Artificial intelligence lane controller management system

Abstract

The invention discloses an artificial intelligence lane controller management system, and particularly relates to the technical field of traffic management. Comprising a lane controller management database, a traffic flow data acquisition module, a traffic flow data processing module, a lane traffic environment data acquisition module, a lane traffic environment data processing module, a lane controller management decision module, a lane control management effect evaluation module and a lane controller management man-machine interaction module. The traffic flow data acquisition module is used for acquiring first traffic flow influence data for managing canopy signal lamps from a lane controller database; the traffic flow data is analyzed through the artificial intelligence algorithm, the first influence index for managing the canopy signal lamp is obtained, and the lane controller can recognize the peak period and the valley period of the traffic flow, so that the timing scheme of the signal lamp is optimized, and the road traffic efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to an artificial intelligence lane controller management system. Background Art

[0002] Artificial intelligence technologies include robots, language recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc. The lane controller is a bridge connecting peripheral devices and lane computers, and is mainly used for equipment management and control of toll lanes, such as canopy lights, lane release lights, automatic barriers, fee displays, lane detectors, etc. With the continuous development of artificial intelligence technology and the growing demand for urban traffic, the artificial intelligence lane controller management system will play an increasingly important role in urban traffic management.

[0003] In the field of traffic management, especially under complex and changeable road conditions, efficient and accurate lane control and reasonable traffic light indication are crucial to ensure traffic safety and improve traffic efficiency. Traditional canopy signal light management systems mainly rely on two methods: timing management and induction management. Timing management changes the color of the signal light according to a preset schedule, which is suitable for scenes with relatively stable traffic flow. Induction management adjusts the timing of the signal light according to the real-time detected traffic flow to improve road traffic efficiency.

[0004] However, it still has some shortcomings in actual use. For example, the timing management method lacks flexibility and is difficult to cope with real-time changes in traffic flow. Although the induction management method can adjust the timing of traffic lights according to traffic flow, its detection range and accuracy are limited and it is easily affected by environmental factors. In addition, traditional lane controllers also have certain delays and errors in data transmission and command execution, which affects the real-time and accuracy of canopy signal light management. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an artificial intelligence lane controller management system to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an artificial intelligence lane controller management system, comprising:

[0007] Lane controller management database: Through sensor technology, traffic flow data is collected to obtain the lane controller management database;

[0008] Traffic flow data collection module: used to collect and manage the first traffic flow impact data of the canopy signal light from the lane controller database;

[0009] Traffic flow data processing module: processes the first traffic flow impact data through an artificial intelligence algorithm to obtain a first impact index for managing canopy signal lights;

[0010] Lane traffic environment data collection module: used to collect and manage the first traffic flow impact data of the canopy signal light from the lane controller database;

[0011] Lane traffic environment data processing module: processes the second environmental impact data through an artificial intelligence algorithm to obtain a second impact index for managing canopy signal lights;

[0012] Lane controller management decision module: Through artificial intelligence algorithm, the first influencing index and the second influencing index of the management of canopy signal lights are compared with the preset thresholds to obtain the time management strategy and lighting management strategy of the management of canopy signal lights;

[0013] Lane control management effect evaluation module: Through artificial intelligence algorithms, the control effect of canopy signal lights is evaluated to obtain canopy signal light control effect indicators;

[0014] Lane controller management human-computer interaction module: used to output the canopy signal light control effect index in the lane control management effect evaluation module to the management personnel information terminal.

[0015] Preferably, the first traffic flow impact data in the traffic flow data collection module includes the monitoring time period, the number of vehicles, the peak time and the average speed of vehicles.

[0016] Preferably, the traffic flow data processing in the traffic flow data processing module includes the following steps:

[0017] S1.1: Obtain traffic flow data from the lane controller database. First, use the timestamp monitoring technology to obtain the monitoring time period t_m. Then use the sensor technology to obtain the number of vehicles n1 passing through the time period t1. Then obtain the peak time t_h when vehicles pass through the canopy signal lights. Finally, use the sensor technology to obtain the number of vehicles n2 passing during the peak hours and the number of vehicles n3 passing per day. Therefore, the model of the traffic flow impact index is: Where Tfi represents the traffic flow impact index, and N represents the number of vehicles with saturated road traffic;

[0018] S1.2: Obtain vehicle driving status data from the lane controller database. During the monitoring period t_p, monitor the vehicle driving data through sensor technology, obtain the vehicle driving distance s, and obtain the average vehicle speed v1, v1 = s / t3, and obtain the real-time driving speed v. Therefore, the model of the vehicle driving status impact index is: Where Vdi represents the vehicle driving state impact index, n represents the number of real-time vehicle speed collections, and vi represents the driving speed of the ith collection;

[0019] S1.3: Based on S1 and S2, the first influencing indicator Tfv1 for managing awning signal lights is obtained through artificial intelligence algorithm, where Tfv = TFi × Vdi.

[0020] Preferably, the second environmental impact data in the lane traffic environment data acquisition module includes environmental visibility, vehicle driving road surface humidity and road surface temperature.

[0021] Preferably, the lane traffic environment data processing in the lane traffic environment data processing module includes the following steps:

[0022] S2.1: Obtain lane traffic environment data from the lane controller database, and monitor the environmental visibility vi, vehicle road humidity RH and road temperature T through sensor technology. Therefore, if the visibility value vi≥vi0, vi0 represents the visibility threshold, then the visibility influence coefficient VIF=1, otherwise VIF=vi / vi0; road slip index RSI, Where RH1 represents the standard deviation of road humidity, RH2 represents the average road humidity, T1 represents the standard deviation of road temperature, T2 represents the average road temperature, a1 and a2 represent the influencing factors of humidity and temperature respectively;

[0023] S2.2: Based on S2.1, the second influencing index Tfv2 for managing canopy traffic lights is obtained through an artificial intelligence algorithm, Tfv2=b1×VIF+b2×RSI, where b1 and b2 represent the weight coefficients of the visibility influence coefficient and the road slippery index, respectively, for example, b1=0.5, b2=0.5.

[0024] Preferably, the canopy signal light time management strategy in the lane controller management decision module: S3.1.1: manage the first influencing index Tfv1 of the canopy signal light according to S1.3, compare the first influencing index with the preset threshold value, and when Tfv1 exceeds the threshold value, obtain the exceeding rate Er, Er=(Tfv1-Tfv0) / Tfv0, where Tfv0 represents the threshold value; extract the historical control strategy from the lane controller database, and combine the historical control strategy and the real-time exceeding rate to obtain the green light display duration t4 of the canopy signal light, t4=t0(1+Er), where t0 represents the green light display duration based on the historical control strategy;

[0025] S3.1.2: Manage the first influencing indicator Tfv1 of the canopy signal light according to S1.3, compare the first influencing indicator with the preset threshold, and when Tfv1 is lower than the threshold, obtain the lower than rate Br, Br = (Tfv0-Tfv1) / Tfv0. If Br is within the normal range, the lane controller will maintain the current green light duration unchanged to ensure that the vehicle can pass through the toll station or intersection smoothly; if Br is not within the normal range, extract the historical control strategy from the lane controller database, and combine the historical control strategy and the real-time lower than rate to obtain the canopy signal light phase interval time t5, t5 = t(1-Br), where t represents the phase interval time based on the historical control strategy.

[0026] Preferably, the canopy signal light lighting management strategy in the lane controller management decision module: manage the second impact index Tfv2 of the canopy signal light according to S2.2, compare the second impact index with a preset threshold value, and obtain the canopy signal light lighting management strategy;

[0027] S3.2.1: Dual response to low visibility and slippery road surface: When Tfv2 exceeds the threshold, the excess ratio Em is obtained, Em = Tfv2 / Tfv3, where Tfv3 represents the threshold. If Em is within the normal range, the lane controller will maintain the current awning signal light brightness; if Em exceeds the upper limit of the normal range, the automatic adjustment mechanism of the lighting system is triggered, and the lane controller automatically increases the brightness of the awning light to the preset high brightness mode;

[0028] S3.2.2: Hierarchical lighting strategy: When Em exceeds the normal range, the historical control strategy is extracted from the lane controller database. The historical control strategy and the real-time exceeding ratio are integrated to adopt a hierarchical lighting strategy. The hierarchical lighting strategy model is: Di = Em-1, where Di represents the exceeding ratio index. The lighting brightness level Lb is matched according to the exceeding ratio index. B = b(Di, Lb), where B represents the lighting brightness of the canopy signal light when the exceeding ratio index is Di and the lighting brightness level is Lb.

[0029] Preferably, the lane control management effect evaluation in the lane control management effect evaluation module includes the following steps:

[0030] S4.1: The lane utilization index model is: Where Lui represents the lane utilization index, t_co represents the average occupancy time of the current lane, t_cc represents the current cycle length of the signal light, Tir represents the traffic flow improvement rate, which is obtained by monitoring the green light utilization rate before and after the canopy signal light. The green light utilization rate is obtained by the ratio of the number of vehicles passing through the green light time to the total green light time. At_co represents the average occupancy time of adjacent lanes.

[0031] S4.2: The light efficiency index model is: Where Lei represents the lighting efficiency index, Ali represents the average light intensity in the area covered by the canopy signal light, Nh represents the average energy consumption of the canopy signal light during operation, and Af represents the number of ambient light sensor adjustments;

[0032] S4.3: Based on the lane utilization index and the lighting efficiency index, the comprehensive index Ceci of the canopy signal light control effect is obtained, Ceci = w × Lui × Lei, where w represents the canopy signal light management adjustment factor.

[0033] Technical effects and advantages of the present invention:

[0034] 1. The present invention analyzes traffic flow data through artificial intelligence algorithms to obtain the first influencing index for managing canopy signal lights. The lane controller can identify the peak and valley hours of traffic flow, thereby optimizing the timing plan of signal lights. By real-time monitoring of vehicle speed data, it can evaluate whether the driving status of vehicles is smooth, reduce congestion during peak hours, and improve road traffic efficiency and the flexibility of canopy signal light management;

[0035] 2. The present invention uses artificial intelligence algorithms to process lane traffic environment data to obtain the second influencing index for managing canopy signal lights. The visibility impact coefficient and the road slipperiness index directly affect the driving safety of vehicles and the smoothness of traffic flow. The lane controller can timely adjust the signal light control strategy by monitoring the changes of these indicators in real time to cope with the impact of bad weather or road conditions on traffic, thereby improving the real-time and accuracy of canopy signal light management.

[0036] 3. The present invention evaluates the effect of lane control management on canopy signal lights through artificial intelligence algorithms, and obtains comprehensive indicators of canopy signal light control effects, which helps lane controllers to achieve automated control of canopy signal lights by integrating traffic flow data and lane traffic environment data, thereby reducing the need for manual intervention and improving management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1As shown, the present invention provides an artificial intelligence lane controller management system, including a lane controller management database, a traffic flow data acquisition module, a traffic flow data processing module, a lane traffic environment data acquisition module, a lane traffic environment data processing module, a lane controller management decision module, a lane control management effect evaluation module and a lane controller management human-computer interaction module.

[0040] The lane controller management database is respectively connected to the traffic flow data acquisition module and the lane traffic environment data acquisition module, the traffic flow data processing module is respectively connected to the traffic flow data acquisition module and the lane controller management decision module, the lane traffic environment data processing module is respectively connected to the lane traffic environment data acquisition module and the lane controller management decision module, and the lane control management effect evaluation module is respectively connected to the lane controller management decision module and the lane controller management human-computer interaction module.

[0041] Lane controller management database: Through sensor technology, traffic flow data is collected to obtain the lane controller management database;

[0042] It should be specifically explained in this embodiment that the lane controller management database is connected to all modules in the system, and is used to receive and store data from each module and update the data in real time.

[0043] Traffic flow data collection module: used to collect the first traffic flow impact data for managing the canopy signal lights from the lane controller database, the first traffic flow impact data including the monitoring time period, the number of vehicles, the peak time and the average speed of the vehicles;

[0044] Traffic flow data processing module: Processing the first traffic flow impact data through an artificial intelligence algorithm to obtain a first impact index for managing canopy signal lights. Traffic flow data processing includes the following steps:

[0045] S1.1: Obtain traffic flow data from the lane controller database. First, obtain the monitoring time period t_m (such as hours, days, and months) through timestamp monitoring technology. Then, obtain the number of vehicles n1 passing through the time period t1 through sensor technology. Then, obtain the peak time t_h when vehicles pass through the canopy signal lights. Finally, obtain the number of vehicles n2 passing during the peak hours and the number of vehicles n3 passing through the day through sensor technology. Therefore, the model of the traffic flow impact index is: Where Tfi represents the traffic flow impact index, N represents the number of vehicles with saturated road traffic, and the peak duration is obtained by sampling the number of vehicles passing through the canopy signal lights in multiple time periods based on historical data through sensor technology, and sorting the number of vehicles passing through each time period by size, and finally obtaining the time period with the largest number of vehicles passing through as the peak duration;

[0046] S1.2: Obtain vehicle driving status data from the lane controller database. During the monitoring period t_p, monitor the vehicle driving data through sensor technology, obtain the vehicle driving distance s, and obtain the average vehicle speed v1, v1 = s / t3, and obtain the real-time driving speed v. Therefore, the model of the vehicle driving status impact index is: Where Vdi represents the vehicle driving state impact index, n represents the number of real-time vehicle speed collections, and v i represents the driving speed of the ith collection;

[0047] S1.3: Based on S1 and S2, the first influencing index Tfv1 of the management of the canopy signal light is obtained through the artificial intelligence algorithm, where Tfv = TFi × Vdi;

[0048] Lane traffic environment data collection module: used to collect and manage the first traffic flow impact data of the canopy signal light from the lane controller database, and the second environment impact data includes environmental visibility, vehicle driving road humidity and road temperature;

[0049] Lane traffic environment data processing module: the second environmental impact data is processed by an artificial intelligence algorithm to obtain a second impact index for managing the canopy signal light. The lane traffic environment data processing includes the following steps:

[0050] S2.1: Obtain lane traffic environment data from the lane controller database, and monitor the environment visibility vi (such as less than 500 meters indicates low visibility), vehicle road humidity RH and road temperature T through sensor technology. Therefore, if the visibility value vi≥vi0, vi0 represents the visibility threshold, then the visibility influence coefficient VIF=1, otherwise VIF=vi / vi0; road slip index RSI, Where RH1 represents the standard deviation of road humidity, RH2 represents the average road humidity, T1 represents the standard deviation of road temperature, T2 represents the average road temperature, a1 and a2 represent the influencing factors of humidity and temperature respectively;

[0051] S2.2: Based on S2.1, the second influencing index Tfv2 for managing canopy traffic lights is obtained through an artificial intelligence algorithm, Tfv2 = b1 × VIF + b2 × RSI, where b1 and b2 represent the weight coefficients of the visibility influence coefficient and the road slippery index, respectively;

[0052] Lane controller management decision module: Through artificial intelligence algorithm, the first influencing index and the second influencing index of the management of the canopy signal light are compared with the preset threshold value respectively, and the time management strategy and lighting management strategy of the management of the canopy signal light are obtained. The lane controller management decision model includes the following steps;

[0053] S3.1: Canopy signal light time management strategy:

[0054] S3.1.1: Manage the first influencing index Tfv1 of the canopy signal light according to S1.3, compare the first influencing index with the preset threshold value, and when Tfv1 exceeds the threshold value, obtain the exceeding rate Er, Er=(Tfv1-Tfv0) / Tfv0, where Tfv0 represents the threshold value; extract the historical control strategy from the lane controller database, and combine the historical control strategy and the real-time exceeding rate to obtain the green light display time t4 of the canopy signal light, t4=t0(1+Er), where t0 represents the green light display time based on the historical control strategy, thereby allowing more vehicles to enter the toll area by extending the green light time of the current toll lane;

[0055] S3.1.2: According to S1.3, the first influencing index Tfv1 of the canopy signal light is managed, and the first influencing index is compared with the preset threshold value. When Tfv1 is lower than the threshold value, the lower than rate Br is obtained, Br = (Tfv0-Tfv1) / Tfv0. If Br is within the normal range, the lane controller will maintain the current green light duration unchanged to ensure that the vehicle can smoothly pass through the toll station or intersection; if Br is not within the normal range, the historical control strategy is extracted from the lane controller database, and the historical control strategy and the real-time lower than rate are combined to obtain the canopy signal light phase interval time t5, t5 = t(1-Br), where t represents the phase interval time based on the historical control strategy, so that when the traffic flow is normal, the lane controller will try to avoid unnecessary signal light switching to reduce interference with traffic flow;

[0056] S3.2: Awning signal light lighting management strategy: manage the second impact index Tfv2 of the awning signal light according to S2.2, compare the second impact index with the preset threshold value, and obtain the awning signal light lighting management strategy;

[0057] S3.2.1: Dual response to low visibility and slippery road surface: When Tfv2 exceeds the threshold, the excess ratio Em is obtained, Em = Tfv2 / Tfv3, where Tfv3 represents the threshold value. If Em is within the normal range, the lane controller will maintain the current awning signal light brightness; if Em exceeds the upper limit of the normal range, that is, VIF indicates that visibility is low and RSI shows that the road surface is slippery, the automatic adjustment mechanism of the lighting system is triggered, and the lane controller automatically increases the brightness of the awning light to the preset high brightness mode to increase the illumination range and intensity of the light, so that the driver can see the road ahead and the surrounding environment more clearly;

[0058] S3.2.2: Hierarchical lighting strategy: When Em exceeds the normal range, the historical control strategy is extracted from the lane controller database, and the hierarchical lighting strategy is adopted by integrating the historical control strategy and the real-time exceeding ratio. The hierarchical lighting strategy model is: Di = Em-1, where Di represents the exceeding ratio index, and the lighting brightness level Lb is matched according to the exceeding ratio index, B = b(Di, Lb), where B represents the lighting brightness of the canopy signal light when the exceeding ratio index is Di and the lighting brightness level is Lb. For example, when Tfv2 is at a low level, basic lighting is adopted; as the Tfv2 value increases, the lighting intensity is gradually increased to cope with more severe driving conditions;

[0059] What needs to be specifically explained in this embodiment is that the lane controller is connected to the canopy signal light through the I / O interface to realize the control of the signal light. These interfaces can transmit control signals to the signal light and receive status feedback of the signal light.

[0060] Lane control management effect evaluation module: Through artificial intelligence algorithm, the control effect of canopy signal lights is evaluated to obtain comprehensive indicators of canopy signal light control effect. The lane control management effect evaluation includes the following steps;

[0061] S4.1: By using artificial intelligence algorithms to analyze lane utilization and signal adjustment effects, the lane controller can identify which lanes need more green light time and which lanes may be too idle by comparing the average occupancy time of the current lane and the adjacent lanes. Based on the lane utilization and traffic flow improvement rate, the lane controller can dynamically adjust the cycle length of the signal light to ensure that traffic flow can be efficiently managed in different time periods. Therefore, the lane utilization index model is: Where Lui represents the lane utilization index, t_co represents the average occupancy time of the current lane, t_cc represents the current cycle length of the signal light, Tir represents the traffic flow improvement rate, which is obtained by monitoring the green light utilization rate before and after the canopy signal light. The green light utilization rate is obtained by the ratio of the number of vehicles passing through the green light time to the total green light time. At_co represents the average occupancy time of adjacent lanes.

[0062] S4.2: Through artificial intelligence algorithms, the lane controller can monitor and analyze the lighting efficiency and energy saving of the canopy lights. It can evaluate the energy efficiency of the canopy lights while providing sufficient lighting. By controlling the light intensity, the lane controller can understand the lighting conditions in the area covered by the canopy lights. By controlling the average energy consumption of the canopy lights during operation, the lane controller can use this data to evaluate the energy consumption costs under different lighting strategies and select the most energy-saving solution. Therefore, the lighting efficiency index model is: Where Lei represents the lighting efficiency index, Ali represents the average light intensity in the area covered by the canopy signal light, Nh represents the average energy consumption of the canopy signal light during operation, and Af represents the number of ambient light sensor adjustments;

[0063] S4.3: Based on the lane utilization index in S4.1 and the lighting efficiency index in S4.2, the comprehensive index of canopy signal light control effect Ceci is obtained, Ceci = w × Lui × Lei, where w represents the canopy signal light management adjustment factor, which can comprehensively reflect the effect index of canopy signal light control management based on multiple factors such as traffic flow data and lane traffic environment data;

[0064] Lane controller management human-computer interaction module: used to output the comprehensive indicators of canopy signal light control effect in the lane control management effect evaluation module to the management personnel information terminal, so that the administrator can quickly grasp the effect of the lane controller in managing the canopy signal light, evaluate the effect of existing traffic management measures, identify existing problems and deficiencies, and then optimize the traffic management process and improve management efficiency and service level.

[0065] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0066] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An artificial intelligence lane controller management system, characterized in that: include: Lane controller management database: Through sensor technology, traffic flow data is collected to obtain the lane controller management database; Traffic flow data collection module: used to collect and manage the first traffic flow impact data of the canopy signal light from the lane controller database; Traffic flow data processing module: processes the first traffic flow impact data through an artificial intelligence algorithm to obtain a first impact index for managing canopy signal lights; Lane traffic environment data acquisition module: used to collect and manage the second environmental impact data of the canopy signal light from the lane controller database; Lane traffic environment data processing module: processes the second environmental impact data through an artificial intelligence algorithm to obtain a second impact index for managing canopy signal lights; Lane controller management decision module: Through artificial intelligence algorithm, the first influencing index and the second influencing index of the management of canopy signal lights are compared with the preset thresholds to obtain the time management strategy and lighting management strategy of the management of canopy signal lights; Lane control management effect evaluation module: Through artificial intelligence algorithms, the control effect of canopy signal lights is evaluated to obtain canopy signal light control effect indicators; Lane controller management human-computer interaction module: used to output the canopy signal light control effect index in the lane control management effect evaluation module to the management personnel information terminal.

2. The artificial intelligence lane controller management system according to claim 1, characterized in that: The first traffic flow impact data in the traffic flow data collection module includes a monitoring time period, the number of vehicles, the peak time, and the average speed of vehicles.

3. The artificial intelligence lane controller management system according to claim 1, characterized in that: The traffic flow data processing in the traffic flow data processing module includes the following steps: S1.1: Obtain traffic flow data from the lane controller database. First, use the timestamp monitoring technology to obtain the monitoring time period t_m. Then use the sensor technology to obtain the number of vehicles n1 passing through the time period t1. Then obtain the peak time t_h when vehicles pass through the canopy signal lights. Finally, use the sensor technology to obtain the number of vehicles n2 passing during the peak hours and the number of vehicles n3 passing per day. Therefore, the model of the traffic flow impact index is: Where Tfi represents the traffic flow impact index, and N represents the number of vehicles with saturated road traffic; S1.2: Obtain vehicle driving status data from the lane controller database. During the monitoring period t_p, monitor the vehicle driving data through sensor technology, obtain the vehicle driving distance s, and obtain the average vehicle speed v1, v1 = s / t3, and obtain the real-time driving speed v. Therefore, the model of the vehicle driving status impact index is: Where Vdi represents the vehicle driving state impact index, n represents the number of real-time vehicle speed collections, and v i represents the driving speed of the ith collection; S1.3: Based on S1 and S2, the first influencing indicator Tfv1 for managing awning signal lights is obtained through artificial intelligence algorithm, where Tfv = TFi × Vdi.

4. The artificial intelligence lane controller management system according to claim 1, characterized in that: The second environmental impact data in the lane traffic environment data acquisition module includes environmental visibility, vehicle driving road surface humidity and road surface temperature.

5. The artificial intelligence lane controller management system according to claim 1, characterized in that: The lane traffic environment data processing in the lane traffic environment data processing module includes the following steps: S2.1: Obtain lane traffic environment data from the lane controller database, and monitor the environmental visibility vi, vehicle road humidity RH and road temperature T through sensor technology. Therefore, if the visibility value vi≥vi0, vi0 represents the visibility threshold, then the visibility influence coefficient VIF=1, otherwise VIF=vi / vi0; road slip index RSI, Where RH1 represents the standard deviation of road humidity, RH2 represents the average road humidity, T1 represents the standard deviation of road temperature, T2 represents the average road temperature, a1 and a2 represent the influencing factors of humidity and temperature respectively; S2.2: Based on S2.1, the second influencing index Tfv2 for managing canopy traffic lights is obtained through an artificial intelligence algorithm, Tfv2 = b1 × VIF + b2 × RSI, where b1 and b2 represent the weight coefficients of the visibility influence coefficient and the road slippery index, respectively.

6. The artificial intelligence lane controller management system according to claim 1, characterized in that: The time management strategy of the canopy signal light in the lane controller management decision module: S3.1.1: manage the first influencing indicator Tfv1 of the canopy signal light according to S1.3, compare the first influencing indicator with the preset threshold, and when Tfv1 exceeds the threshold, obtain the exceeding rate Er, Er = (Tfv1-Tfv0) / Tfv0, where Tfv0 represents the threshold; extract the historical control strategy from the lane controller database, and combine the historical control strategy and the real-time exceeding rate to obtain the green light display time t4 of the canopy signal light, t4 = t0(1+Er), where t0 represents the green light display time based on the historical control strategy; S3.1.2: Manage the first influencing indicator Tfv1 of the canopy signal light according to S1.3, compare the first influencing indicator with the preset threshold, and when Tfv1 is lower than the threshold, obtain the lower than rate Br, Br = (Tfv0-Tfv1) / Tfv0. If Br is within the normal range, the lane controller will maintain the current green light duration unchanged to ensure that the vehicle can pass through the toll station or intersection smoothly; if Br is not within the normal range, extract the historical control strategy from the lane controller database, and combine the historical control strategy and the real-time lower than rate to obtain the canopy signal light phase interval time t5, t5 = t(1-Br), where t represents the phase interval time based on the historical control strategy.

7. The artificial intelligence lane controller management system according to claim 1, characterized in that: The lighting management strategy of the canopy signal light in the lane controller management decision module: manage the second impact index Tfv2 of the canopy signal light according to S2.2, compare the second impact index with the preset threshold value, and obtain the lighting management strategy of the canopy signal light; S3.2.1: Dual response to low visibility and slippery road surface: When Tfv2 exceeds the threshold, the excess ratio Em is obtained, Em = Tfv2 / Tfv3, where Tfv3 represents the threshold. If Em is within the normal range, the lane controller will maintain the current awning signal light brightness; if Em exceeds the upper limit of the normal range, the automatic adjustment mechanism of the lighting system is triggered, and the lane controller automatically increases the brightness of the awning light to the preset high brightness mode; S3.2.2: Hierarchical lighting strategy: When Em exceeds the normal range, the historical control strategy is extracted from the lane controller database. The historical control strategy and the real-time exceeding ratio are integrated to adopt a hierarchical lighting strategy. The hierarchical lighting strategy model is: Di = Em-1, where Di represents the exceeding ratio index. The lighting brightness level Lb is matched according to the exceeding ratio index. B = b(Di, Lb), where B represents the lighting brightness of the canopy signal light when the exceeding ratio index is Di and the lighting brightness level is Lb.

8. The artificial intelligence lane controller management system according to claim 1, characterized in that: The lane control management effect evaluation in the lane control management effect evaluation module includes the following steps: S4.1: The lane utilization index model is: Where Lui represents the lane utilization index, t_co represents the average occupancy time of the current lane, t_cc represents the current cycle length of the signal light, Tir represents the traffic flow improvement rate, which is obtained by monitoring the green light utilization rate before and after the canopy signal light. The green light utilization rate is obtained by the ratio of the number of vehicles passing through the green light time to the total green light time. At_co represents the average occupancy time of adjacent lanes. S4.2: The light efficiency index model is: Where Lei represents the lighting efficiency index, Ali represents the average light intensity in the area covered by the canopy signal light, Nh represents the average energy consumption of the canopy signal light during operation, and Af represents the number of ambient light sensor adjustments; S4.3: Based on the lane utilization index and the lighting efficiency index, the comprehensive index Ceci of the canopy signal light control effect is obtained, Ceci = w × Lui × Lei, where w represents the canopy signal light management adjustment factor.

Images