An AI dynamic monitoring and protection system based on edge computing and its implementation method

Abstract

This invention discloses an AI dynamic monitoring and protection system and its implementation method based on edge computing, relating to the field of highway toll equipment monitoring technology. It solves the technical problem that existing technologies cannot simultaneously monitor the operational status of hardware devices and software services. The invention acquires security data from the highway toll system and corresponding environmental data at the time of acquisition; calculates the correlation coefficient between the operational data and log data, and processes the security data based on the correlation coefficient to obtain target equipment data and target software data; calculates equipment fault assessment coefficients and software fault assessment coefficients based on the target equipment data and software target data; calculates a security assessment coefficient based on the equipment fault assessment coefficients and software fault assessment coefficients, and corrects the security assessment coefficient based on environmental data to obtain a target security assessment coefficient; and determines whether to issue an early warning based on the target security assessment coefficient, thus solving the aforementioned technical problems.

Description

Technical Field

[0001] This invention belongs to the field of highway toll collection equipment monitoring, specifically an AI dynamic monitoring and protection system and its implementation method based on edge computing. Background Technology

[0002] Monitoring and maintaining highway toll collection equipment and software systems is a crucial part of toll station operation and management. Traditional technologies utilize networks, sensors, and edge data processing to achieve real-time monitoring of equipment and software, primarily by receiving data sent by the equipment to determine its online status. When equipment malfunctions, electromechanical management personnel are required to conduct regular inspections and resolve issues on-site.

[0003] Existing monitoring systems primarily monitor hardware or software services independently by receiving data from devices. Their functionality is relatively limited, only displaying online or offline status and failing to simultaneously monitor both hardware and software operation. Such systems rely on regular equipment inspections by electromechanical personnel and require manual on-site intervention when faults occur, resulting in low response efficiency. Furthermore, due to a lack of in-depth data analysis and intelligent processing capabilities, current technologies cannot predict potential faults, only reactively identifying and addressing them after they occur. This not only impacts operational continuity but also increases maintenance costs and management complexity.

[0004] Therefore, this invention proposes an AI dynamic monitoring and protection system and its implementation method based on edge computing to solve the above problems. Summary of the Invention

[0005] This invention aims to solve at least one of the technical problems existing in the prior art. To this end, this invention proposes an AI dynamic monitoring and protection system and implementation method based on edge computing, which solves the technical problems of existing technologies that can only independently monitor hardware devices or software services and cannot simultaneously monitor the operating status of both; the monitoring system only displays the online or offline status of the device, requiring manual on-site handling of faults, resulting in low response efficiency; and the inability to predict potential faults through data analysis, leading to passive fault discovery and affecting operational continuity.

[0006] To achieve the above objectives, a first aspect of the present invention provides an AI dynamic monitoring and protection system based on edge computing, comprising: a data acquisition module, a data analysis module, and an early warning module;

[0007] Data acquisition module: used to acquire security data of the highway toll collection system and environmental data at the corresponding time of acquisition; among which, security data includes: equipment operation data and software log data;

[0008] Data analysis module: Calculates the correlation coefficient between operational data and log data, and processes the safety data based on this correlation coefficient to obtain device target data and software target data; and,

[0009] The equipment failure assessment coefficient and the software failure assessment coefficient are calculated based on the equipment target data and the software target data; the safety assessment coefficient is calculated based on the equipment failure assessment coefficient and the software failure coefficient, and the safety assessment coefficient is corrected based on the environmental data to obtain the target safety assessment coefficient.

[0010] Early warning module: Determines whether to issue an early warning based on the target's safety assessment coefficient.

[0011] Preferably, the acquisition of security data from the highway toll system and environmental data at the corresponding collection time includes:

[0012] Real-time data collection of highway toll collection equipment operation data is achieved through data sensors. This operation data includes: equipment temperature, current, voltage, output power, vibration amplitude, noise level, and operating time.

[0013] Log data from the highway toll collection software system is collected using data acquisition equipment, including tools such as Fluentd or Prometheus. The log data includes API response time, CPU utilization, memory utilization, network throughput, log error rate, and network latency.

[0014] Environmental data is collected in real time through data sensors; the environmental data includes ambient temperature and ambient humidity.

[0015] It should be noted that operational data refers to various indicators that reflect the physical status and operational performance of highway toll collection equipment, which are acquired in real time through data acquisition equipment. Operational data mainly comes from sensors, monitoring systems, or equipment interfaces and can help determine the health status of the equipment and potential failure risks. Log data refers to structured or unstructured record information generated from the software system, which is used to describe the events, operations, and performance that occur during the system's operation. Log data is mainly used to analyze the operating status, performance bottlenecks, and abnormal behaviors of the software system, providing a basis for optimizing system performance and troubleshooting.

[0016] Preferably, the step of calculating the correlation coefficient between the running data and the log data includes: calculating the correlation coefficient of the running data and calculating the correlation coefficient of the log data;

[0017] The method for calculating the correlation coefficient of the running data is as follows:

[0018] A1: By obtaining several sets of operational data and log data from the historical database of the highway toll system, as well as the equipment status corresponding to each data point in the operational data and the software status corresponding to each data point in the log data; among them, the equipment status includes: equipment failure and equipment normal; the software status includes: software failure and software normal.

[0019] A2: Mark several sets of running data as Y i,g ; where Y i,g It refers to the i-th data in the g-th group of running data, where g={1,2,3,…,M}, M is the total number of groups, and i={1,2,3,…,N}, N is the total number of data in the running data;

[0020] A3: Through formula P i =G i / g calculates the probability that each data point in the runtime data will cause a device failure; where P i G refers to the probability that the i-th data point in the runtime data will cause a device failure, where i is the label of each data point in the runtime data. i This refers to the total number of equipment failures caused by the i-th data in the operating data;

[0021] A4: Through formula XG i =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i The correlation coefficient between each data point in the operational data and the equipment failure is obtained; where XG i It refers to the correlation coefficient between the i-th data point in the operating data and the equipment failure.

[0022] It should be noted that the larger the correlation coefficient, the stronger the correlation with the fault event; the historical database of the highway toll system refers to the database that stores all historical operating data, log records and related status information related to the highway toll system.

[0023] Preferably, the correlation coefficient of the calculated log data includes:

[0024] B1: Several sets of log data are marked as R j,g Among them, R j,g It refers to the j-th data in the g-th log data, where j={1,2,3,…,L} and L is the total number of data in the log data;

[0025] B2: Through formula P j =G j / g calculates the probability that each piece of data in the log data will cause a software failure; where P jThis refers to the probability that the j-th data point in the log data causes a software failure, where j is the label of each data point in the log data, and G... j This refers to the total number of software failures caused by the j-th data in the log data;

[0026] B3: Through formula XG j =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i Obtain the correlation coefficient between each data point in the log data and the software fault; where XG j It refers to the correlation coefficient between the j-th data in the log data and the software fault.

[0027] Preferably, the processing of security data based on correlation coefficients includes:

[0028] Determine whether the correlation coefficient between each data point in the operational data and the device fault, and the correlation coefficient between each data point in the log data and the software fault, are greater than a preset correlation coefficient threshold; if yes, retain the corresponding data; otherwise, remove the corresponding data.

[0029] The retained runtime data is marked as device target data, and the retained log data is marked as software target data.

[0030] It should be noted that the preset correlation coefficient threshold is set by experts in the field based on actual security requirements. The higher the actual security requirements, the larger the preset correlation coefficient threshold.

[0031] Preferably, the calculation of the equipment failure assessment coefficient and the software failure assessment coefficient based on the equipment target data and the software target data includes: calculating the equipment failure assessment coefficient based on the equipment target data and calculating the software failure assessment coefficient based on the software target data;

[0032] The equipment failure assessment coefficient calculated based on the equipment target data includes:

[0033] Extract the target data of the equipment and the corresponding correlation coefficients; label the target data of the equipment as SM. e The correlation coefficient corresponding to the target data of the equipment is marked as XG. e Among them, SM e It refers to the e-th data in the target data of the device, XG e It refers to the correlation coefficient corresponding to the e-th data in the target data of the equipment, where e={1,2,3,…,Q}, and Q is the total number of data contained in the target data of the equipment.

[0034] Using the formula x=∑(1 / XG) eThe equipment weighting factor is calculated; where x is the equipment weighting factor, ∑ is the summation symbol, and the summation range is e;

[0035] Through formula α e =1 / (XG e The weight coefficient corresponding to each data point in the target data of the equipment is calculated using ×x); where α e This refers to the weight coefficient corresponding to the e-th data in the target data of the equipment;

[0036] Using the formula P1=∑(α) e ×e^((SM e -ZS e ) / ZS e The equipment failure assessment coefficient is calculated; where P1 refers to the equipment failure assessment coefficient, ∑ is the summation symbol, and the summation range is e, ZS e It refers to the optimal data corresponding to the e-th data in the target data of the equipment.

[0037] It should be noted that the optimal data corresponding to the e-th data in the target data of the equipment refers to the best value or reference value of the data under the ideal operating state or normal operating state of the equipment.

[0038] Preferably, the calculation of the software fault assessment coefficient based on the software target data includes:

[0039] Extract the software target data and its corresponding correlation coefficients; label the software target data as RM. k The correlation coefficient corresponding to the software target data is labeled as RX. k Among them, RM k It refers to the k-th data in the software target data, RX k It refers to the correlation coefficient corresponding to the kth data in the software target data, k={1,2,3,…,V}, where V is the total number of data contained in the software target data;

[0040] Using the formula y=∑(1 / RX k The software weight factor is calculated; where y is the software weight factor, ∑ is the summation symbol, and the summation range is k.

[0041] Through formula β k =1 / (RX k The weight coefficients corresponding to each data point in the software target data are calculated using β(x,y); where β is... k It refers to the weight coefficient corresponding to the kth data in the software target data;

[0042] Using the formula P2=∑(β) k ×e^((RM k -ZR k) / ZR k The software fault assessment coefficients are calculated; where P2 refers to the software fault assessment coefficients, ∑ is the summation formula, and the summation range is k, ZR. k It refers to the optimal data corresponding to the k-th data in the software target data.

[0043] It should be noted that the optimal data corresponding to the kth data in the software target data refers to the best or reference value of the data when the software is in an ideal or normal operating state.

[0044] Preferably, the correction of the safety assessment coefficient based on environmental data includes:

[0045] Extract the equipment failure assessment coefficient P1 and the software failure assessment coefficient P2;

[0046] The safety assessment coefficient is calculated using the formula P=θ1×P1+θ2×P2; where P is the safety assessment coefficient, and θ1 and θ2 are the initial weighting coefficients.

[0047] The highest ambient temperature, lowest ambient temperature, highest ambient humidity, and lowest ambient humidity of the day are obtained based on the weather forecasting platform and labeled as Tmax, Tmin, Hmax, and Hmin, respectively.

[0048] The ambient temperature index is calculated using the formula Tn=(T-Tmin) / (Tmax-Tmin); where Tn is the ambient temperature index and T is the ambient temperature.

[0049] The ambient humidity index is calculated using the formula Hn=(H-Hmin) / (Hmax-Hmin); where Hn is the ambient humidity index and H is the ambient humidity.

[0050] The initial weighting coefficient θ1 is corrected based on the ambient temperature index, specifically as follows:

[0051] The weighting coefficients after θ1 correction are calculated using the formula θ1'=θ1+f1×Tn-f2×Hn; where θ1' is the weighting coefficient after θ1 correction, f1 is the temperature influence factor, and f2 is the humidity influence factor.

[0052] The initial weighting coefficient θ2 is corrected based on the environmental humidity index, specifically as follows:

[0053] The weight coefficient after θ2 correction is obtained by calculating θ2 using the formula θ2'=θ2-f1×Tn+f2×Hn; where θ2' is the weight coefficient after θ2 correction.

[0054] By normalizing the corrected weight coefficients θ1' and θ2', the target weight coefficients are obtained. The specific normalization formula is as follows:

[0055] 1 = θ1' / (θ1'+θ2') and 2 = θ2' / (θ1'+θ2'); where 1 and 2 is the target weight coefficient;

[0056] Update the initial weight coefficients θ1 and θ2 to... 1. 2;

[0057] Through the formula P'= 1×P1+ The target safety assessment coefficient is calculated by 2×P2; where P' is the target safety assessment coefficient.

[0058] It should be noted that the initial weighting coefficients are set by experts in the field based on practical experience. In historical maintenance data, if the impact of equipment failure is greater, then θ1 > θ2.

[0059] The temperature influence factor reflects the sensitivity of temperature to equipment failure. If historical data shows that the equipment failure rate increases by 20% for every 10°C increase in temperature, then f1=0.2 is set. The humidity influence factor reflects the sensitivity of humidity to software anomalies. Both the temperature influence factor and the humidity influence factor can be obtained by analyzing the historical database of the highway toll system and the corresponding historical environmental data.

[0060] High temperatures significantly increase the risk of equipment failure, necessitating an increase in the weight of equipment evaluation to ensure the system prioritizes hardware health. High humidity can cause circuit board leakage or short circuits, affecting network equipment stability. At the same time, high-frequency signals attenuate more rapidly in humid air, leading to increased network latency or packet loss. By increasing the weight of software evaluation, the system pays more attention to network metrics in log data (such as latency and packet loss rate) and promptly detects software anomalies.

[0061] Preferably, the step of determining whether to issue an early warning based on the target security assessment coefficient includes:

[0062] Determine whether the target security assessment coefficient is greater than the preset target security assessment coefficient threshold; if yes, generate an early warning message and send it to the client; otherwise, continue to monitor and judge.

[0063] It should be noted that the preset target security assessment coefficient threshold is set by experts in the field based on actual security requirements. The higher the actual security requirements, the larger the preset target security assessment coefficient threshold.

[0064] A second aspect of the present invention provides an AI dynamic monitoring and protection method based on edge computing, comprising:

[0065] Step 1: Obtain security data from the highway toll collection system and environmental data at the corresponding collection time;

[0066] Step 2: Calculate the correlation coefficient between the running data and the log data, and process the safety data based on the correlation coefficient to obtain the device target data and the software target data;

[0067] Step 3: Calculate the equipment failure assessment coefficient and the software failure assessment coefficient based on the equipment target data and software target data;

[0068] Step 4: Calculate the safety assessment coefficient based on the equipment failure assessment coefficient and the software failure assessment coefficient, and then correct the safety assessment coefficient based on environmental data to obtain the target safety assessment coefficient;

[0069] Step 5: Determine whether to issue an early warning based on the target safety assessment coefficient.

[0070] Compared with the prior art, the beneficial effects of the present invention are:

[0071] 1. This invention acquires security data from a highway toll collection system and corresponding environmental data at the time of acquisition; calculates the correlation coefficient between operational data and log data, and processes the security data based on the correlation coefficient to obtain equipment target data and software target data; calculates equipment fault assessment coefficients and software fault assessment coefficients based on the equipment target data and software target data; calculates a safety assessment coefficient based on the equipment fault assessment coefficients and software fault assessment coefficients, and corrects the safety assessment coefficient based on environmental data to obtain a target safety assessment coefficient; and determines whether to issue an early warning based on the target safety assessment coefficient. This invention solves the technical problems of existing technologies that can only independently monitor hardware equipment or software services, and cannot simultaneously consider the operational status of both; that the monitoring system only displays the online or offline status of the equipment, requiring manual on-site fault handling, resulting in low response efficiency; and that it cannot predict potential faults through data analysis, leading to passive fault discovery and affecting operational continuity.

[0072] 2. This invention can quantitatively analyze the correlation between equipment operation data and equipment failures, and between software log data and software failures, thereby screening out key data that contributes significantly to failure prediction. By utilizing rich data resources in historical databases, combined with probabilistic statistical methods and mathematical formulas, the correlation coefficient between each piece of operation data and log data and the failure event is calculated. The larger the correlation coefficient value, the stronger the correlation with the failure. Based on this, by setting a preset correlation coefficient threshold, target equipment data and target software data that are highly correlated with the failure are further screened out, effectively reducing the interference of redundant data and improving the accuracy of subsequent evaluation. This method can not only accurately locate potential failure factors, but also provide scientific data basis for the system, significantly improving the failure prediction capability and the system's intelligence level, while reducing unnecessary calculation costs and complexity, laying a solid foundation for the efficient operation and maintenance and safe management of highway toll systems.

[0073] 3. This invention calculates equipment fault assessment coefficients and software fault assessment coefficients based on equipment target data and software target data respectively, enabling a comprehensive evaluation of the operating status of hardware equipment and software systems. It also dynamically corrects the overall safety assessment coefficients using environmental data, significantly improving the accuracy and intelligence of fault prediction. By introducing weighting factors and exponential functions into the equipment and software target data, it fully considers the importance of different data and their deviation from ideal states, making the assessment results more scientific and reasonable. Dynamic adjustment of the initial weighting coefficients using environmental temperature and humidity indices reflects the actual impact of the external environment on the operating status of equipment and software, ensuring the system can accurately warn of potential risks even under extreme weather conditions. By setting preset target safety assessment coefficient thresholds to achieve automated early warning, it not only reduces the need for manual intervention but also significantly improves response efficiency, providing a reliable guarantee for the stable operation of highway toll collection systems. It effectively integrates multi-source data, taking into account the comprehensive assessment needs of hardware and software, greatly enhancing the system's adaptability and robustness, and laying a solid foundation for intelligent operation and maintenance management. Attached Figure Description

[0074] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0075] Figure 1 This is a schematic diagram of the system modules according to an embodiment of the present invention;

[0076] Figure 2 This is a schematic diagram illustrating the specific process of an embodiment of the present invention;

[0077] Figure 3 This is a schematic diagram of the method steps in an embodiment of the present invention. Detailed Implementation

[0078] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0079] See also Figures 1-2 The first aspect of the present invention provides an AI dynamic monitoring and protection system based on edge computing, comprising: a data acquisition module, a data analysis module, and an early warning module;

[0080] Data acquisition module: used to acquire security data of the highway toll collection system and environmental data at the corresponding time of acquisition; among which, security data includes: equipment operation data and software log data;

[0081] Data analysis module: Calculates the correlation coefficient between operational data and log data, and processes the safety data based on this correlation coefficient to obtain device target data and software target data; and,

[0082] The equipment failure assessment coefficient and the software failure assessment coefficient are calculated based on the equipment target data and the software target data; the safety assessment coefficient is calculated based on the equipment failure assessment coefficient and the software failure coefficient, and the safety assessment coefficient is corrected based on the environmental data to obtain the target safety assessment coefficient.

[0083] Early warning module: Determines whether to issue an early warning based on the target's safety assessment coefficient.

[0084] Acquire security data from the highway toll collection system and corresponding environmental data at the time of data collection, including:

[0085] Real-time data collection of highway toll collection equipment operation data is achieved through data sensors. This operation data includes: equipment temperature, current, voltage, output power, vibration amplitude, noise level, and operating time.

[0086] Log data from the highway toll collection software system is collected using data acquisition equipment, including tools such as Fluentd or Prometheus. The log data includes API response time, CPU utilization, memory utilization, network throughput, log error rate, and network latency.

[0087] Environmental data is collected in real time through data sensors; the environmental data includes ambient temperature and ambient humidity.

[0088] The correlation coefficient between the running data and the log data is calculated, including: calculating the correlation coefficient of the running data and calculating the correlation coefficient of the log data;

[0089] The method for calculating the correlation coefficient of the running data is as follows:

[0090] A1: By obtaining several sets of operational data and log data from the historical database of the highway toll system, as well as the equipment status corresponding to each data point in the operational data and the software status corresponding to each data point in the log data; among them, the equipment status includes: equipment failure and equipment normal; the software status includes: software failure and software normal.

[0091] A2: Mark several sets of running data as Y i,g ; where Y i,g It refers to the i-th data in the g-th group of running data, where g={1,2,3,…,M}, M is the total number of groups, and i={1,2,3,…,N}, N is the total number of data in the running data;

[0092] A3: Through formula P i =G i / g calculates the probability that each data point in the runtime data will cause a device failure; where P i G refers to the probability that the i-th data point in the runtime data will cause a device failure, where i is the label of each data point in the runtime data. i This refers to the total number of equipment failures caused by the i-th data in the operating data;

[0093] A4: Through formula XG i =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i The correlation coefficient between each data point in the operational data and the equipment failure is obtained; where XG i It refers to the correlation coefficient between the i-th data point in the operating data and the equipment failure.

[0094] Calculate the correlation coefficient of log data, including:

[0095] B1: Several sets of log data are marked as R j,g Among them, R j,g It refers to the j-th data in the g-th log data, where j={1,2,3,…,L} and L is the total number of data in the log data;

[0096] B2: Through formula Pj =G j / g calculates the probability that each piece of data in the log data will cause a software failure; where P j This refers to the probability that the j-th data point in the log data causes a software failure, where j is the label of each data point in the log data, and G... j This refers to the total number of software failures caused by the j-th data in the log data;

[0097] B3: Through formula XG j =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i Obtain the correlation coefficient between each data point in the log data and the software fault; where XG j It refers to the correlation coefficient between the j-th data in the log data and the software fault.

[0098] Security data is processed based on correlation coefficients, including:

[0099] Determine whether the correlation coefficient between each data point in the operational data and the device fault, and the correlation coefficient between each data point in the log data and the software fault, are greater than a preset correlation coefficient threshold; if yes, retain the corresponding data; otherwise, remove the corresponding data.

[0100] The retained runtime data is marked as device target data, and the retained log data is marked as software target data.

[0101] For example, a highway toll station's toll collection system includes hardware equipment (such as ETC antennas and lane controllers) and software systems (such as toll service and network communication modules). During system operation, sensors collect real-time operational data from the equipment, log collection tools (such as Fluentd) record log data from the software system, and environmental sensors monitor ambient temperature and humidity; specifically as follows:

[0102] 1. Data collection;

[0103] Running data:

[0104] Temperature: 42℃;

[0105] Current: 6A;

[0106] Vibration amplitude: 0.8mm;

[0107] Log data:

[0108] API response time: 0.5 seconds;

[0109] CPU utilization: 80%;

[0110] Memory usage: 75%;

[0111] Environmental data:

[0112] Ambient temperature: 42℃;

[0113] Ambient humidity: 75%;

[0114] 2. Calculate the correlation coefficient;

[0115] Retrieve several sets of operational and log data from the historical database, along with the corresponding device and software statuses. Calculate the correlation coefficient using the following formula:

[0116] Correlation coefficient of running data:

[0117] Assume the probability of temperature causing equipment failure is 0.7;

[0118] Assume the probability of current causing equipment failure is 0.3;

[0119] Assume the probability that vibration amplitude will cause equipment failure is 0.5;

[0120] Assuming that the formula XG i =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i The correlation coefficients were calculated as follows:

[0121] Correlation coefficient for temperature: 0.8;

[0122] Correlation coefficient of current: 0.5;

[0123] Correlation coefficient of vibration amplitude: 0.7;

[0124] Log data correlation coefficient:

[0125] The probability of API response time causing software failure: 0.6;

[0126] The probability of CPU utilization causing software failure: 0.4;

[0127] The probability of memory usage causing software failure: 0.6;

[0128] Through formula XG j =(e^(P i )-e^(-P i )) / (e^(P i )+e^(-P i The correlation coefficients were calculated as follows:

[0129] The correlation coefficient for API response time is 0.7.

[0130] Correlation coefficient of CPU utilization: 0.4;

[0131] Correlation coefficient of memory utilization: 0.65;

[0132] 3. Filter the target data;

[0133] Set the preset correlation coefficient threshold to 0.6, and retain data with correlation coefficients greater than the threshold:

[0134] Equipment target data: temperature and vibration amplitude;

[0135] Software target data: API response time and memory usage.

[0136] The equipment failure assessment coefficient and the software failure assessment coefficient are calculated based on the equipment target data and the software target data, including: the equipment failure assessment coefficient calculated based on the equipment target data and the software failure assessment coefficient calculated based on the software target data.

[0137] The equipment failure assessment coefficient calculated based on the equipment target data includes:

[0138] Extract the target data of the equipment and the corresponding correlation coefficients; label the target data of the equipment as SM. e The correlation coefficient corresponding to the target data of the equipment is marked as XG. e Among them, SM e It refers to the e-th data in the target data of the device, XG e It refers to the correlation coefficient corresponding to the e-th data in the target data of the equipment, where e={1,2,3,…,Q}, and Q is the total number of data contained in the target data of the equipment.

[0139] Using the formula x=∑(1 / XG) e The equipment weighting factor is calculated; where x is the equipment weighting factor, ∑ is the summation symbol, and the summation range is e;

[0140] Through formula α e =1 / (XG e The weight coefficient corresponding to each data point in the target data of the equipment is calculated using ×x); where α e This refers to the weight coefficient corresponding to the e-th data in the target data of the equipment;

[0141] Using the formula P1=∑(α) e ×e^((SM e -ZS e ) / ZS e The equipment failure assessment coefficient is calculated; where P1 refers to the equipment failure assessment coefficient, ∑ is the summation symbol, and the summation range is e, ZSe It refers to the optimal data corresponding to the e-th data in the target data of the equipment.

[0142] Software fault assessment coefficients are calculated based on software target data, including:

[0143] Extract the software target data and its corresponding correlation coefficients; label the software target data as RM. k The correlation coefficient corresponding to the software target data is labeled as RX. k Among them, RM k It refers to the k-th data in the software target data, RX k It refers to the correlation coefficient corresponding to the kth data in the software target data, where k={1,2,3,…,V}, and V is the total number of data contained in the software target data.

[0144] Using the formula y=∑(1 / RX k The software weight factor is calculated; where y is the software weight factor, ∑ is the summation symbol, and the summation range is k.

[0145] Through formula β k =1 / (RX k The weight coefficients corresponding to each data point in the software target data are calculated using β(x,y); where β is... k It refers to the weight coefficient corresponding to the kth data in the software target data;

[0146] Using the formula P2=∑(β) k ×e^((RM k -ZR k ) / ZR k The software fault assessment coefficients are calculated; where P2 refers to the software fault assessment coefficients, ∑ is the summation formula, and the summation range is k, ZR. k It refers to the optimal data corresponding to the k-th data in the software target data.

[0147] The safety assessment coefficients are revised based on environmental data, including:

[0148] Extract the equipment failure assessment coefficient P1 and the software failure assessment coefficient P2;

[0149] The safety assessment coefficient is calculated using the formula P=θ1×P1+θ2×P2; where P is the safety assessment coefficient, and θ1 and θ2 are the initial weighting coefficients.

[0150] The highest ambient temperature, lowest ambient temperature, highest ambient humidity, and lowest ambient humidity of the day are obtained based on the weather forecasting platform and labeled as Tmax, Tmin, Hmax, and Hmin, respectively.

[0151] The ambient temperature index is calculated using the formula Tn=(T-Tmin) / (Tmax-Tmin); where Tn is the ambient temperature index and T is the ambient temperature.

[0152] The ambient humidity index is calculated using the formula Hn=(H-Hmin) / (Hmax-Hmin); where Hn is the ambient humidity index and H is the ambient humidity.

[0153] The initial weighting coefficient θ1 is corrected based on the ambient temperature index, specifically as follows:

[0154] The weighting coefficients after θ1 correction are calculated using the formula θ1'=θ1+f1×Tn-f2×Hn; where θ1' is the weighting coefficient after θ1 correction, f1 is the temperature influence factor, and f2 is the humidity influence factor.

[0155] The initial weighting coefficient θ2 is corrected based on the environmental humidity index, specifically as follows:

[0156] The weight coefficient after θ2 correction is obtained by calculating θ2 using the formula θ2'=θ2-f1×Tn+f2×Hn; where θ2' is the weight coefficient after θ2 correction.

[0157] By normalizing the corrected weight coefficients θ1' and θ2', the target weight coefficients are obtained. The specific normalization formula is as follows:

[0158] 1 = θ1' / (θ1'+θ2') and 2 = θ2' / (θ1'+θ2'); where 1 and 2 is the target weight coefficient;

[0159] Update the initial weight coefficients θ1 and θ2 to... 1. 2;

[0160] Through the formula P'= 1×P1+ The target safety assessment coefficient is calculated by 2×P2; where P' is the target safety assessment coefficient.

[0161] Whether to issue an early warning is determined based on the target security assessment coefficient, including:

[0162] Determine whether the target security assessment coefficient is greater than the preset target security assessment coefficient threshold; if yes, generate an early warning message and send it to the client; otherwise, continue to monitor and judge.

[0163] For example: extracting target data of the equipment and the corresponding correlation coefficients;

[0164] Assume XG1 = 0.8; XG2 = 0.7;

[0165] Using the formula x=∑(1 / XG) e Calculate the equipment weighting factor;

[0166] Assume x = 2.68;

[0167] Through formula α e =1 / (XG e Calculate the weight coefficient corresponding to each data point in the target data of the equipment (×x);

[0168] Assume α1 = 0.46; α2 = 0.54;

[0169] Using the formula P1=∑(α) e ×e^((SM e -ZS e ) / ZS e )) Calculate the equipment failure assessment coefficient;

[0170] Substituting the data, we get P1 = 1.429;

[0171] Extract the target data of the software and the corresponding correlation coefficients;

[0172] Assume RX1 = 0.7 and RX2 = 0.6;

[0173] Using the formula y=∑(1 / RX k Calculate the software weighting factors;

[0174] Assume y = 3.1;

[0175] Through formula β k =1 / (RX k (×y) Calculate the weight coefficient corresponding to each data point in the software's target data;

[0176] Assume β1 = 0.45; β2 = 0.55;

[0177] Using the formula P2=∑(β) k ×e^((RM k -ZR k ) / ZR k )) Calculate the software fault assessment coefficient;

[0178] Substituting the data, we get P2 = 1.7685;

[0179] The safety assessment coefficient is calculated using the formula P=θ1×P1+θ2×P2;

[0180] The highest ambient temperature, lowest ambient temperature, highest ambient humidity, and lowest ambient humidity of the day are obtained based on the weather forecasting platform and labeled as Tmax, Tmin, Hmax, and Hmin, respectively.

[0181] The ambient temperature index is calculated using the formula Tn=(T-Tmin) / (Tmax-Tmin);

[0182] Assume Tn = 0.53;

[0183] The ambient humidity index is calculated using the formula Hn=(H-Hmin) / (Hmax-Hmin);

[0184] Assume Hn = 0.83;

[0185] The initial weighting coefficient θ1 is corrected based on the ambient temperature index, specifically as follows:

[0186] The weight coefficient after θ1 correction is calculated using the formula θ1'=θ1+f1×Tn-f2×Hn;

[0187] Substituting the data, we get θ1' = 0.617;

[0188] The initial weighting coefficient θ2 is corrected based on the environmental humidity index, specifically as follows:

[0189] The weight coefficient after θ2 correction is calculated using the formula θ2'=θ2-f1×Tn+f2×Hn;

[0190] Substituting the data, we get θ2' = 0.383;

[0191] By normalizing the corrected weight coefficients θ1' and θ2', the target weight coefficients are obtained, specifically:

[0192] 1 = θ1' / (θ1'+θ2') = 0.617 2 = θ2' / (θ1'+θ2') = 0.383;

[0193] Update the initial weight coefficients θ1 and θ2 to... 1. 2;

[0194] Through the formula P'= 1×P1+ 2×P2 is used to calculate the target safety assessment coefficient;

[0195] Substituting the data, we get P' = 1.557;

[0196] Assume the preset target security assessment coefficient threshold is 1.5;

[0197] Since P'=1.557>1.5, the system generates an early warning message and sends it to the client.

[0198] This example demonstrates how the method of this invention can comprehensively analyze equipment operation data, software log data, and environmental data to calculate a target safety assessment coefficient and issue early warnings based on the results. This method can effectively predict potential faults and improve system operating efficiency and safety.

[0199] See Figure 3 A second aspect of the present invention provides an AI dynamic monitoring and protection method based on edge computing, comprising:

[0200] Step 1: Obtain security data from the highway toll collection system and environmental data at the corresponding collection time;

[0201] Step 2: Calculate the correlation coefficient between the running data and the log data, and process the safety data based on the correlation coefficient to obtain the device target data and the software target data;

[0202] Step 3: Calculate the equipment failure assessment coefficient and the software failure assessment coefficient based on the equipment target data and software target data;

[0203] Step 4: Calculate the safety assessment coefficient based on the equipment failure assessment coefficient and the software failure assessment coefficient, and then correct the safety assessment coefficient based on environmental data to obtain the target safety assessment coefficient;

[0204] Step 5: Determine whether to issue an early warning based on the target safety assessment coefficient.

[0205] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0206] Working principle of the invention:

[0207] This invention acquires security data from a highway toll collection system and corresponding environmental data at the time of acquisition; calculates the correlation coefficient between operational data and log data, and processes the security data based on the correlation coefficient to obtain equipment target data and software target data; calculates equipment fault assessment coefficients and software fault assessment coefficients based on the equipment target data and software target data; calculates a safety assessment coefficient based on the equipment fault assessment coefficients and software fault assessment coefficients, and corrects the safety assessment coefficient based on environmental data to obtain a target safety assessment coefficient; and determines whether to issue an early warning based on the target safety assessment coefficient. This invention solves the technical problems of existing technologies that can only independently monitor hardware devices or software services, unable to simultaneously consider the operational status of both; that monitoring systems only display the online or offline status of equipment, requiring manual on-site fault handling, resulting in low response efficiency; and that they cannot predict potential faults through data analysis, leading to passive fault discovery and affecting operational continuity.

[0208] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An AI dynamic monitoring and protection system based on edge computing, characterized in that, include: Data acquisition module, data analysis module, and early warning module; Data acquisition module: used to acquire security data of the highway toll collection system and environmental data at the corresponding time of acquisition; among which, security data includes: equipment operation data and software log data; Data analysis module: Calculates the correlation coefficient between operational data and log data, and processes the safety data based on this correlation coefficient to obtain device target data and software target data; and, The equipment failure assessment coefficient and the software failure assessment coefficient are calculated based on the equipment target data and the software target data; the safety assessment coefficient is calculated based on the equipment failure assessment coefficient and the software failure coefficient, and the safety assessment coefficient is corrected based on the environmental data to obtain the target safety assessment coefficient. Early warning module: Determines whether to issue an early warning based on the target's security assessment coefficient; The acquisition of security data from the highway toll system and corresponding environmental data at the time of collection includes: Real-time data collection of highway toll collection equipment operation data via data sensors; Log data from the highway toll collection software system is collected using data acquisition equipment, including either Fluentd or Prometheus tools. Environmental data is collected in real time through data sensors; the environmental data includes: ambient temperature and ambient humidity. The processing of security data based on correlation coefficients includes: Determine whether the correlation coefficient between each data point in the operational data and the device fault, and the correlation coefficient between each data point in the log data and the software fault, are greater than a preset correlation coefficient threshold; if yes, retain the corresponding data; otherwise, remove the corresponding data. The retained runtime data is marked as device target data, and the retained log data is marked as software target data.

2. The AI ​​dynamic monitoring and protection system based on edge computing according to claim 1, characterized in that, The determination of whether to issue an early warning based on the target security assessment coefficient includes: Determine whether the target security assessment coefficient is greater than the preset target security assessment coefficient threshold; if yes, generate an early warning message and send it to the client; otherwise, continue to monitor and judge.

3. An AI dynamic monitoring and protection method based on edge computing, applied to the AI ​​dynamic monitoring and protection system based on edge computing as described in claim 1 or 2, characterized in that, include: Step 1: Obtain security data from the highway toll collection system and environmental data at the corresponding collection time; Step 2: Calculate the correlation coefficient between the running data and the log data, and process the safety data based on the correlation coefficient to obtain the device target data and the software target data; Step 3: Calculate the equipment failure assessment coefficient and the software failure assessment coefficient based on the equipment target data and software target data; Step 4: Calculate the safety assessment coefficient based on the equipment failure assessment coefficient and the software failure assessment coefficient, and then correct the safety assessment coefficient based on environmental data to obtain the target safety assessment coefficient; Step 5: Determine whether to issue an early warning based on the target safety assessment coefficient.

Images