A security monitoring and management system based on big data Internet of Things

By introducing bandwidth resource consumption monitoring, image quality analysis and transmission delay judgment modules into the big data IoT security monitoring and management system, and combining fuzzy logic to evaluate security incident response capabilities, the bandwidth shortage and delay problems in high-density monitoring scenarios are solved, and the problem of bandwidth shortage and delay in high-density monitoring scenarios is realized The reliability of real-time transmission and the timeliness of emergency response.

CN118740694BActive Publication Date: 2024-11-15DALIAN HUIZHIYEXUE NETWORK TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411215878.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-15
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

In the security monitoring and management of the Internet of Things in big data, when high-definition image data is transmitted in real time in high-density monitoring scenarios, insufficient bandwidth or excessive delay may lead to lag or delay in monitoring images, affecting the real-time monitoring and response of security events, especially in sudden During the incident, key image data may not be transmitted in time, delaying the implementation of security measures.

Method used

A security monitoring and management system based on the Internet of Things was designed, including bandwidth resource consumption monitoring module, image quality analysis module, transmission delay judgment module and response analysis module. The bandwidth resource usage is monitored in real time through SolarWinds, and time series decomposition technology is used. and fuzzy logic evaluate the real-time response capabilities of security events, divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and intelligent management.

Benefits of technology

Effectively identify and handle abnormal situations, optimize resource configuration, improve system stability and response speed, ensure the reliability of real-time transmission of key image data in high-density monitoring scenarios, improve the timeliness and accuracy of emergency treatment, and avoid delays and Severe consequences of bandwidth limitation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118740694B_ABST
    Figure CN118740694B_ABST
Patent Text Reader

Abstract

The invention discloses a security monitoring management system based on big data Internet of Things, and relates to the technical field of big data security monitoring. By dividing the bandwidth resource consumption into normal time periods and abnormal time periods, the change of bandwidth resource usage data in the abnormal time periods is analyzed, the weight assignment of each abnormal time period of bandwidth resource consumption is determined, and the overall image quality index is calculated; at the same time, the transmission delay of the video stream to the monitoring terminal in real time is judged; the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time are analyzed through fuzzy logic, and the real-time response capability of security events is evaluated, so that the abnormal situation can be effectively identified and handled, resource allocation is optimized, the stability and response speed of the system are improved, and the reliability of real-time transmission of key image data in high-density monitoring scenarios is ensured, thereby improving the timeliness and accuracy of emergency processing and avoiding serious consequences caused by delays and bandwidth limitations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of big data security monitoring, and in particular to a security monitoring management system based on big data Internet of Things. Background Art

[0002] Security monitoring management based on big data Internet of Things refers to connecting sensors and smart devices distributed in various places through Internet of Things technology to collect and transmit large amounts of data in real time. These data cover environmental monitoring, equipment status, personnel activities, etc. These data are summarized, analyzed and processed through the big data analysis platform to generate valuable insights and early warning information.

[0003] This management model can not only achieve real-time monitoring and rapid response to security conditions, but also predict potential security risks through data analysis and formulate more scientific security management strategies. Its core lies in using advanced technical means to improve the intelligence and automation level of security management and ensure the security and stability of the system.

[0004] The prior art has the following deficiencies:

[0005] When conducting security monitoring and management of the big data Internet of Things, in high-density monitoring scenarios, real-time transmission of large amounts of high-definition image data consumes huge bandwidth resources. If the bandwidth is insufficient or the transmission delay is too large, the monitoring image may become stuck or delayed, affecting the real-time monitoring and response of security events. Especially when responding to emergencies, delays and bandwidth limitations may prevent key image data from being transmitted in a timely manner, delaying the implementation of safety measures and leading to serious consequences. For example, at a disaster site, delays in real-time monitoring may affect the timeliness and accuracy of emergency rescue decisions. Summary of the invention

[0006] The purpose of the present invention is to provide a security monitoring and management system based on big data Internet of Things to solve the shortcomings of the background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a security monitoring and management system based on big data Internet of Things, comprising a bandwidth resource consumption monitoring module, an image quality analysis module, a transmission delay judgment module, a response analysis module and a partition management module;

[0008] Bandwidth resource consumption monitoring module: Use SolarWinds to monitor the bandwidth resource usage of the monitoring system in real time over several time periods, obtain bandwidth resource usage data in each time period, and perform time series analysis on it. Based on the analysis results, determine the normal and abnormal time periods for bandwidth resource consumption.

[0009] The bandwidth resource consumption monitoring module specifically includes: performing time series analysis on the bandwidth resource usage data collected by SolarWinds in each time period in the database, and determining the normal time period and abnormal time period of bandwidth resource consumption according to the analysis results, specifically:

[0010] Extract bandwidth usage data from the database, including two fields: timestamp and bandwidth usage. Convert the timestamp to a time series format and set it as the index of the data. Use the time series decomposition technique to decompose the bandwidth usage data into three parts: trend, seasonality, and residual. The bandwidth usage yt is expressed as: ; Among them, Tt is the trend component, St is the seasonal component, and Rt is the residual component;

[0011] Based on the trend component, the normal range of bandwidth usage is calculated. The normal range is determined by calculating the mean and standard deviation of the trend component, including calculating the mean μ and standard deviation σ of the trend component, analyzing the mean and standard deviation of the trend component, and calculating the normal range of bandwidth usage; comparing the bandwidth usage data of each time period with the normal range, and marking the time period beyond the normal range as an abnormal time period;

[0012] Image quality analysis module: when bandwidth resource consumption is abnormal, analyze the changes in bandwidth resource usage data during the bandwidth resource consumption abnormal time period, determine the weight assignment of each bandwidth resource consumption abnormal time period, and calculate the overall image quality index after weighted average calculation of the weight assignment of each bandwidth resource consumption abnormal time period;

[0013] Transmission delay judgment module: monitors the time required for video data to be transmitted from the camera to the monitoring center, and judges the transmission delay of the video stream to the monitoring terminal in real time;

[0014] Response analysis module: Analyzes the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time through fuzzy logic to evaluate the real-time response capability of security events;

[0015] Division management module: Based on the evaluation results, the real-time response capability of security incidents is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and different real-time response levels are managed intelligently.

[0016] In a preferred embodiment, the bandwidth resource usage data collected by SolarWinds in each time period in the database is subjected to time series analysis, and the normal time period and abnormal time period of bandwidth resource consumption are determined according to the analysis results, specifically:

[0017] Extract bandwidth usage data from the database, including two fields: timestamp and bandwidth usage. Convert the timestamp to a time series format and set it as the index of the data. Use the time series decomposition technique to decompose the bandwidth usage data into three parts: trend, seasonality, and residual. The bandwidth usage yt is expressed as: ; Among them, Tt is the trend component, St is the seasonal component, and Rt is the residual component;

[0018] Based on the trend component, the normal range of bandwidth usage is calculated. The normal range is determined by calculating the mean and standard deviation of the trend component, including calculating the mean μ and standard deviation σ of the trend component, analyzing the mean and standard deviation of the trend component, and calculating the normal range of bandwidth usage; comparing the bandwidth usage data of each time period with the normal range, and marking the time period beyond the normal range as an abnormal time period.

[0019] In a preferred embodiment, the changes in bandwidth resource usage data are analyzed, including analyzing the bandwidth usage fluctuation index and the data transmission efficiency deviation index in the bandwidth resource usage data, and determining the weight assignment of each bandwidth resource consumption abnormal time period based on the analysis results.

[0020] In a preferred embodiment, the method for obtaining the bandwidth usage fluctuation index is:

[0021] The amount of network bandwidth used during the period of abnormal bandwidth resource consumption Collect and create corresponding data sets ,in, , h is a positive integer greater than 0;

[0022] Select the decay factor λ and calculate the exponentially weighted moving average of the network bandwidth in the data set. The specific calculation formula is: ; In the formula, The EWMA value at time i, The EWMA value at the previous moment, The actual bandwidth usage at time i, where the initial conditions are: , that is, the EWMA value at the initial moment is equal to the actual bandwidth usage at the initial moment;

[0023] The EWMA values ​​of the actual bandwidth usage at different times are analyzed, and the average of the EWMA values ​​during the period of abnormal bandwidth resource consumption is calculated. The specific calculation expression is: ; is the mean of the EWMA values. The standard deviation of the EWMA values ​​is calculated based on the mean of the EWMA values, that is, the bandwidth usage fluctuation index is calculated.

[0024] In a preferred embodiment, the method for obtaining the data transmission efficiency deviation index is:

[0025] Obtain actual data transmission efficiency values ​​and establish corresponding time series data , , Q is a positive integer greater than 0, which determines the three parameters p, d and q of the ARIMA model. p represents the number of autoregressive terms in the model, d represents the number of difference operations, and q represents the number of moving average terms in the model.

[0026] Time series data Differencing is done d times to make it stationary, and then the ARIMA model is fitted. The calculation expression of the model is: ; In the formula, for The d-order difference of , h is a constant term, indicating the average level of the sequence, is the autoregression coefficient, is the moving average coefficient, is the historical data value, is the error term;

[0027] Use the fitted ARIMA model to make predictions and get the predicted transmission efficiency value , for the predicted transmission efficiency value Analyze the actual data transmission efficiency value and calculate the data transmission efficiency deviation index. ; Where KG is the data transmission efficiency deviation index.

[0028] In a preferred embodiment, the bandwidth usage fluctuation index and the data transmission efficiency deviation index are converted into a first eigenvector, and the first eigenvector is used as the input of a machine learning model. The machine learning model uses the weighted assignment labels of the bandwidth resource usage data within the time period of abnormal bandwidth resource consumption predicted by each group of first eigenvectors as a prediction target, and takes minimizing the sum of prediction errors of the weighted assignment labels of the bandwidth resource usage data within all time periods of abnormal bandwidth resource consumption as a training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The weight assignment of the bandwidth resource usage data within the time period of abnormal bandwidth resource consumption is determined according to the model output results, and the overall image quality index is calculated after weighted average calculation of the weight assignments of each time period of abnormal bandwidth resource consumption.

[0029] In a preferred embodiment, the time for the camera to capture the video image and convert it into a digital signal and the time for compressing and encoding the original video data are obtained, the data conversion time abnormal value is obtained, and the real-time generation of the video data is analyzed. The method for obtaining the data conversion time abnormal value is:

[0030] Collect the time when the camera captures the video image and converts it into a digital signal and the time when it is compressed and encoded to form a data set ,in, , B is a positive integer greater than 0; convert the data into time It obeys the normal distribution and uses the Bayesian method to estimate the distribution parameters. , S is the mean, D is the standard deviation,

[0031] For the normal distribution, the probability of calculating the time observation data under given parameters is calculated. The specific calculation expression is: ; In the formula, is the probability distribution of the time observation data in the data set, R is the actual observed time data, and the posterior distribution is calculated using Bayesian theorem. The calculation expression is: ; is the probability of time anomaly data in the data set, that is, the data transformation time anomaly value.

[0032] In a preferred embodiment, the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time are analyzed by fuzzy logic, specifically:

[0033] The overall image quality index and data conversion time anomaly are used as the input of fuzzy logic, and the real-time response capability is used as the output of the model;

[0034] For each input variable and output variable, define the corresponding membership function, establish a fuzzy rule base, and map the input variable to the output variable;

[0035] Using fuzzy inference methods to map input membership to output membership;

[0036] According to the output membership function and membership degree, the center of gravity position of the fuzzy set is calculated, and the center of gravity position is converted into a specific real-time response capability value.

[0037] In a preferred embodiment, the real-time response capability of security events is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, specifically:

[0038] The real-time response capability values ​​obtained within a period of time are used to establish a data set, and the mean and standard deviation of the real-time response capability values ​​in the set are calculated. The mean and standard deviation of the real-time response capability values ​​are analyzed, and the real-time response capability of security incidents is divided into different response levels.

[0039] If the mean of the real-time response capability values ​​is greater than or equal to the reference threshold of the mean of the real-time response capability values, and the standard deviation of the real-time response capability values ​​is less than the reference threshold of the standard deviation of the real-time response capability values, the real-time response capability of the security incident is classified as a normal response;

[0040] If the mean of the real-time response capability value is greater than or equal to the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a mild abnormal response;

[0041] If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a moderate abnormal response;

[0042] If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is less than the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security event is classified as an abnormal response.

[0043] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0044] 1. The present invention systematically monitors and analyzes bandwidth resource usage data, video stream transmission delay, and overall image quality index, and combines fuzzy logic to evaluate the real-time response capability of security events, effectively identifying and handling abnormal situations. Through the comprehensive application of bandwidth resource consumption monitoring module, image quality analysis module, transmission delay judgment module, response analysis module, and partition management module, it can optimize resource allocation, improve system stability and response speed, and ensure the reliability of real-time transmission of key image data in high-density monitoring scenarios.

[0045] 2. Through intelligent management, the present invention divides the real-time response capability of security events into normal response, mild abnormal response, moderate abnormal response and abnormal response, and takes corresponding measures for different response levels, such as optimizing system parameters, strengthening monitoring, and conducting emergency investigation and repair, to ensure that the monitoring system can operate efficiently under various conditions. This solution not only improves the timeliness and accuracy of emergency response, avoids serious consequences caused by delays and bandwidth limitations, but also improves the overall effectiveness and security of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0047] Figure 1 The figure is a flow chart of the method of the present invention.

[0048] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] For examples, see Figure 1 , 2 As shown, the security monitoring and management system based on big data Internet of Things described in this embodiment includes a bandwidth resource consumption monitoring module, an image quality analysis module, a transmission delay judgment module, a response analysis module and a division management module;

[0051] Bandwidth resource consumption monitoring module: Use SolarWinds to monitor the bandwidth resource usage of the monitoring system in real time over several time periods, obtain bandwidth resource usage data in each time period, and perform time series analysis on it. Based on the analysis results, determine the normal and abnormal time periods for bandwidth resource consumption.

[0052] Image quality analysis module: when bandwidth resource consumption is abnormal, analyze the changes in bandwidth resource usage data during the bandwidth resource consumption abnormal time period, determine the weight assignment of each bandwidth resource consumption abnormal time period, and calculate the overall image quality index after weighted average calculation of the weight assignment of each bandwidth resource consumption abnormal time period;

[0053] Transmission delay judgment module: monitors the time required for video data to be transmitted from the camera to the monitoring center, and judges the transmission delay of the video stream to the monitoring terminal in real time;

[0054] Response analysis module: Analyzes the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time through fuzzy logic to evaluate the real-time response capability of security events;

[0055] Division management module: Based on the evaluation results, the real-time response capability of security incidents is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and different real-time response levels are managed intelligently.

[0056] Among them, in the bandwidth resource consumption monitoring module, SolarWinds real-time monitoring system bandwidth resource usage in several time periods is used to obtain bandwidth resource usage data in each time period and perform time series analysis on it. According to the analysis results, the normal time period and abnormal time period of bandwidth resource consumption are determined, specifically:

[0057] Install SolarWinds and configure it to monitor all network traffic of the monitoring system. Divide the day into 24 hours, with one time period per hour. Use SolarWinds to monitor and record bandwidth usage data in real time for each time period. Store the data collected by SolarWinds in a database, recording information such as timestamps, bandwidth usage, latency, packet loss rate, etc. Clean the collected data to remove outliers and noise data.

[0058] Perform time series analysis on bandwidth resource usage data collected by SolarWinds in each time period in the database, and determine normal and abnormal time periods for bandwidth resource consumption based on the analysis results, specifically:

[0059] Extract bandwidth usage data from the database, including two fields: timestamp and bandwidth usage. Convert the timestamp to a time series format and set it as the index of the data. Handle missing values ​​and outliers. Missing values ​​can be filled using forward fill, and outliers can be removed using data outside of 3 standard deviations.

[0060] Using time series decomposition technology, the bandwidth usage data is decomposed into three parts: trend, seasonality, and residual. The bandwidth usage yt can be expressed as: ; Among them, Tt is the trend component, St is the seasonal component, and Rt is the residual component.

[0061] Based on the trend component, the normal range of bandwidth usage is calculated. The normal range can be determined by calculating the mean and standard deviation of the trend component, including calculating the mean μ and standard deviation σ of the trend component, analyzing the mean and standard deviation of the trend component, and calculating the normal range of bandwidth usage. The normal range is: Normal range ;

[0062] The bandwidth usage data of each time period is compared with the normal range, and the time period outside the normal range is marked as an abnormal time period. For each time period t, if the bandwidth usage yt satisfies: or The time period is marked as abnormal.

[0063] Draw a time series graph of bandwidth usage, marking normal and abnormal time periods. The graph shows the trend components, normal range, and abnormal points of bandwidth usage.

[0064] Image quality analysis module: When bandwidth resource consumption is abnormal, the changes in bandwidth resource usage data during the bandwidth resource consumption abnormal time period are analyzed, the weight assignment of each bandwidth resource consumption abnormal time period is determined, and the weighted average calculation of the weight assignment of each bandwidth resource consumption abnormal time period is performed to calculate the overall image quality index.

[0065] When bandwidth resource consumption is abnormal, the change of bandwidth resource usage data in the time period of abnormal bandwidth resource consumption is analyzed, wherein the change of bandwidth resource usage data is analyzed, including analyzing the bandwidth usage fluctuation index and the data transmission efficiency deviation index in the bandwidth resource usage data, and determining the weight assignment of each bandwidth resource consumption abnormal time period according to the analysis results.

[0066] The method for obtaining the bandwidth usage fluctuation index is as follows:

[0067] The amount of network bandwidth used during the period of abnormal bandwidth resource consumption Collect and create corresponding data sets ,in, , h is a positive integer greater than 0;

[0068] Select the decay factor λ, usually between 0 and 1, and calculate the exponentially weighted moving average of the network bandwidth in the data set. The specific calculation formula is: ; In the formula, The EWMA value at time i, The EWMA value at the previous moment, The actual bandwidth usage at time i, where the initial conditions are: , that is, the EWMA value at the initial moment is equal to the actual bandwidth usage at the initial moment;

[0069] The EWMA values ​​of the actual bandwidth usage at different times are analyzed, and the average of the EWMA values ​​during the period of abnormal bandwidth resource consumption is calculated. The specific calculation expression is: ; is the mean of the EWMA values. The standard deviation of the EWMA values ​​is calculated based on the mean of the EWMA values, that is, the bandwidth usage fluctuation index is calculated.

[0070] The larger the bandwidth usage fluctuation index, the more bandwidth usage often rises and falls during the time period, that is, the larger the fluctuation. The allocation and use of network resources become unstable, which may affect network performance and user experience. For monitoring systems and other applications that rely on stable bandwidth, it may cause performance degradation or intermittent failures.

[0071] Drastic fluctuations in bandwidth usage may be an indicator of potential network problems or abnormal behavior, such as network attacks (such as DDoS attacks), hardware failures, configuration errors, or malware activities. High volatility may mean that there is some abnormal traffic in the network that requires further investigation and processing. It is necessary to enhance network security measures, monitor abnormal traffic, and respond in a timely manner.

[0072] The method for obtaining the data transmission efficiency deviation index is:

[0073] Obtain actual data transmission efficiency values ​​and establish corresponding time series data , , Q is a positive integer greater than 0, which determines the three parameters p, d and q of the ARIMA model. p (autoregressive order): indicates the number of autoregressive terms in the model, that is, the impact of past observations on current values. d (difference order): indicates the number of difference operations, which is used to make non-stationary time series data stable. q (moving average order): indicates the number of moving average terms in the model, that is, the impact of past error terms on current values.

[0074] Time series data Differencing is done d times to make it stationary, and then the ARIMA model is fitted. The calculation expression of the model is: ; In the formula, for The d-order difference of , h is a constant term, indicating the average level of the sequence, is the autoregression coefficient, is the moving average coefficient, is the historical data value, is the error term;

[0075] Check whether the residual of the fitted ARIMA model is white noise, that is, the autocorrelation function of the residual should be close to zero. Use the fitted ARIMA model to make predictions and obtain the predicted transmission efficiency value. , for the predicted transmission efficiency value Analyze the actual data transmission efficiency value and calculate the data transmission efficiency deviation index. ; Where KG is the data transmission efficiency deviation index.

[0076] The larger the data transmission efficiency deviation index, the greater the difference between the actual data transmission efficiency and the predicted efficiency, and the greater the uncertainty in the transmission process. A high deviation index usually reflects the instability of network transmission, such as insufficient bandwidth, increased latency, and increased packet loss rate. The image quality will fluctuate significantly, which may cause the image to be clear in some time periods and blurry or intermittent in other time periods.

[0077] A large data transmission efficiency deviation index means that data packets may encounter delays, packet loss, and other problems during transmission. These problems will cause image data to fail to reach the receiving end on time, resulting in image delays and freezes. Images in real-time video surveillance may freeze frequently, the viewing experience deteriorates, and important monitoring information may be lost.

[0078] The bandwidth usage fluctuation index and the data transmission efficiency deviation index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the weighted labels of the bandwidth resource usage data in the time period of abnormal bandwidth resource consumption predicted by each group of first eigenvectors as the prediction target, and takes minimizing the sum of the prediction errors of the weighted labels of the bandwidth resource usage data in the time period of abnormal bandwidth resource consumption as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The weighted labels of the bandwidth resource usage data in the time period of abnormal bandwidth resource consumption are determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0079] The method for obtaining the weight assignment of the bandwidth resource usage data during the bandwidth resource consumption abnormal period is as follows: from the first feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, It is the output function of the model, EY is the bandwidth usage fluctuation index, KG is the data transmission efficiency deviation index, LD is the weight assignment of the bandwidth resource consumption abnormal time period, and the overall image quality index is calculated by weighted averaging the weight assignments of each bandwidth resource consumption abnormal time period.

[0080] Transmission delay judgment module: monitors the time required for video data to be transmitted from the camera to the monitoring center, and judges the transmission delay of the video stream to the monitoring terminal in real time.

[0081] Monitoring the time required for video data to be transmitted from the camera to the monitoring center and determining the transmission delay of the video stream to the monitoring terminal in real time refers to monitoring and analyzing the time required for video signals to be transmitted on the network in order to evaluate the real-time and responsiveness of the system.

[0082] In the process of transmitting video data from the camera to the monitoring center, the data may need to be processed and forwarded multiple times, and each step may increase the delay. The accumulation of these delays will affect the real-time performance and final transmission effect of the video stream.

[0083] Get the time when the camera captures the video image and converts it into a digital signal, as well as the time when the original video data is compressed and encoded, get the data conversion time anomaly value, and analyze the real-time generation of the video data. The method for obtaining the data conversion time anomaly value is:

[0084] Collect the time when the camera captures the video image and converts it into a digital signal and the time when it is compressed and encoded to form a data set ,in, , B is a positive integer greater than 0; convert the data into time It obeys the normal distribution and uses the Bayesian method to estimate the distribution parameters. , S is the mean, D is the standard deviation,

[0085] For the normal distribution, the probability of calculating the time observation data under given parameters is calculated. The specific calculation expression is: ; In the formula, is the probability distribution of the time observation data in the data set, R is the actual observed time data, and the posterior distribution is calculated using Bayesian theorem. The calculation expression is: ; is the probability of time anomaly data in the data set, that is, the data transformation time anomaly value.

[0086] Response analysis module: Analyzes the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time through fuzzy logic to evaluate the real-time response capability of security incidents.

[0087] The overall image quality index and data conversion time anomaly are used as the input of fuzzy logic, and the real-time response capability is used as the output of the model;

[0088] For each input variable and output variable, define the corresponding membership function. For example, use a triangular or trapezoidal membership function to represent the fuzzy set of variables. The overall image quality index includes: Low, Medium, High; the data conversion time abnormal values ​​include: Small (Low), Medium (Medium), Large (High); the real-time response capability includes: Weak (Weak), Average (Average), Strong (Strong);

[0089] Build a fuzzy rule base to map input variables to output variables. The rules can be determined based on expert knowledge or historical data. For example:

[0090] If the overall image quality index is High and the data conversion time abnormal value is Low, the real-time response capability is Strong; if the overall image quality index is Medium and the data conversion time abnormal value is Medium, the real-time response capability is Average;

[0091] If the overall image quality index is Low and the data conversion time outlier is High, the real-time responsiveness is Weak;

[0092] Use fuzzy inference methods (such as Mamdani fuzzy inference) to map input membership to output membership, specifically:

[0093] Convert specific input values ​​into membership in fuzzy sets. For example, calculate their membership in different fuzzy sets.

[0094] According to the fuzzy rule base, all relevant rules are applied and the membership of the output variable in each fuzzy set is calculated.

[0095] Aggregate the results of all rules to obtain the membership of the output variable in different fuzzy sets.

[0096] The fuzzy output is converted into a specific value, usually using the centroid method for defuzzification, specifically:

[0097] According to the output membership function and membership degree, the centroid position of the fuzzy set is calculated.

[0098] Convert center of mass position into concrete real-time responsiveness values.

[0099] Through the fuzzy logic system, the impact of the overall image quality index and data conversion time outliers on the real-time response capability is comprehensively analyzed.

[0100] Division management module: Based on the evaluation results, the real-time response capability of security incidents is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and different real-time response levels are managed intelligently.

[0101] The real-time response capability values ​​obtained within a period of time are used to establish a data set, and the mean and standard deviation of the real-time response capability values ​​in the set are calculated. The mean and standard deviation of the real-time response capability values ​​are analyzed, and the real-time response capability of security incidents is divided into different response levels, specifically:

[0102] If the mean of the real-time response capability value is greater than or equal to the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is less than the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a normal response; regular monitoring is maintained to ensure the continuous and stable operation of the system. Continuously record and analyze data, establish long-term trend analysis, and prevent potential problems. Regularly perform system maintenance and optimization to keep the equipment and network in the best condition.

[0103] If the mean of the real-time response capability value is greater than or equal to the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a mild abnormal response; conduct a detailed inspection of the system to identify and eliminate the causes of fluctuations, such as network congestion, equipment performance degradation, etc. Adjust and optimize system parameters, and improve bandwidth management, load balancing, and data transmission strategies.

[0104] If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a moderate abnormal response; the emergency plan is initiated to conduct emergency investigation and repair, such as adjusting the network configuration, replacing or upgrading equipment. Strengthen monitoring efforts, increase monitoring frequency and accuracy, and ensure that problems are discovered and resolved as early as possible.

[0105] If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is less than the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as an abnormal response. Perform a comprehensive system inspection, including hardware, network, and software, to identify all potential problems. Consider upgrading or replacing the system to improve overall performance. Notify relevant departments and personnel, coordinate resources, and respond and repair quickly. After fixing the problem, regularly review system performance to ensure that the problem does not recur.

[0106] In this embodiment, by acquiring bandwidth resource usage data in each time period and performing time series analysis on it, the normal time period and abnormal time period of bandwidth resource consumption are determined according to the analysis results; when bandwidth resource consumption is abnormal, the change of bandwidth resource usage data in the abnormal time period of bandwidth resource consumption is analyzed to determine the weight assignment of each abnormal time period of bandwidth resource consumption, and the weight assignment of each abnormal time period of bandwidth resource consumption is weighted averaged to calculate the overall image quality index; the time required for video data to be transmitted from the camera to the monitoring center is monitored to determine the transmission delay of the video stream to the monitoring terminal in real time; the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time are analyzed by fuzzy logic to evaluate the real-time response capability of security events; according to the evaluation results, the real-time response capability of security events is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and different real-time response levels are intelligently managed. It can effectively identify and handle abnormal situations, optimize resource allocation, improve the stability and response speed of the system, ensure the reliability of real-time transmission of key image data in high-density monitoring scenarios, thereby improving the timeliness and accuracy of emergency processing and avoiding serious consequences caused by delays and bandwidth limitations.

[0107] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0108] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0109] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0114] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A security monitoring and management system based on big data Internet of Things, characterized by: It includes bandwidth resource consumption monitoring module, image quality analysis module, transmission delay judgment module, response analysis module and division management module; Bandwidth resource consumption monitoring module: Use SolarWinds to monitor the bandwidth resource usage of the monitoring system in real time over several time periods, obtain bandwidth resource usage data in each time period, and perform time series analysis on it. Based on the analysis results, determine the normal and abnormal time periods for bandwidth resource consumption. The bandwidth resource consumption monitoring module specifically includes: performing time series analysis on the bandwidth resource usage data collected by SolarWinds in each time period in the database, and determining the normal time period and abnormal time period of bandwidth resource consumption according to the analysis results, specifically: Extract bandwidth usage data from the database, including two fields: timestamp and bandwidth usage. Convert the timestamp to a time series format and set it as the index of the data. Use the time series decomposition technique to decompose the bandwidth usage data into three parts: trend, seasonality, and residual. The bandwidth usage yt is expressed as: ; Among them, Tt is the trend component, St is the seasonal component, and Rt is the residual component; Based on the trend component, the normal range of bandwidth usage is calculated. The normal range is determined by calculating the mean and standard deviation of the trend component, including calculating the mean μ and standard deviation σ of the trend component, analyzing the mean and standard deviation of the trend component, and calculating the normal range of bandwidth usage; comparing the bandwidth usage data of each time period with the normal range, and marking the time period beyond the normal range as an abnormal time period; Image quality analysis module: when bandwidth resource consumption is abnormal, analyze the changes in bandwidth resource usage data during the bandwidth resource consumption abnormal time period, determine the weight assignment of each bandwidth resource consumption abnormal time period, and calculate the overall image quality index after weighted average calculation of the weight assignment of each bandwidth resource consumption abnormal time period; Analyze the changes in bandwidth resource usage data, including analyzing the bandwidth usage fluctuation index and data transmission efficiency deviation index in the bandwidth resource usage data, and determine the weight assignment of each bandwidth resource consumption abnormal time period based on the analysis results; The bandwidth usage fluctuation index is obtained by calculating the amount of network bandwidth used during the period of abnormal bandwidth resource consumption. Collect and create corresponding data sets ,in, , h is a positive integer greater than 0; Select the decay factor λ and calculate the exponentially weighted moving average of the network bandwidth in the data set. The specific calculation formula is: ; In the formula, The EWMA value at time i, The EWMA value at the previous moment, The actual bandwidth usage at time i, where the initial conditions are: , that is, the EWMA value at the initial moment is equal to the actual bandwidth usage at the initial moment; The EWMA values ​​of the actual bandwidth usage at different times are analyzed, and the average of the EWMA values ​​during the period of abnormal bandwidth resource consumption is calculated. The specific calculation expression is: ; is the mean of the EWMA values. Based on the calculated mean of the EWMA values, the standard deviation of the EWMA values ​​is calculated, that is, the bandwidth usage fluctuation index is calculated. The method for obtaining the data transmission efficiency deviation index is as follows: obtain the actual data transmission efficiency value and establish the corresponding time series data , , Q is a positive integer greater than 0, which determines the three parameters p, d and q of the ARIMA model. p represents the number of autoregressive terms in the model, d represents the number of difference operations, and q represents the number of moving average terms in the model. Time series data Differencing is done d times to make it stationary, and then the ARIMA model is fitted. The calculation expression of the model is: ; In the formula, for The d-order difference of , h is a constant term, indicating the average level of the sequence, is the autoregression coefficient, is the moving average coefficient, is the historical data value, is the error term; Use the fitted ARIMA model to make predictions and get the predicted transmission efficiency value , for the predicted transmission efficiency value Analyze the actual data transmission efficiency value and calculate the data transmission efficiency deviation index. ; In the formula, is the data transmission efficiency deviation index; The bandwidth usage fluctuation index and the data transmission efficiency deviation index are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the weighted labels of the bandwidth resource usage data in the bandwidth resource consumption abnormal time period predicted by each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the weighted labels of the bandwidth resource usage data in all bandwidth resource consumption abnormal time periods as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The weighted values ​​of the bandwidth resource usage data in the bandwidth resource consumption abnormal time period are determined according to the model output results, and the overall image quality index is calculated after the weighted average calculation of the weighted values ​​of each bandwidth resource consumption abnormal time period is performed; Transmission delay judgment module: monitors the time required for video data to be transmitted from the camera to the monitoring center, and judges the transmission delay of the video stream to the monitoring terminal in real time; Response analysis module: Analyzes the overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time through fuzzy logic to evaluate the real-time response capability of security events; Division management module: Based on the evaluation results, the real-time response capability of security incidents is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, and different real-time response levels are managed intelligently.

2. According to claim 1, a security monitoring and management system based on big data Internet of Things is characterized by: Get the time when the camera captures the video image and converts it into a digital signal, as well as the time when the original video data is compressed and encoded, get the data conversion time anomaly value, and analyze the real-time nature of video data generation. The method for obtaining the data conversion time anomaly value is as follows: Collect the time when the camera captures the video image and converts it into a digital signal and the time when it is compressed and encoded to form a data set ,in, , B is a positive integer greater than 0; convert the data into time It obeys the normal distribution and uses the Bayesian method to estimate the distribution parameters. , S is the mean, D is the standard deviation, For the normal distribution, the probability of calculating the time observation data under given parameters is calculated. The specific calculation expression is: ; In the formula, is the probability distribution of the time observation data in the data set, R is the actual observed time data, and the posterior distribution is calculated using Bayesian theorem. The calculation expression is: ; is the probability of time anomaly data in the data set, that is, the data transformation time anomaly value.

3. A security monitoring and management system based on big data Internet of Things according to claim 2, characterized in that: The overall image quality index and the transmission delay of the video stream to the monitoring terminal in real time are analyzed through fuzzy logic, specifically: The overall image quality index and data conversion time anomaly are used as the input of fuzzy logic, and the real-time response capability is used as the output of the model; For each input variable and output variable, define the corresponding membership function, establish a fuzzy rule base, and map the input variable to the output variable; Using fuzzy inference methods to map input membership to output membership; According to the output membership function and membership degree, the center of gravity position of the fuzzy set is calculated, and the center of gravity position is converted into a specific real-time response capability value.

4. A security monitoring and management system based on big data Internet of Things according to claim 3, characterized in that: The real-time response capability of security incidents is divided into normal response, mild abnormal response, moderate abnormal response and abnormal response, specifically: The real-time response capability values ​​obtained within a period of time are used to establish a data set, and the mean and standard deviation of the real-time response capability values ​​in the set are calculated. The mean and standard deviation of the real-time response capability values ​​are analyzed, and the real-time response capability of security incidents is divided into different response levels. If the mean of the real-time response capability values ​​is greater than or equal to the reference threshold of the mean of the real-time response capability values, and the standard deviation of the real-time response capability values ​​is less than the reference threshold of the standard deviation of the real-time response capability values, the real-time response capability of the security incident is classified as a normal response; If the mean of the real-time response capability value is greater than or equal to the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a mild abnormal response; If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is greater than or equal to the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security incident is classified as a moderate abnormal response; If the mean of the real-time response capability value is less than the reference threshold of the mean of the real-time response capability value, and the standard deviation of the real-time response capability value is less than the reference threshold of the standard deviation of the real-time response capability value, the real-time response capability of the security event is classified as an abnormal response.