Intelligent processing system based on big data automatic operation and maintenance platform

Abstract

The invention relates to the technical field of data processing, and discloses an intelligent processing system based on a big data automatic operation and maintenance platform, which comprises a data monitoring module, a data analysis module, a data evaluation module and an early warning module, the data monitoring module is used for collecting hardware performance index data, hardware operation state data, service performance indexes, network flow data and sudden abnormal data, the data analysis module carries out analysis and calculation according to the collected multiple groups of data, and the data evaluation module carries out calculation on a comprehensive health index according to the received data and a calculation result. Whether an unsafe condition exists in the automatic operation and maintenance platform is judged according to the minimum value of the comprehensive health index, and an alarm signal is sent to the early warning module to give an alarm if the unsafe condition exists, so that operation and maintenance personnel can find and solve factors possibly influencing the system stability in time, the fault occurrence probability is reduced, and the safety of the system is improved. And the security of the system and data is protected.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and specifically to an intelligent processing system based on a big data automated operation and maintenance platform. Background Art

[0002] With the rapid development of information technology, all walks of life have accumulated a large amount of data, which is called "big data". Big data has four main characteristics, namely large capacity, high speed, diversity and low value density. In order to extract valuable information from these massive data, it is necessary to use big data technology for storage, processing and analysis. The development of big data technology provides powerful data support and analysis capabilities for automated operation and maintenance. With the continuous expansion of corporate business and the increasing complexity of IT systems, traditional operation and maintenance methods have been difficult to meet the needs of modern enterprises. Enterprises need more efficient and intelligent operation and maintenance methods to ensure the stable operation of the system and the continuity of business. Therefore, an automated operation and maintenance platform based on big data came into being. It can realize the automation and intelligent management of the operation and maintenance process through intelligent means. With the wide application and practice of big data automated operation and maintenance platforms in various industries, it has accumulated rich industry experience and best practices. These experiences and practices provide valuable references and references for later comers, which help them to build automated operation and maintenance platforms suitable for themselves more quickly.

[0003] In the big data environment, data security is particularly important. However, existing intelligent processing systems may still have many deficiencies in operation and are vulnerable to cyber attacks and data leaks, leading to risks such as platform failure and information leakage. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent processing system based on a big data automated operation and maintenance platform, which has the advantages of being able to quickly understand the overall health status of the platform, thereby quickly locating potential problems and reducing troubleshooting time. It covers multiple key indicators and can comprehensively reflect the operating status of the platform, helping operation and maintenance personnel to promptly discover and resolve factors that may affect system stability, reduce the probability of failures, and protect the security of the system and data.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent processing system based on a big data automated operation and maintenance platform, comprising a data monitoring module, a data analysis module, a data evaluation module and an early warning module;

[0008] The data monitoring module is used to collect hardware performance index data Yjxn, hardware operation status data Yjyx, service performance index Fwxn, network traffic data Wlll and sudden abnormal data Tfyc. The data monitoring module summarizes and integrates the collected data and sends it to the data analysis module;

[0009] The data analysis module calculates the hardware utilization rate Yjsy according to the hardware performance index data Yjxn, calculates the hardware operation health index Yjyk according to the hardware operation status data Yjyx, calculates the server load Fwfh according to the service performance index Fwxn, calculates the network load Wlfh according to the network traffic data Wlll, and calculates the sudden abnormality index Tfzs according to the sudden abnormality data Tfyc. The data analysis module sends the calculated data to the data evaluation module;

[0010] The data evaluation module calculates the comprehensive health index Zhjk according to the received data, and determines whether there is an unsafe situation on the automated operation and maintenance platform according to the minimum value of the comprehensive health index, and sends an alarm signal to the early warning module if it is determined that there is an unsafe situation;

[0011] The early warning module issues an alarm according to the received alarm signal.

[0012] Preferably, the hardware performance indicator data Yjxn includes CPU usage time Cpsy, memory usage Ncsy, disk read and write speed Cpdx, and disk delay time Cpyc. The above data can be obtained through the tools provided by the operating system;

[0013] The hardware operation status data Yjyx includes hardware temperature data Yjwd, hardware power data Yjgl, and fan speed data Yjfs. The above data can be monitored and obtained by sensors.

[0014] Preferably, the hardware performance indicator data Yjxn includes CPU usage time Cpsy, memory usage Ncsy, disk read and write speed Cpdx, and disk delay time Cpyc. The above data can be obtained through the tools provided by the operating system;

[0015] The hardware operation status data Yjyx includes hardware temperature data Yjwd, hardware power data Yjgl, and fan speed data Yjfs. The above data can be monitored and obtained by sensors.

[0016] Preferably, the service performance indicator Fwxn includes service response time Fwxy, server error rate Fwcw, and server request volume Fwqq, and the above data can be obtained through an application monitoring tool;

[0017] The network traffic data Wlll includes real-time traffic usage data Llsy, network bandwidth usage rate Kdsy, number of connections Ljsl, and connection time Ljsj. The above data can be obtained through the task processor;

[0018] The sudden abnormal data Tfyc includes the historical sudden abnormal probability Tfgl and the abnormal attack rate Ycgj, and the above data can be obtained through the security log.

[0019] Preferably, the calculation formula of the hardware utilization rate Yjsy is:

[0020]

[0021] Among them, ZCp represents the total CPU usage time, represents the CPU usage, α1 represents the corresponding weight, and ZHc represents the total memory. represents the memory usage, α2 represents the corresponding weight, Madx represents the maximum read and write speed of the disk, Indicates the relative usage of disk write speed, α3 represents the corresponding weight, and Mayc represents the maximum delay time of the disk. represents the relative situation of disk latency, α4 represents the corresponding weight, α1+α2+α3+α4=1, and γ represents the exponential weighting factor used to adjust the impact of each resource utilization rate.

[0022] Preferably, the calculation formula of the hardware operation health index Yjyk is:

[0023]

[0024] in, Indicates the relative condition of hardware temperature, β1 is the corresponding weight, Yjwd i is the current hardware temperature, Yjwd min Yjwd is the minimum safe hardware temperature. max is the maximum safe hardware temperature. Indicates the relative usage of hardware power, Yjgl max Represents the maximum power, Yjgl i represents the current power, β2 represents the corresponding weight, represents the relative situation of the fan speed, β3 represents the corresponding weight, and β1+β2+β3=1.

[0025] Preferably, the calculation formula of the server load Fwfh is:

[0026]

[0027] Among them, Mafx represents the threshold of service response time, represents the ratio of the average service response time to the threshold, γ1 represents the corresponding weight, Mafc represents the maximum acceptable error rate, Represents the conversion of the server error rate into a percentage relative to the maximum acceptable error rate, indicating that the server error rate has a significant increase in the server load. γ2 represents the corresponding weight. It represents the multiple of the current total request volume relative to the benchmark request volume plus 1, reflecting the increase of the current request volume relative to the normal load. Jzfq represents the request volume under normal circumstances, and γ3 represents the corresponding weight.

[0028] Preferably, the calculation formula of the network load Wlfh is:

[0029]

[0030] Among them, Wlzl represents the total flow data, represents the proportion of real-time traffic, δ1 represents the corresponding weight, and Zljs represents the maximum number of connections. represents the proportion of the number of connections, δ2 represents the corresponding weight, Qjsj represents the expected connection time, represents the proportion of connection time, and δ3 represents the corresponding weight.

[0031] Preferably, the calculation formula of the sudden abnormality index Tfzs is:

[0032]

[0033] in, t represents the average value of the historical probability of sudden anomalies in the past T time units, Tfgl,t represents the historical probability of sudden anomalies in the tth time unit, T is the number of time units used to calculate the average value, ε1 represents the corresponding weight, Represents the ratio of the current abnormal attack rate to the maximum attack rate, Magj represents the maximum attack rate, ε2 represents the corresponding weight, 1+log2 represents the use of a logarithmic function to smoothly reflect the impact of the number of attacks on the sudden anomaly index, Ycsl represents the number of abnormal attacks detected during the observation period, Sjzl represents the total number of events detected during the observation period, including normal and abnormal events, and ε3 represents the corresponding weight.

[0034] Preferably, the calculation formula of the comprehensive health index Zhjk is:

[0035]

[0036] Among them, θ1, θ2, θ3, θ4, and θ5 are the corresponding weights of the hardware utilization rate Yjsy, the hardware operation health index Yjyk, the server load Fwfh, the network load Wlfh, and the sudden abnormality index Tfzs, respectively, and θ1+θ2+θ3+θ4+θ5=1.

[0037] Preferably, when the comprehensive health index Zhjk is less than the minimum value of the comprehensive health index, it means that there is an unsafe situation in the current automated operation and maintenance platform, and an alarm signal is sent to the early warning module.

[0038] Compared with the prior art, the present invention provides an intelligent processing system based on a big data automated operation and maintenance platform, which has the following beneficial effects:

[0039] 1. The present invention helps to maintain the stable operation of the system and reduce the security risks caused by resource exhaustion by monitoring the hardware utilization rate. The hardware operation health index helps to ensure that the equipment operates within a safe working range. The server load can timely discover potential performance bottlenecks and prevent service interruptions or performance degradation caused by resource overload. The network load can quickly discover abnormal traffic patterns. By calculating the sudden abnormality index, the potential failure risk can be predicted more accurately, and possible abnormal situations can be discovered in advance, so as to take preventive measures, reduce the probability of failure, and protect the security of the system and data.

[0040] 2. Through real-time monitoring and calculation of the comprehensive health index, the present invention enables operation and maintenance personnel to quickly understand the overall health status of the platform, thereby quickly locating potential problems and reducing troubleshooting time. The automated alarm system can promptly notify the operation and maintenance personnel before or when a problem occurs, allowing them to respond and handle it quickly to avoid the problem from expanding. The calculation of the comprehensive health index covers multiple key indicators and can comprehensively reflect the operating status of the platform, helping operation and maintenance personnel to promptly discover and resolve factors that may affect system stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the structural system of the present invention; DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] See also Figure 1, an intelligent processing system based on a big data automated operation and maintenance platform, including a data monitoring module, a data analysis module, a data evaluation module and an early warning module;

[0044] The data monitoring module is used to collect hardware performance index data Yjxn, hardware operation status data Yjyx, service performance index Fwxn, network traffic data Wlll and sudden abnormal data Tfyc. The data monitoring module summarizes and integrates the collected data and sends it to the data analysis module;

[0045] Hardware performance indicator data Yjxn includes CPU usage time Cpsy, memory usage Ncsy, disk read and write speed Cpdx, and disk delay time Cpyc. The above data can be obtained through the tools provided by the operating system;

[0046] The hardware operation status data Yjyx includes the hardware temperature data Yjwd, the hardware power data Yjgl, and the fan speed data Yjfs. The above data can be monitored and obtained through sensors;

[0047] The service performance indicator Fwxn includes the service response time Fwxy, the server error rate Fwcw, and the server request volume Fwqq. The above data can be obtained through the application monitoring tool;

[0048] The network traffic data Wlll includes real-time traffic usage data Llsy, network bandwidth usage rate Kdsy, number of connections Ljsl, and connection time Ljsj. The above data can be obtained through the task processor;

[0049] The sudden abnormal data Tfyc includes the historical sudden abnormal probability Tfgl and the abnormal attack rate Ycgj. The above data can be obtained through the security log;

[0050] The data analysis module calculates the hardware utilization rate Yjsy based on the hardware performance indicator data Yjxn;

[0051] The calculation formula of hardware utilization rate Yjsy is:

[0052]

[0053] By monitoring hardware usage, the system can ensure that servers and other hardware devices do not crash or become unstable due to overload, which helps maintain the stable operation of the system and reduce security risks caused by resource exhaustion. At the same time, hardware usage data can help the automated operation and maintenance platform dynamically adjust resource allocation when needed, thereby optimizing performance and preventing potential security threats. ZCp represents the total CPU usage time. Represents the CPU usage. The higher the value, the heavier the CPU load. α1 represents the corresponding weight. ZNc represents the total memory. Represents the memory usage. The higher the value, the tighter the memory usage. α2 represents the corresponding weight. Madx represents the maximum read and write speed of the disk. Indicates the relative usage of disk write speed. The higher the value, the closer the disk write speed is to the maximum value. α3 represents the corresponding weight. Mayc represents the maximum delay time of the disk. Represents the relative situation of disk latency. The higher the value, the closer the disk latency is to the maximum value. α4 represents the corresponding weight, α1+α2+α3+α4=1. γ represents the exponential weighting factor used to adjust the impact of each resource utilization rate. The larger γ is, the more prominent the high utilization rate is.

[0054] Calculate the hardware operation health index Yjyk based on the hardware operation status data Yjyx;

[0055] The calculation formula of the hardware operation health index Yjyk is:

[0056]

[0057] The hardware operation health index is calculated through temperature data, power data, and fan speed data, and overheating problems are discovered in a timely manner to avoid hardware damage or performance degradation caused by overheating. This helps ensure that the equipment operates within a safe working range and prevents failures caused by overload. By continuously monitoring the hardware operation status, potential problems can be discovered in advance, which can significantly reduce the need for manual inspections and improve operation and maintenance efficiency. Indicates the relative condition of the hardware temperature. The higher the value, the closer the temperature is to the safety upper limit. β1 is the corresponding weight. Yjwd i is the current hardware temperature, Yjwd min Yjwd is the minimum safe hardware temperature. max is the maximum safe hardware temperature. Indicates the relative usage of hardware power. The higher the value, the closer the power is to the maximum power. max Represents the maximum power, Yjgl i represents the current power, β2 represents the corresponding weight, Represents the relative situation of the fan speed. The higher the value, the closer the fan speed is to the maximum speed. β3 represents the corresponding weight, and β1+β2+β3=1;

[0058] Calculate the server load Fwfh based on the service performance indicator Fwxn;

[0059] The calculation formula for server load Fwfh is:

[0060]

[0061] Server load can timely discover potential performance bottlenecks and prevent service interruptions or performance degradation caused by resource overload. Reasonable server load management helps maintain high availability and high performance of the system, thereby improving user access speed and satisfaction, and helping to improve the efficiency and stability of the big data automated operation and maintenance platform. Mafx represents the threshold of service response time. Represents the ratio of the average service response time to the threshold. If the average response time exceeds the threshold, this ratio will be greater than 1, indicating that the service response time has an increasing impact on the server load. γ1 represents the corresponding weight, and Mafc represents the maximum acceptable error rate. Represents the conversion of the server error rate into a percentage relative to the maximum acceptable error rate, indicating the ratio of the current error rate to the maximum acceptable error rate. If the error rate is very high, this ratio will be close to or exceed 100%, indicating that the server error rate has a significant increase in the server load. γ2 represents the corresponding weight. represents the multiple of the current total request volume relative to the benchmark request volume plus 1. The addition of 1 is to ensure that even when the total request volume is equal to the benchmark request volume, there is a positive number inside the logarithmic function, which reflects the increment of the current request volume relative to the normal load. Jzfq represents the request volume under normal conditions, and γ3 represents the corresponding weight;

[0062] Calculate the network load Wlfh according to the network traffic data Wlll;

[0063] The calculation formula of network load Wlfh is:

[0064]

[0065] Network load can quickly detect abnormal traffic patterns, such as sudden increases in data traffic or unusual packet sizes, which may be signs of network attacks. At the same time, measures can be taken before the bandwidth reaches the limit, such as limiting non-critical traffic, ensuring the smooth operation of important businesses, preventing resource overload, and improving system stability and security. Network strategies can be optimized, such as automatically disconnecting long-term idle connections to reduce unnecessary resource consumption. Among them, Wlal represents the total traffic data, represents the proportion of real-time traffic, δ1 represents the corresponding weight, and Zljs represents the maximum number of connections. represents the proportion of the number of connections, δ2 represents the corresponding weight, Qjsj represents the expected connection time, represents the proportion of connection time, and δ3 represents the corresponding weight;

[0066] Calculate the sudden abnormality index Tfzs according to the sudden abnormality data Tfyc;

[0067] The calculation formula of the sudden abnormality index Tfzs is:

[0068]

[0069] By calculating the sudden abnormality index, the potential failure risk can be predicted more accurately, possible abnormal situations can be discovered in advance, and preventive measures can be taken to reduce the probability of failure and protect the security of the system and data. t represents the average value of the historical probability of sudden anomalies in the past T time units, Tfgl,t represents the historical probability of sudden anomalies in the tth time unit, T is the number of time units used to calculate the average value, ε1 represents the corresponding weight, represents the ratio of the current abnormal attack rate to the maximum attack rate, Magj represents the maximum attack rate, and ε2 represents the corresponding weight. represents the use of a logarithmic function to smoothly reflect the impact of the number of attacks on the sudden anomaly index, Ycsl represents the number of abnormal attacks detected during the observation period, Sjzl represents the total number of events detected during the observation period, including normal and abnormal events, and ε3 represents the corresponding weight;

[0070] The data analysis module sends the calculated data to the data evaluation module;

[0071] The data evaluation module calculates the comprehensive health index Zhjk based on the received data;

[0072] The calculation formula of the comprehensive health index Zhjk is:

[0073]

[0074] Among them, θ1, θ2, θ3, θ4, and θ5 are the corresponding weights of the hardware utilization rate Yjsy, the hardware operation health index Yjyk, the server load Fwfh, the network load Wlfh, and the sudden abnormality index Tfzs, and θ1+θ2+θ3+θ4+θ5=1;

[0075] When the comprehensive health index Zhjk is less than the minimum value of the comprehensive health index, it means that the current automated operation and maintenance platform is unsafe, and an alarm signal is sent to the early warning module;

[0076] By real-time monitoring and calculating the comprehensive health index, operation and maintenance personnel can quickly understand the overall health status of the platform, thereby quickly locating potential problems and reducing troubleshooting time. The automated alarm system can promptly notify operation and maintenance personnel before or when a problem occurs, allowing them to respond and handle it quickly to avoid the problem from expanding. The calculation of the comprehensive health index covers multiple key indicators and can fully reflect the operating status of the platform, helping operation and maintenance personnel to promptly discover and resolve factors that may affect system stability;

[0077] The early warning module issues an alarm based on the received alarm signal.

[0078] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent processing system based on a big data automated operation and maintenance platform, characterized by: Including data monitoring module, data analysis module, data evaluation module and early warning module; The data monitoring module is used to collect hardware performance index data Yjxn, hardware operation status data Yjyx, service performance index Fwxn, network traffic data Wlll and sudden abnormal data Tfyc. The data monitoring module summarizes and integrates the collected data and sends it to the data analysis module; The data analysis module calculates the hardware utilization rate Yjsy according to the hardware performance index data Tjxn, calculates the hardware operation health index Yjyk according to the hardware operation status data Yjyx, calculates the server load Fwfh according to the service performance index Fwxn, calculates the network load Wlfh according to the network traffic data Wlll, and calculates the sudden abnormality index Tfzs according to the sudden abnormality data Tfyc. The data analysis module sends the calculated data to the data evaluation module; The data evaluation module calculates the comprehensive health index Zhjk according to the received data, and determines whether there is an unsafe situation on the automated operation and maintenance platform according to the minimum value of the comprehensive health index, and sends an alarm signal to the early warning module if it is determined that there is an unsafe situation; The early warning module issues an alarm according to the received alarm signal.

2. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 1 is characterized by: The hardware performance indicator data Yjxn includes CPU usage time Cpsy, memory usage Ncsy, disk read and write speed Cpdx, and disk delay time Cpyc. The above data can be obtained through the tools provided by the operating system; The hardware operation status data Yjyx includes hardware temperature data Yjwd, hardware power data Yjgl, and fan speed data Yjfs. The above data can be monitored and obtained by sensors.

3. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 1 is characterized by: The service performance indicator Fwxn includes service response time Fwxy, server error rate Fwcw, and server request volume Fwqq. The above data can be obtained through application monitoring tools; The network traffic data Wlll includes real-time traffic usage data Llsy, network bandwidth usage rate Kdsy, number of connections Ljsl, and connection time Ljsj. The above data can be obtained through the task processor; The sudden abnormal data Tfyc includes the historical sudden abnormal probability Tfgl and the abnormal attack rate Ycgj, and the above data can be obtained through the security log.

4. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 2 is characterized by: The calculation formula of the hardware utilization rate Yjsy is: Among them, ZCp represents the total CPU usage time, represents the CPU usage, α1 represents the corresponding weight, ZNc represents the total memory, represents the memory usage, α2 represents the corresponding weight, Madx represents the maximum read and write speed of the disk, Indicates the relative usage of disk write speed, α3 represents the corresponding weight, and Mayc represents the maximum delay time of the disk. represents the relative situation of disk latency, α4 represents the corresponding weight, α1+α2+α3+α4=1, and γ represents the exponential weighting factor used to adjust the impact of each resource utilization rate.

5. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 2 is characterized by: The calculation formula of the hardware operation health index Yjyk is: in, Indicates the relative condition of hardware temperature, β1 is the corresponding weight, Yjwd i is the current hardware temperature, Yjwd min Yjwd is the minimum safe hardware temperature. max is the maximum safe hardware temperature. Indicates the relative usage of hardware power, Yjgl max Represents the maximum power, Yjgl i represents the current power, β2 represents the corresponding weight, represents the relative situation of the fan speed, β3 represents the corresponding weight, and β1+β2+β3=1.

6. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 3 is characterized by: The calculation formula of the server load Fwfh is: Among them, Mafx represents the threshold of service response time, represents the ratio of the average service response time to the threshold, γ1 represents the corresponding weight, Mafc represents the maximum acceptable error rate, ×100 represents the conversion of the server error rate into a percentage relative to the maximum acceptable error rate, indicating that the server error rate has a significant increase in the server load. γ2 represents the corresponding weight. It represents the multiple of the current total request volume relative to the benchmark request volume plus 1, reflecting the increase of the current request volume relative to the normal load. Jzfq represents the request volume under normal circumstances, and γ3 represents the corresponding weight.

7. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 3 is characterized by: The calculation formula of the network load Wlfh is: Among them, Wlzl represents the total flow data, represents the proportion of real-time traffic, δ1 represents the corresponding weight, and Zljs represents the maximum number of connections. represents the proportion of the number of connections, δ2 represents the corresponding weight, Qjsj represents the expected connection time, represents the proportion of connection time, and δ3 represents the corresponding weight.

8. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 3 is characterized by: The calculation formula of the sudden abnormality index Tfzs is: in, t represents the average value of the historical probability of sudden anomalies in the past T time units, Tfgl,t represents the historical probability of sudden anomalies in the tth time unit, T is the number of time units used to calculate the average value, ε1 represents the corresponding weight, represents the ratio of the current abnormal attack rate to the maximum attack rate, Magj represents the maximum attack rate, and ε2 represents the corresponding weight. represents the use of a logarithmic function to smoothly reflect the impact of the number of attacks on the sudden anomaly index, Ycsl represents the number of abnormal attacks detected during the observation period, Sjzl represents the total number of events detected during the observation period, including normal and abnormal events, and ε3 represents the corresponding weight.

9. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 8, characterized in that: The calculation formula of the comprehensive health index Zhjk is: Among them, θ1, θ2, θ3, θ4, and θ5 are the corresponding weights of the hardware utilization rate Yjsy, the hardware operation health index Yjyk, the server load Fwfh, the network load Wlfh, and the sudden abnormality index Tfzs, respectively, and θ1+θ2+θ3+θ4+θ5=1.

10. The intelligent processing system based on the big data automated operation and maintenance platform according to claim 9, characterized in that: When the comprehensive health index Zhjk is less than the minimum value of the comprehensive health index, it means that there is an unsafe situation in the current automated operation and maintenance platform, and an alarm signal is sent to the early warning module.

Images