Area Green Wave Coordination Control Method and System for Traffic Safety Early Warning

Abstract

This application relates to the field of traffic control technology, and provides a regional green wave coordinated control method and system for traffic safety warning. The method includes: traversing a target traffic area to collect traffic data and constructing a regional dynamic traffic feature matrix; performing green wave coordination analysis based on the matrix to generate a sub-region division scheme; extracting sub-region traffic flow features and calculating green wave coordinated control parameters; formulating an initial control scheme according to the parameters and executing it, and collecting feedback data; compensating and optimizing the parameters according to the feedback results to obtain a final regional coordinated control scheme. This application solves the technical problem that traditional green wave control only statically optimizes the traffic efficiency and cannot dynamically respond to traffic safety risks, resulting in difficulty in coordinating efficiency and safety, and achieves the technical effect of realizing the deep coupling of safety warning and green wave control through real-time traffic data feedback and dynamic parameter compensation, significantly reducing the accident risk while ensuring the traffic efficiency.

Description

Technical Field

[0001] This application relates to the technical field of traffic control, and particularly to a regional green wave coordination control method and system for traffic safety warning. Background Art

[0002] In modern urban traffic management, with the increasing complexity of road networks and the growth of traffic flow, traditional green wave control methods mainly focus on improving traffic efficiency, neglecting safety factors, which leads to an increase in safety risks in some traffic areas. Especially at intersections where traffic accidents occur frequently, traditional green wave control fails to respond promptly to dynamic traffic safety conditions, lacks a real-time safety warning mechanism, and cannot effectively cope with sudden traffic events. This limitation prevents the traffic control system from fully realizing its potential in enhancing road safety. With the continuous development of intelligent traffic technologies, how to dynamically adjust to the safety risks of different traffic areas while ensuring traffic efficiency has become one of the main challenges faced by traffic management systems. Summary of the Invention

[0003] This application provides a regional green wave coordination control method and system for traffic safety warning, aiming to solve the technical problem that traditional green wave control only statically optimizes traffic efficiency and cannot dynamically respond to traffic safety risks, resulting in difficulties in coordinating efficiency and safety.

[0004] In the first aspect disclosed in this application, a regional green wave coordination control method for traffic safety warning is provided. The method includes: traversing a target traffic area to collect traffic road data and constructing a regional dynamic traffic feature matrix; performing green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-region division plan; extracting traffic flow features of multiple regions based on the sub-region division plan, calculating and obtaining green wave coordination control parameters according to the traffic flow features of the multiple regions; formulating an initial control plan according to the green wave coordination control parameters, executing the initial control plan for data feedback, and compensating the green wave coordination control parameters according to the feedback result to obtain a regional coordination control plan.

[0005] Another aspect disclosed in this application provides a regional green wave coordination control system for traffic safety warning. The system includes: a data collection component: traversing the target traffic area to collect traffic road data and constructing a regional dynamic traffic feature matrix; a green wave coordination analysis component: performing green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-region division scheme; a control parameter calculation component: extracting traffic flow characteristics of multiple regions based on the sub-region division scheme and calculating green wave coordination control parameters according to the traffic flow characteristics of the multiple regions; a control parameter compensation component: formulating an initial control scheme according to the green wave coordination control parameters, executing the initial control scheme for data feedback, and compensating the green wave coordination control parameters according to the feedback result to obtain a regional coordination control scheme.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The above-mentioned regional green wave coordination control method for traffic safety warning first comprehensively collects traffic data in the target area and constructs a feature matrix that can reflect the real-time traffic state. Subsequently, green wave coordination analysis is performed using this dynamic feature matrix to divide the entire area into several sub-regions. Then, traffic flow feature data is extracted from these sub-regions, and based on this, the optimal green wave coordination control parameters are calculated. After implementing the initial control scheme, operation feedback data will be continuously collected, and the control parameters will be dynamically adjusted and optimized through this feedback information, and finally a perfect regional coordination control scheme will be formed. The whole process realizes a closed-loop control from data collection, analysis and decision-making to execution and feedback, ensuring that traffic signal coordination is both efficient and safe.

[0008] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0010] Figure 1 It is a schematic flow chart of a regional green wave coordination control method for traffic safety warning in an embodiment.

[0011] Figure 2It is an architecture diagram of a regional green wave coordination control system for traffic safety warning in an embodiment.

[0012] Description of reference numerals: data acquisition component 11, green wave coordination analysis component 12, control parameter calculation component 13, control parameter compensation component 14. Detailed implementation manners

[0013] By providing a regional green wave coordination control method and system for traffic safety warning in an embodiment of the present application, the technical problem that traditional green wave control only statically optimizes the traffic efficiency and cannot dynamically respond to traffic safety risks, resulting in difficulty in coordinating efficiency and safety, is solved. The technical effect is achieved of dynamically adjusting the subtitle color according to the ambient light and the user's historical preferences, and optimizing the subtitle content through logical reasoning and scenario analysis, improving the readability and accuracy of the subtitles, and ensuring the personalization and accuracy of the subtitles in the digital technology-based playback device.

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0015] It should be noted that the terms including "and", "having", and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 shown, the present application provides a regional green wave coordination control method for traffic safety warning, and the method includes:

[0017] Traverse the target traffic area to collect traffic road data and construct a regional dynamic traffic feature matrix.

[0018] In the embodiments of the present application, when traversing the target traffic area to collect traffic road data, the real-time traffic flow data of each intersection is first collected, including information such as traffic volume and vehicle speed at each intersection. These data provide a basis for constructing the regional dynamic traffic feature matrix in the subsequent process, helping to comprehensively analyze the traffic conditions and potential safety risks. In addition, the accident history data of these intersections is also collected, such as the spatio-temporal distribution of past traffic accidents, accident types, and their relationship with traffic volume. Subsequently, by fusing these multi-dimensional data, a feature matrix that comprehensively reflects the regional traffic operation status and safety risks can be constructed, and this feature matrix is used as the regional dynamic traffic feature matrix. This regional dynamic traffic feature matrix not only contains traffic flow parameters but also integrates safety risk factors, providing a more comprehensive data basis for subsequent green wave coordination control.

[0019] Furthermore, the present application provides a method for traversing the target traffic area to collect traffic road data and construct a regional dynamic traffic feature matrix, including:

[0020] Traversing the target traffic area through a multi-source heterogeneous sensor network to collect full-road network data, and obtaining real-time traffic flow parameters; performing spatio-temporal alignment processing on the real-time traffic flow parameters to generate a standardized spatio-temporal correlation data set; performing slicing processing on the spatio-temporal correlation data set based on a dynamic time window to construct a multi-dimensional traffic state vector; calculating the intersection correlation degree of the target traffic area to determine the traffic impact factor between road segments; and fusing the multi-dimensional traffic state vector with the traffic impact factor to generate the regional dynamic traffic feature matrix.

[0021] Preferably, the entire road network data of the target traffic area is collected through the deployed multi-source heterogeneous sensor network. The geomagnetic sensor array in the multi-source heterogeneous sensor network is arranged on each lane to continuously monitor the traffic flow and occupancy rate, generating the first data stream; the video detection device captures the driving trajectories of vehicles and extracts microscopic behavior parameters such as following distance and lane-changing frequency, generating the second data stream; the floating vehicle GPS data is used to calculate the average speed and travel time reliability of the road section, generating the third data stream; the roadside weather station collects environmental parameters such as visibility and road surface skid coefficient, generating the fourth data stream; the V2X communication module receives the emergency braking and abnormal lane-changing warning signals of connected vehicles in real time, generating the fifth data stream. By storing the first data stream, the second data stream, the third data stream, the fourth data stream, and the fifth data stream in a set, real-time traffic flow parameters are obtained. Subsequently, the data streams from different data sources may be asynchronous in time. To ensure data unity, all data will be synchronized according to timestamps to ensure that the data collected by different sensors and devices can be processed within the same time frame. Similarly, different data streams usually come from different locations and may involve different intersections or road sections. To align spatial information, the data needs to be matched and classified according to spatial units such as road sections, lanes, and intersections. For example, the traffic flow data collected by the geomagnetic sensors is aligned with the data captured by the video surveillance according to the corresponding positions through map coordinates or regional division. After completing the spatio-temporal alignment of the real-time traffic flow parameters, to eliminate the differences in dimension and scale between different data sources, all the collected data needs to be standardized. Common methods include normalizing each data stream (such as the maximum-minimum normalization method) or using the z-score normalization method, so that the numerical values of different data streams can be compared and processed on the same scale. After completing data synchronization, standardization, and spatial alignment, these processed data are integrated into a standardized spatio-temporal correlation dataset to ensure data unity and consistency. Then, based on the dynamic time window, these spatio-temporal correlation data are sliced to construct multi-dimensional traffic state vectors, which contain the traffic state information of each intersection and road section in different time dimensions. The collected accident history data is then divided according to intersections, and the divided accident history data is time-aligned. After alignment, correlation analysis methods such as Pearson correlation coefficient or Euclidean distance are used to quantify the similarity of traffic flow and traffic conditions between intersections, and based on these similarities, it is determined which intersections have a strong correlation in traffic conditions. The calculated similarity will be used as the traffic impact factor between road sections, which reflects how the traffic conditions of one road section affect the traffic flow of its adjacent road sections.Then, the multi-dimensional traffic state vector is fused with the calculated traffic impact factor, that is, the multi-dimensional traffic state vector and the traffic impact factor are input into the fusion model. The fusion model performs a non-linear mapping according to the traffic state of each time period or section in the multi-dimensional traffic state vector, such as traffic flow, speed, density, etc., and the traffic impact factor between sections, combined with the mapping relationship learned from the sample data, according to the topological structure of the target traffic area, so that the multi-dimensional traffic state vector and the traffic impact factor are fused to generate a regional dynamic traffic feature matrix. This regional dynamic traffic feature matrix is a three-dimensional matrix with spatio-temporal continuity, including the time dimension (such as time stamps per minute or per second), the space dimension (each intersection and section), and the feature dimension (such as traffic flow fluctuation coefficient, speed dispersion, accident risk index, etc.). Through this matrix, the dynamic traffic characteristics of the target traffic area can be comprehensively reflected, providing comprehensive data support for subsequent green wave coordination control and safety warning.

[0022] For the fusion model, it can be constructed based on the deep neural network in the neural network. The construction method is to input the historical traffic state, historical traffic impact factor, and historical traffic feature matrix into the network, and continuously optimize the network performance through processes such as forward propagation, loss calculation, backpropagation, and parameter optimization until the maximum number of iterations is reached or the loss converges. After training, the current network will be verified, and the accuracy of the network on the verification data will be calculated. When the accuracy meets the preset accuracy, the current deep neural network will be used as the fusion model; otherwise, hyperparameters such as the learning rate and the number of training batches will be adjusted to further improve the network's ability.

[0023] Based on the regional dynamic traffic feature matrix, green wave coordination analysis is performed on the target traffic area to generate a sub-region division plan.

[0024] In one embodiment, first, based on the regional dynamic traffic feature matrix, traffic dynamic analysis is performed on the target traffic area to obtain traffic accident record logs. These accident data help identify potential safety risks at specific times and locations and provide a reference for subsequent sub-area division. Subsequently, according to the spatio-temporal correlation degree of accidents and the road section topology structure of the target traffic area, constraint conditions for sub-area division are set. Here, factors such as intersection spacing and road grade are considered. The intersection spacing affects the time for vehicles to pass through each intersection. Shorter spacing may require more precise green wave coordination to avoid traffic conflicts, while longer spacing may require a longer green wave cycle. The road grade (such as expressway, arterial road, secondary arterial road, etc.) affects the traffic flow capacity and traffic demand. High-grade roads carry a large traffic volume and require different green wave strategies. By combining these factors, dynamic clustering of intersections is carried out to determine the preliminary sub-area division plan. Then, real-time traffic state change data is retrieved, and based on real-time traffic parameters such as traffic flow, speed, and lane occupancy, multi-objective optimization of the preliminary sub-area division plan is performed. The optimization objectives include improving coordination efficiency, reducing accident risks, etc. After optimization, the green wave coordination is divided in combination with the intersection spacing and road grade to generate a topological structure diagram with variable boundary markings. Finally, the topological structure diagram with variable boundary markings is synchronized to the sub-area division plan to ensure that the green wave control plan for each sub-area can be flexibly adjusted according to real-time traffic conditions and regional requirements, thereby achieving more efficient and safe traffic flow coordination and early warning.

[0025] Furthermore, the present application provides a method for performing green wave coordination analysis on a target traffic area based on the regional dynamic traffic feature matrix to generate a sub-area division plan, the method comprising:

[0026] Performing traffic dynamic analysis based on the regional dynamic traffic feature matrix to obtain traffic accident record logs, the traffic accident record logs including the spatio-temporal correlation degree of accidents; setting sub-area division constraint conditions according to the spatio-temporal correlation degree of accidents in combination with the road section topology structure of the target traffic area, dynamically clustering the intersection nodes of the target traffic area according to the sub-area division constraint conditions to determine an initial sub-area division plan; retrieving real-time traffic state change data to perform multi-objective optimization on the initial sub-area division plan, performing green wave coordination division according to the optimization result, and constructing a topological structure diagram with variable boundary markings; synchronizing the topological structure diagram with variable boundary markings to the sub-area division plan.

[0027] Preferably, traffic dynamic analysis is performed based on the data in the regional dynamic traffic feature matrix, that is, the flow fluctuation coefficient, the distribution characteristics of accident-prone periods, and the intersection correlation index are extracted from the regional dynamic traffic feature matrix. The flow fluctuation coefficient is used to measure the traffic flow fluctuations in different time periods, helping to identify potential traffic congestion and high-risk periods for accidents; the distribution characteristics of accident-prone periods can help determine which periods are more likely to have accidents, and thus pay special attention to the control optimization of these periods during green wave coordination; the intersection correlation index evaluates the traffic impact relationship between intersections, facilitating the determination of which intersections need to be specially coordinated when adjusting traffic flow. By standardizing the flow fluctuation coefficient, the distribution characteristics of accident-prone periods, and the intersection correlation index, and then performing weighted summation on the processed data, the accident spatio-temporal correlation degree of each road section is obtained, and these accident spatio-temporal correlation degrees are added to the traffic accident record log. Subsequently, according to the accident spatio-temporal correlation degree in the traffic accident record log and the road section topology structure of the target traffic area (including factors such as intersection spacing and road grade), the constraint conditions for sub-region division are set. Road sections with shorter intersection spacing usually require more precise green wave coordination to reduce traffic conflicts, while intersections with longer spacing may require longer green wave cycles to maintain traffic flow. The difference in road grade also affects the sub-region division. High-grade roads usually carry more traffic flow, so their green wave coordination should be differentiated from that of low-grade roads. Through these constraint conditions, dynamic clustering of the intersection nodes in the target traffic area is performed, that is, the standardized accident spatio-temporal correlation degree, intersection spacing, and road grade are spliced to form a multi-dimensional feature vector for each intersection, and then K-means clustering is used for aggregation operations. K-means clustering randomly selects K intersections as the initial clustering centers, and according to the distance between the feature vector of each intersection and the clustering centers, each intersection is assigned to the nearest clustering center, and then based on the intersections assigned to each cluster, new clustering centers (the mean of each dimension) are calculated until the clustering centers no longer change or reach the preset number of iterations. Through the above steps, finally, the intersections are divided into several sub-regions according to the accident spatio-temporal correlation degree, intersection spacing, and road grade, and these sub-regions form the initial sub-region division plan. The intersections in each sub-region have similar characteristics, and these characteristics determine their green wave coordination requirements. For example, the intersections in the same sub-region may have similar road grades, accident occurrence risks, and traffic flow densities, and can share similar green wave coordination strategies; the intersections between different sub-regions may require different green wave coordination strategies to adapt to different traffic flows, accident risks, and road section requirements. After that, real-time traffic state change data is retrieved, including real-time traffic conflict warning signals, which reflect potential emergencies and safety hazards in the current traffic state. Based on these data, multi-objective optimization is performed, and the optimization objectives include maximizing the coordination benefit between sub-regions and minimizing the safety risk within sub-regions.Maximizing the coordination benefit of sub - intervals aims to make the traffic flow between different sub - regions more efficiently coordinated by optimizing the allocation of green - wave signals, thereby reducing traffic congestion in the entire region. Minimizing the safety risk within a sub - region focuses on dynamically adjusting the green - wave signals within each sub - region based on information such as real - time traffic flow, vehicle speed, and traffic accident records to reduce the likelihood of traffic accidents. The optimization is carried out using Particle Swarm Optimization (PSO). The PSO algorithm needs to first define the position and velocity of particles. Each position of a particle represents a sub - region division scheme, and the position of each particle is the division information of intersections, indicating which sub - region an intersection belongs to. The velocity of a particle represents the change in sub - region division. For example, the velocity of a particle can be the change information of intersection division, that is, the switching situation between sub - regions, and the particle velocity can be expressed as a division operation (for example, an intersection moves from sub - region 1 to sub - region 2). Then, it is evaluated through an objective function (the difference between coordination benefit and safety risk) to obtain the fitness of the particle. The objective of the objective function is to maximize the coordination benefit and minimize the safety risk. Among them, the coordination benefit refers to whether the traffic flow, vehicle speed, lane occupancy, etc. within a sub - region are coordinated, which can be quantified by simulating and evaluating the green - wave coordination effect between intersections within a sub - region; the safety risk can be evaluated by the mean value of the spatio - temporal correlation degree of accidents in each sub - region. The PSO algorithm explores the solution space by updating the velocity and position of particles. In each generation of iteration, particles update their velocity and position and are evaluated using the objective function. Particles with high fitness indicate that their sub - region division scheme is better. Each particle records its own optimal solution, and there is a global optimal solution among all particles. In this way, the PSO can gradually adjust the initial sub - region division to make the intersections within each sub - region more in line with the coordination and safety requirements. Then, according to the results of multi - objective optimization, green - wave coordination division is carried out, that is, the optimization results are marked in the road - segment topological structure to construct a topological structure diagram with variable - boundary markings. This diagram shows the boundaries of each sub - region and marks the traffic - flow relationship with adjacent sub - regions and the coordination of green - wave signals in each sub - region. Through this topological structure diagram, the green - wave control scheme of each sub - region can be flexibly adjusted to meet different traffic - flow and safety requirements. Finally, the constructed topological structure diagram with variable - boundary markings is synchronized to the preliminary sub - region division scheme to ensure that the green - wave control strategy of each sub - region is consistent with the traffic flow, road grade, accident risk, and real - time changes in the region, thereby achieving more efficient and safe traffic coordination control. Through the above steps, comprehensively considering the intersection spacing, road grade, accident historical data, and real - time traffic conditions, an optimized green - wave coordination sub - region division scheme is finally generated, providing a basis for subsequent green - wave coordination control and traffic - safety early warning.

[0028] Extract the traffic - flow characteristics of multiple regions based on the sub - region division scheme, and calculate and obtain the green - wave coordination control parameters according to the traffic - flow characteristics of multiple regions.

[0029] In one embodiment, after completing the sub-region division scheme, the target traffic area is detected according to the traffic flow characteristics of multiple regions, with key parameters such as traffic flow, vehicle speed, and lane occupancy at each intersection being focused on. Through these characteristics, the traffic flow states of different regions can be effectively identified, as well as potential traffic bottlenecks or conflict points. These conflict points refer to specific intersections or road sections where there is a potential risk of vehicle flow conflicts or congestion. On this basis, in combination with the traffic accident record log, the conflict point density for each intersection is weighted and calculated. The traffic accident record log provides spatio-temporal correlation data of accident occurrences, which can help identify high-risk road sections or time periods. By combining the conflict point density with the accident risk, a risk weight matrix is constructed. This matrix contains multiple safety risk indicators and is used to quantify the safety risk levels of different intersections. The risk weight matrix can provide a reference basis for subsequent green wave coordination to ensure priority optimization in high-risk regions or time periods. Subsequently, the green wave bandwidth parameter is introduced, and in combination with the safety risk indicators, a green wave bandwidth optimization model is constructed. Through this model, while ensuring maximum bandwidth utilization, the traffic safety risk can be minimized to the greatest extent. The green wave bandwidth optimization model comprehensively considers factors such as traffic flow, conflict point density, and risk weight at each intersection to optimize the cycle and duration of the green wave signal, thereby providing the most suitable green wave coordination control parameters for each intersection. Finally, through the calculation of the green wave bandwidth optimization model, the green wave coordination control parameters for each intersection are obtained. These parameters include the duration of the green light, signal cycle, etc., which work together to achieve efficient management of traffic flow while ensuring traffic safety within the region.

[0030] Furthermore, this application provides a method for extracting the traffic flow characteristics of multiple regions based on the sub-region division scheme and calculating and obtaining the green wave coordination control parameters, which includes:

[0031] Detecting the target traffic area according to the traffic flow characteristics of multiple regions to obtain the conflict point density of multiple intersections; performing weighted calculation in combination with the traffic accident record log according to the conflict point density to construct a risk weight matrix, where the risk weight matrix contains multiple safety risk indicators; introducing the green wave bandwidth parameter and combining the multiple safety risk indicators to construct a green wave bandwidth optimization model, and performing green wave calculation through the green wave bandwidth optimization model to obtain the green wave coordination control parameters.

[0032] Optionally, based on the traffic flow characteristics of multiple regions, detect the target traffic area to obtain the conflict point density of each intersection. The conflict point density refers to the potential conflict frequency between vehicles at a specific intersection or section. To calculate this indicator, data collected by millimeter-wave radar, such as traffic flow and vehicle movement trajectories, and data collected by video fusion technology, such as vehicle speed and lane occupancy, are extracted from the traffic flow characteristics. By combining the data collected by these two technologies, the probability of vehicles conflicting or colliding at intersections within a specific time period can be statistically calculated, and these probabilities of conflict or collision are used as the conflict point density of each intersection. Subsequently, obtain the traffic accident record log. The historical accident data in the traffic accident record log records the accident situations that occurred in the past at different intersections and sections, including the time, location, type of the accident and its relationship with the traffic flow, etc. These data help to identify the time periods and regions with frequent traffic accidents, and thus provide a basis for subsequent risk assessment. Perform weighted calculation based on the obtained conflict point density and the traffic accident record log to obtain multiple safety risk indicators, and organize these safety risk indicators into a risk weight matrix. High-risk regions will be assigned greater weights, so as to be preferentially optimized in the green wave coordination. Finally, introduce the green wave bandwidth parameter and combine it with the constructed multiple safety risk indicators to construct a green wave bandwidth optimization model. This model comprehensively considers multiple factors such as traffic flow, conflict point density, and accident records to maximize the bandwidth utilization and reduce the occurrence of traffic accidents. Through the calculation of the optimization model, the green wave coordination control parameters for each intersection, such as the green light duration and signal cycle, are obtained. These control parameters can ensure the safety and smoothness of traffic within the region without sacrificing the bandwidth utilization rate. Through these steps, the calculation of the green wave coordination control parameters based on the traffic flow characteristics, conflict point density, and historical accident data is finally realized, providing effective data support and optimization solutions for traffic safety early warning and green wave control.

[0033] Further, the present application provides a method for constructing a green wave bandwidth optimization model by introducing a green wave bandwidth parameter and combining the multiple safety risk indicators, and performing green wave calculation through the green wave bandwidth optimization model to obtain the green wave coordination control parameters. The method includes:

[0034] Conduct utilization analysis based on the green wave bandwidth parameter to determine the first target data, conduct safety analysis based on the multiple safety risk indicators to determine the second target data; perform data integration according to the first target data and the second target data to construct a bi-objective function, conduct constraint analysis through the bi-objective function, establish the green wave bandwidth optimization model for solution to determine the initial control parameters; conduct visual verification on the initial control parameters based on the green wave bandwidth optimization model, and perform online correction on the initial control parameters according to the verification results to obtain the green wave coordination control parameters.

[0035] Optionally, based on the green wave bandwidth parameter, conduct an analysis of the utilization of the green wave bandwidth to determine the first target data, i.e., the bandwidth utilization rate. The bandwidth utilization rate represents the effective use degree of the cycle and duration of the green wave signal within the area. By analyzing the traffic flow, vehicle speed, and green wave bandwidth requirements at each intersection, the bandwidth utilization situation of each sub-area within the area can be identified. The goal of maximizing the bandwidth utilization rate is to ensure that the green wave signal at each intersection can improve the passing capacity of the traffic flow as much as possible without wasting resources, reducing waiting time and congestion. Based on multiple safety risk indicators, conduct a safety analysis to determine the second target data, i.e., the safety risk coefficient. The safety risk coefficient is used to evaluate the traffic safety risks at different intersections, especially the potential hazards in high-conflict risk areas, and is obtained by normalizing the safety risk indicators. By calculating the safety risks at each intersection, areas with a higher frequency of traffic accidents can be identified, and priority can be given to optimizing the green wave control for these areas to minimize the possibility of accidents. Subsequently, based on the first target data (bandwidth utilization rate) and the second target data (safety risk coefficient), conduct data integration to construct a bi-objective function (the weighted difference between the bandwidth utilization rate and the safety risk coefficient). This function combines the two objectives of traffic efficiency and traffic safety, aiming to balance traffic fluency and safety. In the bi-objective function, the weights of the bandwidth utilization rate and the safety risk coefficient can be adjusted according to actual needs to ensure that while optimizing the green wave bandwidth, the requirements of traffic safety are taken into account. Through this bi-objective function, conduct constraint analysis to ensure that the set objectives can be met within the feasible range during the optimization process. For example, when optimizing the green wave bandwidth, constraint conditions such as road capacity, traffic flow, and time headway between intersections need to be considered. These conditions can help ensure that the green wave control scheme is both efficient and safe. Then, using this bi-objective function and constraint conditions, establish a green wave bandwidth optimization model and solve it. Through model solution, obtain the initial control parameters for each intersection, including the green light duration, signal cycle, red light time, etc. These control parameters ensure that under the given traffic conditions, the green wave signal can be effectively coordinated to improve the efficiency and safety of the traffic flow within the area. Finally, based on the green wave bandwidth optimization model, conduct a visual verification of the initial control parameters. The visual verification process includes using real-time traffic data and simulation software to display the effects of the initial control parameters under different traffic scenarios and analyze their actual impacts on the traffic flow. If the verification results show that the green wave control strategies at some intersections are still not ideal or there are safety hazards, the initial control parameters can be corrected online according to the verification results. By continuously adjusting and optimizing the control parameters, finally obtain more accurate and reliable green wave coordination control parameters to ensure the achievement of the optimal traffic coordination effect. Through the above process, based on the calculation and adjustment of the green wave bandwidth optimization model, the optimal green wave coordination control parameters are obtained, thus achieving the goal of improving the traffic flow efficiency while reducing the traffic safety risk.

[0036] Furthermore, the present application provides a method for visually verifying the initial control parameters based on the green wave bandwidth optimization model, and online correcting the initial control parameters according to the verification results to obtain the green wave coordinated control parameters. The method includes:

[0037] Obtaining real-time motion trajectory data of connected vehicles, superimposing the green wave bandwidth parameters and the real-time motion trajectory data of the connected vehicles in the target traffic area based on the initial control parameters to construct a three-dimensional spatio-temporal trajectory visualization interface; performing conflict impact analysis based on the three-dimensional spatio-temporal trajectory visualization interface and drawing a parameter sensitivity analysis map; and performing balance adjustment verification on the initial control parameters according to the parameter sensitivity analysis map to generate the verification results.

[0038] Optionally, obtain the real-time motion trajectory data of connected vehicles, which are obtained through V2X communication technology. The V2X communication module can transmit dynamic information such as the position information, driving speed, and acceleration of connected vehicles in real time. Through these data, the motion trajectory of the vehicle in the target traffic area and the driving conditions at different intersections and sections can be accurately captured. Among them, V2X (Vehicle-to-Everything) is a communication technology designed to enable communication between vehicles and other vehicles (V2V, Vehicle-to-Vehicle), road infrastructure (V2I, Vehicle-to-Infrastructure), pedestrians (V2P, Vehicle-to-Pedestrian), and the network (V2N, Vehicle-to-Network). V2X technology uses a wireless communication network to enable vehicles to exchange real-time data with the surrounding environment, providing key traffic information and enhancing the driving experience. Subsequently, based on the initial control parameters, the green wave bandwidth parameters are superimposed on the real-time motion trajectory data of connected vehicles. This step is achieved by constructing a three-dimensional spatio-temporal trajectory visualization interface, which visualizes information such as the vehicle's motion trajectory, green wave bandwidth allocation, and traffic signal cycle in the spatio-temporal dimension. The three-dimensional spatio-temporal trajectory interface can intuitively display the driving state of each vehicle at different time periods, including the vehicle's real-time position, speed, and the change of green wave signals. Through this visualization interface, the interaction relationship between green wave signal control and actual traffic flow can be understood in detail. After that, based on the three-dimensional spatio-temporal trajectory visualization interface, conflict impact analysis is carried out. Specifically, quantitatively analyze the impact of different green wave signal control strategies (such as signal phase difference) on traffic flow, especially on traffic conflicts. In the analysis, focus on the impact of a phase difference of ±2 seconds on bandwidth and conflict rate. The phase difference refers to the time difference between the green light cycles of adjacent intersections. A change of ±2 seconds can significantly affect the allocation of green wave bandwidth, thereby affecting the traffic flow between intersections and the possibility of traffic conflicts. By simulating the changes in bandwidth utilization rate and conflict rate caused by the phase difference, the optimal green wave signal phase setting can be identified, reducing traffic conflicts and improving traffic efficiency. Based on the above conflict impact analysis, a parameter sensitivity analysis graph is drawn, which shows the sensitivity of key indicators such as bandwidth utilization rate and conflict rate under different control parameters. Through this graph, it can be intuitively seen which parameters have a greater impact on traffic flow, conflict occurrence, and bandwidth utilization, providing a basis for subsequent parameter adjustment. Finally, based on the parameter sensitivity analysis graph, the balance adjustment verification of the initial control parameters is carried out.In this step, the focus is on achieving a balance between safety and efficiency, that is, while optimizing bandwidth utilization and improving traffic flow efficiency, ensuring that traffic safety risks are not overly ignored. By adjusting initial control parameters (such as green light cycle, signal phase, etc.) and repeatedly verifying the simulation, an optimal control scheme that can both improve traffic efficiency and reduce the conflict rate is finally found. After adjustment and verification, verification results are generated, including bandwidth utilization, conflict reduction rate, and fuel efficiency optimization value. Among them, bandwidth utilization reflects the actual utilization efficiency of the green wave bandwidth, ensuring that the green wave signal can be maximally utilized during peak traffic flow periods; the conflict reduction rate represents the ratio of traffic conflicts reduced by adjusting the green wave control strategy, ensuring traffic safety; the fuel efficiency optimization value represents the improvement of fuel efficiency and reduction of environmental pollution by optimizing the green wave signal to reduce the waiting time of vehicles at intersections. Finally, through this series of analyses and verifications, optimized green wave coordination control parameters are obtained, ensuring the high efficiency, safety, and environmental friendliness of traffic flow.

[0039] Furthermore, the present application provides a method of weighted calculation in combination with the accident record log according to the conflict point density to construct a risk weight matrix, and the method includes:

[0040] Traverse the target traffic area according to the conflict point density to analyze adjacent road sections, and determine the speed dispersion of adjacent road sections; perform weighted calculation according to the speed dispersion in combination with the accident record log to determine multiple risk weight coefficients; perform a safety warning assessment on the target traffic area based on the multiple risk weight coefficients to generate a graded warning signal; perform a safety risk analysis according to the graded warning signal to generate the multiple safety risk indicators and construct a risk weight matrix.

[0041] Optionally, first, traverse the target traffic area according to the conflict point density, analyze adjacent road segments, and calculate the speed dispersion during this analysis to measure the stability and consistency of traffic flow. Specifically, the speed dispersion can be achieved by calculating the variance of speed gradients and the platoon dispersion coefficient. The variance of speed gradients is calculated based on the speed difference and average speed between adjacent vehicles, reflecting the fluctuation degree of the speeds of adjacent vehicles. A larger gradient variance indicates unstable traffic flow, with a large difference in vehicle speeds, which may increase the risk of traffic conflicts; the platoon dispersion coefficient is calculated through the average speed and standard deviation of speed, measuring the speed difference between vehicles in the same platoon. A higher dispersion coefficient means a larger speed difference between vehicles within the platoon, increasing the probability of rear-end collisions. Through these two indicators, the stability of traffic flow at each road segment or intersection can be judged, providing data support for subsequent safety risk assessment. Subsequently, weighted calculations are performed based on the speed dispersion data in combination with the traffic accident record log. The traffic accident record log contains historical accident data for different road segments and intersections, including the spatio-temporal distribution of accidents and accident types. By combining the speed dispersion with the total number of accidents at each road segment or intersection in the traffic accident record, multiple risk weight coefficients are obtained, which are used to quantify the safety risks of different road segments or intersections. A higher risk coefficient indicates a greater potential for traffic accidents at that road segment or intersection. Through this weighted calculation, the safety risks of different regions can be more accurately evaluated. After that, based on the obtained multiple risk weight coefficients, a safety warning assessment is carried out for the target traffic area. The core of the assessment is to judge the safety risk of the area by setting a dynamic safety threshold. If the risk weight coefficient of a certain road segment or intersection exceeds this threshold, a safety warning will be triggered, generating graded warning signals, including level-1 warning, level-2 warning, and level-3 warning. Among them, a level-1 warning indicates a low safety risk in the area, smooth traffic flow, and normal operation can continue; a level-2 warning indicates a medium safety risk in the area, potential traffic problems need to be noted, and traffic signals may need to be adjusted or monitoring increased; a level-3 warning indicates a high safety risk in the area, accidents may occur, and immediate measures need to be taken, such as adjusting the green wave signal, increasing warning signs, or dispatching patrol vehicles. Then, based on the above graded warning signals, further safety risk analysis is carried out, that is, the risk weight coefficient is multiplied by the graded warning signal to obtain multiple safety risk indicators, and a risk weight matrix is constructed based on these safety risk indicators, providing a scientific basis for subsequent traffic safety management and green wave coordination, and helping to accurately identify and handle high-risk areas.

[0042] Formulate an initial control plan according to the green wave coordination control parameters, execute the initial control plan for data feedback, and compensate the green wave coordination control parameters according to the feedback results to obtain a regional coordination control plan.

[0043] In one embodiment, an initial control scheme is developed based on green wave coordination control parameters. This scheme is a preliminary optimization result based on information such as current traffic flow, vehicle speed, intersection layout, and green wave bandwidth. The initial control scheme determines parameters such as green light duration, signal cycle, and red light cycle at each intersection and activates the green wave control system based on these settings. Subsequently, the initial control scheme is executed and data feedback is generated. This feedback data helps evaluate the effectiveness of the initial control scheme and whether it can effectively optimize traffic flow, reduce traffic conflicts, and improve traffic efficiency. Based on this feedback, the green wave coordination control parameters in the initial control scheme are compensated. The compensation process adjusts the green wave signal control strategy based on actual traffic conditions. The goal of compensation is to minimize the difference between the initial scheme and actual traffic conditions and improve overall traffic flow efficiency. By continuously adjusting and compensating the green wave coordination control parameters, an optimized regional coordination control scheme is ultimately derived. This scheme can better adapt to actual traffic conditions, ensure smooth traffic flow, reduce traffic accidents, and maximize the benefits of green wave coordination.

[0044] Furthermore, the present application provides the method of executing the initial control scheme to perform data feedback, compensating the green wave coordinated control parameters according to the feedback results, and obtaining a regional coordinated control scheme, the method comprising:

[0045] A sub-area correlation matrix is established according to the green wave coordination control parameters, and the vehicle mobility and phase coupling coefficient between adjacent sub-areas are calculated through the sub-area correlation matrix; the initial control scheme is executed according to the vehicle mobility and the phase coupling coefficient to perform data monitoring and generate a green wave control monitoring value; a sub-area coordination judgment is performed based on the green wave control monitoring value to generate a sub-area coordination judgment result; green wave coordination feedback is performed according to the sub-area coordination judgment result, and the green wave coordination control parameter is gradient compensated according to the feedback result to generate the regional coordination control scheme.

[0046] Preferably, based on the green wave coordination control parameters, a sub - area correlation matrix is established. The function of this matrix is to reflect the traffic flow relationship and the degree of mutual influence among sub - areas within the target traffic area. By classifying the intersection correlation degrees obtained above according to sub - areas, counting the correlation situations of intersections in each sub - area, a sub - area correlation matrix is established. This matrix can quantify the correlation degree between different sub - areas and help understand how the traffic conditions in a certain sub - area affect the traffic flow in adjacent areas. For example, in sub - area 1, there are intersections 1, 2, and 3; in sub - area 2, there are intersections 4 and 5; in sub - area 3, there are intersections 6 and 7. Among them, intersection 1 is correlated with intersections 2, 4, and 6, and intersection 3 is correlated with intersections 2 and 5. Then, calculate the average value of the correlation degrees between intersection 1 and intersection 4 and between intersection 3 and intersection 5, and then calculate the ratio of the number of intersections correlated between sub - area 1 and sub - area 2 to the number of all intersections correlated in sub - area 1, and multiply the ratio by the average value of the correlation degrees as the correlation degree between sub - area 1 and sub - area 2. Subsequently, using the sub - area correlation matrix, calculate the vehicle flow migration rate and phase coupling coefficient between adjacent sub - areas with larger correlation degrees. The vehicle flow migration rate is obtained by counting the number of vehicles flowing from one sub - area to another within a unit time, which reflects the rate of vehicle flow from one sub - area to another. Usually affected by factors such as intersection spacing and signal cycle, by calculating the vehicle flow migration rate, it can be determined the degree of traffic flow between adjacent sub - areas and how to achieve a smooth transition of vehicle flow through coordinated green wave signals; the phase coupling coefficient is obtained by calculating the ratio of the sum of the squares of the green - light signal phase differences to the sum of the squares of the green - light signal durations, which represents the synchronization degree between the green - light phases of adjacent sub - areas during the green wave signal coordination process. The calculation of the phase coupling coefficient can help understand how the green wave signals between two sub - areas affect each other, ensure the effective cooperation of green - light signals in different sub - areas, and avoid traffic signal chaos. After that, based on the vehicle flow migration rate and phase coupling coefficient, execute the initial control plan and conduct real - time data monitoring. The monitored contents include indicators such as the implementation of green wave signals, traffic flow, and vehicle passing rate at each intersection. By real - time monitoring these data, it can be evaluated whether the green wave control plan is effectively coordinated among sub - areas and generate corresponding green wave control monitoring values. These monitoring values reflect the actual effect of the green wave coordination control, such as the smoothness of traffic flow, congestion situation in each sub - area, and whether the expected control target is achieved. Then, based on the green wave control monitoring values, conduct sub - area coordination determination. The purpose of sub - area coordination determination is to evaluate the coordination situation of green wave signals between different sub - areas. If the coordination effect of the green wave signal in a certain sub - area is poor, resulting in the traffic flow in adjacent sub - areas being affected, adjustment is required. The sub - area coordination determination result is comprehensively analyzed according to factors such as traffic flow changes, vehicle speed fluctuations, and congestion situations, so as to obtain the evaluation result of the coordination effect of each sub - area. Finally, based on the sub - area coordination determination result, conduct green wave coordination feedback.If the determination result indicates that there are problems with the green wave coordination in some sub - areas, or the traffic flow fails to reach the expected smooth state, adjustments need to be made according to the feedback. The feedback mechanism performs gradient compensation on the green wave coordination control parameters according to the actual situation. The gradient compensation finely adjusts parameters such as the duration, cycle, and phase of the green wave signal, so that the green wave signals in each sub - area can more precisely adapt to the changes in traffic flow. Through this compensation, the green wave coordination between sub - areas can be optimized, and finally an optimized regional coordination control plan can be generated. This process ensures that the green wave coordination control can continuously make dynamic adjustments according to the real - time traffic flow, thereby maximizing the efficiency of traffic flow, reducing congestion, and enhancing road safety.

[0047] Furthermore, after the present application provides compensating the green wave coordination control parameters according to the feedback result and obtaining the regional coordination control plan, the method includes:

[0048] Performing short - term traffic conflict prediction based on the real - time motion trajectory data of the connected vehicles to construct a conflict heat map; performing mapping coincidence analysis on the conflict heat map and the real - time motion trajectory data of the connected vehicles, and identifying multiple potential risk areas according to the coincidence result; sending the regional coordination control plan to the signal controller for execution, and giving early warnings based on the multiple safety risk indicators in combination with the multiple potential risk areas to generate traffic safety early warning signals.

[0049] Optionally, based on the real-time movement trajectory data of connected vehicles, short-term conflict prediction of traffic flow is carried out. By inputting information such as the speed, acceleration, and position of vehicles into the short-term conflict prediction model (constructed in the same way), the possible microscopic traffic conflict situations within the next 5 to 15 seconds are predicted, and a conflict heat map is constructed according to the prediction results. The conflict heat map shows the density of these predicted conflict areas, usually indicating the level of conflict risk through the depth of color. The conflict heat map can intuitively display the traffic conflict hotspots in each road section or intersection within a specific time period. Subsequently, a mapping coincidence analysis is carried out between the conflict heat map and the real-time movement trajectory data of connected vehicles. By combining the conflict areas in the heat map with the real-time vehicle data, the movement conditions of different vehicles within the predicted conflict areas are analyzed. This analysis can help identify which areas have higher potential traffic risks, especially which intersections or road sections where vehicle flows may trigger conflicts, forming multiple potential risk areas. According to the analysis results, the regional coordination control plan is sent to the corresponding signal controller for execution. The regional coordination control plan improves the traffic flow in potential risk areas and reduces possible conflict events by adjusting the green wave signal and traffic signal cycle. After the regional coordination control plan is issued, a comprehensive analysis is carried out based on multiple safety risk indicators and multiple potential risk areas, and a traffic safety warning signal is generated through threshold comparison to remind vehicles and drivers of upcoming traffic risks. The warning signal will be adjusted according to the dynamic changes of the traffic flow to ensure that a warning is issued in a timely manner in high-risk areas. Then, through the roadside unit RSU (Road Side Unit), a hierarchical warning instruction is sent to the target vehicle. The warning instruction includes a recommended speed range and a lane change recommendation. Among them, the recommended speed range indicates the recommended speed for the target vehicle when approaching the risk area to help the driver adjust the speed and avoid conflicts. If the risk in a certain area is relatively high, the warning instruction will also include a lane change recommendation to prompt the target vehicle to select a safe lane or avoid the high-risk area. Through this process, the occurrence of traffic conflicts can be effectively predicted and reduced, and at the same time, real-time safety warnings are provided through the intelligent transportation system to improve road safety.

[0050] In summary, the embodiments of the present application have at least the following technical effects:

[0051] In the embodiment of the present application, the target traffic area is first traversed to collect traffic road data, and a regional dynamic traffic feature matrix is constructed; subsequently, green wave coordination analysis is performed on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-area division scheme; then, traffic flow features of multiple areas are extracted based on the sub-area division scheme, and green wave coordination control parameters are calculated according to the traffic flow features of multiple areas; finally, an initial control scheme is formulated according to the green wave coordination control parameters, the initial control scheme is executed for data feedback, and the green wave coordination control parameters are compensated according to the feedback result to obtain a regional coordination control scheme. These technical effects together solve the technical problem that traditional green wave control only statically optimizes traffic efficiency and cannot dynamically respond to traffic safety risks, resulting in difficulty in coordinating efficiency and safety, and achieve the technical effects of dynamically adjusting the subtitle color according to environmental light and user historical preferences, and optimizing subtitle content through logical reasoning and scenario analysis, improving the readability and accuracy of subtitles, and ensuring the personalization and accuracy of subtitles in digital technology-based playback devices.

[0052] Embodiment 2, based on the same inventive concept as the regional green wave coordination control method for traffic safety warning in the foregoing embodiment, as Figure 2 shown, the present application provides a regional green wave coordination control system for traffic safety warning, and the system includes: a data collection component 11: traversing the target traffic area to collect traffic road data and constructing a regional dynamic traffic feature matrix; a green wave coordination analysis component 12: performing green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-area division scheme; a control parameter calculation component 13: extracting traffic flow features of multiple areas based on the sub-area division scheme and calculating green wave coordination control parameters according to the traffic flow features of multiple areas; a control parameter compensation component 14: formulating an initial control scheme according to the green wave coordination control parameters, executing the initial control scheme for data feedback, and compensating the green wave coordination control parameters according to the feedback result to obtain a regional coordination control scheme.

[0053] Further, the data collection component 11 is further used to execute the following method:

[0054] Traversing the target traffic area through a multi-source heterogeneous sensor network to collect whole-road network data, obtaining real-time traffic flow parameters; performing spatio-temporal alignment processing on the real-time traffic flow parameters to generate a standardized spatio-temporal correlation data set; performing slicing processing on the spatio-temporal correlation data set based on a dynamic time window to construct a multi-dimensional traffic state vector; calculating the intersection correlation degree of the target traffic area to determine the traffic influence factor between road segments; fusing the multi-dimensional traffic state vector with the traffic influence factor to generate the regional dynamic traffic feature matrix.

[0055] Furthermore, the green wave coordination analysis component 12 is also used to execute the following method:

[0056] Based on the regional dynamic traffic feature matrix, conduct traffic dynamic analysis to obtain a traffic accident record log, where the traffic accident record log includes accident spatio-temporal correlation; set sub-region division constraint conditions according to the accident spatio-temporal correlation in combination with the road section topological structure of the target traffic region, and dynamically cluster the intersection nodes of the target traffic region according to the sub-region division constraint conditions to determine an initial sub-region division scheme; retrieve real-time traffic state change data to perform multi-objective optimization on the initial sub-region division scheme, conduct green wave coordination division according to the optimization result, and construct a topological structure diagram with variable boundary identifiers; synchronize the topological structure diagram with variable boundary identifiers to the sub-region division scheme.

[0057] Furthermore, the control parameter calculation component 13 is also used to execute the following method:

[0058] Detect the target traffic region according to the traffic flow characteristics of multiple regions to obtain the conflict point density of multiple intersections; conduct weighted calculation according to the conflict point density in combination with the traffic accident record log to construct a risk weight matrix, where the risk weight matrix includes multiple safety risk indicators; introduce a green wave bandwidth parameter and combine the multiple safety risk indicators to construct a green wave bandwidth optimization model, and conduct green wave calculation through the green wave bandwidth optimization model to obtain the green wave coordination control parameters.

[0059] Furthermore, the control parameter calculation component 13 is also used to execute the following method:

[0060] Conduct utilization analysis based on the green wave bandwidth parameter to determine the first target data, conduct safety analysis based on the multiple safety risk indicators to determine the second target data; conduct data integration according to the first target data and the second target data to construct a bi-objective function, conduct constraint analysis through the bi-objective function, establish the green wave bandwidth optimization model for solution to determine the initial control parameters; conduct visual verification on the initial control parameters based on the green wave bandwidth optimization model, and perform online correction on the initial control parameters according to the verification result to obtain the green wave coordination control parameters.

[0061] Furthermore, the control parameter calculation component 13 is also used to execute the following method:

[0062] Obtain the real-time motion trajectory data of connected vehicles, superimpose the green wave bandwidth parameter and the real-time motion trajectory data of the connected vehicles in the target traffic area based on the initial control parameter, and construct a three-dimensional spatio-temporal trajectory visualization interface; conduct conflict impact analysis based on the three-dimensional spatio-temporal trajectory visualization interface, and draw a parameter sensitivity analysis map; verify the balance adjustment of the initial control parameter according to the parameter sensitivity analysis map, and generate the verification result.

[0063] Further, the control parameter calculation component 13 is further configured to execute the following method:

[0064] Analyze adjacent road segments by traversing the target traffic area according to the conflict point density to determine the speed dispersion degree of adjacent road segments; perform weighted calculation according to the speed dispersion degree in combination with the traffic accident record log to determine multiple risk weight coefficients; conduct safety warning assessment on the target traffic area based on the multiple risk weight coefficients, generate a graded warning signal; conduct safety risk analysis according to the graded warning signal to generate the multiple safety risk indicators and construct a risk weight matrix.

[0065] Further, the control parameter compensation component 14 is further configured to execute the following method:

[0066] Establish a sub-region correlation matrix according to the green wave coordination control parameter, calculate the vehicle flow migration rate and phase coupling coefficient between adjacent sub-regions through the sub-region correlation matrix; execute the initial control scheme according to the vehicle flow migration rate and the phase coupling coefficient for data monitoring to generate a green wave control monitoring value; conduct sub-region coordination determination based on the green wave control monitoring value to generate a sub-region coordination determination result; conduct green wave coordination feedback according to the sub-region coordination determination result, and perform gradient compensation on the green wave coordination control parameter according to the feedback result to generate the regional coordination control scheme.

[0067] Further, the control parameter compensation component 14 is further configured to execute the following method:

[0068] Perform short-term traffic conflict prediction based on the real-time motion trajectory data of connected vehicles to construct a conflict heat map; conduct mapping coincidence analysis on the conflict heat map and the real-time motion trajectory data of connected vehicles, and identify multiple potential risk areas according to the coincidence result; send the regional coordination control scheme to the signal controller for execution, and conduct early warning based on the multiple safety risk indicators in combination with the multiple potential risk areas to generate a traffic safety early warning signal.

[0069] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0071] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A regional green wave coordination control method for traffic safety warning, characterized in that, The method includes: Traversing the target traffic area to collect traffic road data and constructing a regional dynamic traffic feature matrix; Performing green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-region division plan; Extracting traffic flow characteristics of multiple regions based on the sub-region division plan, and calculating and obtaining green wave coordination control parameters according to the traffic flow characteristics of multiple regions; Formulating an initial control plan according to the green wave coordination control parameters, executing the initial control plan for data feedback, and compensating the green wave coordination control parameters according to the feedback results to obtain a regional coordination control plan; Performing green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix to generate a sub-region division plan, the method including: Performing traffic dynamic analysis based on the regional dynamic traffic feature matrix to obtain a traffic accident record log, the traffic accident record log including accident spatio-temporal correlation, including: standardizing the traffic flow fluctuation coefficient, accident-prone time period distribution characteristics, and intersection correlation index, and then performing weighted summation on the processed data to obtain the accident spatio-temporal correlation of each road section, and adding these accident spatio-temporal correlations to the traffic accident record log; Setting sub-region division constraint conditions according to the accident spatio-temporal correlation in combination with the road section topology structure of the target traffic area, and dynamically clustering the intersection nodes of the target traffic area according to the sub-region division constraint conditions to determine an initial sub-region division plan; Retrieving real-time traffic state change data to perform multi-objective optimization on the initial sub-region division plan, and performing green wave coordination division according to the optimization result to construct a topological structure diagram with variable boundary identifiers; Synchronizing the topological structure diagram with variable boundary identifiers to the sub-region division plan; Extracting traffic flow characteristics of multiple regions based on the sub-region division plan, and calculating and obtaining green wave coordination control parameters according to the traffic flow characteristics of multiple regions, the method including: Detecting the target traffic area according to the traffic flow characteristics of multiple regions to obtain the conflict point density of multiple intersections; Performing weighted calculation according to the conflict point density in combination with the traffic accident record log to construct a risk weight matrix, the risk weight matrix including multiple safety risk indicators; Introducing a green wave bandwidth parameter to construct a green wave bandwidth optimization model in combination with the multiple safety risk indicators, and performing green wave calculation through the green wave bandwidth optimization model to obtain the green wave coordination control parameters.

2. The regional green wave coordination control method for traffic safety warning according to claim 1, characterized in that, Traversing the target traffic area to collect traffic road data and constructing a regional dynamic traffic feature matrix, the method including: Traversing the target traffic area through a multi-source heterogeneous sensor network to collect whole-road network data and obtain real-time traffic flow parameters; Performing spatio-temporal alignment processing on the real-time traffic flow parameters to generate a standardized spatio-temporal correlation data set; Performing slicing processing on the spatio-temporal correlation data set based on a dynamic time window to construct a multi-dimensional traffic state vector; Calculating the intersection correlation degree of the target traffic area to determine the traffic influence factor between road sections; Fusing the multi-dimensional traffic state vector with the traffic influence factor to generate the regional dynamic traffic feature matrix.

3. The regional green wave coordinated control method for traffic safety warning according to claim 1, wherein Introduce the green wave bandwidth parameter and combine it with the multiple safety risk indicators to construct a green wave bandwidth optimization model. Perform green wave calculation through the green wave bandwidth optimization model to obtain the green wave coordinated control parameters. The method includes: Conduct utilization analysis based on the green wave bandwidth parameter to determine the first target data, and conduct safety analysis based on the multiple safety risk indicators to determine the second target data; Integrate the data according to the first target data and the second target data to construct a bi-objective function. Conduct constraint analysis through the bi-objective function, establish the green wave bandwidth optimization model for solution, and determine the initial control parameters; Based on the green wave bandwidth optimization model, conduct visual verification on the initial control parameters, and perform online correction on the initial control parameters according to the verification results to obtain the green wave coordinated control parameters.

4. The regional green wave coordinated control method for traffic safety warning according to claim 3, characterized in that Based on the green wave bandwidth optimization model, conduct visual verification on the initial control parameters, and perform online correction on the initial control parameters according to the verification results to obtain the green wave coordinated control parameters. The method includes: Obtain the real-time movement trajectory data of connected vehicles, and superimpose the green wave bandwidth parameter and the real-time movement trajectory data of the connected vehicles in the target traffic area based on the initial control parameters to construct a three-dimensional space-time trajectory visualization interface; Conduct conflict impact analysis based on the three-dimensional space-time trajectory visualization interface, and draw a parameter sensitivity analysis map; Conduct balance adjustment verification on the initial control parameters according to the parameter sensitivity analysis map to generate the verification results.

5. The regional green wave coordination control method for traffic safety warning according to claim 1, wherein, Perform weighted calculation according to the conflict point density and the traffic accident record log to construct a risk weight matrix. The method includes: Traverse the target traffic area according to the conflict point density to analyze adjacent road sections, and determine the speed dispersion degree of adjacent road sections; Perform weighted calculation according to the speed dispersion degree and the traffic accident record log to determine multiple risk weight coefficients; Conduct safety warning assessment on the target traffic area based on the multiple risk weight coefficients to generate a graded warning signal; Conduct safety risk analysis according to the graded warning signal to generate the multiple safety risk indicators to construct a risk weight matrix.

6. The regional green wave coordinated control method for traffic safety warning according to claim 1, characterized in that Execute the initial control scheme to perform data feedback, and compensate the green wave coordinated control parameters according to the feedback results to obtain a regional coordinated control scheme. The method includes: Establish a sub-region correlation matrix according to the green wave coordinated control parameters, and calculate the vehicle flow migration rate and phase coupling coefficient between adjacent sub-regions through the sub-region correlation matrix; Execute the initial control scheme for data monitoring according to the vehicle flow migration rate and the phase coupling coefficient to generate a green wave control monitoring value; Conduct sub-region collaboration determination based on the green wave control monitoring value to generate a sub-region collaboration determination result; Conduct green wave coordination feedback according to the sub-region collaboration determination result, and perform gradient compensation on the green wave coordinated control parameters according to the feedback results to generate the regional coordinated control scheme.

7. The regional green wave coordinated control method for traffic safety warning according to claim 4, characterized in that After compensating the green wave coordinated control parameters according to the feedback results to obtain a regional coordinated control scheme, the method includes: Conduct short-term traffic conflict prediction based on the real-time movement trajectory data of connected vehicles to construct a conflict heat map; Perform mapping coincidence analysis on the conflict heat map and the real-time movement trajectory data of the connected vehicles, and identify multiple potential risk areas according to the coincidence results; Send the area coordination control scheme to the signal controller for execution, and generate a traffic safety warning signal based on the multiple safety risk indicators and the multiple potential risk areas.

8. Area green wave coordination control system for traffic safety warning, characterized in that, The system is used to execute the area green wave coordination control method for traffic safety warning according to any one of claims 1-7, and includes: Data acquisition component: Traverse the target traffic area to collect traffic road data and construct a regional dynamic traffic feature matrix; Green wave coordination analysis component: Perform green wave coordination analysis on the target traffic area based on the regional dynamic traffic feature matrix and generate a sub-area division scheme; Control parameter calculation component: Extract the traffic flow characteristics of multiple areas based on the sub-area division scheme, and calculate and obtain the green wave coordination control parameters according to the traffic flow characteristics of multiple areas; Control parameter compensation component: Formulate an initial control scheme according to the green wave coordination control parameters, execute the initial control scheme for data feedback, and compensate the green wave coordination control parameters according to the feedback results to obtain an area coordination control scheme.

Images