Road traffic signal control system and method

Abstract

The invention discloses a road traffic signal control system and method, and the method comprises the steps: collecting real-time data through a sensor, a camera and a geomagnetic device, combining historical data with emergency analysis, and predicting a flow mode and a change trend; green light time distribution is dynamically optimized, a fixed timing, inductive and adaptive control strategy is adopted, and traffic light duration and priority adjustment is achieved; through regional cooperation and linkage control, green wave bands and branch intersection red light optimization are set, and peak period traffic signals are intelligently dispatched. A machine learning model is used to predict a flow peak value, environment and accident detection data are combined, a signal lamp period is dynamically adjusted, vehicle waiting time, traffic efficiency, carbon emission and traffic satisfaction are evaluated, and a traffic control strategy is comprehensively optimized. According to the road traffic signal control system and method, the traffic flow in different time periods is predicted by adopting the flow prediction model based on big data analysis and machine learning, and the signal period is adjusted in advance.

Description

Technical Field

[0001] The present invention belongs to the field of road traffic signal control, and in particular relates to a road traffic signal control system and method. Background Art

[0002] A road traffic signal control is an intelligent system used to regulate and manage road traffic flow. Its main function is to control the flow of vehicles and pedestrians in different directions through traffic lights (such as red and green lights) to ensure the safety and smoothness of traffic. This system adjusts the changes in traffic signals through perception, decision-making and execution, thereby optimizing traffic flow and preventing accidents. Traffic lights are the most intuitive part of the system, usually including three colors: red, yellow and green. Different combinations are used to adjust the traffic status of vehicles, pedestrians or non-motor vehicles. The signal controller is the brain of the system. It is responsible for controlling and switching the cycle and timing of traffic lights. Traditional The old controllers are based on time periods, while modern controllers often support more intelligent scheduling, such as dynamic adjustment based on traffic flow, real-time data, etc., through reasonable signal timing and flow analysis, to avoid long signal waiting, reduce congestion at intersections, reasonably set traffic light cycles, avoid traffic accidents, ensure the safety of vehicles, pedestrians and non-motor vehicles, through intelligent scheduling, according to the switching of signal lights and changes in traffic flow, optimize traffic flow, make the use of road resources more efficient, through data collection and real-time monitoring, traffic management departments can timely understand road conditions and make effective emergency responses.

[0003] However, although existing road traffic signal control systems have played a role in optimizing traffic flow and improving safety in many aspects, they also have some defects and limitations. Although some advanced traffic signal control systems have adopted adaptive control (such as adaptive signal switching based on traffic flow), there are still many systems that lack true self-learning capabilities and cannot automatically optimize traffic flow based on long-term data. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a road traffic signal control system and method, which adopts a traffic prediction model, based on big data analysis and machine learning, to predict traffic flow in different time periods and adjust the signal cycle in advance.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] A road traffic signal control system, comprising:

[0007] The data acquisition module is used to collect real-time road traffic data through geomagnetic sensors, video surveillance, radar sensors, and meteorological monitoring equipment arranged on the road;

[0008] The data processing module is used to analyze and process the collected real-time traffic data using intelligent machine learning and deep learning algorithms, and dynamically predict and adjust the switching cycle and time allocation of traffic lights;

[0009] Traffic flow prediction module, which is used to intelligently analyze traffic flow trends during peak hours, holidays and special events based on historical traffic flow data and real-time data, and optimize the signal light cycle timing plan in advance;

[0010] Traffic light control and execution module, used to communicate traffic lights with the central control system and local traffic monitoring platform in real time, dynamically adjust traffic light cycles according to real-time collected and processed data, and control light switching duration according to real-time detected traffic flow and queue length;

[0011] The accident response and elimination module is used to detect traffic accidents through video surveillance and sensors. When an accident is detected, the system automatically adjusts the traffic light cycle in the affected area;

[0012] The user participation module is used to receive real-time road traffic conditions such as traffic flow, traffic light status, and accident information fed back by users through the citizen-side application App. The system dynamically optimizes the traffic light control strategy based on user feedback information.

[0013] A road traffic signal control method, comprising:

[0014] Collect real-time data through sensors, cameras, and geomagnetic equipment, including environmental data, number of vehicles, driving speed, fleet length, pedestrian and non-motor vehicle flow information, use historical traffic flow data and real-time collected data, combined with emergency analysis, to predict traffic patterns and traffic change trends;

[0015] According to real-time traffic conditions, artificial intelligence algorithms are used to optimize green light time allocation. Fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, green wave belts are set on main roads during peak hours.

[0016] Intelligently dispatch traffic signals according to the real-time traffic changes during peak hours. If the green light time expires but the rear vehicle has not passed, the green light time will be automatically extended. Combined with real-time and historical data, the green light time and cycle allocation will be dynamically adjusted.

[0017] Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are controlled in a coordinated manner, and the duration of red lights at branch intersections is dynamically adjusted according to the traffic flow conditions of the main roads;

[0018] Based on historical data and real-time traffic information, machine learning models are used to predict future traffic peaks and changing trends, and traffic signal control strategies are optimized through perception of environmental data information collected by sensors;

[0019] Accidents are detected by camera equipment, and the system's intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, it evaluates indicators including average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction.

[0020] As a preferred method, real-time data including environmental data, number of vehicles, driving speed, convoy length, pedestrian and non-motor vehicle flow information are collected through sensors, cameras, and geomagnetic equipment, and historical traffic flow data and real-time collected data are used in combination with emergency analysis to predict traffic patterns and traffic change trends:

[0021] Integrate real-time data and historical data collected by geomagnetic, camera, radar sensor, traffic camera, and environmental sensor monitoring equipment;

[0022] The obtained information on convoy length, vehicle speed, traffic density, and number of pedestrians is used to capture the current traffic conditions and future change trends of the road section;

[0023] Combined with real-time monitoring data, the impact of emergencies on traffic flow is analyzed, and traffic changes are predicted in advance. Combined with flow prediction and signal control systems, reinforcement learning is used to optimize traffic signal scheduling strategies.

[0024] As a preferred method, according to the real-time traffic conditions, artificial intelligence algorithms are used to optimize the green light time allocation, and fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, the method of setting green wave bands on main roads during peak hours is as follows:

[0025] Through various sensors and traffic flow monitoring equipment, traffic condition data of road sections can be collected in real time;

[0026] Through deep neural networks, the system uses intelligent algorithms to learn traffic flow patterns and changing trends, predict traffic conditions on different road sections, optimize traffic light durations based on predictions, dynamically adjust signal timings based on prediction results, and automatically adjust green and red light times.

[0027] Based on the real-time traffic conditions and flow forecasts of different road sections, the intelligent transportation system dynamically adjusts the signal timing of the entire traffic network and generates green wave belts on the main roads;

[0028] By coordinating the traffic lights at multiple intersections and setting the signal cycle, vehicles can maintain green signals when passing through multiple intersections during peak hours.

[0029] As a preferred method, according to the real-time traffic changes during peak hours, intelligently dispatch traffic signals, automatically extend the green light time when the green light time ends but the rear vehicle has not passed, and dynamically adjust the green light time and cycle allocation method by combining real-time data and historical data:

[0030] Based on the adaptive control algorithm, the green light time, cycle and timing strategy are dynamically adjusted. When the system detects that the green light is about to end, if there are still vehicles that have not passed the end of the intersection, the system will automatically extend the green light time according to the real-time traffic flow;

[0031] The signal timing is continuously adjusted according to the changes in real-time traffic flow, and the model is updated through feedback information.

[0032] As a preferred method, the signal lights at multiple intersections are controlled in linkage through a communication network and a regional traffic control algorithm, and the red light duration of the branch intersection is dynamically adjusted according to the traffic flow conditions of the main road:

[0033] Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment;

[0034] By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing;

[0035] By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections;

[0036] Continuously optimize signal control strategies through interaction with traffic flow.

[0037] As a preferred method, based on historical data and real-time traffic information, a machine learning model is used to predict future traffic peaks and change trends, and the method of perceiving and optimizing the traffic signal control strategy through environmental data information collected by sensors is as follows:

[0038] Through historical data and real-time traffic data, historical data includes long-term traffic flow patterns, common peak hours, and holiday traffic change data, and real-time traffic information includes real-time monitoring of traffic density, vehicle speed, and traffic event information through sensors. The system's prediction model estimates upcoming traffic changes and upcoming peak hours;

[0039] Through regression analysis, time series models, reinforcement learning, and ensemble learning machine learning techniques, based on training and prediction of real-time and historical traffic data, we can adjust traffic forecasts and optimize signal control decisions in a dynamically changing traffic environment;

[0040] Through meteorological sensors, vehicle-mounted sensors, and environmental temperature and humidity monitors, the system senses changes in the environment and automatically adjusts traffic signal control strategies;

[0041] By continuously collecting traffic data and training models, the system learns to adapt to different traffic flow patterns and complex traffic environments. Based on real-time traffic monitoring data, the system senses changes in traffic flow and adjusts the traffic light control strategy.

[0042] As a preferred method, the camera equipment is used to detect the occurrence of the accident, and the system intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, the method for evaluating indicators including average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction is as follows:

[0043] Computer vision algorithms are used to analyze images in real time to detect traffic accidents or obstacles. When an accident is confirmed, the system automatically adjusts the signal light cycle at surrounding intersections based on the location of the accident, by lengthening the green light time of other roads, reducing the signal green light time of the accident section, or re-adjusting the route to avoid the traffic in the accident area.

[0044] Combining historical data with real-time data, the system predicts changes in traffic flow after an accident and automatically adjusts signal light cycles and traffic guidance strategies;

[0045] Average vehicle waiting time Based on real-time traffic data and signal light timing, the system calculates the average waiting time for each vehicle in real time;

[0046] The traffic efficiency of the intersection is evaluated by calculating the number of vehicles passing through per unit time, speed, and flow rate;

[0047] By monitoring the speed, waiting time and passing time of vehicles in real time, carbon emissions are estimated based on vehicle type and engine efficiency;

[0048] Through camera monitoring and sensor feedback, we can understand the waiting time, crossing time and traffic density of pedestrians and non-motor vehicles, and evaluate their satisfaction through questionnaire surveys, public feedback and other data;

[0049] Through real-time monitoring and evaluation of the above-mentioned multiple indicators, the system makes adaptive adjustments. Based on the comparison of historical data and feedback from real-time traffic, the system performs optimization of signal timing, event response mechanism, and multi-objective optimization operations.

[0050] Another technical problem to be solved by the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a road traffic signal control system and method as described above is implemented.

[0051] Another technical problem to be solved by the present invention is to provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, a road traffic signal control system and method are implemented.

[0052] The beneficial effects of the present invention are:

[0053] Through real-time data collection from sensors, cameras, geomagnetic equipment, etc., combined with historical data analysis, it is possible to accurately predict flow patterns and traffic trends, thereby predicting traffic bottlenecks in advance and avoiding excessive congestion. Artificial intelligence algorithms optimize green light time allocation based on real-time data to avoid ineffective waiting due to unreasonable signal light timing, thereby improving traffic efficiency. During peak hours or special circumstances, the system can automatically extend the green light time if the rear vehicle has not yet passed, ensuring smooth flow and reducing the time wasted by drivers due to long waiting times at red lights. During peak hours, the system can improve traffic fluidity through regional collaborative optimization and the setting of green wave belts on main roads, making the main roads Vehicles on the road can pass smoothly and reduce congestion. This method of dynamically adjusting the traffic light cycle can effectively guide the traffic at each intersection and avoid traffic jams caused by uncoordinated traffic lights. Through the communication network and regional traffic control algorithm, the system can control the traffic lights at multiple intersections in a linked manner, and adjust the traffic light duration at the branch intersection according to the flow conditions of the main road to avoid unnecessary traffic waiting, thereby reducing the overall traffic flow pressure; traffic accidents are detected by camera equipment. Once an accident occurs, the system can immediately identify it and automatically adjust the traffic light cycle in the accident area through intelligent algorithms, reducing secondary traffic congestion and safety hazards after the accident. This method based on The dynamic adjustment mechanism of accident response can quickly restore traffic order and reduce the chain reaction caused by accidents; by combining historical data with real-time monitoring, the system can more accurately evaluate the changing trend of traffic flow and the impact of emergencies, and adjust the timing of traffic lights in a timely manner to ensure that the impact of various emergencies on traffic is minimized; by dynamically optimizing traffic light control, the idling time of vehicles is reduced, especially in traffic-intensive areas, a large number of vehicles are prevented from staying at red lights for a long time, and the carbon emissions of vehicles are reduced; combined with traffic flow monitoring, the system can reasonably allocate green light time and cycle, reduce traffic congestion during high-emission periods, and promote a more environmentally friendly urban traffic environment. Pedestrian traffic optimization: the system can ensure the safety and smoothness of pedestrian and non-motor vehicle traffic without affecting the traffic flow of the main roads, and promote low-carbon travel. In addition to vehicle traffic, the system also takes into account the traffic needs of pedestrians and non-motor vehicles. By adjusting the timing of traffic lights, it ensures the safety of non-motor vehicles and pedestrians, reduces excessive waiting time, and improves the convenience and satisfaction of overall travel. Based on the perception optimization of environmental data information, the system can understand the road conditions and weather changes (such as haze, rain and snow, etc.) in real time, and adjust the signal control strategy according to these changes to ensure that traffic signals can meet the needs of safety and traffic in bad weather, further improving the user experience.During peak traffic hours, the system can intelligently predict the changing trend of future traffic flow and dynamically adjust the time allocation of traffic lights to avoid unreasonable signal timing when traffic surges, thereby avoiding traffic congestion. The system not only predicts traffic based on historical data, but also responds to real-time emergencies, such as accidents, bad weather or traffic changes caused by major events, and adjusts the timing of traffic lights in a timely manner; through the prediction of future traffic peaks and changing trends by machine learning models, the system can provide intelligent decision-making support, respond to possible traffic peaks or traffic events in advance, provide scientific data basis for traffic managers, optimize traffic light control strategies, and use historical data and real-time collected data. The system can not only respond to current traffic conditions, but also provide traffic flow optimization solutions through long-term data analysis to reduce invalid delays and resource waste in traffic flow. ; BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 The present invention is a schematic diagram of a road traffic signal control system flow. DETAILED DESCRIPTION

[0055] The principles and features of the present invention are described below, and the examples are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention is described more specifically by way of example in the following paragraphs. According to the following description and claims, the advantages and features of the present invention will become clearer.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0057] Example

[0058] See also Figure 1 As shown, a road traffic signal control system includes:

[0059] The data acquisition module is used to collect real-time road traffic data through geomagnetic sensors, video surveillance, radar sensors, and meteorological monitoring equipment arranged on the road;

[0060] The data processing module is used to analyze and process the collected real-time traffic data using intelligent machine learning and deep learning algorithms, and dynamically predict and adjust the switching cycle and time allocation of traffic lights;

[0061] Traffic flow prediction module, which is used to intelligently analyze traffic flow trends during peak hours, holidays and special events based on historical traffic flow data and real-time data, and optimize the signal light cycle timing plan in advance;

[0062] Traffic light control and execution module, used to communicate traffic lights with the central control system and local traffic monitoring platform in real time, dynamically adjust traffic light cycles according to real-time collected and processed data, and control light switching duration according to real-time detected traffic flow and queue length;

[0063] The accident response and elimination module is used to detect traffic accidents through video surveillance and sensors. When an accident is detected, the system automatically adjusts the traffic light cycle in the affected area;

[0064] The user participation module is used to receive real-time road traffic conditions such as traffic flow, traffic light status, and accident information fed back by users through the citizen-side application App. The system dynamically optimizes the traffic light control strategy based on user feedback information.

[0065] By dynamically predicting traffic flow and adjusting the signal light cycle, the system can achieve the optimal timing of traffic lights, avoid ineffective waiting during peak hours or traffic jams, reduce vehicle queuing and idling time, and thus improve traffic efficiency. Based on the analysis of historical traffic data and real-time data, the system can accurately predict traffic trends during peak hours, holidays, and special events, thereby optimizing the timing of traffic lights in advance and avoiding congestion caused by sudden increases in traffic flow. The system monitors traffic conditions in real time through video surveillance and sensors. Once a traffic accident occurs, the system can quickly identify and automatically adjust the signal light cycle, quickly divert traffic in the accident area, and reduce subsequent secondary congestion and safety hazards. Through machine learning and deep learning, the system can extract patterns and trends from a large amount of historical data and real-time traffic data to achieve intelligent traffic signal control. This automated adjustment process not only improves the efficiency of traffic management, but also reduces errors caused by human intervention. Through real-time data and traffic forecasts, the system can dynamically adjust the signal light timing scheme according to different traffic flow changes, weather conditions and special events (such as holidays, large-scale events, etc.), ensuring the flexibility and adaptability of traffic management. By optimizing traffic signal timing, reducing vehicle idling and invalid queuing time, it helps to reduce vehicle fuel consumption and carbon emissions, and supports low-carbon and environmentally friendly traffic management methods. Citizens can feedback traffic flow, signal light status and accident information through the App, which can make traffic management closer to the actual situation. The system dynamically optimizes the signal light control strategy based on these feedbacks, further improving the efficiency of traffic flow and the adaptability of traffic conditions. By providing real-time traffic information, users can better understand the current road conditions, help drivers make better travel decisions, and at the same time enhance the public's trust in the traffic management system. Through real-time communication with the central control system and the local traffic monitoring platform, the system can realize the coordinated control of regional or inter-city traffic lights and improve the traffic efficiency of the entire traffic network. The system is highly scalable and can be upgraded and optimized with the growth of traffic demand and technological progress, supporting more types of traffic data and control strategies.

[0066] A road traffic signal control method, comprising:

[0067] Collect real-time data through sensors, cameras, and geomagnetic equipment, including environmental data, number of vehicles, driving speed, fleet length, pedestrian and non-motor vehicle flow information, use historical traffic flow data and real-time collected data, combined with emergency analysis, to predict traffic patterns and traffic change trends;

[0068] According to real-time traffic conditions, artificial intelligence algorithms are used to optimize green light time allocation. Fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, green wave belts are set on main roads during peak hours.

[0069] Intelligently dispatch traffic signals according to the real-time traffic changes during peak hours. If the green light time expires but the rear vehicle has not passed, the green light time will be automatically extended. Combined with real-time and historical data, the green light time and cycle allocation will be dynamically adjusted.

[0070] Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are controlled in a coordinated manner, and the duration of red lights at branch intersections is dynamically adjusted according to the traffic flow conditions of the main roads;

[0071] Based on historical data and real-time traffic information, machine learning models are used to predict future traffic peaks and changing trends, and traffic signal control strategies are optimized through perception of environmental data information collected by sensors;

[0072] Accidents are detected by camera equipment, and the system's intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, it evaluates indicators including average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction.

[0073] By setting up green wave belts on main roads during peak hours, the traffic efficiency of main roads can be greatly improved, the waiting time of vehicles can be reduced, and traffic congestion can be reduced. During peak hours or when the vehicle queue is long, the system can intelligently extend the green light time to ensure that the rear vehicles can pass smoothly, improve the traffic capacity of the intersection, and avoid traffic congestion; the system can quickly detect and respond to traffic accidents through real-time monitoring and intelligent analysis. Automatically adjust the signal light cycle around the accident point to reduce traffic congestion caused by the accident and ensure smooth traffic flow. By combining historical data and real-time traffic analysis, the system can predict the changing trend of traffic flow and respond to sudden traffic changes (such as bad weather, traffic accidents, etc.) to minimize traffic accidents and congestion. By dynamically optimizing the signal light cycle, it reduces the idling of vehicles due to long waiting times, reduces fuel consumption, reduces carbon emissions, and promotes green travel. The system adjusts the signal light cycle in real time, which not only optimizes the passage of motor vehicles, but also fully considers the needs of pedestrians and non-motor vehicles, improves the all-round efficiency of traffic, and supports environmental protection and low-carbon travel. Combined with a variety of control strategies (fixed timing, induction, adaptive control), the system can flexibly respond to different traffic conditions, optimize traffic flow, and ensure intelligent regulation and flexible adaptation of traffic signals. By integrating environmental monitoring data, the system can automatically adjust the control strategy according to weather and environmental changes to ensure that under various conditions The system can achieve optimal traffic management under all circumstances; the system realizes the linkage control of traffic lights at multiple intersections through regional traffic control algorithms, so that the traffic flow between main roads and branch roads is coordinated and consistent, avoiding traffic congestion in local areas from affecting the entire traffic network, thereby improving the overall traffic efficiency of the city. The system can not only cope with short-term traffic flow changes, but also predict future traffic flow peaks through historical data, make traffic dispatch preparations in advance, and avoid sudden traffic bottlenecks; through the analysis of historical data and real-time traffic by machine learning models, the system can dynamically optimize signal control strategies, continuously learn and adjust to adapt to changing traffic needs; by dynamically adjusting the timing of signal lights, especially extending the green light time, vehicles, pedestrians and non-motor vehicles are avoided from waiting for a long time, which improves traffic efficiency and travel satisfaction. The signal control system based on data analysis and intelligent algorithms makes traffic management more efficient and transparent, and citizens can experience smoother traffic flow during their travels, reducing unnecessary troubles.

[0074] Real-time data is collected through sensors, cameras, and geomagnetic equipment, including environmental data, number of vehicles, driving speed, fleet length, pedestrian and non-motor vehicle flow information, and historical traffic flow data and real-time collected data are combined with emergency analysis to predict traffic patterns and traffic change trends. The method is as follows:

[0075] Integrate real-time data and historical data collected by geomagnetic, camera, radar sensor, traffic camera, and environmental sensor monitoring equipment;

[0076] The obtained information on convoy length, vehicle speed, traffic density, and number of pedestrians is used to capture the current traffic conditions and future change trends of the road section;

[0077] Combined with real-time monitoring data, the impact of emergencies on traffic flow is analyzed, and traffic changes are predicted in advance. Combined with flow prediction and signal control systems, reinforcement learning is used to optimize traffic signal scheduling strategies.

[0078] By integrating historical data and real-time monitoring data, the system can accurately predict the changing trend of future traffic flow and make traffic signal dispatch in advance, which can effectively avoid congestion during peak traffic hours and improve traffic efficiency. Through real-time monitoring of vehicle speed, fleet length and traffic density, the system can detect early signs of traffic congestion, adjust signal cycle and priority in time, reduce traffic stagnation time and improve traffic efficiency. Emergency events (such as traffic accidents, bad weather, road construction, etc.) will have a significant impact on traffic flow. The system can quickly identify events and automatically adjust traffic signal light cycles through real-time data and environmental monitoring analysis to avoid the spread of traffic accidents and ensure the passage of emergency vehicles. Combined with traffic prediction and signal control systems, the system can intelligently adjust traffic lights according to emergencies to ensure traffic continuity and safety. By combining real-time traffic data with historical traffic data, the system can better capture the laws and anomalies of traffic flow, thereby adapting to various traffic needs and changes in traffic patterns. Using reinforcement learning algorithms, the system can be based on historical experience and real-time The system can conduct self-learning and optimization based on data to improve the intelligence level of traffic signal dispatching. As time goes by, the system can continuously improve signal control strategies to adapt to changing traffic conditions. Through intelligent analysis of the impact of emergencies on traffic flow, the system can adjust traffic lights in a timely manner to ensure the passage of emergency vehicles, public transportation and high-risk sections, and reduce secondary congestion or traffic conflicts caused by traffic accidents. For areas with large pedestrian and non-motor vehicle traffic, the system can automatically adjust the priority of traffic signals according to traffic flow and pedestrian flow to ensure the safety of vulnerable groups. Through precise control of traffic light switching timing and signal cycle, the waiting time and idling of vehicles are reduced, fuel consumption and carbon emissions are reduced, and reasonable signal dispatching is used to support the passage of non-motor vehicles and pedestrians, promote green and low-carbon transportation methods, and promote the realization of environmental protection goals. Through intelligent traffic signal dispatching, the waiting time of vehicles, pedestrians and non-motor vehicles is reduced, and the efficiency and comfort of travel are improved. Based on data-driven and intelligent optimization, the public can enjoy a smoother, safer and more environmentally friendly travel experience.

[0079] According to the real-time traffic conditions, artificial intelligence algorithms are used to optimize the green light time allocation. Fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, the method of setting green wave belts on main roads during peak hours is as follows:

[0080] Through various sensors and traffic flow monitoring equipment, traffic condition data of road sections can be collected in real time;

[0081] Through deep neural networks, the system uses intelligent algorithms to learn traffic flow patterns and changing trends, predict traffic conditions on different road sections, optimize traffic light durations based on predictions, dynamically adjust signal timings based on prediction results, and automatically adjust green and red light times.

[0082] Based on the real-time traffic conditions and flow forecasts of different road sections, the intelligent transportation system dynamically adjusts the signal timing of the entire traffic network and generates green wave belts on the main roads;

[0083] By coordinating the traffic lights at multiple intersections and setting the signal cycle, vehicles can maintain green signals when passing through multiple intersections during peak hours.

[0084] By dynamically adjusting the timing of traffic lights, especially the setting of green wave bands during peak hours, vehicles can travel smoothly between multiple intersections, reducing parking waiting time, thereby effectively reducing traffic congestion. The optimization of traffic light timing can ensure that main roads with heavy traffic have sufficient green light time, improve the road's traffic capacity, and avoid traffic bottlenecks caused by unreasonable signal timing; the system can automatically adjust the duration of traffic lights based on real-time traffic conditions and prediction results, avoiding the lag and inaccuracy of manual control, ensuring that traffic light control is more efficient and intelligent, and through deep neural network data analysis and pattern learning, the system can continuously optimize signal timing strategies and improve Improve the automation and intelligence level of traffic management; during peak hours, the system can intelligently generate green wave belts, so that vehicles on the main roads can pass smoothly when passing through multiple intersections, greatly improving road traffic efficiency and reducing the time wasted due to waiting at traffic lights. By coordinating the traffic light cycle, vehicles can pass continuously, reducing traffic delays caused by traffic light switching, especially in the core areas of the city or on main roads; through the optimization of green wave belts and traffic light timing, vehicles can stop less during peak hours, improving the driving experience and reducing fuel consumption caused by frequent stopping and starting. Reasonable traffic light scheduling can not only reduce congestion, but also reduce the occurrence of traffic accidents. For example, it avoids overly complex signal switching between multiple intersections, reduces traffic conflict points, and reduces accident risks; by optimizing signal timing, vehicles reduce waiting time at intersections, reduce idling, reduce fuel consumption and carbon emissions, and contribute to environmental protection. Optimizing signal control can also better coordinate the priority needs of public transportation, non-motor vehicles and pedestrians, promote the implementation of green transportation modes, and enhance the city's sustainable development capabilities; through an intelligent traffic management system, it can quickly respond to sudden traffic incidents such as traffic accidents and road closures, automatically adjust signal timing, ensure smooth roads, and provide priority passage for emergency vehicles; with the advancement of urbanization, traffic flow, road layout and travel demand will continue to change. The system is adaptable and can continuously adjust signal control strategies based on real-time data and traffic forecasts to improve the long-term adaptability of the system. The system is not only suitable for a single intersection, but can also coordinate signals over a larger range to meet the traffic management needs of cities of different sizes.

[0085] According to the real-time traffic changes during peak hours, traffic signals are intelligently dispatched. When the green light time expires but the rear vehicle has not passed, the green light time is automatically extended. Combining real-time data and historical data, the method of dynamically adjusting the green light time and cycle allocation is as follows:

[0086] Based on the adaptive control algorithm, the green light time, cycle and timing strategy are dynamically adjusted. When the system detects that the green light is about to end, if there are still vehicles that have not passed the end of the intersection, the system will automatically extend the green light time according to the real-time traffic flow;

[0087] The signal timing is continuously adjusted according to the changes in real-time traffic flow, and the model is updated through feedback information.

[0088] By dynamically extending the green light time, the system can ensure that vehicles at the end of the intersection during peak hours will not be stranded due to signal changes, thereby improving the traffic efficiency of passing vehicles and reducing parking waiting time. Automatically extending the green light time helps alleviate bottlenecks at intersections with large traffic flows and avoid congestion caused by inappropriate signal cycles. Especially during peak hours, extending the green light time can balance the distribution of traffic flow and improve the traffic capacity of main roads. The solution can dynamically adjust the green light duration according to real-time traffic changes, avoiding the problem that fixed timing solutions cannot cope with traffic fluctuations. The system can adapt to the impact of factors such as different time periods, different weather conditions, and special events on traffic flow, ensuring that traffic signals are always In line with current traffic demands, during peak hours, the system can optimize the green light duration according to traffic density and real-time data to avoid large-scale vehicle detention and traffic jams caused by unreasonable signal duration settings; usually, when the green light is about to end, some vehicles may not have passed the intersection yet. The system can dynamically determine whether to extend the green light duration to ensure that all vehicles have a chance to pass and avoid unnecessary waiting. Through adaptive control, traffic signals can be adjusted according to the real-time flow of vehicles, and traffic demands of different sections and time periods can be met in real time, thereby improving the overall road traffic efficiency; because the system can accurately control the green light time, traffic conflicts caused by frequent stops and starts are reduced. , reducing the probability of traffic accidents. While vehicles pass through intersections smoothly, it also reduces safety hazards caused by rear-end collisions or rapid lane changes. Through intelligent delay control, the system can predict the passage needs of the rear vehicle based on real-time feedback, and automatically extend the green light time when necessary to avoid traffic accidents caused by premature signal switching; the waiting time of vehicles is reduced, and idling is reduced, thereby reducing fuel consumption and carbon emissions. The promotion of green travel can also improve the air quality of the city by reducing the energy consumption caused by frequent stopping and starting, improving traffic smoothness, effectively saving energy and reducing the burden on the environment; automatically extending the green light time can greatly reduce the driver's waiting time at the intersection Waiting time, avoiding the trouble of frequent stops and starts, and improving the driver's travel experience, especially during peak hours, vehicles can travel smoothly without frequent stops due to unreasonable traffic signal cycles, improving the overall travel efficiency and comfort; the system builds an efficient and flexible traffic signal control network through the combination of real-time data streams, historical traffic data and flow predictions. With the development of transportation technology, it can further integrate more traffic monitoring equipment, vehicle communication technology, and even real-time data of autonomous driving vehicles to enhance the intelligence of the system. The system can continuously optimize the algorithm with the accumulation of data and technological progress, and gradually improve the adaptive control model, with high maintainability and scalability.

[0089] Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are linked and controlled. According to the traffic flow conditions of the main road, the method for dynamically adjusting the red light duration at the branch intersection is as follows:

[0090] Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment;

[0091] By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing;

[0092] By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections;

[0093] Continuously optimize signal control strategies through interaction with traffic flow.

[0094] By extending the green light duration of the main road to form a green wave belt, the smooth passage of vehicles on the main road can be ensured, and parking and delays caused by signal light switching can be reduced. During the peak traffic period of the main road, the signal cycle of the branch road is shortened, which helps to alleviate the traffic pressure at the branch intersection and reduce the queue phenomenon on the branch road; by accurately scheduling the signal light cycle of each intersection, the system can maximize the use of the traffic capacity of the main road while ensuring the balance of branch road traffic, avoiding excessive congestion in some sections and waste of signal idleness in other sections. The green light time of multiple intersections is linked to form a green wave belt, which allows vehicles to travel along the main road without frequent stops. By dynamically adjusting the red light time of branch roads according to the flow of the main road, unnecessary waiting is reduced, especially during peak hours, the waiting time of branch roads is optimized to avoid long-term detention of vehicles. Real-time monitoring and adjustment of branch intersections can timely detect queuing phenomena, reasonably allocate green light duration, avoid long-term queuing of vehicles in front of intersections, and reduce traffic detention; through the coordinated adjustment of signal lights, the flow balance between main roads and branch roads can be ensured, and the risk of traffic conflicts and accidents caused by uncoordinated traffic signals can be reduced. Effective signal control can alleviate Traffic jams can be reduced, traffic accidents caused by parking, lane changes, and sudden braking can be reduced, and road safety can be improved; vehicles do not need to stop and accelerate frequently, which can effectively reduce vehicle idling time and fuel consumption, thereby reducing carbon emissions, especially during peak hours. Through precise signal control, the carbon footprint of urban traffic can be significantly reduced, the time for vehicles to stop and wait can be reduced, energy waste can be reduced, and the energy efficiency of the traffic management system can be improved; through the Internet of Vehicles technology, traffic lights can be intelligently adjusted according to real-time traffic conditions and historical data, and the overall intelligence level of traffic management can be improved. The control method of this solution is not limited to a single intersection, but is applicable to the traffic control system of the entire region or city. With the advancement of technology and the accumulation of data, more intersections, road sections and traffic flow prediction data can be integrated into the system to achieve a wider range of traffic signal linkage control; with the gradual development of autonomous driving technology, this solution can be more deeply coordinated with autonomous driving vehicles. For example, autonomous driving vehicles can share data with traffic management systems to further improve the coordination efficiency of traffic flow. The system can flexibly adjust signal control strategies according to real-time traffic conditions, such as responding to special situations such as temporary road closures, traffic accidents or bad weather, to ensure the smooth operation of traffic flow.

[0095] Based on historical data and real-time traffic information, the machine learning model is used to predict future traffic peaks and change trends. The method of perceiving and optimizing the traffic signal control strategy through environmental data information collected by sensors is as follows:

[0096] Through historical data and real-time traffic data, historical data includes long-term traffic flow patterns, common peak hours, and holiday traffic change data, and real-time traffic information includes real-time monitoring of traffic density, vehicle speed, and traffic event information through sensors. The system's prediction model estimates upcoming traffic changes and upcoming peak hours;

[0097] Through regression analysis, time series models, reinforcement learning, and ensemble learning machine learning techniques, based on training and prediction of real-time and historical traffic data, we can adjust traffic forecasts and optimize signal control decisions in a dynamically changing traffic environment;

[0098] Through meteorological sensors, vehicle-mounted sensors, and environmental temperature and humidity monitors, the system senses changes in the environment and automatically adjusts traffic signal control strategies;

[0099] By continuously collecting traffic data and training models, the system learns to adapt to different traffic flow patterns and complex traffic environments. Based on real-time traffic monitoring data, the system senses changes in traffic flow and adjusts the traffic light control strategy.

[0100] Through the prediction model based on historical and real-time data, the system can accurately estimate future traffic peaks and changing trends, and make signal control decisions in advance. Especially during peak hours or special circumstances, traffic light control can more effectively avoid traffic jams. The system can dynamically adjust the green and red light durations of traffic lights based on traffic forecasts, vehicle speeds, traffic density, and environmental data in real time to ensure smooth traffic and reduce traffic bottlenecks. The system not only relies on predetermined rules, but can also automatically optimize the traffic light cycle and adjust the timing of traffic lights based on real-time data to avoid congestion and waste. As the system learns, the intelligence and accuracy of traffic light timing are gradually improved, reducing human intervention and improving traffic management efficiency. Environmental sensors (such as meteorological, On-board sensors, etc.) provide the system with information about changes in the external environment. The system can adjust the traffic light strategy according to factors such as weather, temperature, and humidity. This perception optimization capability can significantly improve the accuracy of traffic control under complex weather conditions. By predicting future traffic peaks through machine learning models, it can identify possible traffic rush hours in advance and make adjustments through corresponding signal control strategies, which can greatly reduce vehicle waiting time and avoid congestion during peak traffic hours. When it is predicted that the traffic density is too high or the length of the vehicle queue is too long, the signal light control system can adjust the traffic light switching time in time to alleviate the vehicle queuing phenomenon. Intelligent scheduling of traffic flow can avoid traffic conflicts caused by improper signal light switching. Especially during peak hours, intelligent traffic lights can reduce unnecessary stops, accelerations and lane changes according to real-time traffic conditions, thereby reducing the occurrence of traffic accidents. In severe weather or special environmental conditions (such as haze, ice and snow), the system adjusts the duration of traffic lights and speed limits through environmental data to increase traffic safety. By reducing traffic congestion and unnecessary stops and waiting, it can significantly reduce fuel consumption and exhaust emissions, and play a positive role in improving urban air quality and reducing greenhouse gas emissions. The adjustment of intelligent traffic lights improves road traffic efficiency, reduces traffic bottlenecks, avoids waste of traffic flow, and makes road resources more efficiently utilized. With the accumulation of data and continuous training of models, the system can self-optimize and adjust its signal control strategy. Machine learning algorithms enable the system to learn different traffic patterns and flow changes, thereby improving long-term decision-making results. The flexibility of the solution enables it to adapt to traffic environments and patterns in different regions, especially in large cities and complex road networks, and to perform adaptive optimization based on specific traffic needs. With the development of autonomous driving technology, the system can work in conjunction with autonomous vehicles, and through vehicle-to-everything (V2X) technology, traffic signals can be coordinated and optimized with the actions of autonomous vehicles to further improve traffic flow and safety. The system can flexibly adjust signal control strategies based on traffic incidents, natural disasters or major public events to respond to sudden traffic conditions.

[0101] Accidents are detected by camera equipment, and the system's intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, the evaluation method includes average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction indicators as follows:

[0102] Computer vision algorithms are used to analyze images in real time to detect traffic accidents or obstacles. When an accident is confirmed, the system automatically adjusts the signal light cycle at surrounding intersections based on the location of the accident, by lengthening the green light time of other roads, reducing the signal green light time of the accident section, or re-adjusting the route to avoid the traffic in the accident area.

[0103] Combining historical data with real-time data, the system predicts changes in traffic flow after an accident and automatically adjusts signal light cycles and traffic guidance strategies;

[0104] Average vehicle waiting time Based on real-time traffic data and signal light timing, the system calculates the average waiting time for each vehicle in real time;

[0105] The traffic efficiency of the intersection is evaluated by calculating the number of vehicles passing through per unit time, speed, and flow rate;

[0106] By monitoring the speed, waiting time and passing time of vehicles in real time, carbon emissions are estimated based on vehicle type and engine efficiency;

[0107] Through camera monitoring and sensor feedback, we can understand the waiting time, crossing time and traffic density of pedestrians and non-motor vehicles, and evaluate their satisfaction through questionnaire surveys, public feedback and other data;

[0108] Through real-time monitoring and evaluation of the above-mentioned multiple indicators, the system makes adaptive adjustments. Based on the comparison of historical data and feedback from real-time traffic, the system performs optimization of signal timing, event response mechanism, and multi-objective optimization operations.

[0109] Through accident detection and automatic adjustment of traffic lights, the system can quickly divert traffic, avoid congestion around accident sites, and reduce traffic bottlenecks after accidents. Through real-time traffic and historical data analysis, the system can automatically adjust the traffic light cycle to ensure priority passage on high-traffic roads and improve traffic efficiency at intersections. Based on real-time monitoring of vehicle waiting time and traffic data, the system can dynamically adjust the timing of traffic lights to reduce vehicle waiting time, avoid ineffective parking and waiting, and improve traffic flow. The system reduces fuel consumption and carbon emissions by reducing vehicle waiting time and improving road traffic efficiency, which helps protect the environment. Through the intelligent traffic light control system, it avoids excessive waiting at red lights and reduces energy waste when vehicles are idling. The system monitors the crossing time, waiting time and traffic density of pedestrians and non-motor vehicles to ensure their smooth passage and improve the service quality of traffic facilities for non-motor vehicles and pedestrians. , combined with public feedback and satisfaction surveys, the system continuously optimizes signal control strategies to ensure that public transportation participants (including pedestrians and non-motor vehicles) can also pass efficiently and improve the overall service level of urban transportation; through real-time feedback of multi-dimensional data and comparison of historical data, the system can intelligently predict and automatically adjust traffic signal timing and flow distribution to adapt to different traffic conditions, especially in emergencies or special circumstances, showing a high degree of flexibility. The system can learn from long-term traffic patterns and optimize future signal control strategies to ensure the long-term stability and efficient operation of the intelligent traffic management system; through intelligent traffic guidance and signal light adjustment, the system can better coordinate various types of traffic flows, reduce traffic conflicts caused by unreasonable signal timing, and improve traffic safety; through data collection, processing and analysis, the system can automatically make decisions on signal light adjustment, greatly reduce human intervention, and improve management efficiency. After long-term operation, the system can continuously optimize signal control strategies based on historical data and improve the level of intelligence.

[0110] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a road traffic signal control system and method as described above is implemented.

[0111] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a road traffic signal control system and method as described above are implemented.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0113] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0114] The above embodiments of the present invention are not intended to limit the protection scope of the present invention, and the implementation modes of the present invention are not limited thereto. All other modifications, replacements or changes made to the above structures of the present invention based on the above contents of the present invention, in accordance with common technical knowledge and customary means in the art, without departing from the above basic technical ideas of the present invention, should fall within the protection scope of the present invention.

Claims

1. A road traffic signal control system, characterized in that: Included are: The data acquisition module is used to collect real-time road traffic data through geomagnetic sensors, video surveillance, radar sensors, and meteorological monitoring equipment arranged on the road; The data processing module is used to analyze and process the collected real-time traffic data using intelligent machine learning and deep learning algorithms, and dynamically predict and adjust the switching cycle and time allocation of traffic lights; Traffic flow prediction module, which is used to intelligently analyze traffic flow trends during peak hours, holidays and special events based on historical traffic flow data and real-time data, and optimize the signal light cycle timing plan in advance; Traffic light control and execution module, used to communicate traffic lights with the central control system and local traffic monitoring platform in real time, dynamically adjust traffic light cycles according to real-time collected and processed data, and control light switching duration according to real-time detected traffic flow and queue length; The accident response and elimination module is used to detect traffic accidents through video surveillance and sensors. When an accident is detected, the system automatically adjusts the traffic light cycle in the affected area; The user participation module is used to receive real-time road traffic conditions such as traffic flow, traffic light status, and accident information fed back by users through the citizen-side application App. The system dynamically optimizes the traffic light control strategy based on user feedback information.

2. A road traffic signal control method, characterized in that: Included are: Collect real-time data through sensors, cameras, and geomagnetic equipment, including environmental data, number of vehicles, driving speed, fleet length, pedestrian and non-motor vehicle flow information, use historical traffic flow data and real-time collected data, combined with emergency analysis, to predict traffic patterns and traffic change trends; According to real-time traffic conditions, artificial intelligence algorithms are used to optimize green light time allocation. Fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, green wave belts are set on main roads during peak hours. Intelligently dispatch traffic signals according to the real-time traffic changes during peak hours. If the green light time expires but the rear vehicle has not passed, the green light time will be automatically extended. Combined with real-time and historical data, the green light time and cycle allocation will be dynamically adjusted. Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are controlled in a coordinated manner, and the duration of red lights at branch intersections is dynamically adjusted according to the traffic flow conditions of the main roads; Based on historical data and real-time traffic information, machine learning models are used to predict future traffic peaks and changing trends, and traffic signal control strategies are optimized through perception of environmental data information collected by sensors; Accidents are detected by camera equipment, and the system's intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, it evaluates indicators including average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction.

3. The road traffic signal control method according to claim 2, characterized in that: Real-time data is collected through sensors, cameras, and geomagnetic equipment, including environmental data, number of vehicles, driving speed, fleet length, pedestrian and non-motor vehicle flow information, and historical traffic flow data and real-time collected data are combined with emergency analysis to predict traffic patterns and traffic change trends. The method is as follows: Integrate real-time data and historical data collected by geomagnetic, camera, radar sensor, traffic camera, and environmental sensor monitoring equipment; The obtained information on convoy length, vehicle speed, traffic density, and number of pedestrians is used to capture the current traffic conditions and future change trends of the road section; Combined with real-time monitoring data, the impact of emergencies on traffic flow is analyzed, and traffic changes are predicted in advance. Combined with flow prediction and signal control systems, reinforcement learning is used to optimize traffic signal scheduling strategies.

4. The road traffic signal control method according to claim 3, characterized in that: According to the real-time traffic conditions, artificial intelligence algorithms are used to optimize the green light time allocation. Fixed timing control, inductive control, and adaptive control strategies are combined to dynamically adjust the duration and priority of traffic lights. Through regional collaborative optimization, the method of setting green wave belts on main roads during peak hours is as follows: Through various sensors and traffic flow monitoring equipment, traffic condition data of road sections can be collected in real time; Through deep neural networks, the system uses intelligent algorithms to learn traffic flow patterns and changing trends, predict traffic conditions on different road sections, optimize traffic light durations based on predictions, dynamically adjust signal timings based on prediction results, and automatically adjust green and red light times. Based on the real-time traffic conditions and flow forecasts of different road sections, the intelligent transportation system dynamically adjusts the signal timing of the entire traffic network and generates green wave belts on the main roads; By coordinating the traffic lights at multiple intersections and setting the signal cycle, vehicles can maintain green signals when passing through multiple intersections during peak hours.

5. The road traffic signal control method according to claim 4, characterized in that: According to the real-time traffic changes during peak hours, traffic signals are intelligently dispatched. When the green light time expires but the rear vehicle has not passed, the green light time is automatically extended. Combining real-time data and historical data, the method of dynamically adjusting the green light time and cycle allocation is as follows: Based on the adaptive control algorithm, the green light time, cycle and timing strategy are dynamically adjusted. When the system detects that the green light is about to end, if there are still vehicles that have not passed the end of the intersection, the system will automatically extend the green light time according to the real-time traffic flow; The signal timing is continuously adjusted according to the changes in real-time traffic flow, and the model is updated through feedback information.

6. The road traffic signal control method according to claim 5, characterized in that: Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are linked and controlled. According to the traffic flow conditions of the main road, the method for dynamically adjusting the red light duration at the branch intersection is as follows: Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment; By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing; By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections; Continuously optimize signal control strategies through interaction with traffic flow.

7. The road traffic signal control method according to claim 6, characterized in that: Based on historical data and real-time traffic information, the machine learning model is used to predict future traffic peaks and change trends. The method of perceiving and optimizing the traffic signal control strategy through environmental data information collected by sensors is as follows: Through historical data and real-time traffic data, historical data includes long-term traffic flow patterns, common peak hours, and holiday traffic change data, and real-time traffic information includes real-time monitoring of traffic density, vehicle speed, and traffic event information through sensors. The system's prediction model estimates upcoming traffic changes and upcoming peak hours; Through regression analysis, time series models, reinforcement learning, and ensemble learning machine learning techniques, based on training and prediction of real-time and historical traffic data, we can adjust traffic forecasts and optimize signal control decisions in a dynamically changing traffic environment; Through meteorological sensors, vehicle-mounted sensors, and environmental temperature and humidity monitors, the system senses changes in the environment and automatically adjusts traffic signal control strategies; By continuously collecting traffic data and training models, the system learns to adapt to different traffic flow patterns and complex traffic environments. Based on real-time traffic monitoring data, the system senses changes in traffic flow and adjusts the traffic light control strategy.

8. The road traffic signal control method according to claim 7, characterized in that: Accidents are detected by camera equipment, and the system's intelligent algorithm automatically adjusts the traffic light cycle around the accident point. Based on historical data comparison and real-time monitoring, the evaluation method includes average vehicle waiting time, intersection traffic efficiency, vehicle carbon emissions, and pedestrian and non-motor vehicle traffic satisfaction indicators as follows: Computer vision algorithms are used to analyze images in real time to detect traffic accidents or obstacles. When an accident is confirmed, the system automatically adjusts the signal light cycle at surrounding intersections based on the location of the accident, by lengthening the green light time of other roads, reducing the signal green light time of the accident section, or re-adjusting the route to avoid the traffic in the accident area. Combining historical data with real-time data, the system predicts changes in traffic flow after an accident and automatically adjusts signal light cycles and traffic guidance strategies; Average vehicle waiting time Based on real-time traffic data and signal light timing, the system calculates the average waiting time for each vehicle in real time; The traffic efficiency of the intersection is evaluated by calculating the number of vehicles passing through per unit time, speed, and flow rate; By monitoring the speed, waiting time and passing time of vehicles in real time, carbon emissions are estimated based on vehicle type and engine efficiency; Through camera monitoring and sensor feedback, we can understand the waiting time, crossing time and traffic density of pedestrians and non-motor vehicles, and evaluate their satisfaction through questionnaire surveys, public feedback and other data; Through real-time monitoring and evaluation of the above-mentioned multiple indicators, the system makes adaptive adjustments. Based on the comparison of historical data and feedback from real-time traffic, the system performs optimization of signal timing, event response mechanism, and multi-objective optimization operations.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the road traffic signal control method as claimed in any one of claims 2 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the road traffic signal control method as described in any one of claims 2-8 is implemented.

Images