An intelligent security management method based on artificial intelligence

Abstract

The application discloses an intelligent security management method based on artificial intelligence and relates to the technical field of security management.The intelligent security management method based on artificial intelligence comprises the following steps: S1, traffic congestion evaluation;S2, traffic signal fault evaluation;S3, traffic management evaluation; and S4, emergency security feedback.The traffic congestion index obtained through traffic data is used to determine whether to perform traffic signal fault evaluation, then the traffic signal fault index obtained based on traffic signal data is used to determine whether to perform traffic signal management, then the traffic management effective index obtained based on management data is used to determine whether to implement an emergency security strategy, and finally, the traffic management effective index obtained after the implementation of the emergency security strategy is used to determine whether to perform feedback, so that the effect of improving the security management efficiency of road traffic is achieved, and the problem that the state change of a traffic signal is not fully considered in the security management of road traffic in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent security management technology, and in particular to an intelligent security management method based on artificial intelligence. Background Technology

[0002] Traditional security management systems, relying primarily on manual monitoring and static preventative measures, are no longer sufficient to meet the demands of today's complex and ever-changing traffic environment. When traffic lights malfunction or malfunction, it often prevents road users from accurately assessing traffic conditions, reducing road efficiency and seriously threatening driving safety. To address this challenge, existing technologies are beginning to incorporate artificial intelligence into smart security management. Through advanced technologies such as computer vision, real-time monitoring and intelligent early warning of traffic signals are achieved, enabling timely detection and handling of malfunctions or anomalies, thereby effectively preventing traffic chaos and accidents.

[0003] Existing technology improves traffic safety by processing and analyzing images captured by surveillance cameras in real time, using image processing algorithms to analyze and identify whether there are any abnormalities in traffic facilities, and finally prompting relevant departments to repair or replace them.

[0004] For example, the invention patent announcement CN108986448B discloses a traffic facility management method and terminal device, which includes: firstly acquiring first traffic facility information sent by a data acquisition terminal, the first traffic facility information including the acquired image and location information of the traffic facility; then, based on the location information of the traffic facility, narrowing the identification range of the traffic facility to a first identification range; determining first status information of the traffic facility based on the first identification range and the acquired image; and finally, determining the maintenance task of the traffic facility based on the first status information.

[0005] For example, the invention patent announcement CN106971587B discloses a traffic information management big data analysis system, which includes: a traffic facility equipped with a facility fault diagnosis unit, which is used to detect faults in the traffic facility and output corresponding facility fault information; a traffic facility fault terminal, which is connected to the traffic facility and used to receive facility fault information and output equipment maintenance request information based on the facility fault information; an image acquisition device; a traffic passage fault terminal, which is connected to the image acquisition device and used to receive traffic passage fault information and output traffic processing request information based on the traffic passage fault information; and a processing terminal, which is connected to the traffic facility fault terminal and the traffic passage fault terminal; the processing terminal pushes equipment maintenance instructions and traffic processing instructions to the terminals where equipment maintenance personnel and traffic management personnel are located, respectively.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0007] Existing security management systems mainly focus on static security measures such as video surveillance and intrusion detection, while paying less attention to traffic signal facilities, a dynamic security element. This makes it difficult for security management systems to detect and handle traffic signal malfunctions in a timely manner, thus missing the best opportunity to prevent chaos and traffic accidents, thereby affecting traffic efficiency and driving safety. There is a problem that the status changes of traffic signals are not fully considered in the security management of road traffic. Summary of the Invention

[0008] This application provides an artificial intelligence-based intelligent security management method, which solves the problem that existing road traffic security management does not fully consider changes in traffic signal status, thereby improving the efficiency of road traffic security management.

[0009] This application provides an artificial intelligence-based smart security management method, comprising the following steps: S1, performing traffic congestion assessment based on acquired traffic data to obtain a traffic congestion index, and determining whether to perform traffic signal fault assessment based on the traffic congestion index, wherein the traffic congestion index is used to quantitatively assess the degree of road traffic congestion; S2, if a traffic signal fault assessment is performed, performing a traffic signal fault assessment based on acquired traffic signal data to obtain a traffic signal fault index, and determining whether to implement traffic signal management based on the traffic signal fault index, wherein the traffic signal fault index is used to quantitatively assess the probability of traffic signal faults; S3, if traffic signal management is implemented, performing a traffic management effectiveness index based on the traffic congestion index and management data after traffic signal management, and determining whether to implement an emergency security strategy based on the traffic management effectiveness index, wherein the traffic management effectiveness index is used to quantitatively assess the effectiveness of traffic signal management; S4, determining whether to provide feedback based on the traffic management effectiveness index obtained after the implementation of the emergency security strategy.

[0010] Furthermore, the traffic data includes non-motorized vehicle lane data and motorized vehicle lane data; the non-motorized vehicle lane data includes average non-motorized vehicle speed and non-motorized vehicle lane congestion length; the motorized vehicle lane data includes average motorized vehicle speed and motorized vehicle lane congestion length; the traffic signal data includes traffic light deviation data, fault duration, and fault frequency; the management data includes accident reduction rate, average vehicle speed improvement coefficient, and traffic signal adjustment duration; the accident reduction rate represents the quantified data of the combined impact of the number of accidents after traffic management and the number of accidents before traffic management on the accident reduction rate; the average vehicle speed improvement coefficient represents the quantified data of the combined impact of the average vehicle speed after traffic management and the average vehicle speed before traffic management on the average vehicle speed improvement coefficient.

[0011] Furthermore, the traffic light deviation data includes green light duration deviation, red light duration deviation, and yellow light duration deviation; the green light duration deviation represents the quantified data of the combined influence of the green light duration and the preset green light duration for the corresponding time period on the green light duration deviation; the red light duration deviation represents the quantified data of the combined influence of the red light duration and the preset red light duration for the corresponding time period on the red light duration deviation; and the yellow light duration deviation represents the quantified data of the combined influence of the yellow light duration and the preset yellow light duration for the corresponding time period on the yellow light duration deviation.

[0012] Furthermore, the specific method for obtaining a traffic congestion index based on the acquired traffic data is as follows: A non-motorized vehicle traffic coefficient is obtained based on the non-motorized vehicle lane data, reference data for non-motorized vehicle lanes obtained from a preset database, and the relative relationship of traffic weights. This non-motorized vehicle traffic coefficient is used to assess the congestion level of the non-motorized vehicle lanes. The reference data for non-motorized vehicle lanes includes the preset maximum speed and total length of the non-motorized vehicle lanes. A motorized vehicle traffic coefficient is obtained based on the motorized vehicle lane data, reference data for motorized vehicle lanes obtained from a preset database, and the relative relationship of traffic weights. This motorized vehicle traffic coefficient is used to assess the congestion level of the motorized vehicle lanes. The reference data for motorized vehicle lanes includes the preset maximum speed and total length of the motorized vehicle lanes. The traffic weights include speed weights and congestion length weights. The non-motorized vehicle traffic coefficient, motorized vehicle traffic coefficient, and congestion weights obtained from the preset database are processed to obtain a traffic congestion index. The congestion weights include non-motorized vehicle weights and motorized vehicle weights.

[0013] Furthermore, the specific process for determining whether to conduct a traffic signal fault assessment based on the traffic congestion index is as follows: determine whether the traffic congestion index is less than a preset traffic congestion threshold obtained from a preset database; if the traffic congestion index is not less than the preset traffic congestion threshold obtained from the preset database, then no traffic signal fault assessment is conducted and the traffic congestion index continues to be monitored; if the traffic congestion index is less than the preset traffic congestion threshold obtained from the preset database, then a traffic signal fault assessment is conducted.

[0014] Furthermore, the specific method for obtaining the traffic signal fault index by assessing traffic signal faults based on the acquired traffic signal data is as follows: A fault duration coefficient is obtained based on the relative relationship between the fault duration and the total duration of a preset time period obtained from a preset database. The fault duration coefficient represents the relative deviation between the fault duration and the total duration of the preset time period. A traffic light coefficient is obtained based on the relative relationship between traffic light deviation data and traffic light weights obtained from a preset database. The traffic light coefficient represents the quantitative data on the influence of traffic light deviation data on the traffic signal fault index. The traffic light weights include green light weight, red light weight, and yellow light weight. The traffic signal fault index is obtained by processing the fault duration coefficient, traffic light coefficient, fault frequency factor, and signal weights obtained from the preset database.

[0015] Furthermore, the specific process for determining whether to implement traffic signal management based on the traffic signal fault index is as follows: Determine whether the traffic signal fault index is less than a preset signal fault threshold obtained from a preset database; if the traffic signal fault index is not less than the preset signal fault threshold obtained from the preset database, then no traffic signal management is implemented; if the traffic signal fault index is less than the preset signal fault threshold obtained from the preset database, then traffic signal management is implemented; the traffic signal management includes signal cycle adjustment and fault information push; the fault information push means pushing traffic signal fault information to preset personnel in real time.

[0016] Furthermore, the specific method for obtaining the traffic management effectiveness index is as follows: A congestion management coefficient is obtained based on the relative relationship between the traffic congestion index before and after traffic signal management. This congestion management coefficient represents quantified data on the combined influence of the traffic congestion index before and after traffic signal management on the traffic management effectiveness index. A speed increase coefficient deviation is obtained based on the relative relationship between the average vehicle speed increase coefficient and a preset speed increase coefficient obtained from a preset database. This speed increase coefficient deviation represents the degree of deviation between the average vehicle speed increase coefficient and the preset speed increase coefficient. The traffic management effectiveness index is obtained based on the relative relationship between the congestion management coefficient, the speed increase coefficient deviation, the accident reduction rate, the traffic signal adjustment duration, and the traffic management weights obtained from a preset database. These traffic management weights include accident management weights, speed management weights, and traffic light adjustment weights.

[0017] Furthermore, the specific process for determining whether to implement an emergency security strategy based on the traffic management effectiveness index is as follows: determine whether the traffic management effectiveness index is less than a preset effective management threshold obtained from a preset database; if the traffic management effectiveness index is not less than the preset effective management threshold obtained from the preset database, then the emergency security strategy is not implemented; if the traffic management effectiveness index is less than the preset effective management threshold obtained from the preset database, then the emergency security strategy is implemented.

[0018] Furthermore, the specific process of implementing the emergency security strategy is as follows: Implementing the emergency security strategy means automatically dispatching patrol personnel based on historical traffic data. The dispatching of patrol personnel includes the number, route, and frequency of patrol personnel. It is then determined whether the traffic management effectiveness index obtained after implementing the emergency security strategy is less than a preset effective management threshold obtained from a preset database. If the traffic management effectiveness index obtained after implementing the emergency security strategy is not less than the preset effective management threshold obtained from the preset database, no feedback is provided. If the traffic management effectiveness index obtained after implementing the emergency security strategy is less than the preset effective management threshold obtained from the preset database, feedback is provided.

[0019] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0020] 1. By using traffic congestion index obtained from traffic data to determine whether to conduct traffic signal fault assessment, then using traffic signal fault index obtained from traffic signal data to determine whether to implement traffic signal management, and finally using traffic management effectiveness index obtained from management data to determine whether to implement emergency security strategies, the efficiency of traffic signal management in intelligent security management is improved, the initiative and foresight of security management are enhanced, and the overall coordination and efficient operation of the security management system are realized. This effectively solves the problem that existing technologies for road traffic security management do not fully consider changes in traffic signal status.

[0021] 2. By comparing the traffic congestion index before and after traffic signal management, a congestion management coefficient is obtained. Then, the speed increase coefficient deviation is obtained based on the relative relationship between the average vehicle speed increase coefficient and the preset speed increase coefficient. Finally, the traffic management effectiveness index is obtained based on the relative relationship between the congestion management coefficient, the speed increase coefficient deviation, the accident reduction rate, the traffic signal adjustment time, and the traffic management weight. This quantitatively assesses the impact of traffic signal management on driving safety, thereby improving the intelligence level of the security management system and enabling it to respond to traffic changes more quickly.

[0022] 3. The non-motorized vehicle traffic coefficient is obtained by analyzing the relative relationship between non-motorized vehicle lane data, non-motorized vehicle lane reference data, and traffic weights. Then, the motorized vehicle traffic coefficient is obtained based on the relative relationship between motorized vehicle lane data, motorized vehicle lane reference data, and traffic weights. Finally, the non-motorized vehicle traffic coefficient, motorized vehicle traffic coefficient, and congestion weights obtained from a preset database are processed to obtain a traffic congestion index. This quantitatively assesses the degree of road traffic congestion, enabling the security management system to better adapt to the dynamic distribution of urban traffic signals, and thus providing strong support for the subsequent detection of traffic signal faults. Attached Figure Description

[0023] Figure 1 A flowchart illustrating an artificial intelligence-based smart security management method provided in this application embodiment;

[0024] Figure 2 A schematic diagram illustrating the change of traffic congestion index with average non-motorized vehicle speed, provided for an embodiment of this application.

[0025] Figure 3 A schematic diagram illustrating the change of traffic congestion index with the length of congestion in non-motorized lanes, provided for an embodiment of this application.

[0026] Figure 4 A schematic diagram illustrating the change of traffic congestion index with average vehicle speed, provided for an embodiment of this application;

[0027] Figure 5 This is a schematic diagram illustrating the change of the traffic congestion index with the length of congestion in the motor vehicle lane, provided in an embodiment of this application. Detailed Implementation

[0028] This application provides an AI-based intelligent security management method that addresses the problem in existing road traffic security management that does not adequately consider changes in traffic signal status. The method uses a traffic congestion index obtained from traffic data to determine whether to conduct a traffic signal fault assessment. Then, it uses a traffic signal fault index obtained from traffic signal data to determine whether to implement traffic signal management. Next, it uses a traffic management effectiveness index obtained from management data to determine whether to implement an emergency security strategy. Finally, it uses a traffic management effectiveness index obtained after implementing the emergency security strategy to determine whether to provide feedback, thereby improving the efficiency of road traffic security management.

[0029] The technical solution in this application embodiment is to address the problem of insufficient consideration of traffic signal status changes in the aforementioned road traffic security management. The overall approach is as follows:

[0030] The system uses traffic congestion index obtained from traffic data to determine whether to conduct traffic signal fault assessment, then uses traffic signal fault index obtained from traffic signal data to determine whether to implement traffic signal management, and finally uses traffic management effectiveness index obtained from management data to determine whether to implement emergency security strategies. This approach has improved the efficiency of road traffic security management.

[0031] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0032] like Figure 1 The diagram shows a flowchart of an artificial intelligence-based smart security management method provided in an embodiment of this application. The method includes the following steps: S1, Traffic congestion assessment: Based on the acquired traffic data, a traffic congestion index is obtained. Based on the traffic congestion index, it is determined whether to conduct a traffic signal fault assessment. The traffic congestion index is used to quantitatively assess the degree of road traffic congestion. S2, Traffic signal fault assessment: If a traffic signal fault assessment is conducted, a traffic signal fault index is obtained based on the acquired traffic signal data. Based on the traffic signal fault index, it is determined whether to implement traffic signal management. The traffic signal fault index is used to quantitatively assess the probability of traffic signal faults. S3, Traffic management assessment: If traffic signal management is implemented, a traffic management effectiveness index is obtained based on the traffic congestion index and management data after traffic signal management. Based on the traffic management effectiveness index, it is determined whether to implement an emergency security strategy. The traffic management effectiveness index is used to quantitatively assess the effectiveness of traffic signal management. S4, Emergency security feedback: Based on the traffic management effectiveness index obtained after the implementation of the emergency security strategy, it is determined whether to provide feedback.

[0033] The intelligent security management system provided in this application primarily serves urban traffic management departments, security monitoring centers, and related emergency response teams. The intelligent security management system is typically installed near traffic accident recording systems, traffic signal control systems, security monitoring centers, and key traffic nodes (such as traffic lights and cameras). It connects various sensors, cameras, and management terminals via wired or wireless means to achieve real-time monitoring and management, realizing comprehensive monitoring and management of road traffic, improving traffic efficiency, ensuring driving safety, and providing strong support for the sustainable development of urban transportation.

[0034] It should be noted that the traffic data includes data on non-motorized vehicle lanes and motorized vehicle lanes; the non-motorized vehicle lane data includes the average speed of non-motorized vehicles and the length of congestion in the non-motorized vehicle lanes; the motorized vehicle lane data includes the average speed of motorized vehicles and the length of congestion in the motorized vehicle lanes; the traffic signal data includes traffic light deviation data, fault duration and fault frequency; and the management data includes the accident reduction rate, the average vehicle speed improvement coefficient and the traffic signal adjustment time.

[0035] The accident reduction rate represents the quantitative data on the combined impact of the number of accidents before and after traffic management on the overall accident reduction rate. It is obtained by calculating the difference between the absolute value of the difference between the number of accidents before and after traffic management, obtained from the traffic accident record system, and the number of accidents before traffic management. The average vehicle speed improvement coefficient represents the quantitative data on the combined impact of the average vehicle speed before and after traffic management on the overall average vehicle speed improvement coefficient. It is obtained by calculating the difference between the absolute value of the difference between the average vehicle speed before and after traffic management and the average vehicle speed before traffic management. The traffic signal adjustment duration is obtained from the operation records of the traffic signal control system.

[0036] When the average vehicle speed is lower than the preset vehicle speed, the traffic situation is judged as congestion. Vehicles on the road are identified in real time through background modeling and foreground detection. Then, image processing technology (such as image segmentation and vehicle detection) is used to identify the start and end positions of the congestion area. Based on the boundary position of the congestion area in the image and the actual geometric layout of the road, and combined with geometric measurement and correction algorithms, the congestion length of the non-motorized vehicle lane and the congestion length of the motorized vehicle lane are calculated. The preset vehicle speed is set according to the specific road requirements. For example, on urban main roads, it can be set to 30 km / h. The average non-motorized vehicle speed and the average vehicle speed are measured by the radar speed measuring instrument equipped with the camera.

[0037] Traffic light deviation data includes green light duration deviation, red light duration deviation, and yellow light duration deviation. Green light duration deviation represents the quantified impact of the green light duration and the preset green light duration for the corresponding time period on the overall green light duration deviation. It is obtained by comparing the absolute value of the difference between the green light duration and the preset green light duration for the corresponding time period with the preset green light duration for the corresponding time period. Red light duration deviation represents the quantified impact of the red light duration and the preset red light duration for the corresponding time period on the overall red light duration deviation. It is obtained by comparing the absolute value of the difference between the red light duration and the preset red light duration for the corresponding time period with the preset red light duration for the corresponding time period. Yellow light duration deviation represents the quantified impact of the yellow light duration and the preset yellow light duration for the corresponding time period on the overall yellow light duration deviation. It is obtained by comparing the absolute value of the difference between the yellow light duration and the preset yellow light duration for the corresponding time period with the preset yellow light duration for the corresponding time period. Fault duration and fault frequency are obtained from the fault records of the traffic signal control system.

[0038] In this embodiment, by using machine learning and deep learning algorithms in artificial intelligence (such as background modeling and foreground detection), traffic data, traffic signal data, and management data, such as average vehicle speed, congestion length, and traffic light deviation, can be acquired. Through artificial intelligence, traffic signal management processes and patrol personnel dispatch can be automatically triggered. Artificial intelligence can also continuously adjust management strategies based on feedback results to improve management efficiency.

[0039] The durations of green, red, and yellow lights are obtained through the interface of the traffic signal control system. The preset green, red, and yellow light durations are represented by the mode of the green, red, and yellow light durations within the corresponding historical time period. For example, if the mode of the green light duration from 7 pm to 8 pm within a month is 1800s, then the preset green light duration from 7 pm to 8 pm is set to 1800s.

[0040] Through the above steps, the effectiveness of traffic congestion, traffic signal malfunctions, and management measures was assessed, thereby enabling real-time adjustments to traffic signals, optimization of traffic flow, and reduction of traffic accidents. This improved the efficiency of road traffic management in intelligent security management, and consequently, enhanced the efficiency of road traffic security management.

[0041] Furthermore, the specific method for obtaining the traffic congestion index based on the acquired traffic data is as follows: The non-motorized vehicle traffic coefficient is obtained based on the non-motorized vehicle lane data, reference data for non-motorized vehicle lanes obtained from a pre-set database, and the relative relationship of traffic weights. The non-motorized vehicle traffic coefficient is used to assess the congestion level of non-motorized vehicle lanes. Reference data for non-motorized vehicle lanes includes the preset maximum speed and total length of the lanes. The motorized vehicle traffic coefficient is obtained based on the motorized vehicle lane data, reference data from a preset database, and the relative relationship of traffic weights. The vehicle traffic coefficient is used to assess the congestion level of motor vehicle lanes. Reference data for motor vehicle lanes includes the preset maximum speed and total length of the lanes. Traffic weights include speed weights and congestion length weights. The speed weight represents the influence of average non-motorized vehicle speed and average motorized vehicle speed on the traffic congestion index, while the congestion length weight represents the influence of non-motorized vehicle lane congestion length and motorized vehicle lane congestion length on the traffic congestion index. The traffic congestion index is obtained by processing the non-motorized vehicle traffic coefficient, the motorized vehicle traffic coefficient, and the congestion weights obtained from the preset database. The congestion weights include non-motorized vehicle weights and motorized vehicle weights. The non-motorized vehicle weight represents the influence of the non-motorized vehicle traffic coefficient on the traffic congestion index, while the motorized vehicle weight represents the influence of the motorized vehicle traffic coefficient on the traffic congestion index.

[0042] It should be added that the specific method for obtaining the traffic congestion index is as follows:

[0043]

[0044] In the formula, t represents the number of the preset time period, t = 1, 2, ..., T, and T represents the total number of preset time periods. t FCS represents the traffic congestion index for the t-th preset time period. t FYC represents the average speed of non-motorized vehicles within the t-th preset time period. t JCS represents the length of congestion in the non-motorized lane during the t-th preset time period. t JYC represents the average speed of motor vehicles within the t-th preset time period. t Let FCS0 represent the maximum speed of the non-motorized lane, FTC0 represent the total length of the non-motorized lane, JCS0 represent the maximum speed of the motorized lane, JTC0 represent the total length of the motorized lane, α1 represent the weight of non-motorized vehicles, α2 represent the weight of motorized vehicles, Y1 represent the speed weight, and Y2 represent the congestion length weight.

[0045] In this embodiment, the preset maximum speed of the non-motorized vehicle lane is set according to specific road regulations, for example, the preset maximum speed of the non-motorized vehicle lane is 30km / h; the total length of the non-motorized vehicle lane is set according to specific road sections, for example, on urban arterial roads, the total length of the non-motorized vehicle lane is set to 0.5km; the preset maximum speed of the motorized vehicle lane is set according to specific road regulations, for example, on urban arterial roads, the preset maximum speed of the motorized vehicle lane is 60km / h; the total length of the motorized vehicle lane is set according to specific road sections, for example, on urban arterial roads, the total length of the motorized vehicle lane is set to 0.5km; the total length of the non-motorized vehicle lane and the total length of the motorized vehicle lane refer to the distance between two traffic lights.

[0046] The weights for non-motorized vehicles and motorized vehicles are obtained from a preset database, and their sum is 1. For example, the average speed of non-motorized vehicles and the congestion length of non-motorized vehicle lanes form a mapping set with the preset non-motorized vehicle weights. Inputting the real-time average speed of non-motorized vehicles and the congestion length of non-motorized vehicle lanes into the mapping set yields the corresponding non-motorized vehicle weights. Similarly, the average speed of motorized vehicles and the congestion length of motorized vehicle lanes form a mapping set with the preset motorized vehicle weights. Inputting the real-time average speed of motorized vehicles and the congestion length of motorized vehicle lanes into the mapping set yields the corresponding motorized vehicle weights. The mapping relationship can be one-to-one or many-to-one.

[0047] Speed ​​weights and congestion length weights are obtained from a preset database, and their sum is 1. For example, non-motorized vehicle speeds and average motorized vehicle speeds form a mapping set with preset speed weights. Inputting real-time non-motorized vehicle speeds and average motorized vehicle speeds into the mapping set yields the corresponding speed weights. Similarly, non-motorized vehicle lane congestion lengths and motorized vehicle lane congestion lengths form a mapping set with preset congestion length weights. Inputting real-time non-motorized vehicle lane congestion lengths and motorized vehicle lane congestion lengths into the mapping set yields the corresponding congestion length weights. The mapping relationship can be one-to-one or many-to-one.

[0048] The traffic congestion index in this algorithm involves processing multiple independent variables (non-motorized vehicle speed, average motorized vehicle speed, non-motorized vehicle lane congestion length, and motorized vehicle lane congestion length), which are interconnected. Lane congestion length is usually accompanied by a decrease in vehicle speed; the two are mutually reinforcing and jointly contribute to traffic congestion. When non-motorized vehicle speed and average motorized vehicle speed decrease, the congestion length of both non-motorized vehicle lanes and motorized vehicle lanes increases accordingly. When non-motorized vehicles and motorized vehicles share the road, the increased congestion length of non-motorized vehicles interferes with the movement of motorized vehicles, leading to a decrease in the average motorized vehicle speed. Interference includes friction interference (drivers reduce speed when non-motorized vehicles approach the motorized vehicle lane laterally) and obstruction interference (non-motorized vehicles occupying the motorized vehicle lane and blocking the movement of motorized vehicles).

[0049] In this algorithm, the traffic congestion index is negatively correlated with the speed of non-motorized vehicles and the average speed of motorized vehicles, and positively correlated with the congestion length of non-motorized lanes and the congestion length of motorized lanes.

[0050] Taking an example with non-motorized vehicle weight, motorized vehicle weight, speed weight, and congestion length weight of 0.6, 0.4, 0.3, and 0.7 respectively, a preset maximum speed of 10 km / h for non-motorized vehicle lanes, a total length of 10 km for non-motorized vehicle lanes, a preset maximum speed of 60 km / h for motorized vehicle lanes, and a total length of 20 km for motorized vehicle lanes, the following results are obtained: Figure 2-5 The analysis is as follows:

[0051] like Figure 2 The diagram shows the change of the traffic congestion index with the average non-motorized vehicle speed provided in this application embodiment. When the non-motorized vehicle lane congestion length, the average motorized vehicle speed, and the motorized vehicle lane congestion length are all 0, the traffic congestion index decreases as the average non-motorized vehicle speed increases.

[0052] like Figure 3 The diagram shown illustrates the change of the traffic congestion index with the length of non-motorized vehicle lane congestion according to an embodiment of this application. When the average non-motorized vehicle speed, average motorized vehicle speed, and motorized vehicle lane congestion length are all 0, the traffic congestion index increases with the increase of the length of non-motorized vehicle lane congestion.

[0053] like Figure 4 The diagram shows the change of the traffic congestion index with the average motor vehicle speed provided in this embodiment of the application. When the average non-motor vehicle speed, the congestion length of the non-motor vehicle lane, and the congestion length of the motor vehicle lane are all 0, the traffic congestion index decreases as the average motor vehicle speed increases.

[0054] like Figure 5 The diagram shown illustrates the change of the traffic congestion index with the length of congestion in the motor vehicle lanes, as provided in this embodiment of the application. When the average speed of non-motorized vehicles, the length of congestion in the non-motorized vehicle lanes, and the average speed of motorized vehicles are all zero, the traffic congestion index increases with the increase of the length of congestion in the motor vehicle lanes.

[0055] Through the above steps, the degree of road traffic congestion was quantitatively assessed, thus providing strong support for the subsequent detection of traffic signal malfunctions.

[0056] Furthermore, the specific process for determining whether to conduct a traffic signal fault assessment based on the traffic congestion index is as follows: Determine if the traffic congestion index is less than a preset traffic congestion threshold obtained from a preset database. If the traffic congestion index is not less than the preset traffic congestion threshold obtained from the preset database, then no traffic signal fault assessment is conducted, and the traffic congestion index continues to be monitored. If the traffic congestion index is less than the preset traffic congestion threshold obtained from the preset database, then a traffic signal fault assessment is conducted (i.e., a traffic signal fault index is obtained). Traffic signal fault assessment means evaluating the obtained traffic signal data to obtain the traffic signal fault index.

[0057] In this embodiment, the preset traffic congestion threshold is represented by the average value of qualified traffic congestion indices over a historical time period. Through the above steps, traffic light malfunctions can be detected in a timely manner, thereby improving the management efficiency of road traffic in smart security management.

[0058] Furthermore, the specific method for obtaining the traffic signal fault index by assessing traffic signal faults based on the acquired traffic signal data is as follows: The fault duration coefficient (i.e., ...) is obtained based on the relative relationship between the fault duration and the total duration of a preset time period obtained from a preset database. The fault duration coefficient represents the relative deviation between the fault duration and the total duration of the preset time period; the traffic light coefficient (i.e., XHD) is obtained based on the relative relationship between the traffic light deviation data and the traffic light weights obtained from the preset database. t The traffic signal fault index is calculated by processing the fault duration coefficient, traffic signal coefficient, fault frequency factor, and signal weights. The fault frequency factor represents the influence of fault frequency on the traffic signal fault index, and the signal weights represent the influence of fault duration on the traffic signal fault index.

[0059] The specific method for obtaining the traffic signal fault index is as follows:

[0060]

[0061] In the formula, t represents the number of the preset time period, t = 1, 2, ..., T, T represents the total number of preset time periods, n represents the number of the signal cycle, n = 1, 2, ..., N, N represents the total number of signal cycles, GZ t YD represents the traffic signal fault index for the t-th preset time period.t GZT represents the traffic congestion index for the t-th preset time period. t XHD represents the duration of the fault in the t-th preset time period. t LVT represents the signal light coefficient for the t-th preset time period. t.n HOT represents the green light duration deviation in the nth signal cycle within the t-th preset time period. t.n HUT represents the red light duration deviation in the nth signal cycle within the t-th preset time period. t.n ZT0 represents the yellow light duration deviation in the nth signal cycle within the t-th preset time period, YD0 represents the preset traffic congestion threshold, GP represents the fault frequency factor, β1 represents the green light weight, β2 represents the red light weight, β3 represents the yellow light weight, and γ represents the signal weight.

[0062] In this embodiment, the preset time period is set according to specific requirements; for example, the preset time period is set to 1 hour.

[0063] The green light weight, red light weight, and yellow light weight are obtained from a preset database, and the sum of the three is 1. For example, the green light duration deviation forms a mapping set with the preset green light weight, and the real-time green light duration deviation is input into the mapping set to obtain the corresponding green light weight; the red light duration deviation forms a mapping set with the preset red light weight, and the real-time red light duration deviation is input into the mapping set to obtain the corresponding red light weight; the yellow light duration deviation forms a mapping set with the preset yellow light weight, and the real-time yellow light duration deviation is input into the mapping set to obtain the corresponding yellow light weight; the mapping relationship can be one-to-one or many-to-one.

[0064] The signal weights are obtained from a preset database. For example, the fault duration and the preset signal weights form a mapping set. The real-time fault duration is input into the mapping set to obtain the corresponding signal weights. The mapping relationship can be one-to-one or many-to-one. In this example, the value range is 0-1.

[0065] The fault frequency factor is obtained from a preset database. For example, a mapping set of fault frequency and its corresponding influencing factors is constructed based on the relationship between historical fault frequency and traffic signal data (such as traffic light deviation data and fault duration). The real-time fault frequency is then input into the mapping set to obtain the corresponding fault frequency factor. The fault frequency represents the number of faults within the expected time period. The expected time period can be set to 1 month.

[0066] The traffic signal fault index in this algorithm is obtained by processing multiple independent variables (signal light deviation data and fault duration), and these independent variables have interrelationships. The larger the signal light deviation, the more likely it is that the signal light equipment will malfunction, which may lead to an increase in the fault duration. The green light duration deviation, red light duration deviation, and yellow light duration deviation are interrelated. An increase in any signal light deviation data may lead to an increase in the duration deviation of other signal lights in order to balance traffic flow and road traffic safety. In this algorithm, the traffic signal fault index is positively correlated with the signal light deviation data and the fault duration.

[0067] Through the above steps, the probability of traffic signal malfunctions was quantitatively assessed, thereby providing strong support for subsequent road traffic management in smart security management.

[0068] Furthermore, the specific process for determining whether to implement traffic signal management based on the traffic signal fault index is as follows: Determine if the traffic signal fault index is less than a preset signal fault threshold obtained from a preset database. If the traffic signal fault index is not less than the preset signal fault threshold obtained from the preset database, then no traffic signal management is implemented. If the traffic signal fault index is less than the preset signal fault threshold obtained from the preset database, then traffic signal management is implemented. Traffic signal management includes signal cycle adjustment and fault information push. Signal cycle adjustment means adjusting the traffic lights to a preset fixed cycle. Fault information push means pushing traffic signal fault information to preset personnel in real time.

[0069] In this embodiment, the preset signal fault threshold is represented by the average value of the qualified traffic signal fault index within a historical time period; the preset fixed period can be set as a green light duration of 30 seconds, a red light duration of 90 seconds, and a yellow light duration of 3 seconds.

[0070] Fault information push: Fault information is pushed to drivers through traffic navigation software (such as Gaode); fault information is pushed to relevant personnel (such as traffic police, maintenance teams, etc.) through the traffic management bureau; fault information includes the location of the faulty intersection (e.g., intersection number or road name) and the specific type of fault (e.g., traffic light failure, abnormal cycle, etc.).

[0071] The above steps improve road traffic efficiency in smart security management.

[0072] Furthermore, the specific method for obtaining the traffic management effectiveness index is as follows: The congestion management coefficient (YG) is obtained based on the relative relationship between the traffic congestion index before and after traffic signal management. The congestion management coefficient represents the quantitative data on the combined impact of the traffic congestion index before and after traffic signal management on the traffic management effectiveness index; the speed increase coefficient deviation (SG) is obtained based on the relative relationship between the average vehicle speed increase coefficient and the preset speed increase coefficient obtained from the preset database. r The deviation of the vehicle speed increase coefficient indicates the degree of deviation between the average vehicle speed increase coefficient and the preset vehicle speed increase coefficient. The traffic management effectiveness index is obtained based on the relative relationship between the congestion management coefficient, the deviation of the vehicle speed increase coefficient, the accident reduction rate, the traffic signal adjustment duration, and the traffic management weights obtained from the preset database. The traffic management weights include the accident management weight, the vehicle speed management weight, and the traffic light adjustment weight. The accident management weight indicates the influence of the accident reduction rate on the traffic management effectiveness index, the vehicle speed management weight indicates the influence of the average vehicle speed increase coefficient on the traffic management effectiveness index, and the traffic light adjustment weight indicates the influence of the traffic signal adjustment duration on the traffic management effectiveness index.

[0073] The specific method for obtaining the traffic management effectiveness index is as follows:

[0074] GL r =YG*[ln(ω1*SGJ r +ω2*SG r +1)+ω3*csch(TZS)],TZS≥TZS0;

[0075]

[0076] In the formula, t represents the preset time period number, t = 1, 2, ..., T, T represents the total number of preset time periods, r represents the preset time period number after traffic signal management, r = 1, 2, ..., R, R represents the total number of preset time periods after traffic signal management, GL r YG represents the traffic management effectiveness index for the r-th preset time period, and SG represents the congestion management coefficient. r YD represents the deviation of the vehicle speed increase coefficient during the r-th preset time period. t YD represents the traffic congestion index for the t-th preset time period. t ′ SGJ represents the traffic congestion index for the t-th preset time period after traffic signal management. r STG represents the accident reduction rate during the r-th preset time period after traffic signal management. rω1 represents the average vehicle speed increase coefficient for the r-th preset time period after traffic signal management, TZS represents the traffic signal adjustment duration, YD0 represents the preset traffic congestion threshold, STG0 represents the preset vehicle speed increase coefficient, TZS0 represents the preset traffic signal adjustment duration, ω1 represents the accident management weight, ω2 represents the vehicle speed management weight, and ω3 represents the traffic light adjustment weight.

[0077] In this embodiment, the preset speed increase coefficient is set according to the target speed. For example, the preset speed increase coefficient can be set to 0.2 between 7 pm and 8 pm. The preset traffic signal adjustment duration is set according to the traffic conditions. For example, if the traffic signal adjustment duration is too short, the signal adjustment effect may be poor. Therefore, the preset traffic signal adjustment duration is set to 5 seconds.

[0078] Accident management weights, vehicle speed management weights, and traffic light adjustment weights are obtained from a preset database, and the sum of the three is 1. For example, the accident reduction rate forms a mapping set with the preset accident management weights, and the real-time accident reduction rate is input into the mapping set to obtain the corresponding accident management weight; the average vehicle speed increase coefficient forms a mapping set with the preset vehicle speed management weights, and the real-time average vehicle speed increase coefficient is input into the mapping set to obtain the corresponding vehicle speed management weight; the traffic signal adjustment duration forms a mapping set with the preset traffic light adjustment weights, and the real-time traffic signal adjustment duration is input into the mapping set to obtain the corresponding weight; the mapping relationship can be one-to-one or many-to-one.

[0079] The traffic management effectiveness index in this algorithm involves processing multiple independent variables (accident reduction rate, average vehicle speed improvement coefficient, and traffic signal adjustment duration), which are interconnected. A higher accident reduction rate may lead to increased vehicle mobility, which in turn leads to a larger average vehicle speed improvement coefficient. A larger average vehicle speed improvement coefficient may lead to a lower traffic congestion index, which in turn leads to a higher accident reduction rate. A longer traffic signal adjustment duration may lead to unstable traffic flow, increasing the probability of accidents and thus reducing the accident reduction rate. A shorter traffic signal adjustment duration helps improve traffic mobility, thereby increasing vehicle speed and the average vehicle speed improvement coefficient.

[0080] In this algorithm, the traffic management effectiveness index is positively correlated with the accident reduction rate and the coefficient of increase in average vehicle speed, while the traffic management effectiveness index is negatively correlated with the traffic signal adjustment duration.

[0081] Through the above steps, the effectiveness of traffic signal management was quantitatively evaluated, thereby improving the effectiveness of road traffic management in smart security management.

[0082] Furthermore, the specific process for determining whether to implement emergency security strategies based on the traffic management effectiveness index is as follows: Determine whether the traffic management effectiveness index is less than the preset effective management threshold obtained from the preset database: If the traffic management effectiveness index is not less than the preset effective management threshold obtained from the preset database, then the emergency security strategy will not be implemented; if the traffic management effectiveness index is less than the preset effective management threshold obtained from the preset database, then the emergency security strategy will be implemented.

[0083] Specifically, the process of implementing the emergency security strategy is as follows: Implementing the emergency security strategy means automatically dispatching patrol personnel based on historical traffic data. Patrol personnel dispatching includes the number, route, and frequency of patrol personnel. It is then determined whether the traffic management effectiveness index obtained after implementing the emergency security strategy is less than a preset effective management threshold obtained from a preset database. If the traffic management effectiveness index obtained after implementing the emergency security strategy is not less than the preset effective management threshold obtained from the preset database, no feedback is provided. If the traffic management effectiveness index obtained after implementing the emergency security strategy is less than the preset effective management threshold obtained from the preset database, feedback is provided.

[0084] In this embodiment, the preset effective management threshold is represented by the average value of the qualified traffic management effectiveness index over a historical time period.

[0085] Patrol personnel dispatch: The cosine similarity of real-time and historical traffic data is calculated to obtain the similarity score. The maximum similarity score is obtained by statistically analyzing all historical and real-time traffic data. Patrol personnel are dispatched based on the emergency security strategy corresponding to the historical traffic data with the maximum similarity score. For example, during the morning rush hour (7:30-9:00), the traffic flow at a certain intersection is 500 vehicles / hour. The section with the highest accident frequency is located on the north side of the intersection. Based on the above traffic data and historical traffic data, the cosine similarity is calculated to obtain the similarity score. The maximum similarity score is obtained by statistically analyzing all historical and real-time traffic data. The emergency security strategy corresponding to the historical traffic data with the maximum similarity score is to dispatch 4 patrol personnel to patrol the north side of the intersection every 15 minutes. Therefore, the emergency security strategy is set to dispatch 4 patrol personnel to patrol every 15 minutes. The priority patrol area for dispatched patrol personnel is the north side of the intersection, observing for illegal parking, abnormal vehicle stops, etc.

[0086] Feedback: When the traffic management effectiveness index obtained after implementing emergency security strategies is less than the preset effective management threshold obtained from the preset database, the upward feedback mechanism is automatically triggered, that is, the traffic data is sent to the receiving end of the superior competent department through the preset communication interface to request assistance.

[0087] By implementing emergency security strategies, resources can be quickly deployed in emergency situations to meet the needs of emergency response. Through clear division of responsibilities and effective communication and coordination mechanisms within these strategies, departments and personnel can respond quickly and work together to address emergencies, thereby achieving intelligent security management of road traffic in emergency situations. Through these steps, resource allocation in intelligent security management is optimized, thereby improving the efficiency of road traffic management.

[0088] In summary, this application embodiment determines whether to conduct a traffic signal fault assessment based on a traffic congestion index obtained from traffic data, then determines whether to implement traffic signal management based on a traffic signal fault index obtained from traffic signal data, and finally determines whether to implement emergency security strategies based on a traffic management effectiveness index obtained from management data. This improves the efficiency of traffic signal management in intelligent security management, enhances the initiative and predictability of security management, and achieves overall coordination and efficient operation of the security management system. It effectively solves the problem that existing technologies for road traffic security management do not fully consider changes in traffic signal status.

[0089] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0094] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for intelligent security management based on artificial intelligence, characterized in that, The method comprises the following steps: S1, obtaining a traffic congestion index according to the acquired traffic data, and determining whether to perform traffic signal fault evaluation based on the traffic congestion index, wherein the traffic congestion index is used to quantitatively evaluate the congestion degree of road traffic; S2, if the traffic signal fault evaluation is performed, obtaining a traffic signal fault index according to the acquired traffic signal data, and determining whether to perform traffic signal management based on the traffic signal fault index, wherein the traffic signal fault index is used to quantitatively evaluate the probability of existence of traffic signal fault; S3, if the traffic signal management is performed, obtaining a traffic management effective index according to the traffic congestion index and management data after the traffic signal management, and determining whether to implement an emergency security strategy based on the traffic management effective index, wherein the traffic management effective index is used to quantitatively evaluate the effectiveness of the traffic signal management; S4, determining whether to perform feedback based on the traffic management effective index obtained after the implementation of the emergency security strategy; The specific method for obtaining the traffic signal fault index according to the acquired traffic signal data comprises the following steps: obtaining a fault duration coefficient according to the relative relationship between the fault duration and the total duration of the preset time period obtained from the preset database, wherein the fault duration coefficient represents the relative deviation between the fault duration and the total duration of the preset time period; obtaining a signal lamp coefficient according to the relative relationship between the signal lamp deviation data and the signal lamp weight obtained from the preset database, wherein the signal lamp coefficient represents the influence degree quantification data of the signal lamp deviation data on the traffic signal fault index; The signal lamp weight comprises a green lamp weight, a red lamp weight and a yellow lamp weight; processing the fault duration coefficient, the signal lamp coefficient and the fault frequency factor and the signal weight obtained from the preset database to obtain the traffic signal fault index.

2. The intelligent security management method based on artificial intelligence according to claim 1, characterized in that: The traffic data comprises non-motor vehicle lane data and motor vehicle lane data; The non-motor vehicle lane data comprises an average non-motor vehicle speed and a non-motor vehicle lane congestion length; The motor vehicle lane data comprises an average motor vehicle speed and a motor vehicle lane congestion length; The traffic signal data comprises signal lamp deviation data, fault duration and fault frequency; The management data comprises an accident reduction rate, a motor vehicle average speed improvement coefficient and a traffic signal adjustment duration; The accident reduction rate represents the influence degree quantification data of the number of accidents after the traffic management and the number of accidents before the traffic management on the accident reduction rate; The motor vehicle average speed improvement coefficient represents the influence degree quantification data of the average speed after the traffic management and the average speed before the traffic management on the motor vehicle average speed improvement coefficient. 3.The AI-based intelligent security management method of claim 2, wherein: The signal lamp deviation data comprises a green lamp duration deviation, a red lamp duration deviation and a yellow lamp duration deviation; The green lamp duration deviation represents the influence degree quantification data of the green lamp duration and the preset green lamp duration of the corresponding time period on the green lamp duration deviation; The red lamp duration deviation represents the influence degree quantification data of the red lamp duration and the preset red lamp duration of the corresponding time period on the red lamp duration deviation; The yellow light time length bias represents the influence degree quantification data of the yellow light time length and the preset yellow light time length of the corresponding time period on the yellow light time length bias.

4. The intelligent security management method based on artificial intelligence according to claim 3, characterized in that: The specific method for obtaining the traffic congestion index according to the acquired traffic data is as follows: The non-motor vehicle passing coefficient is obtained according to the relative relationship of the non-motor vehicle lane data, the non-motor vehicle lane reference data acquired from the preset database and the traffic weight, the non-motor vehicle passing coefficient is used to evaluate the congestion degree of the non-motor vehicle lane, and the non-motor vehicle lane reference data includes the non-motor vehicle lane preset maximum speed and the non-motor vehicle lane total length; The motor vehicle passing coefficient is obtained according to the relative relationship of the motor vehicle lane data, the motor vehicle lane reference data acquired from the preset database and the traffic weight, the motor vehicle passing coefficient is used to evaluate the congestion degree of the motor vehicle lane, and the motor vehicle lane reference data includes the motor vehicle lane preset maximum speed and the motor vehicle lane total length; The traffic weight includes the speed weight and the congestion length weight; The traffic congestion index is obtained by processing the non-motor vehicle passing coefficient, the motor vehicle passing coefficient and the congestion weight acquired from the preset database; The congestion weight includes the non-motor vehicle weight and the motor vehicle weight. 5.The AI-based intelligent security management method of claim 1, wherein: The specific process of judging whether to perform traffic signal fault evaluation based on the traffic congestion index is as follows: Judging whether the traffic congestion index is less than the preset traffic congestion threshold value acquired from the preset database: If the traffic congestion index is not less than the preset traffic congestion threshold value acquired from the preset database, no traffic signal fault evaluation is performed and the traffic congestion index is continuously monitored; If the traffic congestion index is less than the preset traffic congestion threshold value acquired from the preset database, traffic signal fault evaluation is performed.

6. The intelligent security management method based on artificial intelligence according to claim 1, wherein: The specific process of judging whether to perform traffic signal management based on the traffic signal fault index is as follows: Judging whether the traffic signal fault index is less than the preset signal fault threshold value acquired from the preset database: If the traffic signal fault index is not less than the preset signal fault threshold value acquired from the preset database, no traffic signal management is performed; If the traffic signal fault index is less than the preset signal fault threshold value acquired from the preset database, traffic signal management is performed; The traffic signal management includes signal cycle adjustment and fault information pushing. The fault information pushing means that the traffic signal fault information is pushed to the preset personnel in real time.

7. The intelligent security management method based on artificial intelligence according to claim 2, characterized in that: The specific method for obtaining the traffic management effective index is as follows: The congestion management coefficient is obtained according to the relative relationship of the traffic congestion index before the traffic signal management and the traffic congestion index after the traffic signal management, the congestion management coefficient represents the influence degree quantification data of the traffic congestion index before the traffic signal management and the traffic congestion index after the traffic signal management on the traffic management effective index; The speed increase coefficient bias is obtained according to the relative relationship of the motor vehicle average speed increase coefficient and the preset speed increase coefficient acquired from the preset database, the speed increase coefficient bias represents the bias degree of the motor vehicle average speed increase coefficient and the preset speed increase coefficient; The traffic management effective index is obtained according to a congestion management coefficient, a deviation of a vehicle speed increasing coefficient, an accident reduction rate, a traffic signal adjustment time length, and a relative relationship of a traffic management weight obtained from a preset database. The traffic management weight includes an accident management weight, a vehicle speed management weight, and a signal lamp adjustment weight. 8.The AI-based intelligent security management method of claim 1, wherein: The specific process of determining whether to implement the emergency security strategy based on the traffic management effective index is as follows: ​ determining whether the traffic management effective index is less than a preset management effective threshold value obtained from a preset database; if the traffic management effective index is not less than the preset management effective threshold value obtained from the preset database, the emergency security strategy is not implemented; if the traffic management effective index is less than the preset management effective threshold value obtained from the preset database, the emergency security strategy is implemented. 9.The AI-based intelligent security management method of claim 8, wherein: The specific process of implementing the emergency security strategy is as follows: implementing the emergency security strategy means that patrol personnel scheduling is automatically performed based on historical traffic data, and the patrol personnel scheduling includes scheduling a number, a route, and a frequency of the patrol personnel; determining whether the traffic management effective index obtained after the emergency security strategy is implemented is less than the preset management effective threshold value obtained from the preset database; if the traffic management effective index obtained after the emergency security strategy is implemented is not less than the preset management effective threshold value obtained from the preset database, no feedback is performed; if the traffic management effective index obtained after the emergency security strategy is implemented is less than the preset management effective threshold value obtained from the preset database, feedback is performed.

Images