;

[0139] Specifically, based on a predefined backup device selection strategy or algorithm, the most suitable backup device type can be determined according to the device operation status parameters and indicator abnormality data. The selected backup device type can be a predefined device type code or identifier.

[0140] Step S566: Preheat and wake up the corresponding type of equipment in the preset standby equipment group according to the standby equipment type data, distribute and allocate services between the target equipment and the selected standby equipment, and obtain an operation and maintenance strategy decision plan.

[0141] Specifically, the standby device that needs to be awakened can be determined based on the standby device type data. Use remote management tools or automated scripts to send wake-up instructions to the standby device or trigger a wake-up operation to make the standby device available. Determine the business diversion strategy between the target device and the standby device based on the operation and maintenance strategy or algorithm. For example, decisions can be made based on factors such as device load conditions and network conditions. Use load balancing devices, router configurations, or network management tools to divert business requests between the target device and the standby device.

[0142] The present invention can timely discover abnormal data in the equipment operation index, such as abnormal temperature, pressure, current, etc., through abnormal value detection, so as to take corresponding measures to deal with it in time, avoid the equipment from continuing to operate in an abnormal state, reduce the risk of equipment failure, and ensure the normal operation of the equipment. By comparing with the preset temperature threshold, it can be determined whether the equipment is in a normal heat dissipation state. If the equipment temperature is lower than or equal to the preset threshold, the current heat dissipation state can be maintained without additional heat dissipation measures. This can avoid unnecessary heat dissipation operations, save energy consumption and reduce the burden on the equipment heat dissipation system, while ensuring that the equipment temperature is within a safe range and ensuring the reliable operation of the equipment. By calculating the temperature difference between the equipment temperature and the preset temperature, the heat dissipation demand of the equipment can be evaluated. The temperature difference data reflects whether the equipment temperature exceeds the preset threshold, and helps the subsequent heat dissipation adjustment decision step to determine appropriate heat dissipation measures to maintain the equipment temperature within a safe range. According to the temperature difference data, the heat dissipation adjustment decision is made, and corresponding heat dissipation measures can be taken according to the degree of deviation of the equipment temperature to reduce the equipment temperature and maintain it within a safe range. By generating heat dissipation adjustment instruction data and actively dissipating heat for the target device, the device temperature can be controlled in a timely and effective manner to prevent failures caused by overheating, ensure that the device temperature is within a safe range, improve the reliability and stability of the device, and reduce the occurrence of failures and maintenance costs. According to the device operating status parameters and indicator abnormality data, select the appropriate backup device type to deal with possible failures or abnormalities of the target device. Selecting the appropriate backup device type helps to provide a reliable backup solution to ensure business continuity and device availability. According to the backup device type data, perform a preheating wake-up operation, that is, start the backup device in advance and put it in working condition so that it can quickly take over the work of the target device when needed. Through business diversion and allocation, part of the workload is transferred from the target device to the backup device, reducing the load pressure of the target device, improving the overall performance and fault tolerance of the system, and achieving efficient operation and maintenance strategy decisions.

[0143] Preferably, the present invention further provides an integrated intelligent operation and maintenance control system for executing the integrated intelligent operation and maintenance control method as described above, the integrated intelligent operation and maintenance control system comprising:

[0144] Intelligent collection module, used to collect multi-dimensional situation awareness of target equipment and obtain equipment operation data, where the equipment operation data includes equipment operation status parameters, equipment temperature data and equipment operation index data;

[0145] The abnormal detection cycle analysis module is used to perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device based on a number of historical fault time point data to obtain detection time window data;

[0146] The status analysis module is used to analyze the operation status of the target device based on the detection time window data according to the device operation status parameters, device temperature data and device operation index data to obtain the device operation status data; and to analyze the manual intervention demand of the target device according to the device operation status data to obtain the manual intervention demand data;

[0147] A service type identification module is used to identify the service type processed by the target device and obtain the service type data processed by the device;

[0148] The intelligent operation and maintenance decision module is used to make operation and maintenance strategy decisions for the target equipment based on the manual intervention demand data and the equipment processing business type data, and obtain an operation and maintenance strategy decision plan; and perform intelligent operation and maintenance operations on the target equipment according to the operation and maintenance strategy decision plan.

[0149] In the present invention, the intelligent acquisition module collects the equipment operation data of the target equipment through multi-dimensional situational awareness, including equipment operation status parameters, equipment temperature data and equipment operation index data, provides real-time equipment status information, and provides accurate data support for subsequent intelligent operation and maintenance decisions. The abnormal detection cycle analysis module analyzes the failure occurrence of the target equipment through historical fault time point statistics, and obtains several historical fault time point data. According to these data, the operation status detection time window analysis can be performed to determine the detection time window, so as to discover the abnormal state and potential faults of the equipment in advance. The state analysis module analyzes the operation status of the target equipment based on the detection time window data and the equipment operation data to obtain the equipment operation status data. These data can be used to judge the health status, performance and any abnormal situation of the equipment, and provide an accurate basis for subsequent operation and maintenance decisions and manual intervention demand analysis. According to the equipment operation status data, analyze whether the target equipment needs manual intervention, judge the equipment with problems or potential risks, and generate corresponding manual intervention demand data. This helps the operation and maintenance personnel to find equipment problems in time and take appropriate measures to avoid equipment failures and business interruptions. The business type identification module identifies the equipment processing business type of the target equipment, that is, determines the business type used by the equipment to process. This helps to better understand the operating environment and requirements of the equipment, and provides a more accurate basis for subsequent intelligent operation and maintenance decisions. The intelligent operation and maintenance decision module makes intelligent operation and maintenance strategy decisions for the target equipment based on the manual intervention demand data and the equipment processing business type data. This module can automatically formulate an operation and maintenance strategy decision plan that adapts to the current status of the equipment and the business type based on real-time data and business needs. According to the operation and maintenance strategy decision plan, perform intelligent operation and maintenance operations. This module can automatically perform operation and maintenance operations, including equipment maintenance, fault repair, performance optimization, etc., to improve operation and maintenance efficiency and reduce the risk of equipment failure and business interruption.

[0150] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An integrated intelligent operation and maintenance control method, characterized in that: The following steps are involved: Step S1: Perform multi-dimensional situation awareness collection on the target device to obtain device operation data, wherein the device operation data includes device operation status parameters, device temperature data and device operation index data; wherein step S1 includes the following steps: Step S11: Monitor the target device in kernel mode to obtain device operation status parameters; Step S12: Perform thermal imaging monitoring on the target device to obtain device temperature data; Step S13: Perform workload analysis on the target device to obtain device operation index data; wherein the device operation state parameters, device temperature data and device operation index data constitute the device operation data; wherein step S13 includes the following steps: Step S131: Perform workload perception on the target device to obtain device workload data, wherein the device workload data includes but is not limited to system call tracking data, process behavior monitoring data and resource utilization statistics data; Step S132: performing semantic analysis on the system call tracing data to obtain workload semantic pattern data; Step S133: Acquire target device configuration information data and target device application dependency data; Step S134: constructing a workload knowledge graph based on the workload semantic pattern data by combining the target device configuration information data and the target device application dependency data to obtain a workload knowledge graph; Step S135: Using the workload knowledge graph, the process behavior monitoring data and resource utilization statistics are subjected to workload fingerprint recognition to obtain workload classification data; Step S136: dynamically evaluate the target device load according to the workload classification data and the resource utilization statistics data to obtain device performance pressure evaluation data; wherein the workload classification data and the device performance pressure evaluation data constitute the device operation data; wherein the device operation state parameters, the device temperature data and the device operation index data constitute the device operation data; Step S2: Perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device according to the several historical fault time point data to obtain detection time window data; wherein step S2 includes the following steps: Step S21: Collect historical logs of the target device to obtain a historical log data set; Step S22: filtering the historical log data set by device abnormality logs to obtain a historical abnormality log data set; Step S23: performing historical fault time point statistics on the target device according to the historical abnormal log data set to obtain a number of historical fault time point data; Step S24: Visualize the timeline of several historical fault time point data to obtain fault timeline data; Step S25: performing time interval clustering analysis on the fault timeline data to obtain fault time interval pattern data; Step S26: Performing an operation status detection time window analysis on the target device according to the fault timeline data and the fault time interval pattern data to obtain detection time window data, wherein step S26 includes the following steps: Step S261: performing a fault rhythm analysis on the fault time interval pattern data to obtain fault rhythm pattern data; Step S262: performing frequency statistics on the fault rhythm pattern data to obtain fault rhythm frequency data; Step S263: Calculate the historical fault time intervals on the fault timeline data to obtain a number of fault time interval data; Step S264: sorting the plurality of fault time interval data in ascending order to obtain sorted time interval data; dividing the sorted time interval data into time periods to obtain time period set data, wherein the time period set data includes a plurality of time period data; Step S265: based on the fault rhythm frequency data and a plurality of fault time interval data, a time period where the fault time interval with the highest fault rhythm frequency is located in the time period set data is selected as the detection time window data; Step S3: Based on the detection time window data, the target device is analyzed for its operating status according to the device operating status parameters, the device temperature data and the device operating index data to obtain the device operating status data; based on the device operating status data, the target device is analyzed for manual intervention requirements to obtain manual intervention requirements data; Step S4: Identify the service type processed by the target device to obtain data on the service type processed by the device; Step S5: Make an operation and maintenance strategy decision for the target device according to the manual intervention demand data and the device processing business type data to obtain an operation and maintenance strategy decision plan; perform intelligent operation and maintenance operations on the target device according to the operation and maintenance strategy decision plan.

2. The integrated intelligent operation and maintenance control method according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: collect the last detection timestamp of the target device to obtain the last detection timestamp data; Step S32: Calculate the next detection time according to the detection time window data and the last detection timestamp data to obtain the next detection time data; Step S33: extract the collection timestamp of the equipment operation status parameter to obtain the parameter collection timestamp; compare and judge the parameter collection timestamp with the next detection time data; Step S34: If the parameter collection timestamp is earlier than the next detection time data, skip this detection and enter the next detection cycle; if the parameter collection timestamp is later than the next detection time data, execute the next step; Step S35: inputting the equipment operation status parameters, equipment temperature data and equipment operation index data into a preset operation status evaluation model to perform operation status scoring, thereby obtaining operation status scoring data; Step S36: performing graded judgment on the operating status of the target device according to the operating status scoring data to obtain device operating status data; Step S37: Perform manual intervention requirement analysis on the target device according to the device operation status data to obtain manual intervention requirement data.

3. The integrated intelligent operation and maintenance control method according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: collecting service data flow of the target device to obtain device service data flow; Step S42: sampling typical cases of the device service data flow to obtain a typical service data set; Step S43: performing semantic mining and annotation on typical business data sets to obtain semantically annotated business data; Step S44: Determine the device processing service type of the semantically annotated service data to obtain device processing service type data.

4. The integrated intelligent operation and maintenance control method according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: if the manual intervention requirement data is data requiring manual intervention, start human-machine collaborative scheduling; if the manual intervention requirement data is data not requiring manual intervention, execute the next step; Step S52: If the service type data processed by the device is user interaction service data, real-time traffic monitoring is performed on the target device to obtain a traffic time series data set; Step S53: Scan the performance status of the target device to obtain performance status data; Step S54: Counting the maximum freeze duration of the target device according to the performance status data to obtain the maximum freeze duration data; Step S55: Compare the maximum jamming duration data with the preset jamming threshold value. When the maximum jamming duration data is less than the preset jamming threshold value, perform a traffic regulation strategy on the target device based on the traffic time series data set to obtain an operation and maintenance strategy decision plan; Step S56: when the maximum jamming duration data is equal to or greater than the preset jamming threshold, optimizing and allocating resources for the target device based on the performance status data to obtain an operation and maintenance strategy decision plan; Step S57: If the device processing business type data is enterprise internal business data, an operation and maintenance strategy decision is made for the target device based on the device operation data to obtain an operation and maintenance strategy decision solution; Step S58: Perform intelligent operation and maintenance operations on the target device according to the operation and maintenance strategy decision plan.

5. The integrated intelligent operation and maintenance control method according to claim 4 is characterized in that: Step S56 includes the following steps: Step S561: performing abnormal value detection on the equipment operation index data based on the equipment operation data to obtain abnormal equipment index data; Step S562: Compare the device temperature data with a preset temperature threshold, and when the device temperature data is less than or equal to the preset temperature threshold, maintain the current device heat dissipation state; Step S563: when the device temperature data is greater than a preset temperature threshold, a temperature difference is calculated between the preset temperature threshold and the device temperature data to obtain temperature difference data; Step S564: making a heat dissipation adjustment decision according to the temperature difference data to obtain heat dissipation gear data; generating heat dissipation adjustment instruction data according to the heat dissipation gear data; and performing active heat dissipation operation on the target device according to the heat dissipation adjustment instruction data; Step S565: Selecting a backup device type for the target device based on the device operation status parameters and the indicator abnormality data to obtain backup device type data; Step S566: Preheat and wake up the corresponding type of equipment in the preset standby equipment group according to the standby equipment type data, distribute and allocate services between the target equipment and the selected standby equipment, and obtain an operation and maintenance strategy decision plan.

6. An integrated intelligent operation and maintenance control system, characterized in that: Used to execute the integrated intelligent operation and maintenance control method according to claim 1, the integrated intelligent operation and maintenance control system comprises: Intelligent collection module, used to collect multi-dimensional situation awareness of target equipment and obtain equipment operation data, where the equipment operation data includes equipment operation status parameters, equipment temperature data and equipment operation index data; The abnormal detection cycle analysis module is used to perform historical fault time point statistics on the target device to obtain a number of historical fault time point data; perform operation status detection time window analysis on the target device based on a number of historical fault time point data to obtain detection time window data; The status analysis module is used to analyze the operation status of the target device based on the detection time window data according to the device operation status parameters, device temperature data and device operation index data to obtain the device operation status data; and to analyze the manual intervention demand of the target device according to the device operation status data to obtain the manual intervention demand data; A service type identification module is used to identify the service type processed by the target device and obtain the service type data processed by the device; The intelligent operation and maintenance decision module is used to make operation and maintenance strategy decisions for the target equipment based on the manual intervention demand data and the equipment processing business type data, and obtain an operation and maintenance strategy decision plan; and perform intelligent operation and maintenance operations on the target equipment according to the operation and maintenance strategy decision plan.

Images