A traffic signal timing optimization method, system, storage medium and program product

Abstract

A traffic signal timing optimization method, system, storage medium and program product, which relates to the field of traffic management data processing systems. The method includes: determining a plurality of adjacent intersection nodes based on the location identification information of the local intersection node; collecting the vehicle passing state data and vehicle characteristic data of the local intersection node to generate traffic flow characteristic parameters; identifying the characteristic vehicle type and vehicle location information of the target characteristic vehicle; calculating the passing influence score of the target characteristic vehicle on the traffic flow of each intersection; constructing a traffic signal optimization model, and calculating an initial timing plan based on the traffic signal optimization model; sending traffic flow output data to the adjacent intersection nodes, and receiving traffic flow input data sent by the adjacent intersection nodes; updating the traffic signal optimization model, generating a final timing plan, and adjusting the signal control parameters of the local intersection node. Implementing this application can improve the accuracy of traffic signal timing.

Description

Technical Field

[0001] This application relates to the field of traffic management data processing systems, and in particular, to a traffic signal timing optimization method, system, storage medium, and program product. Background Art

[0002] With the acceleration of the urbanization process and the continuous growth of the motor vehicle ownership, the problem of urban traffic congestion has become increasingly prominent. In order to improve the road traffic efficiency and reduce traffic congestion, traffic management departments everywhere generally adopt intelligent traffic signal control systems for traffic management. In the complex urban road network environment, how to achieve intelligent timing control of traffic lights has become an important issue in current urban traffic management.

[0003] In related technologies, common traffic signal timing control schemes mainly adopt two methods: fixed timing and inductive timing. The fixed timing scheme is based on historical traffic flow data and pre-sets the signal cycle and phase ratio for different time periods. The inductive timing scheme adjusts the signal timing parameters dynamically by installing vehicle detectors at intersections and according to the vehicle queue length and waiting time detected in real time. Some advanced traffic management systems also adopt area coordinated timing technology to coordinate the signal timing of multiple intersections within the area by setting the green wave band on the main road.

[0004] However, the area coordinated timing technology in related technologies mainly optimizes according to the traffic flow characteristics of the main road, and the timing accuracy is insufficient when dealing with different vehicles, and the optimization effect is not good; for example, when special vehicles such as large vehicles and novice vehicles appear in the area, due to their long starting time and slow passing speed, etc., it is easy to break the original passing rhythm, causing difficulties for the following vehicles to follow and passing, and triggering secondary congestion. Summary of the Invention

[0005] This application provides a traffic signal timing optimization method, system, storage medium, and program product for improving the accuracy of traffic signal timing.

[0006] In a first aspect, the present application provides a traffic signal timing optimization method, which is applied to a traffic management system. The method includes: determining a plurality of adjacent intersection nodes interconnected with the local intersection node based on the location identification information of the local intersection node; collecting vehicle passing state data and vehicle characteristic data of the local intersection node, and generating traffic flow characteristic parameters according to the vehicle passing state data and the vehicle characteristic data; performing characteristic vehicle identification based on the vehicle characteristic data to obtain the characteristic vehicle type and vehicle location information of the target characteristic vehicle; calculating the passing influence score of the target characteristic vehicle on the traffic flow of each intersection according to the traffic flow characteristic parameters, the characteristic vehicle type, and the vehicle location information; constructing a traffic signal optimization model according to the traffic flow characteristic parameters and the passing influence score, and calculating an initial timing plan based on the traffic signal optimization model; sending traffic flow output data including the passing influence score and the initial timing plan to the adjacent intersection nodes, and receiving traffic flow input data sent by the adjacent intersection nodes; updating the traffic signal optimization model based on the traffic flow input data and the traffic flow output data, generating a final timing plan, and adjusting the signal control parameters of the local intersection node based on the final timing plan.

[0007] In the above embodiment, the traffic management system realizes the accurate identification and passing influence assessment of characteristic vehicles through the interconnection and cooperation based on the local intersection node and adjacent intersection nodes, combined with vehicle characteristic identification and passing influence scoring; the traffic management system dynamically adjusts the timing plan according to information such as vehicle type and location, and realizes regional collaborative optimization through data interaction between nodes, improves the flexibility and accuracy of signal timing, effectively alleviates the influence of characteristic vehicles on traffic flow, and improves the overall traffic efficiency of the road network.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the step of calculating the passing influence score of the target characteristic vehicle on the traffic flow of each intersection according to the traffic flow characteristic parameters, the characteristic vehicle type, and the vehicle location information specifically includes: calculating the passing influence factor of the target characteristic vehicle based on the vehicle size parameters and acceleration performance parameters corresponding to the characteristic vehicle type; determining the relative distance and driving direction between the target characteristic vehicle and each intersection according to the vehicle location information; calculating the passing influence score of the target characteristic vehicle on the traffic flow of each intersection based on the relative distance, the driving direction, and the passing influence factor.

[0009] In the above embodiment, the traffic management system establishes a more accurate passing influence evaluation mechanism by comprehensively considering the size parameters, acceleration performance parameters of characteristic vehicles, and the relative position relationship with each intersection, can accurately quantify the actual influence degree of different types of vehicles on traffic flow, and improves the pertinence and effectiveness of signal control.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the traffic impact factor of the target characteristic vehicle based on the vehicle size parameters and acceleration performance parameters corresponding to the characteristic vehicle type, the method further includes: obtaining the license plate information of the target characteristic vehicle, querying the driving years data, historical violation data, and traffic accident records of the corresponding target characteristic vehicle based on the license plate information; determining the driving risk level of the target characteristic vehicle according to the driving years data, historical violation data, and traffic accident records; and adjusting the traffic impact factor based on the driving risk level.

[0011] In the above embodiments, the traffic management system improves the control ability of high-risk vehicles and enhances traffic safety guarantee by introducing the analysis of vehicle historical data, including information such as driving years, violation records, and accident records, and dynamically adjusting the traffic impact factor according to the risk level.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of sending the traffic flow output data including the traffic impact score and the initial timing plan to the adjacent intersection node and receiving the traffic flow input data sent by the adjacent intersection node specifically includes: calculating the estimated arrival time and estimated passing time of the target characteristic vehicle on each approach of the local intersection node based on the initial timing plan; performing weighted correction on the estimated arrival time and estimated passing time according to the traffic impact score of the target characteristic vehicle to obtain the corrected time data; integrating the corrected time data, the traffic impact score, and the initial timing plan into the traffic flow output data, and sending the traffic flow output data to the adjacent intersection node; and receiving the traffic flow input data fed back by the adjacent intersection node.

[0013] In the above embodiments, the traffic management system realizes more accurate traffic flow prediction by weighted correction of the arrival time and passing time of the characteristic vehicle, can timely transmit the optimized traffic information to adjacent intersections, promotes the collaborative timing optimization within the road network range, and improves the regional traffic organization efficiency.

[0014] In combination with some embodiments of the first aspect, in some embodiments, before the step of performing characteristic vehicle recognition based on the vehicle characteristic data to obtain the characteristic vehicle type and vehicle position information of the target characteristic vehicle, the method further includes: collecting the intersection environment parameters of the local intersection node; calculating the environment impact factor based on the intersection environment parameters; and adjusting the confidence threshold of vehicle characteristic recognition according to the environment impact factor.

[0015] In the above embodiments, the traffic management system establishes a more reliable vehicle characteristic recognition mechanism by introducing the intersection environment parameters and the environment impact factor, adaptively adjusts the recognition threshold according to the environmental conditions, improves the accuracy and reliability of characteristic vehicle recognition, and provides a better data basis for subsequent timing optimization.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the steps of calculating the environmental impact factor based on intersection environmental parameters specifically include: extracting weather conditions, light intensity, road surface conditions, and visibility from the intersection environmental parameters; identifying abnormal features including water accumulation, icing, and occlusion in the road surface conditions, and determining the duration of the abnormal features in combination with the weather conditions; calculating the light influence coefficient according to the light intensity, abnormal features, and visibility; and calculating the environmental impact factor based on the abnormal features, duration, and light influence coefficient.

[0017] In the above embodiments, by analyzing multi-dimensional environmental factors such as weather conditions, light intensity, and road surface conditions, the traffic management system can accurately identify and evaluate the impact of abnormal road conditions on traffic operation, improving the adaptability of the timing plan to environmental changes.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the steps of constructing a traffic signal optimization model based on traffic flow characteristic parameters and traffic impact scores, and calculating an initial timing plan based on the traffic signal optimization model, the method further includes: inputting the initial timing plan into a timing evaluation model to obtain a plan feasibility score; determining a similar scenario of the initial timing plan in the historical timing plan library based on the traffic flow characteristic parameters and target characteristic vehicles; and when the plan feasibility score is lower than a preset feasible threshold, adjusting the initial timing plan based on the timing plan of the similar scenario.

[0019] In the above embodiments, by introducing a timing evaluation model and historical plan analysis, the traffic management system realizes the feasibility verification of the timing plan, can optimize and adjust the plan based on the experience of similar scenarios, and improves the reliability of the timing plan.

[0020] In a second aspect, an embodiment of the present application provides a traffic management system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the traffic management system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions, which, when the computer program product runs on a traffic management system, enables the traffic management system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] Fourthly, an embodiment of the present application provides a computer-readable storage medium, including instructions, which, when running on a traffic management system, cause the traffic management system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the traffic management system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. Due to the adoption of a collaborative timing mechanism based on the interconnection of local intersection nodes and adjacent intersection nodes, as well as an accurate calculation method for characteristic vehicle recognition and traffic impact scoring, it is possible to achieve differential management and precise timing control of different types of vehicles, effectively solving the problem that the single fixed timing scheme in the prior art cannot cope with the complex traffic flow characteristics. Through multi-dimensional data collection and analysis, accurately identify and evaluate the impact of characteristic vehicles on traffic flow, and achieve regional collaborative optimization through data interaction between nodes, improving the accuracy and adaptability of signal timing, and effectively improving the overall traffic efficiency of the road network.

[0026] 2. Due to the adoption of a historical data analysis method based on license plate information query, combined with multi-dimensional information such as driving years, violation records, and accident records for driving risk assessment, it is possible to comprehensively and accurately evaluate the actual operation risk of vehicles, effectively solving the limitation problem of only relying on road condition characteristics for impact assessment in the prior art. By establishing a driving risk level assessment system and dynamically adjusting the traffic impact factor, the timing scheme can adapt to the traffic needs of vehicles with different risk levels, improving the level of traffic safety management.

[0027] 3. Due to the adoption of an adaptive recognition mechanism based on intersection environment parameters, and dynamically adjusting the recognition threshold through environmental impact factors, it is possible to maintain a stable and reliable characteristic vehicle recognition effect under different environmental conditions, effectively solving the problem that the recognition performance in the prior art is easily affected by the environment. By comprehensively analyzing the impact of various environmental factors on recognition accuracy, a more robust recognition mechanism is established, improving the reliability of characteristic vehicle recognition and the accuracy of signal timing. Description of the Drawings

[0028] Figure 1 is a flowchart of a traffic signal timing optimization method in an embodiment of the present application;

[0029] Figure 2It is another schematic flowchart of the traffic signal timing optimization method in the embodiments of this application;

[0030] Figure 3 It is a schematic structural diagram of an entity device of the traffic management system in the embodiments of this application. Specific implementation manners

[0031] The terms used in the following embodiments of this application are only for the purpose of describing specific embodiments, and are not intended to limit this application. As used in the specification of this application, the singular forms "a", "an", "the above", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations including one or more of the listed items.

[0032] Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0033] For ease of understanding, the application scenarios of the embodiments of this application are introduced below.

[0034] Near the roads around the loop of a certain megacity, with the rapid growth of the vehicle ownership, the traffic congestion problem has become increasingly serious. Especially during the morning and evening rush hours, a large number of social vehicles mix with characteristic vehicles such as buses and trucks. Due to the differences in the passing characteristics of different vehicles, the operation efficiency of the traffic flow is low. For example, when a large truck starts at an intersection, due to its poor acceleration performance, it often requires a longer passing time, making it difficult for the following vehicles to pass. At the same time, novice vehicles often have a slower speed and less skilled operation when passing through intersections, which also affects the overall passing efficiency.

[0035] In the related art, real-time control of traffic signals can be achieved by adopting fixed timing and basic inductive timing schemes. Such schemes mainly rely on vehicle detectors to obtain real-time traffic flow data and adjust signal timing based on preset control rules. The scenarios of using the traffic signal timing optimization method in the related art are introduced below.

[0036] Currently, the traffic signal control system adopted in a certain city is mainly based on two methods: fixed-time and inductive timing. On the main roads, the system switches different timing schemes through a pre-set time schedule, extending the green light time for the main roads during the morning and evening rush hours, and adopting a shorter cycle length during the off-peak hours. At intersections equipped with loop detectors, the system can dynamically adjust the green light time according to the queue length. However, this scheme is difficult to effectively cope with the impact brought by special vehicles. For example, when a fully loaded truck is at the front of a vehicle fleet, since the system cannot identify its vehicle type characteristics and impact degree, it still allocates the green light time according to the passing time of ordinary vehicles, resulting in the vehicle not being able to pass through the intersection within one cycle, causing serious congestion of the vehicles behind.

[0037] By adopting the traffic signal timing optimization method in the embodiment of the present application, through the accurate identification and classification of different types of special vehicles, it is not only possible to accurately evaluate the actual impact degree of special vehicles on the traffic flow, but also to predict potential risks based on historical data analysis, providing a more reliable decision-making basis for signal optimization. The following introduces the scenarios where the traffic signal timing optimization method in the present application is used.

[0038] After adopting the traffic signal timing optimization method provided by the present application, the system can accurately identify and evaluate the impact of special vehicles. At a certain intersection, the system identifies a large transport vehicle through multi-source data fusion technology, and calculates a relatively high passing impact score based on parameters such as its vehicle size and acceleration performance. At the same time, by querying the historical driving data of the vehicle, it is found that it has multiple violation records, and the system accordingly raises its risk level. Based on these evaluation results, when the vehicle approaches the intersection, the system adjusts the timing scheme in advance and appropriately extends the green light time to ensure that it can pass through the intersection safely. In addition, the system also sends the passing information of the vehicle to the downstream intersection to make preparations in advance. This collaborative optimization mechanism improves the passing efficiency of special vehicles and at the same time reduces the impact on other vehicles.

[0039] It can be seen that by adopting the traffic signal timing optimization method in the embodiment of the present application, while achieving accurate identification and evaluation of the impact of special vehicles, it can also effectively solve the problem that the traditional fixed-time scheme lacks response to the passing needs of special vehicles, and thus realizes a more flexible and efficient traffic signal control.

[0040] For the sake of understanding, the following combines the above scenarios to describe the process of the method provided in this embodiment. Please refer to Figure 1 , which is a schematic flowchart of the traffic signal timing optimization method in the embodiment of the present application.

[0041] S101. Based on the location identification information of the local intersection node, determine multiple adjacent intersection nodes interconnected with the local intersection node.

[0042] Among them, the local intersection node represents the intersection that currently needs traffic signal timing optimization; the location identification information refers to the data used to uniquely identify the geographical location of the intersection, including longitude and latitude coordinates, intersection numbers, etc.; the adjacent intersection node represents the adjacent intersection that has a direct traffic flow interaction with the local intersection node, usually located on the same main road or secondary road; interconnection means that there is an information interaction channel between each intersection node, enabling real-time data transmission and sharing.

[0043] When the traffic management system receives an instruction to optimize the signal timing of a certain intersection, it needs to first determine the scope of the surrounding intersections related to this intersection to achieve regional coordinated control. Specifically, the traffic management system first obtains the location information of the local intersection node, and then queries the road network topology database to obtain all the road information directly connected to the local intersection node. Subsequently, the traffic management system searches for adjacent intersection nodes along these roads and filters out the set of adjacent intersection nodes that need to be coordinated and optimized according to factors such as actual distance, traffic flow correlation, and communication conditions. For intersections on the main road, the search range can be extended to a farther distance to ensure the continuity of the green wave band; for intersections on the secondary road, the coordination of adjacent nodes is mainly considered.

[0044] In some embodiments, the determination process of adjacent intersection nodes can be achieved in various ways: Optionally, the traffic management system can calculate the physical distance between nodes based on the Euclidean distance, and set different distance thresholds in combination with road grades and traffic capacities. When the distance between nodes is less than the corresponding threshold, it is included in the coordination scope. For example, the distance threshold for adjacent intersections on the main road can be set to 1000 meters, and on the secondary road can be set to 500 meters; Optionally, the traffic management system can analyze the traffic flow correlation between nodes based on historical traffic flow data, calculate the correlation coefficient, and determine that there is a traffic flow correlation between nodes when the correlation coefficient is greater than 0.7, and include it in the scope of coordinated optimization. It can be understood that other methods such as network connectivity analysis based on graph theory and path selection models based on traffic demand distribution can also be used to determine adjacent intersection nodes, which are not limited here.

[0045] S102. Collect the vehicle passing state data and vehicle characteristic data of the local intersection node, and generate traffic flow characteristic parameters according to the vehicle passing state data and vehicle characteristic data.

[0046] Among them, the vehicle passing state data represents the real-time operation state information of vehicles in all directions of the intersection, including dynamic parameters such as vehicle speed, acceleration, and headway; the vehicle characteristic data refers to the data used to describe the physical attributes and behavior characteristics of vehicles, including vehicle type, vehicle length, driving trajectory, etc.; the traffic flow characteristic parameters represent the statistical indicators used to describe the overall traffic operation state of the intersection, including traffic flow, density, average speed, queue length, etc.

[0047] After determining the adjacent intersection nodes, the traffic management system needs to obtain the real-time traffic operation data at the intersection to evaluate the current traffic state. Specifically, the traffic management system continuously collects the vehicle passing data of each approach lane through a variety of sensing devices deployed at the intersection, such as video detectors, geomagnetic detectors, and radars. For the passing state data, the system records the vehicle position and speed information every 100 ms; for the vehicle feature data, the system identifies the vehicle type through video image analysis and extracts the key dimension parameters. Subsequently, the traffic management system cleans and aggregates the original data, calculates various traffic flow parameters, and classifies and stores them according to the lane and time dimensions.

[0048] In some embodiments, the generation of traffic flow characteristic parameters can be achieved in various ways: Optionally, the traffic management system can adopt the moving time window method, set a statistical period of 5 minutes, count the number of various vehicles and calculate the flow ratio, calculate the average lane speed and occupancy rate in combination with the speed measurement data, and evaluate the current service level through the density-flow relationship model; Optionally, the traffic management system can calculate performance indicators such as the number of stops, delay time, and passing time based on the vehicle trajectory data, and establish an intersection operation state evaluation model in combination with historical data. It can be understood that other methods such as traffic state prediction based on deep learning and delay analysis based on queuing theory can also be used to generate traffic flow characteristic parameters, which are not limited here.

[0049] S103. Identify the characteristic vehicles based on the vehicle feature data to obtain the characteristic vehicle type and vehicle position information of the target characteristic vehicle.

[0050] Among them, the characteristic vehicle refers to the vehicle type that has an impact on the traffic flow operation, including large trucks, buses, novice vehicles, etc.; the characteristic vehicle type is the identifier for classifying the characteristic vehicles, used to distinguish the impact characteristics of different vehicles; the vehicle position information represents the real-time spatial position of the characteristic vehicle in the road network, including longitude and latitude coordinates, the lane where it is located, the distance from the stop line, etc.

[0051] After obtaining the traffic flow characteristic parameters, the traffic management system needs to identify the vehicles that have a special impact on traffic operation. Specifically, the traffic management system first preprocesses the vehicle feature data, including operations such as image enhancement and noise removal. Then, it classifies the vehicles based on the deep learning model and identifies the characteristic vehicles including large trucks, school buses, dangerous goods transport vehicles, etc. For the identified characteristic vehicles, the system further extracts their detailed characteristic parameters, including body size, wheelbase, load, etc. At the same time, the system real-time tracks the position changes of these vehicles and records their movement trajectories to provide a basis for subsequent impact assessment.

[0052] In some embodiments, the identification and tracking of characteristic vehicles can be achieved in various ways: Optionally, the traffic management system can use the YOLOv5-based object detection algorithm to identify vehicle types, extract vehicle information by combining license plate recognition technology, and achieve vehicle trajectory tracking through a multi-object tracking algorithm, and calculate the position coordinates of the vehicle in the road network in real time; Optionally, the traffic management system can estimate the vehicle state based on multi-sensor data fusion, combine multi-source data such as geomagnetism, video, and lidar, and use the Kalman filter algorithm to improve the identification and positioning accuracy. It can be understood that other methods such as vehicle type recognition based on image semantic segmentation and cooperative perception based on the vehicle network can also be used to identify characteristic vehicles, which are not limited here.

[0053] S104. Calculate the passing influence score of the target characteristic vehicle on the traffic flow of each intersection according to the traffic flow characteristic parameters, characteristic vehicle types, and vehicle position information.

[0054] Among them, the passing influence score represents the quantitative value of the influence degree of the characteristic vehicle on the traffic operation at the intersection, and the score range is 0-100; the target characteristic vehicle refers to the specific characteristic vehicle whose influence degree needs to be evaluated currently; the passing influence of the traffic flow refers to the influence degree of the characteristic vehicle on performance indicators such as intersection passing capacity, delay time, and queue length.

[0055] After the traffic management system identifies the characteristic vehicles, it needs to evaluate the actual impact of these vehicles on traffic operation. Specifically, the traffic management system first establishes a multi-dimensional scoring index system, including aspects such as space occupancy, starting characteristics, and following characteristics. Then, it determines the basic influence factors according to the type attributes of the characteristic vehicles, and calculates the space attenuation coefficient in combination with the distance relationship between the vehicle and each intersection. For characteristic vehicles whose driving trajectories span multiple intersections, the system needs to evaluate their influence degrees on each intersection along the line respectively. Finally, the system comprehensively considers the current traffic flow operation state and calculates the normalized influence score.

[0056] In some embodiments, the calculation of the passing influence score can be achieved in various ways: Optionally, the traffic management system can use the weighted summation method to linearly combine the vehicle type influence factor, distance attenuation factor, and traffic flow state factor, where the weight coefficients are obtained through training with historical data and dynamically adjusted according to the actual scenario. For example, the weight of the type influence factor is increased in the congestion state; Optionally, the traffic management system can establish a scoring model based on fuzzy logic, use various influence factors as input variables, and obtain the comprehensive score through fuzzy inference rules. It can be understood that other methods such as influence degree prediction based on neural networks and traffic flow influence simulation based on cellular automata can also be used to calculate the passing influence score, which are not limited here.

[0057] S105. Construct a traffic signal optimization model based on traffic flow characteristic parameters and traffic impact scores, and calculate an initial timing plan based on the traffic signal optimization model.

[0058] Among them, the traffic signal optimization model refers to a mathematical model for solving the optimal signal timing plan, including an objective function and constraint conditions; the initial timing plan refers to the initial solution of the optimization model, including parameters such as cycle length, phase difference, and green ratio; the signal control parameters refer to the specific parameter settings for implementing traffic signal control.

[0059] After obtaining the traffic impact score, the traffic management system needs to establish a signal optimization model considering the impact of characteristic vehicles. Specifically, the traffic management system first constructs an optimization objective function, comprehensively considering the minimization of overall delay and the satisfaction of the traffic demand of characteristic vehicles. Then, various constraint conditions are set, including minimum green time, maximum cycle length, safety interval time, etc. The system uses a heuristic algorithm to solve the optimization model and obtains an initial timing plan that meets the constraint conditions. During the solution process, the system needs to consider the spatial distribution of characteristic vehicles and appropriately adjust the green ratio allocation of the affected intersections.

[0060] In some embodiments, the solution of the signal optimization model can be achieved in various ways: Optionally, the traffic management system can use a genetic algorithm to encode the timing plan as a chromosome, perform population evolution through operations such as selection, crossover, and mutation, and select the individual with the highest fitness as the optimal solution, where the fitness function needs to consider the impact score of characteristic vehicles; Optionally, the traffic management system can use a particle swarm optimization algorithm to search for the optimal solution by simulating the movement of particles in the solution space, and the update of the speed and position of the particles needs to consider the impact factors of characteristic vehicles. It can be understood that other methods such as adaptive optimization based on reinforcement learning and collaborative optimization based on ant colony algorithm can also be used to optimize the timing plan, which is not limited here.

[0061] S106. Send the traffic flow output data including the traffic impact score and the initial timing plan to the adjacent intersection node, and receive the traffic flow input data sent by the adjacent intersection node.

[0062] Among them, the traffic flow output data represents the traffic flow prediction information flowing from the local intersection to the adjacent intersection, including traffic volume, vehicle type composition, arrival time, etc.; the traffic flow input data refers to the traffic flow prediction information flowing from the adjacent intersection into the local intersection.

[0063] After generating the initial timing plan, the traffic management system needs to interact with adjacent intersections for data to achieve regional coordination. Specifically, based on the initial timing plan, the traffic management system first calculates the traffic capacity and the predicted arrival time distribution of vehicle flows for each exit lane. Then, combined with the traffic impact scores of characteristic vehicles, the prediction results are corrected to generate more accurate vehicle flow output data. The system sends this data to relevant adjacent intersection nodes through a dedicated communication network and simultaneously receives the vehicle flow input data fed back by these nodes. The data interaction process needs to consider real-time requirements, usually requiring the transmission delay not to exceed 100 ms.

[0064] In some embodiments, data interaction between intersections can be achieved in various ways: Optionally, the traffic management system can adopt a real-time communication mechanism based on WebSocket to establish a persistent connection between intersection nodes, encapsulate traffic flow data in JSON format to achieve two-way data push, and set up a heartbeat detection mechanism to ensure connection reliability; Optionally, the traffic management system can build a data exchange platform based on a distributed message queue, adopt a publish-subscribe mode to achieve data sharing among multiple intersections, and support data caching and retransmission. It can be understood that other methods such as vehicle-road collaborative communication based on 5G networks and distributed data sharing based on blockchain can also be used to achieve intersection data interaction, which is not limited here.

[0065] S107. Update the traffic signal optimization model based on the vehicle flow input data and the vehicle flow output data, generate the final timing plan, and adjust the signal control parameters of the local intersection node based on the final timing plan.

[0066] Among them, the final timing plan represents an optimized timing plan considering the regional coordination effect; the signal control parameters include specific control parameters such as cycle length, phase difference, and green ratio; parameter adjustment refers to converting the optimized timing plan into actual signal control instructions.

[0067] After completing the data interaction, the traffic management system needs to conduct final optimization by comprehensively considering regional traffic demands. Specifically, the traffic management system first integrates the received vehicle flow input data into the optimization model to update demand prediction and constraint conditions. Then, based on the updated model, re-optimization calculations are performed to obtain the final timing plan considering the impacts of upstream and downstream intersections. The system converts the final plan into specific control parameters, including the start time and duration of each phase, and issues instructions through the signal machine to achieve real-time control. During the parameter adjustment process, the system will ensure the smoothness of phase switching to avoid impacts on traffic operation caused by sudden changes.

[0068] In some embodiments, the final optimization of the timing plan can be achieved in various ways: Optionally, the traffic management system can adopt a rolling horizon optimization strategy, set an optimization period of 5 - 15 minutes, update the model parameters based on the latest traffic data at the beginning of each period, and quickly solve for a stage-optimal plan through an online optimization algorithm; Optionally, the traffic management system can establish a scenario-matching-based plan optimization mechanism, match the current traffic state with typical scenarios in the historical database, and fine-tune the matched plan in combination with real-time data. It can be understood that other methods such as adaptive optimization based on predictive control and collaborative decision-making based on multi-agent can also be used to achieve the final optimization of the timing plan, which is not limited here.

[0069] In the above embodiments, the traffic management system realizes the differential management of different types of vehicles by establishing a characteristic vehicle impact assessment model. In practical applications, the system can also dynamically adjust the assessment parameters according to real-time road conditions and environmental conditions to further improve the adaptability of timing optimization. The scenarios of this embodiment are supplemented below.

[0070] In the regional traffic coordinated control of a certain urban agglomeration, the system can not only process the identification and assessment of characteristic vehicles at a single intersection, but also establish a cross-regional collaborative optimization network. For example, when a school bus fleet needs to pass through multiple intersections, the system will dynamically calculate the optimal passing route in combination with environmental factors such as real-time road conditions and weather conditions. The nodes of each intersection interact through real-time data to construct a "green wave band" to guide the school bus fleet to pass through orderly. At the same time, the system also predicts possible traffic risks based on historical data analysis and adjusts the timing plan of the affected area in advance. This multi-dimensional optimization strategy not only improves the passing efficiency of characteristic vehicles, but also realizes the overall coordination of regional traffic.

[0071] After combining the above scenarios, the following provides a further and more specific process description of the method provided in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of the traffic signal timing optimization method in the embodiments of the present application.

[0072] S201. Based on the location identification information of the local intersection node, determine multiple adjacent intersection nodes interconnected with the local intersection node.

[0073] Referring to step S101, the traffic management system will determine multiple adjacent intersection nodes.

[0074] S202. Collect the vehicle passing state data and vehicle characteristic data of the local intersection node, and generate traffic flow characteristic parameters according to the vehicle passing state data and vehicle characteristic data.

[0075] Referring to step S102, the traffic management system will determine the traffic flow characteristic parameters.

[0076] S203: Collect the intersection environment parameters of the local intersection node.

[0077] Among them, intersection environmental parameters represent data on external environmental factors that affect traffic operations and equipment detection performance; weather conditions refer to meteorological elements including precipitation, temperature, wind speed, etc.; light intensity represents the brightness of ambient light, measured in lumens / square meter; road surface conditions refer to the physical properties of the road surface, including friction coefficient, water depth, etc.; sight distance conditions represent visibility levels, which are affected by factors such as haze and dust.

[0078] Before performing feature vehicle identification, the traffic management system needs to evaluate the impact of the current environment on detection performance. Specifically, the traffic management system collects multi-dimensional environmental data in real time through environmental monitoring equipment deployed at intersections, including weather stations, light sensors, road surface condition detectors, etc. The system preprocesses and calibrates the collected data, removes outliers, and supplements missing values. For dynamically changing parameters, the system uses a sliding window method to calculate short-term trends and evaluate the potential impact of environmental changes on detection performance. The system also needs to consider the working characteristics of different detection equipment and collect key environmental parameters that affect its performance in a targeted manner.

[0079] In some embodiments, the collection and processing of environmental parameters can be achieved in a variety of ways: Optionally, the traffic management system can first start the self-check program of the environmental monitoring equipment to ensure data reliability, and then collect various sensor data according to the preset 1-minute sampling period, and then perform data standardization to unify the parameters of different dimensions to the same scale, and finally smooth the noise data through the Kalman filter algorithm; Optionally, the traffic management system can establish a multi-source data fusion mechanism, first obtain local monitoring equipment data, and then access the weather forecast data of the regional meteorological station, and then collect environmental monitoring data of surrounding intersections, and finally use DS evidence theory to perform data fusion to obtain more reliable environmental status assessment results. It is understandable that other methods such as environmental feature extraction based on deep learning and distributed environmental perception based on the Internet of Things can also be used to achieve the collection and processing of environmental parameters, which are not limited here.

[0080] S204: Calculate environmental impact factors based on intersection environmental parameters.

[0081] Among them, the environmental impact factor is a quantitative indicator of the degree of influence of different environmental conditions on the detection performance, and its value range is 0-1; the detection performance refers to the evaluation indicators such as the accuracy and recall rate of feature vehicle recognition; the quantitative indicators of the degree of influence include sub-indicators such as lighting influence factor, weather influence factor, and road surface influence factor; the weight coefficient represents the relative importance of each environmental parameter on the detection performance.

[0082] After obtaining the environmental parameters, the traffic management system needs to evaluate the comprehensive impact of environmental conditions on the detection system. Specifically, the traffic management system first establishes a mapping relationship model between environmental parameters and detection performance, considering the individual impacts and interactions of various environmental factors. Then, it inputs the real-time environmental parameters into the model and calculates the impact degrees of various environmental factors. For adverse weather conditions that have a significant impact on performance, such as heavy rain and heavy fog, the system needs to reduce the corresponding impact factor values; for normal weather conditions with less impact, the system maintains higher impact factor values. Finally, the system comprehensively considers various impacts and generates a comprehensive impact factor reflecting the current environmental conditions.

[0083] In some embodiments, the calculation of the environmental impact factor can be achieved in various ways: Optionally, the traffic management system can first construct an environmental assessment model based on fuzzy inference, using parameters such as light intensity, precipitation intensity, visibility, etc. as input variables, then design a fuzzy rule base to define the relationship between parameters and the impact degree, then perform fuzzy inference to obtain the membership degree values of various impact factors, and finally perform defuzzification through the centroid method to obtain accurate impact factor values; Optionally, the traffic management system can adopt a neural network method. First, it trains an environment-performance mapping network using historical data, then inputs the real-time environmental parameters into the trained network, and finally obtains the impact factor values under the current environmental conditions through the network output. It can be understood that other methods such as regression prediction based on machine learning and rule inference based on expert systems can also be used to calculate the environmental impact factor, which is not limited here.

[0084] In some embodiments, the traffic management system calculates the environmental impact in combination with road conditions and weather. That is, the traffic management system extracts weather conditions, light intensity, road surface conditions, and visibility from the intersection environmental parameters; identifies abnormal features including water accumulation, icing, and occlusion in the road surface conditions, and determines the duration of the abnormal features in combination with the weather conditions; calculates the light impact coefficient based on the light intensity, abnormal features, and visibility; and calculates the environmental impact factor based on the abnormal features, duration, and light impact coefficient.

[0085] Among them, the intersection environmental parameters represent a set of external environmental factor data that affect traffic operation and equipment detection performance; the weather conditions refer to the real-time monitoring data of meteorological elements including precipitation, temperature, wind speed, etc.; the light intensity represents the brightness of the environmental light, measured in lumens per square meter; the road surface conditions refer to the physical characteristics of the road surface, including friction coefficient, water accumulation depth, etc.; the visibility represents the visibility level, affected by factors such as fog and haze; the abnormal features refer to the abnormal states of the road surface that affect driving safety; the light impact coefficient represents the impact degree of light conditions on detection performance; the environmental impact factor represents the quantitative value of the impact of comprehensive environmental conditions on system performance.

[0086] Before a traffic management system performs feature vehicle recognition, it is necessary to evaluate the impact of the current environmental conditions on the detection performance. Specifically, the traffic management system first collects real-time data through environmental monitoring devices deployed at intersections, including weather stations, light sensors, road surface condition detectors, etc. Then, the collected data is preprocessed and feature extracted to identify abnormal road surface conditions and evaluate their duration. The system combines the light intensity and visibility conditions to establish an environmental impact assessment model, and obtains a comprehensive impact factor through multi-factor weighted calculation. This factor will be used to adjust the parameter thresholds for feature vehicle recognition subsequently to ensure the reliability of the recognition results.

[0087] In some embodiments, the calculation of the environmental impact factor can be achieved in various ways: Optionally, the traffic management system can process environmental data based on a fuzzy inference system. First, each environmental parameter is converted into a linguistic variable through fuzzy processing, then the inference operation is performed through an expert rule base to obtain the degree of influence of each item, and finally, the precise influence factor value is obtained through defuzzification by the centroid method; Optionally, the traffic management system can adopt a multi-layer neural network structure, use the preprocessed environmental parameters as the input layer data, capture the complex relationships between the parameters through the non-linear transformation of the hidden layer, and finally obtain the normalized influence factor at the output layer. It can be understood that other methods such as environmental impact modeling based on support vector regression and environmental feature extraction based on deep learning can also be used to calculate the environmental impact factor, which is not limited here.

[0088] S205. Adjust the confidence threshold for vehicle feature recognition according to the environmental impact factor.

[0089] Among them, the confidence threshold represents the judgment standard for the credibility of the feature vehicle recognition result, and is used to filter out low-confidence recognition results; the threshold adjustment refers to the process of dynamically changing the confidence judgment standard according to the environmental conditions.

[0090] After obtaining the environmental impact factor, the traffic management system needs to adjust the judgment standard for feature recognition accordingly. Specifically, the traffic management system first determines the direction and amplitude of the threshold adjustment according to the magnitude of the environmental impact factor. When the environmental conditions are poor, the system appropriately reduces the confidence threshold to avoid excessive valid recognition results being filtered out; when the environmental conditions are good, the system increases the confidence threshold to ensure the high reliability of the recognition results. During the adjustment process, the system needs to ensure that the threshold is always within the preset reasonable range and consider the differences in the recognition difficulty of different types of feature vehicles, and adopt a differentiated adjustment strategy.

[0091] In some embodiments, the dynamic adjustment of the confidence threshold can be achieved in various ways: Optionally, the traffic management system can first establish a linear mapping relationship between the environmental impact factor and the threshold adjustment amount, then set the benchmark threshold and the allowable adjustment range, then calculate the specific adjustment amount according to the current environmental impact factor, and finally add the adjustment amount to the benchmark threshold to obtain the actually used threshold; Optionally, the traffic management system can establish an adaptive adjustment mechanism based on performance feedback, and dynamically optimize the threshold adjustment strategy by monitoring the change in the accuracy rate of the recognition result. It can be understood that other methods such as threshold optimization based on reinforcement learning and parameter search based on heuristic algorithms can also be used to achieve the dynamic adjustment of the confidence threshold, which is not limited here.

[0092] S206. Perform feature vehicle recognition based on vehicle feature data to obtain the feature vehicle type and vehicle position information of the target feature vehicle.

[0093] Referring to step S103, the traffic management system will identify the target feature vehicle.

[0094] It should be noted that the traffic management system uses a deep convolutional neural network structure for feature vehicle recognition. This network adopts an improved YOLOv5 architecture, which includes three main components: a backbone network, a feature pyramid network, and a detection head. The backbone network uses the CSPDarknet structure to extract multi-scale features, and improves the feature extraction ability through residual connections and cross-stage partial networks. The feature pyramid network adopts an adaptive feature fusion module, and dynamically weights and fuses features of different scales through an attention mechanism to enhance the detection ability for vehicles of different sizes. The detection head part includes a classification branch and a regression branch. The classification branch outputs the probability of the vehicle type, and the regression branch predicts the position and size of the bounding box. The network training uses a multi-task loss function, including classification loss, localization loss, and confidence loss. Among them, the classification loss uses the cross-entropy function, the localization loss uses the GIoU loss, and the confidence loss is based on binary cross-entropy. To improve the detection accuracy, the system also introduces data augmentation strategies, including techniques such as Mosaic and MixUp, to enhance the adaptability of the model to complex scenarios. In practical applications, this method can achieve a feature vehicle detection accuracy rate of more than 95%.

[0095] The improved YOLOv5 architecture mainly optimizes the feature extraction network and the feature fusion mechanism. In the feature extraction network, a dual-branch attention module is introduced, which contains two sub-modules: spatial attention and channel attention. Spatial attention generates an attention map by calculating the response intensity of each spatial position in the feature map. It uses a parallel structure of adaptive average pooling and max pooling to extract spatial information, and then fuses it through a 1x1 convolutional layer to obtain spatial weights. Channel attention calculates the importance of each channel through the SE module structure. First, it performs global average pooling on the feature map to obtain a channel descriptor, then uses two fully connected networks to learn the correlation between channels, and finally obtains channel weights through the sigmoid function. The outputs of the two attention branches are multiplied by the original feature map element-wise to achieve adaptive enhancement of features. The feature fusion mechanism adopts a cross-scale adaptive fusion module, which dynamically adjusts the fusion ratio of features at different scales through learnable weight coefficients. The weight coefficients are normalized by the softmax function to ensure that the sum of the contributions of features at different scales is 1. This improved structure enhances the detection performance of the model for vehicles with different size features, especially the detection accuracy under complex lighting and occlusion conditions.

[0096] S207. Calculate the traffic impact factor of the target feature vehicle based on the vehicle size parameters and acceleration performance parameters corresponding to the feature vehicle type.

[0097] Among them, the vehicle size parameters represent the physical size characteristics of the feature vehicle, including vehicle length, vehicle width, vehicle height, etc.; the acceleration performance parameters are indicators that describe the dynamic characteristics of the vehicle, including maximum acceleration, starting acceleration, maximum speed, etc.; the traffic impact factor represents the basic quantization value of the influence of the inherent attributes of the feature vehicle on the operation of the traffic flow; the vehicle dynamic characteristics refer to the motion characteristics shown by the vehicle during acceleration, deceleration, turning, etc.

[0098] After the traffic management system identifies the feature vehicle type, it needs to quantitatively evaluate the basic influence degree of this type of vehicle. Specifically, the traffic management system first extracts the standard parameters of this type of vehicle from the vehicle feature database, including typical sizes and performance indicators. Then it analyzes the impact of the vehicle's physical characteristics on the road traffic capacity, focusing on factors such as vehicle occupancy space, starting characteristics, and following characteristics. For large vehicles, the system focuses on evaluating the impact of their space occupancy and turning radius; for vehicles with limited performance, the system focuses on evaluating the impact of their acceleration and deceleration characteristics on the traffic flow. Finally, the system combines various impacts through weighting to generate a traffic impact factor that reflects the overall impact of this type of vehicle.

[0099] In some embodiments, the calculation of the traffic impact factor can be achieved in various ways: Optionally, the traffic management system can first establish an impact assessment model based on the physical characteristics of the vehicle, convert the vehicle size into a standard vehicle equivalent coefficient, then calculate the average traffic time increment based on the acceleration performance parameters, then evaluate the increase in safety distance caused by the vehicle operation characteristics, and finally obtain the comprehensive impact factor through multi-factor weighting; Optionally, the traffic management system can adopt a data-driven method to establish an association model between vehicle characteristics and traffic flow parameters based on historical observation data, and determine the impact weights of various characteristic parameters through regression analysis. It can be understood that other methods such as analytical calculation based on traffic flow theory and impact assessment based on microscopic simulation can also be used to calculate the traffic impact factor, which is not limited here.

[0100] In some embodiments, the traffic management system performs impact calculation based on license plate information, that is, the traffic management system obtains the license plate information of the target characteristic vehicle, and queries the driving years data, historical violation data, and traffic accident records of the corresponding target characteristic vehicle based on the license plate information; according to the driving years data, historical violation data, and traffic accident records, determine the driving risk level of the target characteristic vehicle; based on the driving risk level, adjust the traffic impact factor.

[0101] Among them, the license plate information refers to the encoded data used to uniquely identify the vehicle; the driving years data refers to the length of time the vehicle has been in use; the historical violation data represents the past traffic violation records of the vehicle; the traffic accident record refers to the traffic accident situation involved by the vehicle; the driving risk level represents the comprehensive evaluation result of the vehicle's safety; the traffic impact factor refers to the quantitative index reflecting the degree of influence of the vehicle on traffic operation.

[0102] After the traffic management system obtains the basic information of the characteristic vehicle, it needs to evaluate the potential risk level of the vehicle. Specifically, the traffic management system first obtains the unique identifier of the target vehicle through the license plate recognition system, and then accesses the traffic management database to obtain the historical data of the vehicle. The system analyzes the historical data, considers factors such as violation frequency and accident severity, and constructs a risk assessment model. Based on the evaluation result, the system dynamically adjusts the traffic impact factor of the vehicle and imposes stricter traffic control on high-risk vehicles.

[0103] In some embodiments, driving risk assessment can be achieved in various ways: Optionally, the traffic management system can establish a risk inference model based on a Bayesian network, use historical data as prior knowledge, calculate the risk level through conditional probability, and dynamically update the model parameters according to new data; Optionally, the traffic management system can adopt a time series analysis method to perform time series modeling on the vehicle's violation and accident data to predict future risk trends. It can be understood that other methods such as risk classification based on decision trees and risk identification based on anomaly detection can also be used to achieve driving risk assessment, which is not limited here.

[0104] S208. Determine the relative distances and driving directions between the target feature vehicle and each intersection according to the vehicle position information.

[0105] Among them, the relative distance represents the actual driving distance from the feature vehicle to each intersection node; the driving direction refers to the movement trend of the feature vehicle, including the forward direction and the turning intention; the path prediction means inferring the possible driving path of the vehicle based on the current state; the spatial relationship analysis represents the assessment of the position correlation between the vehicle and the road network elements.

[0106] After obtaining the real-time position of the vehicle, the traffic management system needs to analyze its spatial relationship with the surrounding intersections. Specifically, the traffic management system first locates the target vehicle on the road network topology map and obtains the position information of the surrounding intersection nodes. Then, based on the road network connection relationship, it calculates the actual driving distance from the vehicle to each intersection, considering the road shape and turning restrictions. The system also needs to analyze the historical trajectory data of the vehicle, combine the lane selection situation, and predict its possible driving direction. For vehicles near intersections, the system also needs to judge their turning intentions according to the lane type and turn signal status where they are located.

[0107] In some embodiments, the determination of the spatial relationship can be achieved in various ways: Optionally, the traffic management system can first construct a shortest path calculation model based on the Dijkstra algorithm, calculate the shortest driving path from the vehicle to each intersection, then extract the distance and direction information of the path, then estimate the arrival time based on the real-time speed of the vehicle, and finally generate a spatio-temporal relationship matrix between the vehicle and each intersection; Optionally, the traffic management system can establish a dynamic analysis model based on trajectory prediction and use a sequence prediction algorithm to predict the movement trajectory of the vehicle in the next period of time. It can be understood that other methods such as path probability estimation based on Bayesian inference and reachability analysis based on graph theory can also be used to achieve the determination of the spatial relationship, which is not limited here.

[0108] S209. Calculate the traffic flow passing influence score of the target feature vehicle on each intersection based on the relative distance, driving direction, and passing influence factor.

[0109] Among them, the traffic impact score represents a comprehensive evaluation index of the actual impact degree of the characteristic vehicle on a specific intersection.

[0110] After determining the spatial relationship, the traffic management system needs to evaluate the actual impact degree of the characteristic vehicle on each intersection. Specifically, the traffic management system first establishes an impact propagation model and defines the functional relationship of the impact intensity decaying with distance. Then it analyzes the relative relationship between the vehicle driving direction and the positions of each intersection and calculates the direction correlation coefficient. For the intersections on the vehicle driving path, the system assigns a higher direction correlation; for the intersections deviating from the path, the correlation coefficient is reduced. The system multiplies the traffic impact factor by the distance decay value and the direction correlation coefficient to obtain the impact score for each intersection. Finally, the system normalizes the scores to ensure the comparability of the scores among different intersections.

[0111] In some embodiments, the calculation of the traffic impact score can be achieved in various ways: Optionally, the traffic management system can first construct an impact propagation function based on the gravity model, use the traffic impact factor as the mass term and the relative distance as the impedance term, then introduce a direction adjustment coefficient to correct the basic impact, then consider the modulation effect of the road network topology on the impact propagation, and finally map the score to the 0-100 interval through the sigmoid function; Optionally, the traffic management system can establish a scoring model based on a fuzzy neural network, use the relative distance, driving direction and traffic impact factor as input variables, and directly output the standardized impact score through the trained network. It can be understood that other methods such as an impact diffusion model based on spatio-temporal analysis and a traffic flow evolution model based on cellular automata can also be used to achieve the calculation of the traffic impact score, which is not limited here.

[0112] S210. Construct a traffic signal optimization model according to the traffic flow characteristic parameters and the traffic impact score, and calculate the initial timing plan based on the traffic signal optimization model.

[0113] Referring to step S105, the traffic management system will generate an initial timing plan.

[0114] It should be noted that the traffic management system uses a mixed-integer programming model based on queuing theory for signal optimization. The objective function of the model consists of two parts: minimizing the total delay of general vehicles and minimizing the weighted delay of characteristic vehicles. The delay calculation is based on a deterministic queuing model, considering factors such as arrival flow, saturation flow, and effective green time. The constraint conditions include cycle length constraint, minimum green time constraint, phase sequence constraint, and passing demand constraint. Among them, the cycle length is limited within the range of 40 - 180 seconds, the minimum green time is set to 10 - 15 seconds according to the lane function, and the phase switching time considers the yellow light time and all-red interval. The influence of characteristic vehicles is introduced into the model by modifying the saturation flow and weight coefficients, and the weight coefficients are dynamically adjusted according to the passing influence score. The model is solved using the branch and bound algorithm, and the optimal solution is searched in the feasible solution space through linear relaxation and branching strategies. To improve the solving efficiency, the system uses heuristic rules to prune the solution space and uses the historical optimal solution as the initial solution to accelerate convergence. In practical applications, the model can complete the solution within 2 seconds, meeting the real-time control requirements.

[0115] In some embodiments, the objective function of the model can be: D = Σαidi + Σβisi + γ(1 - C / Cmax); where D represents the comprehensive optimization objective value, which is used to evaluate the quality of the overall timing plan; di is the average delay time of vehicles at the i-th approach, reflecting the passing efficiency of each approach; si is the number of stops of vehicles at the i-th approach, reflecting the continuity of vehicle passing; C is the current passing capacity of the intersection, Cmax is the maximum passing capacity of the intersection, and the C / Cmax ratio reflects the utilization rate of the intersection capacity; αi, βi, γ are the corresponding weight coefficients, which can be dynamically adjusted according to the real-time traffic conditions.

[0116] It should be noted that when the weight coefficients are dynamically adjusted according to the passing influence score, it is based on an adaptive learning algorithm. The system first constructs an evaluation index system based on vehicle characteristics, including three dimensions: vehicle type influence degree, space occupancy rate, and delay sensitivity. For each characteristic vehicle, the basic weight value is calculated based on its passing influence score, and then it is dynamically corrected according to the current traffic state. The correction process uses the exponential smoothing method, and the new weight value is equal to the weighted sum of the historical weight and the currently calculated weight. The smoothing coefficient is optimized based on historical data using the least squares method. When the traffic flow is close to saturation, the system will increase the weight coefficient of characteristic vehicles to ensure that they obtain sufficient passing time; when the flow is small, the weight is appropriately reduced to balance the passing demand of general vehicles. The weight adjustment range is controlled by upper and lower bounds to avoid over-biasing towards a certain type of vehicle.

[0117] During the correction process, the smoothing coefficient is determined using an adaptive optimization method based on historical data. The system first constructs a time series prediction error model, expressing the prediction error as a function of the smoothing coefficient. By minimizing the sum of squared prediction errors, an optimization objective function is established. The gradient descent method is used to iteratively optimize the smoothing coefficient, where the gradient calculation takes into account the sensitivity of the prediction error to the smoothing coefficient. To avoid overfitting, a regularization term is introduced to limit the variation range of the smoothing coefficient. During the iterative process, the system dynamically adjusts the learning rate, reducing the learning rate when the error descent rate slows down to ensure convergence. The finally obtained smoothing coefficient can not only ensure the accuracy of prediction but also maintain the stability of weight adjustment. Specifically, assuming the historical weight sequence is {0.6, 0.65, 0.55, 0.7}, when the smoothing coefficient obtained through optimization is 0.3, the new weight calculation will assign a weight of 0.3 to the historical weight and a weight of 0.7 to the currently calculated weight, thereby obtaining the smoothed weight value.

[0118] S211. Send the traffic flow output data including the traffic impact score and the initial timing plan to the adjacent intersection node, and receive the traffic flow input data sent by the adjacent intersection node.

[0119] Referring to step S106, the traffic management system will perform data interconnection.

[0120] In some embodiments, the traffic management system performs data interconnection based on time data, that is, the traffic management system calculates the estimated arrival time and estimated passing time of the target characteristic vehicles at each approach of the local intersection node based on the initial timing plan; weights and corrects the estimated arrival time and estimated passing time according to the traffic impact score of the target characteristic vehicles to obtain corrected time data; integrates the corrected time data, traffic impact score and initial timing plan into traffic flow output data, and sends the traffic flow output data to the adjacent intersection node; receives the traffic flow input data fed back by the adjacent intersection node.

[0121] Among them, the estimated arrival time represents the moment when the vehicle is expected to arrive at the intersection; the estimated passing time refers to the time required for the vehicle to pass through the intersection; the corrected time data represents the time prediction value after considering the influence of the characteristic vehicle; the traffic flow output data is the traffic flow prediction information transmitted to the adjacent intersection; the traffic flow input data represents the traffic flow information received from the adjacent intersection.

[0122] After generating the initial timing plan, the traffic management system needs to interact with surrounding intersections for data to achieve coordinated control. Specifically, the traffic management system first predicts the arrival and passing times of each vehicle based on the current vehicle position and speed. Then, considering the influence degree of the characteristic vehicle, the prediction result is corrected. The system integrates the corrected data with the timing plan, sends it to the relevant intersections through a dedicated communication network, and receives the feedback data to provide a basis for subsequent optimization.

[0123] In some embodiments, the prediction and interaction of traffic flow data can be achieved in various ways: Optionally, the traffic management system can use a Kalman filter to predict vehicle trajectories, construct a state transition model based on historical data, and continuously update the prediction results through real-time observation data; Optionally, the traffic management system can establish a time series prediction model based on long short-term memory networks to capture the evolution law of traffic flow. It can be understood that other methods such as traffic flow simulation based on cellular automata and delay prediction based on queuing theory can also be used to achieve the prediction and interaction of traffic flow data, which are not limited herein.

[0124] S212. Update the traffic signal optimization model based on the traffic flow input data and traffic flow output data, generate the final timing plan, and adjust the signal control parameters of the local intersection node based on the final timing plan.

[0125] Referring to step S107, the traffic management system will generate the final timing plan and perform signal control.

[0126] In some embodiments, the traffic management system will perform verification of the timing data, that is, the traffic management system will input the initial timing plan into the timing evaluation model to obtain the plan feasibility score; determine the similar scenarios of the initial timing plan in the historical timing plan library based on the traffic flow characteristic parameters and target characteristic vehicles; when the plan feasibility score is lower than the preset feasible threshold, adjust the initial timing plan based on the timing plans of the similar scenarios.

[0127] Among them, the timing evaluation model refers to a mathematical model used to evaluate the feasibility of the timing plan; the plan feasibility score refers to the practicality evaluation index of the timing plan; the similar scenario refers to the historical state with similar traffic characteristics; the preset feasible threshold refers to the minimum requirement for the plan feasibility; the timing plan adjustment refers to the optimization and correction process of the initial plan.

[0128] After generating the initial timing plan, the traffic management system needs to evaluate its actual feasibility. Specifically, the traffic management system first inputs the timing plan into the evaluation model to calculate its feasibility score. Then, it searches for similar scenarios in the historical data as a reference for plan adjustment. When the score does not meet the requirements, the system optimizes the plan based on the successful experiences of the similar scenarios to ensure the practicality of the final plan.

[0129] In some embodiments, the evaluation and adjustment of the timing plan can be achieved in various ways: Optionally, the traffic management system can establish a feasibility analysis model based on fuzzy comprehensive evaluation, comprehensively considering multiple evaluation indicators such as delay, number of stops, and queue length; Optionally, the traffic management system can adopt a case-based reasoning method to find the most matching historical case through similarity calculation and extract its timing characteristics for plan optimization. It can be understood that other methods such as plan evaluation based on reinforcement learning and parameter optimization based on genetic algorithms can also be used to achieve the evaluation and adjustment of the timing plan, which is not limited here.

[0130] In the embodiments of the present application, due to the adoption of the feature vehicle recognition technology based on deep learning and the multi-dimensional impact evaluation method, combined with historical data analysis and environmental factor monitoring, a complete feature vehicle management mechanism is established. Therefore, it is possible to achieve accurate recognition and impact evaluation of different types of feature vehicles, and through the regional collaborative optimization mechanism, multi-intersection linkage control is realized, effectively solving the problem that traditional fixed timing plans are difficult to cope with complex traffic flow characteristics, and further realizing more intelligent and efficient traffic signal control. The system not only improves the passing efficiency of feature vehicles, but also enhances traffic safety through the risk warning and active management and control mechanism. At the same time, based on the environment adaptive mechanism, the reliability of the control strategy under various weather conditions is ensured, and finally the overall optimization of regional traffic organization is achieved.

[0131] The traffic management system in the embodiments of the present invention will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the traffic management system in the embodiments of the present application.

[0132] It should be noted that Figure 3 The structure of the traffic management system shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0133] As Figure 3 shown, the traffic management system includes a CPU 301, which can perform various appropriate actions and processes according to the program stored in the ROM 302 or the program loaded from the storage section 308 into the RAM 303, such as executing the methods described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. The I / O interface 305 is also connected to the bus 304.

[0134] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0135] Specifically, according to an embodiment of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the CPU 301, various functions defined in the present invention are performed.

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings.

[0137] Specifically, the traffic management system of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, the traffic signal timing optimization method provided in the above embodiment is implemented.

[0138] On the other hand, the present invention also provides a computer-readable storage medium. The storage medium may be included in the traffic management system described in the above embodiment; or it may exist separately and not be assembled into the traffic management system. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of the traffic management system, the traffic management system implements the traffic signal timing optimization method provided in the above embodiment.

[0139] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0140] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

Claims

1. A traffic signal timing optimization method, characterized in that: Applied to a traffic management system, the method comprises: Based on the location identification information of the local intersection node, determining a plurality of adjacent intersection nodes interconnected with the local intersection node; Collecting vehicle traffic status data and vehicle characteristic data of the local intersection node, and generating traffic flow characteristic parameters according to the vehicle traffic status data and the vehicle characteristic data; Performing characteristic vehicle identification based on the vehicle characteristic data to obtain characteristic vehicle type and vehicle position information of the target characteristic vehicle; Calculating the traffic impact factor of the target characteristic vehicle based on the vehicle size parameters and acceleration performance parameters corresponding to the characteristic vehicle type; Determine the relative distance and driving direction of the target feature vehicle from each intersection according to the vehicle position information; Based on the relative distance, the driving direction and the traffic impact factor, calculating the traffic impact score of the target characteristic vehicle on the traffic flow at each intersection; According to the traffic flow characteristic parameters and the traffic impact score, a traffic signal optimization model is constructed, and an initial timing plan is calculated based on the traffic signal optimization model; Sending the traffic flow output data including the traffic impact score and the initial timing plan to the adjacent intersection node, and receiving the traffic flow input data sent by the adjacent intersection node; The traffic signal optimization model is updated based on the vehicle flow input data and the vehicle flow output data to generate a final timing plan, and the signal control parameters of the local intersection node are adjusted based on the final timing plan.

2. The method according to claim 1, characterized in that After the step of calculating the traffic impact factor of the target characteristic vehicle based on the vehicle size parameter and the acceleration performance parameter corresponding to the characteristic vehicle type, the method further includes: Acquire the license plate information of the target characteristic vehicle, and query the driving age data, historical violation data and traffic accident records corresponding to the target characteristic vehicle based on the license plate information; Determining the driving risk level of the target characteristic vehicle according to the driving years data, the historical violation data and the traffic accident record; Based on the driving risk level, the traffic impact factor is adjusted.

3. The method according to claim 1, characterized in that The step of sending the traffic flow output data including the traffic impact score and the initial timing plan to the adjacent intersection node, and receiving the traffic flow input data sent by the adjacent intersection node, specifically includes: Based on the initial timing plan, the estimated arrival time and the estimated travel time of the target characteristic vehicles at each entrance road of the local intersection node are calculated; Performing weighted correction on the estimated arrival time and the estimated travel time according to the travel impact score of the target characteristic vehicle to obtain corrected time data; Integrate the corrected time data, the traffic impact score and the initial timing plan into traffic flow output data, and send the traffic flow output data to the adjacent intersection node; Receive the vehicle flow input data fed back by the adjacent intersection node.

4. The method according to claim 1, characterized in that: Before the step of performing characteristic vehicle identification based on the vehicle characteristic data to obtain characteristic vehicle type and vehicle position information of the target characteristic vehicle, the method further includes: Collecting the intersection environment parameters of the local intersection node; Calculating environmental impact factors based on the intersection environmental parameters; The confidence threshold of vehicle feature recognition is adjusted according to the environmental impact factor.

5. The method according to claim 4, characterized in that The step of calculating the environmental impact factor based on the intersection environmental parameters specifically includes: Extracting weather conditions, light intensity, road surface conditions and sight distance conditions from the intersection environmental parameters; Identify abnormal features of the road condition including water accumulation, ice, and obstruction, and determine the duration of the abnormal features in combination with the weather conditions; Calculating a lighting influence coefficient according to the lighting intensity, the abnormal characteristics and the viewing distance; The environmental impact factor is calculated according to the abnormal characteristics, the duration and the light impact coefficient.

6. The method according to claim 1, characterized in that After the step of constructing a traffic signal optimization model according to the traffic flow characteristic parameters and the traffic impact score, and calculating an initial timing plan based on the traffic signal optimization model, the method further includes: Input the initial timing plan into the timing evaluation model to obtain a feasibility score of the plan; Based on the traffic flow characteristic parameters and the target characteristic vehicles, determining similar scenarios of the initial timing plan in a historical timing plan library; When the feasibility score of the scheme is lower than a preset feasible threshold, the initial timing scheme is adjusted based on the timing schemes of similar scenarios.

7. A traffic management system, characterized in that: The traffic management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the traffic management system to execute the method described in any one of claims 1-6.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a traffic management system, the traffic management system is caused to execute the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product runs on a traffic management system, the traffic management system is enabled to perform the method according to any one of claims 1 to 6.

Images