Intelligent traffic management system and method based on cloud computing

Abstract

The invention provides an intelligent traffic management system and method based on cloud computing, and relates to the technical field of traffic management. The intelligent traffic management system based on cloud computing comprises a multi-source data acquisition module, the multi-source data acquisition module is connected with a data fusion and preprocessing module, and the data fusion and preprocessing module is connected with a behavior prediction module. Real-time data acquisition and a behavior prediction model are utilized, signal lamp time and shunting strategies can be flexibly adjusted, traffic condition changes can be coped with in real time, management efficiency is improved, interaction among all traffic participants is optimized through group behavior analysis, balance and high efficiency of the whole traffic flow are ensured, and the traffic safety is improved. Through reinforcement learning and an adaptive algorithm, the method can continuously learn and optimize a strategy from feedback, dynamically adapts to different cities and traffic scenes, provides personalized suggestions and guidance for each traffic participant through multiple channels, and improves travel experience and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to an intelligent traffic management system and method based on cloud computing. Background Art

[0002] Traffic management refers to the process by which the government or relevant agencies optimize road traffic flow, ensure traffic safety, and improve traffic efficiency through planning, organization, control, coordination and other measures. Its core goals include reducing traffic accidents, ensuring the safety of pedestrians and drivers, improving road use efficiency, reducing congestion, shortening travel time, promoting environmental protection, reducing traffic emissions, promoting green travel modes, ensuring the rational allocation of road resources, and providing fair travel conditions for all traffic participants. Traffic management usually involves traffic light control, road planning, the formulation and implementation of traffic rules, public transportation scheduling and other aspects.

[0003] Existing traffic management technologies mainly rely on pre-programmed traffic lights based on fixed time periods. The switching time of the lights is set according to fixed periods, without considering real-time traffic flow changes. Or the traffic flow conditions are collected through road monitoring cameras, but in most cases, traffic management personnel manually analyze video images and make intervention decisions based on experience, such as adjusting lights or diverting traffic. Some systems use historical traffic data (such as traffic volume during peak hours) to formulate traffic management strategies. Based on past congestion, the duration of traffic lights and road diversion plans are pre-set. More advanced systems use sensors to detect vehicle density and automatically adjust the time of lights. For example, inductive traffic lights can extend the green light time when there are no vehicles at the intersection. Or navigation systems such as Google Maps and Waze use real-time traffic information to provide drivers with the best route options to avoid congestion. However, their optimization is limited to the individual level and fails to effectively optimize the overall traffic flow. The traditional timed signal light control and historical data-based strategies in the above technologies cannot dynamically respond to real-time traffic changes, which will cause delayed response during peak hours or emergencies. Although the navigation system can provide optimized routes for individuals, the lack of coordination between traffic participants may cause different drivers to choose similar routes according to the same plan, which will aggravate congestion on certain roads. Most existing traffic management systems are based on fixed rules and are difficult to learn and optimize based on long-term traffic changes. The guidance of traditional traffic systems mainly relies on fixed road signs or broadcasts, which lack flexibility and cannot provide specific suggestions for individuals. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides an intelligent traffic management system and method based on cloud computing, which solves the problem of low efficiency of the traffic management and dredging methods in the prior art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent traffic management system based on cloud computing, including multi-source data acquisition, the multi-source data acquisition is connected to a data fusion and preprocessing module, the data fusion and preprocessing module is connected to a behavior prediction module, the behavior prediction module is connected to a behavior pattern library, and the behavior pattern library is connected to a dynamic path planning and diversion module;

[0006] The multi-source data acquisition is connected to a real-time data input module, the real-time data input module is connected to a group behavior modeling and collaborative analysis module, the group behavior modeling and collaborative analysis module is connected to an adaptive signal control module, the adaptive signal control module is connected to a social collaborative guidance and intervention module, the social collaborative guidance and intervention module is connected to real-time guidance of drivers or pedestrians, and the social collaborative guidance and intervention module is connected to a feedback and adaptive learning module.

[0007] Preferably, the group behavior modeling is bidirectionally connected to the collaborative analysis module and the behavior pattern library. The behavior pattern library covers the behavioral characteristics of drivers and pedestrians, such as acceleration, braking, lane changing, and weaving. The results of the behavior prediction module will be used by the group behavior modeling module to analyze the current traffic conditions, identify possible bottlenecks or problem points, and formulate a variety of potential traffic management strategies through collaborative analysis. Then, these strategies will be evaluated to determine which strategy can achieve the best effect under specific conditions. The final strategy is selected and executed as the output of the system.

[0008] Preferably, the multi-source data collection is to collect traffic data through vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones, and the traffic data includes vehicle speed, position, acceleration, pedestrian flow, and weather conditions.

[0009] Preferably, the data fusion and preprocessing module cleans and standardizes the received raw data to remove noise and redundant data, wherein the data fusion process integrates the data from different sensors into a unified, structured data format.

[0010] Preferably, the behavior prediction module uses deep learning and reinforcement learning models to predict the future behavior of traffic participants based on historical data and real-time data.

[0011] Preferably, the group behavior modeling and collaborative analysis module uses group behavior models and game theory to analyze the overall behavior of all traffic participants, simulate the overall traffic flow, calculate the impact of individual behavior on the overall traffic flow, and generate the optimal traffic coordination plan.

[0012] Preferably, the adaptive signal control module adjusts the time and strategy of traffic lights in real time based on the results of behavior prediction and group collaborative analysis, flexibly increases or decreases the time of traffic lights according to the current traffic flow conditions, or even cancels traffic lights, and formulates differentiated signal control strategies to adapt to the characteristics of different road sections, such as highway intersections and near schools.

[0013] Preferably, the dynamic path planning and diversion module analyzes traffic conditions and behavior prediction data in real time, generates a personalized driving path planning plan for each vehicle, performs real-time path adjustment and diversion, avoids congestion, and ensures the efficient flow of the overall traffic flow; the social collaborative guidance and intervention module sends guidance and prompt information to traffic participants in real time through channels such as vehicle-mounted systems and mobile applications, and performs intelligent intervention in special circumstances, such as closing some lanes, setting up variable lane signs, and guiding emergency vehicles to pass first.

[0014] A cloud computing-based intelligent traffic management method specifically comprises the following steps:

[0015] S1. Real-time multi-source data collection and fusion

[0016] Through a variety of sensors and devices, such as vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones, real-time data of vehicles and pedestrians, including speed, location, acceleration, walking path, and weather conditions, is collected. The data is cleaned and standardized to form a structured data set.

[0017] S2. Traffic Participant Behavior Prediction

[0018] Use deep learning and reinforcement learning algorithms to train based on historical and real-time data, build a behavior pattern library, and predict the future behavior of traffic participants;

[0019] S3. Group collaboration analysis and traffic flow optimization

[0020] Based on the behavior prediction results, the group behavior modeling module analyzes the overall traffic flow, simulates the interaction between traffic participants, and generates the optimal coordination strategy, including dynamic lane allocation, real-time traffic light adjustment, and priority right of way allocation, to ensure smooth and efficient traffic flow;

[0021] S4. Adaptive traffic light control and dynamic path planning

[0022] The adaptive signal control module adjusts the traffic light time and strategy in real time based on the behavior prediction and group collaboration analysis results, flexibly increases or decreases the traffic light time, or even cancels the traffic light. The dynamic path planning and diversion module generates the optimal path planning for each vehicle based on real-time traffic prediction, and performs real-time path adjustment and diversion according to congestion or emergencies.

[0023] S5. Social collaborative guidance and intelligent intervention

[0024] Send real-time guidance and prompt information to drivers and pedestrians through in-vehicle systems and mobile application channels, suggesting that they adjust their driving or crossing methods according to traffic flow conditions;

[0025] S6. Feedback Learning and Adaptive Optimization

[0026] By real-time monitoring of traffic flow changes and feedback from traffic participants, the overall management strategy is continuously learned and optimized. By using reinforcement learning algorithms, the behavior prediction model and group collaboration strategy are continuously improved to ensure that they can adapt to the needs of different cities and traffic scenarios and enhance the intelligence and flexibility of the system.

[0027] The present invention provides an intelligent traffic management system and method based on cloud computing.

[0028] Beneficial effects:

[0029] The present invention provides an intelligent traffic management system and method based on cloud computing. Through the Internet of Things and 5G technology, the system can obtain multi-source data from road cameras, vehicle-mounted sensors, and pedestrian equipment in real time to ensure timely grasp of traffic conditions. Based on deep learning and group behavior analysis algorithms, the system can predict the behavior of traffic participants and optimize traffic flow in real time, such as signal light control, path planning, and vehicle guidance, to improve the efficiency of traffic flow. The present invention can accurately predict the driver's lane change, acceleration, braking, and other behaviors, as well as the pedestrian's travel trajectory, by deeply analyzing the historical data and current behavior of vehicles and pedestrians, and prevent potential risks in advance. Through group behavior modeling and game theory analysis, the system can optimize traffic participants. The system can also adaptively adjust the signal light strategy according to the dynamic changes of traffic flow, flexibly manage the traffic pressure of different sections, reduce waiting time, and improve the overall traffic efficiency. Through reinforcement learning and data feedback, the system can continuously optimize the prediction model and management strategy, adapt to different cities and traffic scenarios, and realize the continuous evolution of the system. Through the vehicle-mounted system, mobile applications, and smart road signs, the system can provide drivers and pedestrians with personalized real-time traffic suggestions, reduce congestion and improve travel safety. In the event of a traffic accident or emergency, the system can intervene intelligently to quickly divert traffic by closing lanes, giving priority, and other measures, thereby reducing the impact of accidents on traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] Example 1

[0033] like Figure 1 As shown, an embodiment of the present invention provides an intelligent traffic management system based on cloud computing, including multi-source data acquisition, the multi-source data acquisition is connected to a data fusion and preprocessing module, the data fusion and preprocessing module is connected to a behavior prediction module, the behavior prediction module is connected to a behavior pattern library, and the behavior pattern library is connected to a dynamic path planning and diversion module;

[0034] The multi-source data acquisition is connected with a real-time data input module, the real-time data input module is connected with a group behavior modeling and collaborative analysis module, the group behavior modeling and collaborative analysis module is connected with an adaptive signal control module, the adaptive signal control module is connected with a social collaborative guidance and intervention module, the social collaborative guidance and intervention module is connected with real-time guidance of drivers or pedestrians, and the social collaborative guidance and intervention module is connected with a feedback and adaptive learning module.

[0035] The group behavior modeling and collaborative analysis modules are bidirectionally connected to the behavior pattern library. The behavior pattern library covers the behavioral characteristics of drivers and pedestrians, such as acceleration, braking, lane changing, and weaving. The results of the behavior prediction module will be used by the group behavior modeling module to analyze the current traffic conditions, identify possible bottlenecks or problem points, and develop a variety of potential traffic management strategies through collaborative analysis. These strategies will then be evaluated to determine which strategy can achieve the best effect under specific conditions (i.e., minimize congestion, improve traffic efficiency, and ensure safety). The final strategy is selected and executed as the output of the system.

[0036] Multi-source data collection is the collection of traffic data through vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones. Traffic data includes vehicle speed, location, acceleration, pedestrian flow, and weather conditions.

[0037] The data fusion and preprocessing module cleans and standardizes the received raw data to remove noise and redundant data. The data fusion process integrates the data from different sensors into a unified and structured data format.

[0038] The behavior prediction module uses deep learning and reinforcement learning models to predict the future behavior of traffic participants based on historical data (such as past traffic conditions and vehicle driving records) and real-time data.

[0039] The group behavior modeling and collaborative analysis module uses group behavior models and game theory to analyze the overall behavior of all traffic participants, simulate the overall traffic flow, calculate the impact of individual behavior on the overall traffic flow, and generate the optimal traffic coordination plan.

[0040] The adaptive signal control module adjusts the timing and strategy of traffic lights in real time based on the results of behavior prediction and group collaborative analysis. It flexibly increases or decreases the time of traffic lights or even cancels traffic lights according to the current traffic flow conditions, and formulates differentiated signal control strategies to adapt to the characteristics of different road sections, such as highway intersections and near schools.

[0041] The dynamic path planning and diversion module analyzes traffic conditions and behavior prediction data in real time, generates personalized driving path planning solutions for each vehicle, makes real-time path adjustments and diversions, avoids congestion, and ensures the efficient flow of overall traffic. The social collaborative guidance and intervention module sends guidance and prompt information to traffic participants in real time through channels such as vehicle-mounted systems and mobile applications. In special circumstances, it conducts intelligent interventions, such as closing some lanes, setting up variable lane signs, and guiding emergency vehicles to pass first.

[0042] Example 2

[0043] The embodiment of the present invention provides an intelligent traffic management method based on cloud computing, which specifically includes the following steps:

[0044] S1. Real-time multi-source data collection and fusion

[0045] Real-time data of vehicles and pedestrians, including speed, location, acceleration, walking path and weather conditions, are collected through a variety of sensors and devices, such as vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones. The data is cleaned and standardized to form a structured data set.

[0046] Road cameras install high-resolution cameras on major traffic routes and intersections to monitor the flow of vehicles and pedestrians in real time. On-board sensors install on-board sensors (such as GPS, speed sensors, accelerometers) in public transportation and private cars to collect vehicle driving data in real time. Pedestrian detection equipment installs intelligent pedestrian detection equipment on sidewalks and crosswalks to collect pedestrian flow data. Drone cruise deploys drones on special roads or high-traffic areas for aerial monitoring and data collection.

[0047] Establish an IoT network covering the entire city to achieve real-time connection between all sensor devices and data processing centers. Use 5G technology to achieve low-latency, high-speed data transmission to ensure rapid processing and response of real-time data. Deploy a cloud computing-based big data platform to receive, store and process data from various sensors.

[0048] Use TensorFlow and PyTorch frameworks to train neural network models for behavior prediction. The model input is cleaned historical and real-time data, and the output is future behavior predictions. Build and maintain a behavior pattern library, and continuously update and optimize the prediction model.

[0049] S2. Traffic Participant Behavior Prediction

[0050] Using deep learning and reinforcement learning algorithms, training is conducted based on historical and real-time data to establish a behavior pattern library to predict the future behavior of traffic participants. The behavior feature profile of each participant can be dynamically updated to improve the accuracy and timeliness of the prediction.

[0051] Set up a group behavior analysis algorithm based on game theory to simulate the interaction between traffic participants. Use Matlab or R tools to implement model simulation. Use multi-objective optimization algorithms (such as genetic algorithms and particle swarm algorithms) to generate optimal coordination strategies, including dynamic lane allocation and signal light control strategies.

[0052] Set up signal control algorithms and integrate them into existing traffic signal controllers to support real-time adjustment of signal light timing and strategies. Use PLC (Programmable Logic Controller) and SCADA (Supervisory Control and Data Acquisition) systems to automate signal control. Use Dijkstra, A* and other path optimization algorithms to design dynamic path planning modules to achieve personalized path recommendations for vehicles. Integrate into vehicle navigation systems and mobile applications to achieve real-time path guidance.

[0053] S3. Group collaboration analysis and traffic flow optimization

[0054] Based on the behavior prediction results, the group behavior modeling module is used to analyze the overall traffic flow, simulate the interaction between traffic participants, and generate the optimal coordination strategy, including dynamic lane allocation, real-time traffic light adjustment, and priority right of way allocation, to ensure smooth and efficient traffic flow.

[0055] A central control center is set up to monitor the operating status of all equipment and real-time data of traffic flow. The control center integrates video walls, data dashboards and control terminals to facilitate real-time viewing and intervention by managers. The SCADA system is used to automate signal light control and feedback. Real-time data and prediction results are transmitted back to the control center via a high-speed network for strategy updates and system optimization.

[0056] S4. Adaptive traffic light control and dynamic path planning

[0057] The adaptive signal control module adjusts the traffic light time and strategy in real time according to the behavior prediction and group collaborative analysis results, flexibly increases or decreases the traffic light time, or even cancels the traffic light. The dynamic path planning and diversion module generates the optimal path planning for each vehicle based on real-time traffic prediction, and performs real-time path adjustment and diversion according to congestion or emergencies.

[0058] Send real-time driving advice and traffic tips to drivers through in-vehicle displays and voice systems. Integrate with existing in-vehicle infotainment systems. Set up smart traffic mobile apps to provide citizens with real-time traffic information, route recommendations, and personal behavior advice. The app needs to support multiple platforms (iOS, Android) and synchronize with data from the traffic control center. Install smart road signs and LED displays on major roads and intersections to publish real-time traffic information and guidance instructions.

[0059] S5. Social collaborative guidance and intelligent intervention

[0060] Through the vehicle system and mobile application channels, real-time guidance and prompt information is sent to drivers and pedestrians, suggesting that they adjust their driving or crossing methods according to traffic flow conditions. In special circumstances, intelligent intervention is carried out, such as closing some lanes, setting up variable lane signs, and guiding emergency vehicles to pass first, so as to maximize traffic flow efficiency;

[0061] S6. Feedback Learning and Adaptive Optimization

[0062] By real-time monitoring of traffic flow changes and feedback from traffic participants, the overall management strategy is continuously learned and optimized. By using reinforcement learning algorithms, the behavior prediction model and group collaboration strategy are continuously improved to ensure that they can adapt to the needs of different cities and traffic scenarios and enhance the intelligence and flexibility of the system.

[0063] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent traffic management system based on cloud computing, including multi-source data collection, characterized by: The multi-source data acquisition is connected to a data fusion and preprocessing module, the data fusion and preprocessing module is connected to a behavior prediction module, the behavior prediction module is connected to a behavior pattern library, and the behavior pattern library is connected to a dynamic path planning and diversion module; The multi-source data acquisition is connected to a real-time data input module, the real-time data input module is connected to a group behavior modeling and collaborative analysis module, the group behavior modeling and collaborative analysis module is connected to an adaptive signal control module, the adaptive signal control module is connected to a social collaborative guidance and intervention module, the social collaborative guidance and intervention module is connected to real-time guidance of drivers or pedestrians, and the social collaborative guidance and intervention module is connected to a feedback and adaptive learning module.

2. The intelligent traffic management system based on cloud computing according to claim 1, characterized in that: The group behavior modeling and collaborative analysis module are bidirectionally connected to the behavior pattern library. The behavior pattern library covers the behavioral characteristics of drivers and pedestrians, such as acceleration, braking, lane changing, and weaving. The results of the behavior prediction module will be used to analyze the current traffic conditions through the group behavior modeling module, identify possible bottlenecks or problem points, and formulate a variety of potential traffic management strategies through collaborative analysis. Then, these strategies will be evaluated to determine which strategy can achieve the best effect under specific conditions. The final strategy is selected and executed as the output of the system.

3. The intelligent traffic management system based on cloud computing according to claim 1, characterized in that: The multi-source data collection is to collect traffic data through vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones. The traffic data includes vehicle speed, position, acceleration, pedestrian flow, and weather conditions.

4. The cloud computing-based intelligent traffic management system according to claim 1, characterized in that: The data fusion and preprocessing module cleans and standardizes the received raw data to remove noise and redundant data, wherein the data fusion process integrates the data from different sensors into a unified, structured data format.

5. The intelligent traffic management system based on cloud computing according to claim 1, characterized in that: The behavior prediction module uses deep learning and reinforcement learning models to predict the future behavior of traffic participants based on historical data and real-time data.

6. The cloud computing-based intelligent traffic management system according to claim 1, characterized in that: The group behavior modeling and collaborative analysis module uses group behavior models and game theory to analyze the overall behavior of all traffic participants, simulate the overall traffic flow, calculate the impact of individual behavior on the overall traffic flow, and generate the optimal traffic coordination plan.

7. The cloud computing-based intelligent traffic management system according to claim 1, characterized in that: The adaptive signal control module adjusts the time and strategy of traffic lights in real time based on the results of behavior prediction and group collaboration analysis. It flexibly increases or decreases the time of traffic lights or even cancels traffic lights according to the current traffic flow conditions, and formulates differentiated signal control strategies to adapt to the characteristics of different road sections, such as highway intersections and near schools.

8. The cloud computing-based intelligent traffic management system according to claim 1, characterized in that: The dynamic path planning and diversion module analyzes traffic conditions and behavior prediction data in real time, generates a personalized driving path planning plan for each vehicle, performs real-time path adjustment and diversion, avoids congestion, and ensures the efficient flow of overall traffic. The social collaborative guidance and intervention module sends guidance and prompt information to traffic participants in real time through channels such as vehicle-mounted systems and mobile applications. In special circumstances, it performs intelligent intervention, such as closing some lanes, setting up variable lane signs, and guiding emergency vehicles to pass first.

9. A cloud computing-based intelligent traffic management method according to any one of claims 1 to 8, characterized in that: The specific steps include: S1. Real-time multi-source data collection and fusion Through a variety of sensors and devices, such as vehicle-mounted sensors, road cameras, pedestrian mobile devices, and drones, real-time data of vehicles and pedestrians, including speed, location, acceleration, walking path, and weather conditions, is collected. The data is cleaned and standardized to form a structured data set. S2. Traffic Participant Behavior Prediction Use deep learning and reinforcement learning algorithms to train based on historical and real-time data, build a behavior pattern library, and predict the future behavior of traffic participants; S3. Group collaboration analysis and traffic flow optimization Based on the behavior prediction results, the group behavior modeling module analyzes the overall traffic flow, simulates the interaction between traffic participants, and generates the optimal coordination strategy, including dynamic lane allocation, real-time traffic light adjustment, and priority right of way allocation, to ensure smooth and efficient traffic flow; S4. Adaptive traffic light control and dynamic path planning The adaptive signal control module adjusts the traffic light time and strategy in real time based on the behavior prediction and group collaboration analysis results, flexibly increases or decreases the traffic light time, or even cancels the traffic light. The dynamic path planning and diversion module generates the optimal path planning for each vehicle based on real-time traffic prediction, and performs real-time path adjustment and diversion according to congestion or emergencies. S5. Social collaborative guidance and intelligent intervention Send real-time guidance and prompt information to drivers and pedestrians through in-vehicle systems and mobile application channels, suggesting that they adjust their driving or crossing methods according to traffic flow conditions; S6. Feedback Learning and Adaptive Optimization By real-time monitoring of traffic flow changes and feedback from traffic participants, the overall management strategy is continuously learned and optimized. By using reinforcement learning algorithms, the behavior prediction model and group collaboration strategy are continuously improved to ensure that they can adapt to the needs of different cities and traffic scenarios and enhance the intelligence and flexibility of the system.

Images