Intelligent event flow transfer regulation method and system applied to traffic scene

Abstract

This invention provides an intelligent event flow control method and system applied to traffic scenarios, belonging to the field of traffic management technology. First, it receives comprehensive perception of traffic events and dynamic correlation information of the traffic network to generate traffic event flow baseline information. Based on the traffic event flow baseline information, it divides the flow into stages and reconstructs the traffic event flow links. According to the traffic event flow stage division and link reconstruction information, it constructs a distributed collaborative response rule set for control resources to generate resource collaborative response configuration information. Following the resource collaborative response configuration information, it drives a distributed control node group to execute collaborative control actions, generating collaborative execution information. Based on feedback traffic event evolution correction data and traffic network operation optimization data, iteratively updates the traffic event flow link reconstruction information and resource collaborative response configuration information to generate traffic event flow control completion information. This invention provides comprehensive perception and precise control, achieving efficient handling of traffic events and improving road network operation efficiency and safety.

Description

Technical Field

[0001] This invention relates to the field of traffic management technology, and more specifically, to an intelligent event flow control method and system applied to traffic scenarios. Background Technology

[0002] Currently, traditional traffic incident control methods mainly rely on manual command and fixed control strategies. While manual command offers a degree of flexibility, it is limited by human reaction speed and experience, making it difficult to make comprehensive and accurate judgments and responses to complex traffic incidents in a short period of time. Fixed control strategies, on the other hand, often fail to adapt to the dynamic changes in traffic incidents. For example, using the same control measures for different types and severity of traffic incidents may not achieve optimal control results.

[0003] Furthermore, most existing traffic control systems lack comprehensive perception of traffic events and integrated utilization of dynamic traffic network information, resulting in incomplete and inaccurate control decisions. Simultaneously, the lack of effective coordination mechanisms among various control resources hinders optimal resource allocation and efficient utilization, thus impacting the overall effectiveness of traffic event control. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide an intelligent event flow control method applied to traffic scenarios, the method comprising: Receive comprehensive perception information on traffic incidents and dynamic correlation information of the traffic network, and generate benchmark information for the flow of traffic incidents; Based on the traffic incident flow benchmark information, the traffic incident flow stages are divided, the traffic incident flow links corresponding to each flow stage are reconstructed, and traffic incident flow stage division and link reconstruction information are generated. Based on the traffic incident flow stage division and link reconstruction information, a distributed collaborative response rule set for regulation resources is constructed, and resource collaborative response configuration information is generated; Driven by resource collaborative response configuration information, the distributed control node group executes phased collaborative control actions to generate traffic event flow control collaborative execution information. Based on the feedback of traffic event evolution correction data and traffic network operation optimization data from the collaborative execution information of traffic event flow control, the traffic event flow link reconstruction information and resource collaborative response configuration information are iteratively updated to generate traffic event flow control completion information.

[0005] Furthermore, embodiments of the present invention also provide an intelligent event flow control system applied to traffic scenarios, comprising: A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described intelligent event flow control method applied to traffic scenarios by executing the machine-executable instructions.

[0006] In another aspect, embodiments of the present invention also provide a computer program product, the computer program product including machine-executable instructions, the machine-executable instructions being stored in a computer-readable storage medium, the processor of a computer device reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the computer device to execute the above-described intelligent event flow control method applied to traffic scenarios.

[0007] Based on the above, by receiving comprehensive perception information of traffic events and dynamic correlation information of the traffic network, a traffic event flow benchmark information is generated. Based on this traffic event flow benchmark information, the flow stages are divided and the flow links are reconstructed. This can present the development trend and correlation of traffic events at different stages. Based on the stage division and link reconstruction information, a distributed collaborative response rule set of control resources is constructed, realizing the collaboration between various control resources, avoiding resource dispersion and waste, and improving resource utilization efficiency. According to the resource collaborative response configuration information, the distributed control node group is driven to execute staged collaborative control actions. The control strategy can be adjusted in a timely manner according to the dynamic changes of traffic events. Based on the data feedback of the control collaborative execution information, the flow link reconstruction information and resource collaborative response configuration information are iteratively updated, which can adapt to various complex traffic scenario changes. The final generated traffic event flow control completion information indicates that the traffic event has been handled efficiently and intelligently, effectively improving the operation efficiency and safety of the traffic network. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the execution flow of the intelligent event flow control method applied to traffic scenarios provided in the embodiments of the present invention.

[0009] Figure 2 This is a schematic diagram of exemplary hardware and software components of an intelligent event flow control system applied to traffic scenarios provided in an embodiment of the present invention. Detailed Implementation

[0010] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating an intelligent event flow control method for traffic scenarios provided by an embodiment of the present invention. The following is a detailed description of this intelligent event flow control method for traffic scenarios.

[0011] Step S110: Receive full-dimensional perception information of traffic events and dynamic correlation information of traffic network, and generate traffic event flow benchmark information.

[0012] In this embodiment, in the traffic carbon emission monitoring and control scenario, the comprehensive perception information of traffic events originates from various monitoring devices deployed in the road network. These devices include, but are not limited to, high-definition cameras installed at intersections, induction coils buried under the road surface, vehicle-mounted terminals installed on various vehicles, and environmental monitoring stations deployed on both sides of the road. High-definition cameras collect real-time image information of the road, including vehicle type, number, speed, and queue length; induction coils record vehicle passage time and vehicle type information through electromagnetic induction; vehicle-mounted terminals upload real-time data such as vehicle position, speed, acceleration, and engine operating conditions; and environmental monitoring stations collect environmental parameters such as carbon emissions, temperature, and humidity in the air. All of this information is transmitted in real-time to the data processing center via a 5G communication network to form raw perception data. The dynamic information related to the traffic network includes road topology data, such as road connections, number of lanes, and speed limits; real-time traffic status data, such as average speed, traffic volume, and congestion level of each road segment; and traffic flow evolution trend data, such as predicted traffic volume of each road segment in the future. The above data comes from the database of the traffic management department, the traffic information service platform, and the analysis results of historical traffic data.

[0013] At the data processing center, the received comprehensive traffic event perception information and dynamic traffic network correlation information are first preprocessed. The preprocessing includes data cleaning to remove noise and outliers; data standardization to convert data from different sources and formats into a unified format and unit; and data fusion to integrate information from different devices and sources to obtain more comprehensive and accurate traffic event information. For example, fusing vehicle image information captured by high-definition cameras with vehicle data recorded by induction coils can more accurately count traffic flow and vehicle type distribution. After preprocessing, the processed data is integrated to generate traffic event flow benchmark information. This benchmark information includes the basic attributes of the traffic event, such as the time, location, and type of the event (e.g., traffic accident, traffic congestion, vehicle malfunction); the scope of the event's impact, such as the affected road segments and number of lanes; and the traffic network status at the time of the event, such as traffic flow, speed, and carbon emission levels on the relevant road segments.

[0014] Step S120: Divide the traffic event flow stages based on the traffic event flow benchmark information, reconstruct the traffic event flow links corresponding to each flow stage, and generate traffic event flow stage division and link reconstruction information.

[0015] After generating baseline information on the flow of traffic incidents, it is necessary to divide the flow process of traffic incidents into stages and reconstruct the links. The purpose is to better understand the evolution of traffic incidents so as to take targeted control measures.

[0016] Step S121: Extract the core feature information of traffic events from the traffic event flow benchmark information, and at the same time extract the road network topology, road traffic status and traffic flow evolution trend from the traffic network dynamic correlation information to generate a set of core information of events and road networks. The core feature information of traffic events includes event triggering type, initial impact range, diffusion rate and associated road network elements.

[0017] When extracting core feature information of traffic events from baseline information on traffic event flow, the event trigger type is determined first. The event trigger type can be determined by analyzing the cause of the event; for example, a traffic accident is caused by a vehicle collision, while traffic congestion may be due to excessive traffic volume or road construction. The initial impact range is determined by the affected road segments and areas around the event location; for example, a traffic accident may cause traffic obstruction on the affected road segment and adjacent road segments. The diffusion rate is calculated based on how the event's impact range changes over time; for example, the diffusion rate of traffic congestion can be measured by the increase in the length of congested road segments per unit time. Related road network elements include road intersections, traffic lights, toll booths, etc., within the event's impact range.

[0018] Simultaneously, the road network topology is extracted from the dynamic correlation information of the traffic network, including road connections, node locations, and road segment lengths; road traffic status, such as real-time vehicle speed, traffic volume, and saturation of each road segment; and traffic flow evolution trends, such as predicted traffic volume and speed trends for each road segment over a future period. The extracted core feature information of traffic events and road network-related information are integrated to generate a set of event and road network core information. This set of event and road network core information is stored in a structured data format, such as a multidimensional array containing event attributes, road network topology, traffic status, and traffic flow trends.

[0019] Step S122: Based on the historical traffic incident flow database, extract historical event data that matches the core feature information of the current traffic incident, filter key time nodes and corresponding changes in the scope of influence and road network status response data in the historical event flow process, and generate historical flow reference data.

[0020] The historical traffic incident database stores a large amount of detailed information about past traffic incidents, including incident type, time, location, scope of impact, handling process, and final outcome. To extract historical incident data that matches the core features of the current traffic incident, a feature similarity-based matching algorithm is used. First, the core features of the current traffic incident, such as incident trigger type, initial scope of impact, and spread rate, are compared with the features in the historical incident database. The similarity between the current incident features and each historical incident feature is calculated, using methods such as cosine similarity and Euclidean distance. Based on a set similarity threshold, historical incident data with high similarity are selected.

[0021] For the selected historical event data, key time nodes in its flow process are further extracted. These key time nodes include the event occurrence time, the time when the impact area reaches its maximum, and the time when traffic returns to normal. Simultaneously, data on changes in the impact area corresponding to these key time nodes are extracted, such as the expansion or contraction of the impact area; and road network status response data, such as changes in traffic flow, vehicle speed, and carbon emission levels. The above data is then organized and standardized to generate historical flow reference data. This historical flow reference data is stored in time series format, with each time point corresponding to a set of impact area and road network status data.

[0022] Step S123: Based on historical traffic flow reference data and the current traffic event diffusion rate, extract the characteristic change critical points in the traffic event flow process and generate event flow characteristic critical point data. The characteristic change critical points are the time nodes when the event diffusion rate, the type of impact range, or the road network response mode changes significantly.

[0023] First, historical data on the flow of events is analyzed to identify time points in historical events where the diffusion rate, type of impact, or road network response pattern undergoes significant changes. These time points are the critical points of historical characteristic changes. By analyzing a large number of historical events, the correlation between these critical points of historical characteristic changes and the core characteristics of the events can be established.

[0024] Then, combining the current traffic incident's spread rate, the aforementioned correlations are used to predict the potential critical point for characteristic changes in the current traffic incident. During the prediction process, the differences between the current traffic incident and historical incidents need to be considered, and the prediction results adjusted and corrected accordingly. For example, if the current traffic incident's spread rate is faster than similar historical incidents, the predicted critical point for characteristic changes may occur earlier.

[0025] Step S1231: Extract the historical event diffusion rate change curve, influence range expansion curve, and road network response mode conversion time point from the historical flow reference data, and establish a historical event flow characteristic database.

[0026] The historical event flow reference data includes curves showing the diffusion rate of each historical event over time, the expansion of its impact range over time, and the time points when the road network response mode transitions. This data is organized and stored to establish a historical event flow characteristic database. The diffusion rate curve, with time on the horizontal axis and diffusion rate on the vertical axis, describes how the event's diffusion rate changes at different points in time. Similarly, the impact range expansion curve, with time on the horizontal axis and the size of the impact range (e.g., area or length) on the vertical axis, shows the expansion process of the event's impact range. The road network response mode transition time points record the specific time when the road network changes from one response mode (e.g., normal traffic mode) to another (e.g., congestion mode).

[0027] Step S1232: Extract features from the diffusion rate change curves in the historical event flow feature database, identify rate abrupt change points in the historical event diffusion rate change curves, and generate a set of historical rate abrupt change points. The rate abrupt change point is the time point when the rate of change of diffusion rate exceeds a preset rate of change threshold.

[0028] A sliding window method is used to process the diffusion rate variation curve. A fixed-size time window is set and slides sequentially across the curve. For the data within each window, the rate of change of diffusion rate is calculated. The rate of change is calculated as (maximum rate within the current window - minimum rate within the current window) / window time length. The calculated rate of change is compared with a preset rate of change threshold. If the rate of change exceeds the threshold, a rate abrupt change point is identified within the window. The time of the abrupt change point and the corresponding diffusion rate value are recorded to generate a historical rate abrupt change point set.

[0029] Step S1233: Extract the influence range expansion curve from the historical event flow feature database, identify the range expansion mode conversion point in the influence range expansion curve, and generate a set of historical range conversion points. The range expansion mode conversion point is the time point when the direction or rate of influence range expansion changes.

[0030] The expansion pattern of the influence range expansion curve includes the expansion direction and expansion rate type. The expansion direction can be unidirectional (e.g., expanding forward along a road) or multidirectional (e.g., spreading in all directions); the expansion rate type can be uniform expansion, accelerating expansion, or decelerating expansion. By analyzing the influence range expansion curve, the time points when the expansion direction or expansion rate type changes are identified. For example, when the influence range changes from expanding along one road to expanding to multiple roads, or when the expansion rate changes from accelerating to decelerating, the corresponding time points are the range expansion pattern transition points. These transition points are recorded to generate a historical range transition point set.

[0031] Step S1234: Associate and match the set of historical rate change points with the set of historical range transition points, and combine the road network response mode transition time points of historical events to filter out the time points that simultaneously satisfy rate change, range transition and road network response mode change, and generate a set of historical feature change critical points.

[0032] First, calculate the time difference between each abrupt change point in the historical rate change point set and each transition point in the historical range transition point set. If the time difference is less than a preset time threshold, the two points are considered related. Then, compare the related points with the road network response mode transition time points of historical events. If their times are also close (time difference less than the time threshold), it is determined that the time point simultaneously satisfies rate change, range transition, and road network response mode change, and is added to the historical feature change critical point set.

[0033] Step S1235: Detect the core features of historical events corresponding to each critical point in the set of historical feature change critical points, establish the association mapping relationship between historical features and critical points, and generate a feature-critical point mapping model.

[0034] For each critical point in the set of historical feature change thresholds, the core features of the corresponding historical event are extracted, such as event trigger type, initial impact range, and diffusion rate. Then, machine learning algorithms, such as decision trees and neural networks, are used to establish a mapping relationship between historical features and critical points. The input of the feature-critical point mapping model is the core features of the event, and the output is the predicted feature change threshold. During model training, historical event data is used as training samples, and the model parameters are adjusted to enable the model to accurately predict feature change thresholds based on the core features of the event.

[0035] Step S1236: Extract the diffusion rate data of the current traffic incident, construct the diffusion rate change curve of the current traffic incident, and combine the core feature information of the current traffic incident with the feature-critical point mapping model to preliminarily predict the possible feature change critical points of the current traffic incident and generate initial prediction critical point data.

[0036] Diffusion rate data is extracted from real-time monitoring data of the current traffic incident. A diffusion rate curve is plotted with time on the horizontal axis and diffusion rate on the vertical axis. Core features of the current traffic incident, such as incident trigger type, initial impact range, and diffusion rate, are input into a trained feature-critical point mapping model. Based on the input feature information, the feature-critical point mapping model outputs the time of possible feature change critical points and the corresponding feature changes for the current traffic incident, generating initial predicted critical point data.

[0037] Step S1237: Collect real-time evolution data at the initial stage of the current traffic incident. The real-time evolution data includes real-time diffusion rate, real-time impact range and real-time road network response data. Verify the initial predicted critical point data.

[0038] Real-time evolution data is continuously collected for a period of time following the occurrence of the traffic incident. The real-time diffusion rate is acquired in real time through traffic monitoring equipment; the real-time impact range is determined by analyzing images captured by traffic cameras and data recorded by induction coils; real-time road network response data includes vehicle speed, traffic flow, and carbon emission levels for each road segment. This real-time evolution data is compared with the initial predicted critical point data to check whether the predicted critical point matches the actual situation. For example, near the predicted critical point time, significant changes are observed in the real-time diffusion rate, impact range, or road network response pattern.

[0039] Step S1238: Based on the deviation between the real-time evolution data and the initial predicted critical point data, adjust the prediction parameters of the feature-critical point mapping model, correct the initial predicted critical point data, and generate the corrected predicted critical point data.

[0040] If there is a deviation between the real-time evolution data and the initial predicted critical point data, calculate the magnitude and direction of the deviation. Based on the deviation, adjust the prediction parameters of the feature-critical point mapping model. For example, if the predicted critical point time is earlier than the actual time, appropriately increase the time delay parameter in the model; if the predicted feature change magnitude does not match the actual value, adjust the corresponding weight parameters in the model. By adjusting the parameters, the initial predicted critical point data is corrected, generating corrected predicted critical point data.

[0041] Step S1239: Continuously collect real-time evolution data of the current traffic event, dynamically update and correct the predicted critical point data, until all characteristic change critical points in the current traffic event flow process are determined.

[0042] Throughout the entire flow of a traffic incident, real-time evolution data is continuously collected. At predetermined time intervals (e.g., every minute), newly collected real-time evolution data is input into the feature-critical point mapping model to re-predict the feature change critical points, which are then compared and updated with the previously corrected predicted critical point data. If the new prediction differs significantly from the previous one, the new prediction takes precedence. This process is repeated until the traffic incident ends, the impact area no longer changes, and the diffusion rate stabilizes. At this point, all feature change critical points in the current traffic incident flow are determined.

[0043] For example, step S1239-1: Set the collection frequency of real-time evolution data, and continuously collect the real-time evolution data of the current traffic event according to the set frequency. The real-time evolution data includes the diffusion rate at different time points, the boundary coordinates of the affected area, the traffic status of related road network nodes, and traffic density data.

[0044] Based on the severity and speed of evolution of traffic incidents, an appropriate real-time evolution data collection frequency is set. For rapidly evolving traffic incidents, such as severe traffic accidents, the collection frequency can be set higher, such as once every 30 seconds; for slower evolving incidents, such as the slow formation of traffic congestion, the collection frequency can be set lower, such as once every 5 minutes. Real-time evolution data is continuously collected through traffic monitoring equipment at the set frequency. The diffusion rate data is obtained by calculating the change in the area of ​​influence per unit time; the boundary coordinates of the area of ​​influence are determined using the Global Positioning System (GPS) or image recognition technology; the traffic status of associated road network nodes includes the degree of congestion and traffic capacity of the nodes; and vehicle flow density data is obtained through induction coils or video analysis technology.

[0045] Step S1239-2: Preprocess the real-time evolution data collected each time, remove abnormal and interfering data, supplement missing key data, and generate preprocessed real-time evolution data.

[0046] The preprocessing process includes data cleaning and data completion. Data cleaning aims to remove outlier data, such as erroneous data due to equipment malfunction or abnormal readings under extreme weather conditions. Statistical methods, such as outlier detection based on mean and standard deviation, or machine learning-based anomaly detection algorithms, can be used to identify and remove outlier data. Data completion addresses missing key data using methods such as interpolation and regression analysis. For example, if diffusion rate data for a certain time point is missing, it can be obtained through linear interpolation based on diffusion rate data from previous and subsequent time points. After preprocessing, preprocessed real-time evolution data is generated.

[0047] Step S1239-3: Based on the preprocessed real-time evolution data, update the current traffic event's diffusion rate change curve and impact range expansion curve, and generate the updated evolution characteristic curve.

[0048] The diffusion rate and influence range data from the preprocessed real-time evolution data are added to the original diffusion rate change curve and influence range expansion curve, respectively, updating the shape and trend of the curves. For example, if the newly collected diffusion rate data is larger than the previous data, the diffusion rate change curve will shift upward at the corresponding time point; if the influence range expands, the influence range expansion curve will extend to the upper right. Updated evolution characteristic curves are generated to more accurately reflect the evolution of the current traffic event.

[0049] Step S1239-4: Detect the updated evolutionary feature curve, identify newly added rate mutation points or range expansion mode conversion points in the curve, and generate new feature change candidate points.

[0050] Using a method similar to steps S1232 and S1233, the updated evolutionary characteristic curves are detected. For diffusion rate change curves, newly added rate abrupt change points are identified; for influence range expansion curves, newly added range expansion mode transition points are identified. These newly added points are used as candidate points for new characteristic changes.

[0051] Step S1239-5: Compare the newly added candidate points of feature change with the corrected prediction critical point data to determine whether the newly added candidate points of feature change are within the preset error range of the corrected prediction critical point data.

[0052] Calculate the time difference between the newly added candidate point of feature change and the corresponding critical point in the corrected predicted critical point data. If the time difference is less than the preset error range (e.g., 3 minutes), the newly added candidate point of feature change is determined to be within the preset error range; otherwise, it is determined to be outside the preset error range.

[0053] Step S1239-6: If the newly added candidate point of feature change is within the preset error range, mark it as the feature change critical point of the current traffic event and add it to the event flow feature critical point data.

[0054] When a newly added candidate point for feature change is within the preset error range, it indicates that the newly added candidate point for feature change matches the predicted critical point. It can be identified as the critical point for feature change of the current traffic event and added to the event flow feature critical point data.

[0055] Step S1239-7: If the newly added candidate points of feature change exceed the preset error range, adjust the prediction parameters of the feature-critical point mapping model based on the newly added candidate points of feature change, correct the predicted critical point data after correction, and generate the predicted critical point data after secondary correction.

[0056] If the newly added candidate points for feature changes exceed the preset error range, it indicates a significant bias in the feature-critical point mapping model's prediction. In this case, it is necessary to adjust the model's prediction parameters based on the information from the newly added candidate points. For example, if the time of the added candidate point is later than the predicted critical point time, the time-related parameters in the model should be adjusted appropriately to make the model's prediction results closer to the actual situation. After adjusting the parameters, the corrected predicted critical point data should be revised again to generate secondary revised predicted critical point data.

[0057] Step S1239-8: Repeat the steps of data collection, preprocessing, curve updating, candidate point identification, comparison and judgment, confirmation or correction until the current traffic event spread rate tends to stabilize, the scope of influence no longer expands, and no new candidate points with characteristic changes appear.

[0058] Following the steps described above, real-time evolution data is continuously collected, preprocessed, and the evolution characteristic curve is updated. New candidate points for feature changes are identified and compared with the predicted critical points for correction. The process stops when the spread rate of the traffic incident becomes stable (the rate of change is less than the preset stability threshold), the scope of influence no longer expands (the change in the scope of influence is less than the preset scope threshold), and no new candidate points for feature changes appear within a certain period of time (e.g., 10 minutes).

[0059] Step S1239-9: Sort all confirmed feature change critical points in chronological order, identify the evolutionary logical relationship between each critical point, and generate sorted feature change critical point data.

[0060] The identified critical points of feature change are sorted chronologically. Then, the evolutionary logic between these critical points is analyzed. For example, the emergence of a critical point might be due to the expansion of the impact range caused by a previous critical point, leading to changes in the road network response pattern. Identifying these logical relationships allows for a better understanding of the evolution of traffic events. This results in the generation of sorted critical point data, which includes the critical points arranged chronologically, their corresponding feature change information, and evolutionary logical relationships.

[0061] Step S1239-10: Integrate the complete information corresponding to the feature change critical point data after sorting, and finally determine all feature change critical points in the current traffic event flow process to generate the final event flow feature critical point data.

[0062] The critical point information, feature change information, and evolutionary logical relationships in the sorted feature change critical point data are integrated to form the final event flow feature critical point data. This event flow feature critical point data is stored in a structured form, such as a table or database record containing information such as critical point time, feature change type, change in impact range, and change in road network response mode.

[0063] Step S124: Based on the critical point data of event flow characteristics, the traffic event flow process is divided into multiple continuous flow stages. The time span, core evolution target and corresponding road network impact area of ​​each flow stage are defined to generate traffic event flow stage division information.

[0064] Based on the temporal sequence of each critical point in the event flow characteristic critical point data, the entire flow process of a traffic event is divided into multiple consecutive flow stages. The start time of each flow stage is the time of the previous critical point, and the end time is the time of the current critical point. For example, if the first critical point is 10 minutes after the event occurs, and the second critical point is 30 minutes after the event occurs, then the time span of the first flow stage is from the event occurrence to 10 minutes, and the time span of the second flow stage is from 10 minutes to 30 minutes.

[0065] For each stage of the process, a core evolutionary objective is determined. The core evolutionary objective is determined based on the characteristic changes of that stage. For example, in the initial stage after an event occurs, the core evolutionary objective might be to control the expansion of the event's impact range; in the stage where the event's impact range reaches its maximum, the core evolutionary objective might be to alleviate traffic congestion and reduce carbon emissions.

[0066] Simultaneously, the road network impact area corresponding to each transition stage is determined. The road network impact area is determined based on the scope of influence at that stage. For example, in the initial stage, the impact area may only include the road segment where the incident occurred; as the event evolves, the impact area may expand to multiple adjacent roads. The time span, core evolution objectives, and road network impact area of ​​each transition stage are integrated to generate traffic event transition stage division information.

[0067] Step S125: For each transition stage, based on the core evolution goal and road network influence area of ​​that transition stage, extract the corresponding road network node information from the dynamic correlation information of the traffic road network to generate a stage road network node set. The road network node information includes road intersections, traffic hubs, road network connection points, and endpoints of key traffic sections.

[0068] For each stage of the transition, relevant road network nodes are selected from the dynamic correlation information of the traffic network based on its core evolution goals and the area of ​​influence of the road network. Road intersections are the convergence points of traffic flows and have a significant impact on the spread and expansion of the impact range of traffic incidents; transportation hubs such as bus stations and subway stations are the gathering and dispersal points of people and vehicles, and traffic incidents may have a significant impact on their operation; road network connection points such as highway entrances and exits and bridges are key connecting parts of the road network; the endpoints of key traffic sections are the starting and ending points of the road sections.

[0069] Detailed information about these road network nodes is extracted, including their location coordinates, type, connected road segments, and traffic capacity, to generate a stage-specific road network node set. The nodes in this stage-specific set are the key targets for monitoring and control during that transition stage.

[0070] Step S126: Based on the set of road network nodes in the current phase and the road network topology of the current phase, detect the traffic connectivity between each road network node, filter the feasible connection paths between road network nodes, eliminate paths with interrupted connectivity, and generate feasible node connection path information for the current phase.

[0071] A road network graph model is constructed using the set of road network nodes for each transition stage and the road network topology. In the road network graph model, nodes represent road network nodes, and edges represent road connections between nodes. Path search algorithms from graph theory, such as depth-first search or breadth-first search, are used to detect the connectivity between road network nodes. For any two nodes, it is determined whether a passable path exists. If a passable path exists, it is added to the set of feasible connection paths; if the path connectivity is interrupted due to road construction, traffic accidents, or other reasons, the path is removed. Feasible node connection path information for each stage is generated, which includes all feasible connection paths between road network nodes in that transition stage.

[0072] Step S127: Combining the spread rate and core evolution objective of traffic events in this transition stage, predict the expansion trend of the traffic event's transition range within this transition stage, match the road network spatial range covered by the expansion trend with the road network spatial range associated with the stage's feasible node connection path information, filter out node connection paths whose spatial locations are included within the expansion trend, and generate initial transition link information for the stage.

[0073] Based on the spread rate and core evolution goals of traffic incidents in this transition phase, a traffic flow prediction model is used to predict the expansion trend of the traffic incident's flow range within this phase. The traffic flow prediction model can be trained based on historical traffic data and current traffic conditions, and can predict how the impact range of traffic incidents will expand over a future period.

[0074] The predicted road network spatial range covered by the expansion trend of the flow range is compared with the road network spatial range associated with the feasible node connection path information for each stage. For each feasible connection path, it is determined whether it is completely or partially located within the spatial range covered by the expansion trend of the flow range. If so, the path is selected as part of the initial flow link for the stage. Initial flow link information for the stage is generated, which includes node connection paths that may be affected by traffic events in this flow stage.

[0075] Step S128: Extract the road traffic status and traffic flow evolution trend data of this transition stage, detect the carrying capacity of each node connection path in the initial transition link information of the stage, identify the path segments that are at risk of exceeding the preset congestion threshold due to predicted traffic flow convergence, and generate the stage transition obstruction risk path information.

[0076] Extract road traffic status data for this transition stage from the dynamic correlation information of the traffic network, such as the current traffic flow, speed, and saturation of each road segment; as well as traffic flow evolution trend data, such as the predicted traffic flow of each road segment in the future.

[0077] For each node connection path in the initial flow link information of the stage, the carrying capacity of the node connection path is calculated based on its road traffic status and traffic flow evolution trend data. The carrying capacity can be determined by the road's design capacity, current traffic flow, and predicted traffic flow. If the predicted traffic flow convergence causes the path's traffic load (e.g., traffic volume) to exceed a preset congestion threshold, then the path segment is determined to have a congestion risk. All path segments with congestion risks are identified, and stage flow congestion risk path information is generated.

[0078] Step S129: For the risk path information of the phase flow obstruction, retrieve the surrounding road network node information again, plan the alternative node connection path, replace the obstruction risk path segment in the initial flow link of the phase, and set the activation conditions and switching process of the alternative path to generate the phase optimized flow link information.

[0079] Once the risk of traffic congestion at a particular stage is identified, alternative connecting routes need to be planned to avoid exacerbating traffic congestion. This involves retrieving road network node information around the risky traffic flow segment to find alternative connecting routes. The planning of alternative routes needs to consider factors such as route length, capacity, and traffic flow to ensure that they can effectively alleviate the traffic congestion caused by the risky traffic flow.

[0080] The planned alternative node connection paths replace the congestion risk path segments in the initial flow link of the generation phase. Simultaneously, activation conditions for alternative paths are set, such as activating an alternative path when the traffic load on a congestion risk path reaches a preset threshold; and switching procedures are defined, such as guiding vehicles from congestion risk paths to alternative paths through traffic light control and traffic guidance information dissemination. The generation phase optimizes the flow link information, which includes optimized node connection paths, alternative paths, their activation conditions, and switching procedures.

[0081] Step S1210: Integrate the stage division information of all flow stages and the corresponding stage optimization flow link information, set the connection rules and switching trigger conditions between the flow links of each stage, and generate traffic event flow stage division and link reconstruction information.

[0082] The process integrates the phase division information (time span, core evolution goals, road network impact area) and corresponding phase optimization flow link information for each transition stage. Then, it sets the connection rules between the flow links of each stage, such as how to guide traffic flow from the current stage's flow links to the next stage's flow links at the end of a transition stage. Simultaneously, it sets switching trigger conditions, such as triggering a link switch when the core evolution goal of a certain transition stage is completed. By integrating the above information, it generates traffic event transition stage division and link reconstruction information.

[0083] Step S130: Based on the traffic event flow stage division and link reconstruction information, construct a distributed collaborative response rule set for regulation resources and generate resource collaborative response configuration information.

[0084] After completing the division of traffic incident flow stages and link reconstruction, it is necessary to construct a distributed collaborative response rule set for regulation resources in order to achieve effective regulation of traffic incidents.

[0085] Step S131: Extract the optimized flow link information, core evolution goals and road network impact areas of each stage from the traffic event flow stage division and link reconstruction information, break down the control requirements of each flow stage, and generate a staged control requirement list. The control requirements include spatial coverage requirements, temporal response requirements, control intensity requirements and coordination requirements.

[0086] From the traffic incident flow phase division and link reconstruction information, we extract the phase optimization flow link information for each flow phase, including node connection paths, alternative paths, etc.; the core evolution goals of each phase, such as controlling the scope of impact and alleviating congestion; and the road network impact area. Based on this information, we analyze the control objectives that need to be achieved in each flow phase, and then break them down to obtain specific control requirements.

[0087] Spatial coverage requirements refer to the road network area that regulatory resources need to cover, ensuring that all road segments and nodes affected by traffic events can be effectively regulated. Temporal response requirements refer to the need for regulatory resources to respond within a specified timeframe to meet the time constraints of traffic event evolution. Regulatory intensity requirements refer to the desired regulatory effects, such as reducing traffic volume, increasing vehicle speed, and reducing carbon emissions. Coordination and cooperation requirements refer to the need for different regulatory resources to cooperate and work together to maximize the overall regulatory effect. These regulatory requirements are then organized and categorized to generate a phased list of regulatory requirements.

[0088] Step S132: Collect detailed information on traffic control resources across the entire region and generate a ledger of traffic control resources across the entire region. The detailed information includes resource type, control function, control coverage, response time, control capability boundary, deployment location, and resource operation status.

[0089] Information on traffic control resources across the entire region is collected through the traffic management department's resource management system and equipment monitoring system. Resource types include traffic lights, traffic guidance screens, reversible lane control equipment, intelligent traffic signal control systems, and carbon emission monitoring equipment. Control function refers to the specific control effects the resource can achieve, such as traffic signal control, traffic guidance information dissemination, and lane direction adjustment. Control coverage refers to the road network area that the resource can affect. Response timeliness refers to the time required for the resource to execute control actions from receiving the control command. Control capability boundary refers to the maximum control effect that the resource can achieve, such as the maximum green light ratio adjustment range of traffic lights and the information display capacity of traffic guidance screens. Deployment location refers to the specific geographical location where the resource is installed. Resource operating status refers to the current working status of the resource, such as normal operation, fault, or maintenance. The above information is integrated to generate a comprehensive control resource ledger for unified management and scheduling of control resources.

[0090] Step S133: Based on the spatial coverage requirements in the phased control demand list, select control resources from the overall control resource ledger that can cover the road network impact area of ​​the corresponding phase, and generate a phased spatial adaptation resource pool.

[0091] For each transition stage in the phased control demand list, resources are selected from the overall control resource ledger based on their spatial coverage requirements. The selection criterion is that the control coverage of the resources can fully or partially cover the road network impact area of ​​that stage. For example, if the road network impact area of ​​a certain transition stage is an intersection and its surrounding road sections, then resources such as traffic lights and traffic guidance screens whose control coverage includes that intersection and surrounding road sections are selected. The selected control resources are then integrated to generate a phased spatial adaptation resource pool.

[0092] Step S134: For the timing response requirements of each stage, select control resources from the stage space adaptation resource pool that can meet the time span requirements of the transition stage, and generate a stage timing adaptation resource subset.

[0093] Each phase of the workflow has its own time span, and control resources need to complete their control actions within this time span. Therefore, it is necessary to select control resources from the phase-space adaptation resource pool whose response time meets the requirements of this time span. The response time is calculated as the sum of the resource's response time and the execution time of the control action. If the response time of a resource is less than or equal to the time span of the workflow phase, then the resource is deemed to meet the timing response requirements. Control resources that meet the criteria are then selected to generate a phase-time adaptation resource subset.

[0094] Step S135: Based on the stage control intensity requirements, detect the control capability boundary of each resource in the stage time-series adaptation resource subset, screen control resources whose control capabilities can meet the stage control intensity requirements, and generate a stage candidate control resource set.

[0095] The phased control intensity requirement specifies the control effect to be achieved in that phase, such as reducing traffic flow by a certain percentage or increasing vehicle speed by a certain value. For each control resource in the phased timing adaptation resource subset, its control capability boundary is checked to determine whether it can meet the phased control intensity requirement. For example, if the phased control intensity requirement is to reduce traffic flow on a certain road segment by 30%, it is necessary to check whether the signal timing adjustment of traffic lights can achieve this goal, or whether the information dissemination of traffic guidance screens can guide a sufficient number of vehicles to detour. Resources whose control capabilities can meet the phased control intensity requirement are selected to generate a phased candidate control resource set.

[0096] Step S136: Based on the stage coordination requirements, detect the compatibility of the control functions and the coordination of actions of each resource in the stage candidate control resource set, set the control action connection logic between different resources, and detect whether there are mutual conflicts of control actions under the set connection logic, and generate stage resource coordination logic.

[0097] The need for phased coordination requires that different regulatory resources can cooperate and work together. Therefore, it is necessary to test the compatibility of regulatory functions and the synergy of actions among the various resources in the phased candidate regulatory resource set.

[0098] Step S1361: Extract detailed descriptions of the regulation functions, regulation action types, action execution processes, action mechanisms, and road network parameters affecting each resource in the candidate regulation resource set for the stage, and generate a resource regulation function and action characteristic ledger.

[0099] For each resource in the candidate control resource set for a given stage, a detailed description of its control function is extracted, such as the signal timing control function of traffic lights and the information dissemination function of traffic guidance screens; the type of control action, such as signal phase adjustment and information display content update; the action execution process, such as the steps of a traffic light from receiving an instruction to completing phase adjustment; the action mechanism, such as traffic lights adjusting traffic flow by changing green light time; and the road network parameters affected by the action, such as traffic flow, vehicle speed, and carbon emission concentration. This information is compiled into a resource control function and action characteristic ledger to facilitate functional compatibility and action synergy testing.

[0100] Step S1362: Based on the stage coordination requirements, set the coordination goals to be achieved in the control process of this transition stage. The coordination goals include smooth action sequence connection, superimposed and enhanced control effect, comprehensive control range coverage and avoidance of mutual interference of actions, and generate a stage coordination goal list.

[0101] Based on the phased coordination requirements, the coordination objectives to be achieved during the control process of this flow phase are clarified. Smooth action sequence means that the control actions of different resources can be sequentially connected in time, avoiding overlap or gaps. Enhanced synergistic control effect means that the control actions of multiple resources can cooperate to produce a better effect than control by a single resource. Comprehensive control coverage means that all road network areas requiring control can be covered by the controlled resources. Avoidance of mutual interference means that the control actions of different resources will not affect each other, leading to reduced control effect or negative effects. The above coordination objectives are described and quantified to generate a phased coordination objective list.

[0102] Step S1363: Combine resources in the candidate control resource set of the stage into pairs, detect the compatibility of control functions of each pair of resources, determine whether the control functions of the two can complement or synergistically enhance each other, if the control functions of the two are for the same road network parameter but have opposite directions of action, then mark them as incompatible functions, and generate resource function compatibility detection results.

[0103] Resources in the candidate control resource set are paired, and for each pair, their control functions are analyzed. If their control functions complement each other—for example, traffic lights control traffic flow while traffic guidance screens guide vehicles to choose the optimal route—the combination can better alleviate traffic congestion, and they are considered functionally compatible. If their control functions target the same road network parameter but act in opposite directions—for example, one resource attempts to increase traffic flow on a certain road segment while the other attempts to decrease it—they are marked as functionally incompatible. All resource pairs are tested, and resource function compatibility test results are generated.

[0104] Step S1364: For functionally compatible resource pairs, further detect the execution timing compatibility of their control actions, determine whether the action execution cycle of the former resource can be connected with the action start cycle of the latter resource, and generate action timing compatibility detection results.

[0105] For resource pairs with functional compatibility, analyze the execution timing of their regulatory actions. The action execution period of the previous resource refers to the time required from the start to the end of the action, and the action startup period of the subsequent resource refers to the time window when the action can start to be executed. If the end time of the action execution period of the previous resource is within the action startup period of the latter, it is determined that the action timings of the two are compatible; otherwise, it is determined that the timings are incompatible. For example, it takes a certain amount of time for a traffic guidance screen to publish a detour message for drivers to receive and respond, and the phase adjustment of traffic lights needs to be carried out after the vehicles start to detour to avoid traffic chaos. By detecting the compatibility of action timings, a detection result of action timing compatibility is generated.

[0106] Step S1365: Based on the detection results of resource functional compatibility and action timing compatibility, screen out resource combinations that are functionally compatible and timing-compatible, and generate a set of basic collaborative resource combinations.

[0107] Combining the detection results of resource functional compatibility and action timing compatibility, screen out resource combinations that meet both functional compatibility and timing compatibility. The above resource combinations have the basic conditions for collaborative work and can cooperate with each other functionally and temporally. Integrate the above resource combinations together to generate a set of basic collaborative resource combinations.

[0108] Step S1366: Detect the scope of action of the regulatory actions of each combination in the set of basic collaborative resource combinations, and determine whether the regulatory scope of the resources within the combination can cover the road network impact area of the stage, and generate a detection result of scope coverage.

[0109] For each resource combination in the set of basic collaborative resource combinations, analyze the scope of action of the regulatory actions of each resource within the combination. Overlay the above scopes of action and determine whether the overlaid scope can completely cover the road network impact area of this transfer stage. If it can completely cover, the scope coverage detection is qualified; otherwise, it is unqualified. Generate a detection result of scope coverage for further screening of resource combinations.

[0110]

[0110] Step S1367: For the resource combinations that pass the scope coverage detection, detect the action mechanisms of the regulatory actions of each resource within the resource combination, set the connection logic between actions, and set the completion flag of the action of the previous resource as the start trigger condition of the action of the subsequent resource, and generate an action connection logic rule.

[0111] For resource combinations that pass the coverage test, a thorough analysis of the regulatory mechanisms of each resource is conducted. Based on these mechanisms, the sequence and connection between actions are determined. For example, a traffic guidance screen first displays detour information; once most vehicles begin to detour, the traffic lights adjust their phases to improve traffic efficiency. The completion flag of the preceding resource action is set as the trigger condition for the subsequent resource action. For instance, after the traffic guidance screen completes its information display and continues for a certain period, the traffic light phase adjustment is triggered. Action connection logic rules are generated to clarify the execution order and trigger conditions of each action within the resource combination.

[0112] Step S1368: Based on the action connection logic rules, simulate the execution process of the control action of resource combination, calculate the superposition result of the control effect generated by the simulation, evaluate the matching degree between the superposition result of the control effect and the quantified target value in the stage collaboration target list, and if the matching degree is higher than the preset effective threshold, mark the action connection logic rule as effective and generate an effective connection logic set.

[0113] Using traffic simulation software or mathematical models, the execution process of resource combination control actions is simulated based on action connection logic rules. During the simulation, the impact of each resource's control actions on road network parameters, such as traffic flow, vehicle speed, and carbon emission levels, is recorded. The superimposed control effects generated by the simulation are calculated, for example, the percentage reduction in traffic flow or the numerical increase in vehicle speed. This superimposed result is compared with the quantified target values ​​in the phased coordination target list to calculate the matching degree. The matching degree can be calculated using methods such as Euclidean distance or cosine similarity. If the matching degree is higher than a preset effective threshold (e.g., 80%), the action connection logic rule is deemed valid and added to the set of valid connection logic rules.

[0114] Step S1369: Integrate the action connection rules, resource function compatibility requirements, action timing compatibility requirements, and scope coverage requirements in the effective connection logic set, set the collaborative cooperation method and action execution order of each resource within the stage, and generate the stage resource collaboration logic framework.

[0115] The action connection rules, resource function compatibility requirements, action timing compatibility requirements, and scope coverage requirements in the effective connection logic set are integrated. Based on these requirements, the collaborative cooperation methods of each resource within the phase are defined, such as master-slave cooperation, parallel work, etc.; and the action execution order is defined, clarifying when each resource's action begins and ends. A phase resource collaboration logic framework is generated, which describes how each resource within the phase works collaboratively to achieve the control objectives.

[0116] Step S13610: Supplement the exception handling mechanism in the stage resource coordination logic framework, set the coordination adjustment method of other resources when a certain resource action is executed abnormally, improve the stage resource coordination logic, and generate the final stage resource coordination logic.

[0117] In the phased resource coordination logic framework, an exception handling mechanism is added. When a resource action malfunctions, such as equipment failure or the control effect not meeting expectations, other resources need to coordinate and adjust. For example, if a traffic light malfunctions and cannot function properly, the traffic guidance screen can publish relevant information to guide vehicles to detour; simultaneously, the variable lane control equipment can adjust the lane direction to alleviate traffic congestion. Resource coordination adjustment methods in abnormal situations are defined, such as activating backup resources and adjusting control parameters. By adding the exception handling mechanism, the phased resource coordination logic is improved, generating the final phased resource coordination logic.

[0118] Step S137: Based on the node distribution and path direction in the stage optimization flow link information, group the resources in the stage candidate control resource set according to the correspondence between deployment location and link node to form multiple distributed resource response units, generate stage distributed resource unit configuration, and each distributed resource response unit undertakes the control task of the corresponding link node and surrounding area.

[0119] The node distribution and path orientation in the phased optimization flow link information reflect the key road network nodes and connection paths within the impact range of traffic incidents. Based on the resource deployment location, resources in the phased candidate control resource set are matched with link nodes. If a resource is deployed close to a link node, it is assigned to the distributed resource response unit corresponding to that node. Each distributed resource response unit contains a set of resources that work collaboratively to undertake the control tasks for the corresponding link node and surrounding area. Phased distributed resource unit configurations are generated, specifying the composition and control area of ​​each distributed resource response unit.

[0120] Step S138: Set the control roles and task assignments of each resource within each distributed resource response unit, set the master-slave collaboration relationship of resources within the distributed resource response unit, with the master resource undertaking the overall coordination task, and the slave resources cooperating to execute specific control actions, and generate the resource collaboration configuration within the unit.

[0121] Within each distributed resource response unit, the control role of each resource is defined based on its control functions, capabilities, and characteristics. For example, the intelligent traffic signal control system can act as the master resource, responsible for coordinating the control actions of other resources within the unit; traffic guidance screens and variable lane control devices can act as slave resources, cooperating with the master resource to execute specific control actions. The task division of each resource is clearly defined, such as the master resource being responsible for formulating control strategies and allocating control tasks, while slave resources are responsible for executing specific control actions and providing feedback on the execution results. A master-slave cooperation relationship is established, whereby the master resource can send control commands to slave resources, and the slave resources, after executing the commands, provide feedback on the execution status to the master resource. A resource cooperation configuration within the unit is generated, detailing the roles, task divisions, and cooperation relationships of each resource within the unit.

[0122] Step S139: Set the collaborative linkage relationship between each distributed resource response unit, establish an information exchange channel and control action synchronization mechanism between distributed resource response units, and generate collaborative linkage configuration between units.

[0123] Different distributed resource response units need to coordinate and collaborate to effectively control the entire traffic incident impact area. This involves establishing collaborative relationships between these units, such as information sharing, task coordination, and resource allocation. Information exchange channels between units should be established, using wired or wireless communication methods, to ensure real-time exchange of control information, such as traffic status data, control instructions, and execution results. A control action synchronization mechanism should be established to ensure that the control actions of different units are coordinated in time, avoiding conflicting or redundant controls. For example, adjacent distributed resource response units need to coordinate when adjusting traffic light phases to achieve smooth traffic flow. Finally, a collaborative configuration between units should be generated, clearly defining the collaboration methods, information exchange channels, and action synchronization mechanisms.

[0124] Step S1310: Integrate the distributed resource unit configuration, intra-unit resource collaboration configuration, inter-unit collaborative linkage configuration, and stage resource collaboration logic of each flow stage, set the resource scheduling path, communication protocol, and data transmission standard, and generate resource collaboration response configuration information.

[0125] The system integrates the distributed resource unit configurations, intra-unit resource collaboration configurations, inter-unit collaborative linkage configurations, and phased resource collaboration logic for each stage of the process. It defines resource scheduling paths, clarifying the transmission path of control commands from the control center to each distributed resource response unit; communication protocols, specifying communication rules between units and between resources within a unit; and data transmission standards, ensuring consistent data format and accurate content. By integrating this information, it generates resource collaborative response configuration information, providing detailed configuration guidance for the distributed control node group to execute phased collaborative control actions.

[0126] Step S140: Drive the distributed control node group to execute phased collaborative control actions according to the resource collaborative response configuration information, and generate traffic event flow control collaborative execution information.

[0127] After generating the resource coordination response configuration information, it is necessary to drive the distributed control node group to perform phased coordination control actions according to the configuration information.

[0128] Step S141: Extract the distributed resource unit configuration, intra-unit resource collaboration configuration, inter-unit collaborative linkage configuration, and phased control requirements list from the resource collaborative response configuration information, determine the traffic control node corresponding to each distributed resource response unit, and integrate all traffic control nodes to form a distributed control node group.

[0129] The distributed resource unit configurations for each stage are extracted from the resource collaborative response configuration information to determine the traffic control resources contained in each distributed resource response unit. Based on the resource collaboration configuration within the unit, the traffic control node corresponding to each resource is identified. For example, a traffic light corresponds to one traffic control node, and a traffic guidance screen corresponds to another. All traffic control nodes are integrated to form a distributed control node group. Nodes in the distributed control node group are interconnected via a network and can receive and execute control commands.

[0130] Step S142: Convert the control requirements and resource collaboration configuration of each flow stage into control instructions that can be executed by each control node, and generate a staged node control instruction set. The control instructions include action type, execution sequence, control range, control parameters and collaborative feedback requirements.

[0131] For each transition stage, based on the phased control demand list and the resource collaboration configuration in the resource collaborative response configuration information, the control demands are converted into specific control instructions. Action types include traffic signal phase adjustment, traffic guidance information dissemination, and variable lane direction switching; the execution sequence specifies the start time and duration of the control action; the control scope clarifies the road network area affected by the control action; control parameters are the specific parameters required to execute the control action, such as the green light ratio of traffic lights and the content of traffic guidance information; collaborative feedback requirements specify the information that the control node needs to provide after executing the action, such as execution status and control effect. These control instructions are categorized according to the control nodes to generate a phased node control instruction set.

[0132] Step S143: Based on the phase connection rules in the traffic event flow phase division and link reconstruction information, set the issuance sequence of the control instruction set of each phase node, set the feedback conditions for the completion of the previous phase instruction execution and the trigger conditions for the issuance of the next phase instruction, and generate the instruction issuance sequence plan.

[0133] The phase transition rules in the traffic incident flow phase division and link reconstruction information define the order and switching conditions between each flow phase. Based on these rules, the issuance sequence of control command sets for each phased node is set. For example, control commands for the next flow phase are issued only after the control action of the previous flow phase is completed. Feedback conditions for the completion of the previous phase's commands are set, such as receiving completion feedback from all control nodes and achieving the preset control effect. Trigger conditions for issuing commands in the next phase are set, i.e., satisfying the feedback conditions for the completion of the previous phase's commands. A command issuance sequence plan is generated, clarifying the issuance time and trigger conditions for the control command set of each phased node.

[0134] Step S144: According to the instruction issuance sequence plan, issue the corresponding phased node control instructions to each traffic control node in the distributed control node group in sequence, record the issuance time, instruction content, receiving node identifier and instruction issuance channel of each phased node control instruction, and generate a detailed instruction issuance ledger.

[0135] According to the instruction issuance sequence plan, when the triggering conditions are met, corresponding phased node control instructions are issued to each traffic control node in the distributed control node group via the communication network. During the issuance process, the issuance time, instruction content (such as action type, execution sequence, control parameters, etc.), receiving node identifier (such as node ID), and instruction issuance channel (such as communication port, protocol, etc.) of each instruction are recorded. A detailed instruction issuance ledger is generated for subsequent instruction execution tracking and auditing.

[0136] Step S145: During the instruction issuance process, collect instruction reception status data of each traffic control node and generate node instruction reception status records. The instruction reception status data includes instruction reception confirmation signals, instruction parsing progress, and action preparation data.

[0137] After issuing instructions to traffic control nodes, the system collects real-time data on the nodes' instruction reception status. Instruction reception confirmation signals are the acknowledgment messages returned by the nodes upon receiving the instructions; instruction parsing progress indicates the degree to which the nodes have parsed the instruction content, such as "parsed completely" or "parsing in progress"; and action preparation data reflects the preparatory work done by the nodes to execute the instructions, such as equipment startup status and parameter configuration. Recording this data generates a node instruction reception status log, allowing for timely monitoring of instruction reception and preparation.

[0138] Step S146: After the traffic control node initiates the control action, the data of the action execution process of the traffic control node is continuously collected. The action execution process data includes the execution progress, real-time changes of control parameters, resource operation status data and local operation status change data of the road network around the node, and generates a real-time data stream of node action execution.

[0139] After receiving instructions and completing preparations, traffic control nodes initiate control actions. During execution, relevant data is continuously collected. Execution progress reflects the degree of completion, such as 30% or 50% completion; real-time changes in control parameters record dynamic adjustments during execution; resource operation status data includes equipment operating voltage, current, and temperature; and local road network operation status data around the node includes traffic flow, speed, and congestion levels. This data is transmitted in real-time to the data processing center to generate a real-time data stream of node action execution, enabling real-time monitoring of the control actions.

[0140] Step S147: Based on the resource collaboration configuration within the unit, and combined with the real-time data stream of the action execution of each traffic control node within the same distributed resource response unit, compare the real-time data of the action execution of each traffic control node with the preset action timing and parameter coordination requirements in the resource collaboration configuration within the unit to generate collaborative execution status data within the unit.

[0141] Step S1471: Extract the master-slave collaboration relationship, the division of labor of control roles and the action coordination requirements in the resource collaboration configuration within the unit, set the action connection sequence, synchronous execution requirements and mutual feedback mechanism of each traffic control node in the distributed resource response unit, and generate the collaboration specification within the unit.

[0142] Extract the master-slave collaboration relationship from the resource collaboration configuration within the unit, clearly defining the master and slave resources; control the division of roles and determine the specific tasks of each resource; define the requirements for action coordination, such as action timing and parameter coordination. Based on this information, set the action sequence of each traffic control node within the unit, i.e., which node executes the action first and which node executes the action later; define synchronous execution requirements, such as certain actions needing to start or end simultaneously; define mutual feedback mechanisms, such as slave resources reporting execution status to master resources, and master resources sending adjustment instructions to slave resources. Generate the unit's collaboration specifications as the basis for judging the collaborative execution status of nodes within the unit.

[0143] Step S1472: Extract key action time series data from the real-time data stream of each traffic control node within the same distributed resource response unit. The key action time series data includes the action start time, key action node completion time, action execution cycle, and action end time, generating a node time series dataset within the unit.

[0144] For each traffic control node within the same distributed resource response unit, key action time-series data is extracted from its real-time action execution data stream. Action start time is the time when the node begins executing the action; key action node completion time is the completion time of key steps in the action execution process; action execution cycle is the total time from start to finish of the action; and action end time is the time when the action is completed. These data are then integrated to generate a node time-series dataset within the unit.

[0145] Step S1473: Based on the action connection sequence in the intra-unit collaborative specification, compare the action start time of adjacent nodes in the intra-unit node time series dataset with the completion time of the previous node's key action node, calculate the action connection time difference, detect the connection status, and generate time series connection detection data.

[0146] Based on the action sequence in the unit's coordination specification, identify two adjacent node actions. Compare the start time of the subsequent node's action with the completion time of the critical action node of the preceding node, and calculate the time difference between the two, i.e., the action connection time difference. If the time difference is within a preset reasonable range (e.g., 0-5 seconds), the connection is considered good; if the time difference is too large or too small, the connection is considered problematic. Generate timing connection detection data, recording the connection time difference and connection status of each adjacent node action.

[0147] Step S1474: Extract real-time change data of control parameters and local operation status change data of surrounding road network from the real-time data stream of each node's action execution. Based on the synchronous execution requirements in the intra-unit coordination specification, detect the synchronous status of control parameter changes of each node and the coordinated enhancement status of road network status changes, and generate synchronous coordination detection data.

[0148] Real-time changes in control parameters are extracted from the real-time data stream of each node's actions, such as changes in the green light time of traffic lights and the information update frequency of traffic guidance screens; as well as changes in the local operating status of the surrounding road network, such as changes in traffic flow and vehicle speed. Based on the synchronous execution requirements in the intra-unit coordination specification, the synchronization of control parameter changes at each node is detected. For example, whether the phase adjustments of multiple traffic lights begin at the same time; and whether changes in road network status exhibit a synergistic enhancement effect, such as whether a decrease in traffic flow is the result of multiple control actions working together. Synchronous coordination detection data is generated, recording the synchronization of parameter changes at each node and the synergistic enhancement of road network status changes.

[0149] Step S1475: Collect mutual feedback data between traffic control nodes within the unit, and generate feedback coordination detection data by combining the mutual feedback mechanism in the unit's coordination specification. The mutual feedback data includes the sending time, receiving time, completeness of feedback content, and timeliness of feedback response.

[0150] Within a unit, traffic control nodes engage in mutual feedback, such as resource nodes reporting action execution status to the master resource and the master resource sending adjustment instructions to slave resources. This mutual feedback data is collected, including the sending and receiving times of feedback information, the completeness of the feedback content, and the timeliness of the feedback response. Combined with the mutual feedback mechanism in the unit's coordination specifications, the compliance of the feedback is determined. For example, whether the feedback information is sent and received within the specified time and whether the feedback content contains the necessary information. Feedback coordination detection data is generated, recording the feedback status and whether it meets the specification requirements.

[0151] Step S1476: Based on the timing connection detection data, synchronous collaboration detection data, and feedback collaboration detection data, construct an evaluation index system for intra-unit collaboration effect. The intra-unit collaboration effect evaluation index system includes timing connection smoothness, synchronous collaboration accuracy, feedback response efficiency, and control effect superposition degree.

[0152] By integrating temporal connection detection data, synchronous coordination detection data, and feedback coordination detection data, an evaluation index system for intra-unit coordination effect is constructed. Temporal connection smoothness is used to evaluate the smoothness of node action transitions, calculated based on the connection time difference; synchronous coordination accuracy is used to evaluate the synchronicity of changes in control parameters of each node, calculated based on the difference in parameter changes; feedback response efficiency is used to evaluate the efficiency of feedback information transmission and processing, calculated based on feedback time difference and response timeliness; and control effect superposition is used to evaluate the synergistic enhancement effect of control actions of multiple nodes, calculated based on the ratio of actual road network state changes to expected changes.

[0153] Step S1477: Calculate the evaluation index values ​​of each evaluation index. The smoothness of the timing connection is determined based on the ratio of the connection time difference to the preset connection threshold. The synchronization and coordination accuracy is determined based on the difference between the real-time change data of the same control parameter at different traffic control nodes. The feedback response efficiency is determined based on the feedback time difference. The superposition degree of the control effect is determined based on the ratio of the actual superposition effect to the expected superposition effect.

[0154] For timing smoothness, the ratio of the timing time difference to the preset timing threshold is calculated. The smaller the ratio, the smoother the timing smoothness and the higher the timing smoothness. For example, if the preset timing threshold is 10 seconds and the timing time difference is 2 seconds, then the timing smoothness is (10-2) / 10=0.8.

[0155] For synchronization and coordination accuracy, the degree of difference between real-time changes of the same control parameter at different nodes is calculated. The smaller the degree of difference, the higher the synchronization and coordination accuracy. The degree of difference can be measured by calculating the standard deviation or variance of the data.

[0156] Feedback response efficiency is determined based on the feedback time difference (receive time - send time); the smaller the time difference, the higher the feedback response efficiency.

[0157] To determine the superposition degree of the control effect, the ratio of the actual superposition effect (such as the percentage reduction in actual traffic flow) to the expected superposition effect (such as the percentage reduction in target traffic flow) is calculated. The closer the ratio is to 1, the higher the superposition degree of the control effect.

[0158] Step S1478: Integrate the values ​​of each evaluation indicator to generate a comprehensive score for the collaborative effect within the unit. The comprehensive score reflects the overall level of collaboration between nodes within the unit.

[0159] The values ​​of each evaluation indicator are weighted and summed to generate a comprehensive score for the synergistic effect within the unit. The weights are determined based on the importance of each indicator; for example, the weights for the smoothness of the timing sequence and the superposition of the control effects can be set higher. The higher the comprehensive score, the better the overall level of coordination and cooperation among the nodes within the unit.

[0160] Step S1479: Identify evaluation indicators in the comprehensive score of collaborative effect that score below the set score threshold, locate the corresponding nodes and action links, record the specific reasons for poor collaborative effect, and generate collaborative deviation reason record data.

[0161] Set a scoring threshold (e.g., 70 points). If the overall collaborative effect score is lower than this threshold, or if the score of a certain evaluation indicator is lower than its corresponding threshold, the collaborative effect is considered poor. Identify evaluation indicators with scores below the threshold. By analyzing timing continuity detection data, synchronous collaboration detection data, and feedback collaboration detection data, pinpoint the specific nodes and actions that caused the low score for that indicator. For example, low timing continuity smoothness might be due to a delay in the action start time of a certain node. Record the specific reasons for poor collaborative effect, such as equipment failure, unreasonable parameter settings, communication delays, etc., generating collaborative deviation cause record data.

[0162] Step S14710: Integrate timing connection detection data, synchronous collaborative detection data, feedback collaborative detection data, evaluation index values, comprehensive score of collaborative effect, and collaborative deviation cause record data to generate collaborative execution status data within the unit.

[0163] By integrating time-series connection detection data, synchronous collaborative detection data, feedback collaborative detection data, values ​​of various evaluation indicators, comprehensive scores of collaborative effects, and records of collaborative deviation reasons, a unit-wide collaborative execution status data is formed. This unit-wide collaborative execution status data comprehensively reflects the collaborative execution status of each node within the unit, including advantages and existing problems.

[0164] Step S148: Based on the inter-unit collaborative linkage configuration, and combining the information interaction data and control action synchronization data between different distributed resource response units, compare the information interaction data and control action synchronization data with the preset information interaction rules and action synchronization requirements in the inter-unit collaborative linkage configuration to generate the collaborative linkage status data between the distributed resource response units.

[0165] The inter-unit collaborative linkage configuration pre-defines information exchange rules and action synchronization requirements. Information exchange rules specify the types, formats, and frequencies of information to be exchanged between units; action synchronization requirements define the temporal coordination of control actions between different units. Information exchange data between different distributed resource response units is collected, such as exchanged traffic status data and control instructions; as well as control action synchronization data, such as action start and end times. This data is compared with the pre-defined information exchange rules and action synchronization requirements to check whether information exchange conforms to the rules and whether action synchronization meets the requirements. For example, whether the frequency of information exchange meets the specified requirements, and whether the action start times of adjacent units are coordinated. Collaborative linkage status data is generated to record the collaborative linkage status between units, including whether there are any issues such as abnormal information exchange or asynchronous actions.

[0166] Step S149: After the control action of a flow stage is completed, collect the action completion data of all traffic control nodes in the flow stage and generate stage control completion data. The action completion data includes the final control effect data, resource remaining status data, node operation status data and control process log.

[0167] Once all control actions in a transition phase are completed, action completion data for each traffic control node is collected. Final control effect data refers to the actual impact of control actions on traffic events and road network conditions, such as the percentage reduction in traffic flow, the increase in vehicle speed, and the reduction in carbon emissions. Resource remaining status data refers to the remaining capacity of control resources after the actions are executed, such as the remaining operating time of traffic lights and the remaining display time of traffic guidance screens. Node operation status data refers to the working status of control nodes after the actions are executed, such as whether they are operating normally or whether there are any faults. The control process log records the execution process of the control actions, including instruction reception time, action initiation time, and key node completion time. These data are integrated to generate phase control completion data.

[0168] Step S1410: Integrate detailed ledgers of instructions issued at all stages of the flow, records of node instruction reception status, real-time data streams of node action execution, intra-unit collaborative execution status data, inter-unit collaborative linkage status data, and stage control completion data to generate traffic event flow control collaborative execution information.

[0169] The system comprehensively integrates detailed ledgers of instructions issued at all stages of the process, records of node instruction reception status, real-time data streams of node action execution, intra-unit collaborative execution status data, inter-unit collaborative linkage status data, and stage control completion data. The above data covers all aspects of control actions, including issuance, reception, execution, collaborative cooperation, and final results.

[0170] Step S150: Based on the traffic event evolution correction data and traffic network operation optimization data fed back by the traffic event flow control and coordination execution information, iteratively update the traffic event flow link reconstruction information and resource coordination response configuration information, and generate traffic event flow control completion information.

[0171] By analyzing traffic incident flow control and coordination execution information, we can obtain traffic incident evolution correction data and traffic network operation optimization data, which are used to iteratively update traffic incident flow link reconstruction information and resource coordination response configuration information to continuously optimize the control effect.

[0172] Step S151: Extract the stage control completion data from the traffic event flow control and coordination execution information, and separate the traffic event evolution correction data and traffic network operation optimization data. The traffic event evolution correction data includes the deviation between the actual evolution trajectory and the predicted trajectory, and the difference between the actual impact range and the predicted range. The traffic network operation optimization data includes the actual traffic efficiency improvement data, traffic flow density change data, and congestion point dissipation data.

[0173] The system extracts stage control completion data for each stage of traffic event flow regulation from the collaborative execution information. From this stage control completion data, it separates traffic event evolution correction data and traffic network operation optimization data. Traffic event evolution correction data reflects the difference between the actual and predicted traffic event evolution, such as the deviation between the actual and predicted trajectories (calculated by comparing the actual and predicted locations at different time points) and the difference between the actual and predicted impact ranges (e.g., the difference between the actual and predicted road segment lengths). Traffic network operation optimization data reflects the improvement effect of regulation actions on the road network operation status, such as actual traffic efficiency improvement data (e.g., the increase in average vehicle speed), traffic density change data (e.g., the reduction in the number of vehicles per unit area), and congestion point dissipation data (e.g., the reduction in the number of congestion points and the shortening of congestion duration).

[0174] Step S152: Detect traffic event evolution correction data, identify key transition stages and corresponding road network nodes that cause evolution trajectory deviations, record the specific manifestations and impact range of the deviations, and generate key nodes and stage information of evolution deviations.

[0175] Analyze traffic event evolution correction data to compare the deviations between the actual and predicted trajectories at different transition stages. Identify the transition stages with significant deviations; these are the key transition stages leading to trajectory deviations. Within these key transition stages, further identify the corresponding road network nodes, i.e., which road network nodes and their surrounding areas primarily experience deviations. Record the specific manifestations of the deviations, including at least one of the following: the deviation value between the actual and predicted trajectories; the difference in area or length between the actual and predicted impact areas; and the difference in traffic density between the actual and predicted traffic density; as well as the scope of the deviation's impact, such as which additional road segments or nodes are affected. Generate information on key nodes and stages of evolutionary deviations, clarifying the stages and nodes requiring focused attention and adjustment.

[0176] Step S153: Combining traffic network operation optimization data, locate road network sections where the improvement effect has not met expectations and the corresponding control stage, record the core reasons for the failure to meet expectations, and generate information on road network sections with insufficient improvement and the reasons.

[0177] Analyze traffic network operation optimization data, comparing actual traffic efficiency improvements, traffic density changes, and congestion point dissipation data with preset improvement targets. If the actual improvement effect of certain road network segments does not meet expectations, such as a smaller increase in vehicle speed than the target value or a less significant reduction in traffic density, then these road segments and their corresponding control stages are identified. By analyzing the control completion data of each stage and the collaborative execution status data within each unit, the core reasons for the unsatisfactory improvement effect are identified, such as insufficient control resources, unreasonable control parameter settings, and poor coordination. Record this information to generate information on road network segments with insufficient improvement and their causes.

[0178] Step S154: For key nodes and stage information of evolution deviation, retrieve the core feature information of traffic events, dynamic road network correlation information and historical flow reference data corresponding to the flow stage, correct the event evolution trend prediction parameters of the flow stage, and generate corrected stage evolution trend data.

[0179] For key transition stages identified in the critical nodes and stage information of evolutionary deviations, the core characteristic information of traffic events corresponding to these stages (such as event triggering type, initial impact range, and diffusion rate), dynamic road network correlation information (such as road network topology, road traffic status, and traffic flow evolution trends), and historical flow reference data are retrieved again. Using this data, the causes of evolutionary trajectory deviations are analyzed, and the parameters of the event evolution trend prediction model are adjusted. For example, if the actual diffusion rate is faster than predicted, the parameters related to the diffusion rate are increased; if the actual impact range expands in a different direction than predicted, the parameters related to the expansion direction of the impact range are adjusted. By correcting the prediction parameters, revised stage evolution trend data is generated, making the prediction results closer to the actual situation.

[0180] Step S155: Based on the revised stage evolution trend data and the information on road network improvement deficiencies and their causes, re-detect the road network node set and feasible connection paths of this transition stage, adjust the node association relationships and alternative path configurations in the stage optimization transition link information, and generate updated stage transition link information.

[0181] Based on the revised stage evolution trend data, the road network impact area for this transition stage is redefined. Based on the new impact area, the road network node set is re-examined, with some nodes added or removed. Simultaneously, based on information regarding road segments with insufficient improvement and their causes, problems in the original feasible connection paths are analyzed, such as insufficient carrying capacity of certain paths or unreasonable alternative path settings. Feasible connection paths are replanned, the relationships between nodes are adjusted, and the configuration of alternative paths is optimized, such as adding new alternative paths and adjusting the activation conditions for alternative paths. Updated stage transition link information is generated to improve the rationality and reliability of the transition links.

[0182] Step S156: Based on the updated stage flow link information, re-divide the control requirements of the flow stage, compare with the original staged control requirement list, correct the spatial coverage, timing response requirements and control intensity standards of the control requirements, and generate an updated staged control requirement list.

[0183] The updated phase transition link information reflects the new set of road network nodes and connection paths, thus requiring a re-analysis of the control requirements for this transition phase. Based on the new road network impact area and transition links, spatial coverage requirements are adjusted to ensure that control resources can cover all key nodes and paths. Based on the revised phase evolution trend data, temporal response requirements are adjusted to make the timing of control actions more consistent with the actual situation of event evolution. Based on the information on road segments with insufficient improvement and their causes, the control intensity requirements are increased or adjusted to achieve the expected improvement effect. By comparing the original phased control requirement list with the revised list, the spatial coverage, temporal response requirements, and control intensity standards are modified to generate an updated phased control requirement list.

[0184] Step S157: Based on the updated phased regulation requirement list, re-select the regulation resources for this flow stage, adjust the composition and configuration of the distributed resource response units, optimize the resource cooperation relationship within the unit and the collaborative linkage mechanism between units, and generate the updated resource collaborative response configuration fragment.

[0185] Step S1571: Extract the spatial coverage requirements, temporal response requirements, control intensity requirements, and coordination requirements from the updated phased control requirements list, and generate the updated phased control requirements details.

[0186] From the updated list of phased control requirements, detailed spatial coverage requirements (such as specific road segments and nodes to be covered), temporal response requirements (such as the start time and duration of control actions), control intensity requirements (such as the target percentage reduction in traffic flow, the target value for increasing vehicle speed, etc.), and coordination requirements (such as the cooperation methods between resources and information exchange requirements) are extracted. These requirements are compiled into a detailed updated list of phased control requirements, which serves as the basis for re-selecting control resources and adjusting their allocation.

[0187] Step S1572: Based on the spatial coverage requirements in the updated stage control requirements details, re-select control resources from the overall control resource ledger that can cover the affected area of ​​the updated road network, and generate the updated stage spatial adaptation resource pool.

[0188] Based on the spatial coverage requirements in the updated phase control demand details, control resources are re-selected in the overall control resource ledger. The selection criterion is that the control coverage of the resources can cover the updated road network impact area. Similar to step S133, but the road network impact area may have changed at this time. An updated phase spatial adaptation resource pool is generated.

[0189] Step S1573: For the timing response requirements in the updated stage control requirements details, select control resources from the updated stage spatial adaptation resource pool that can meet the time span requirements of the updated stage, and generate a subset of updated stage timing adaptation resources.

[0190] Based on the timing response requirements in the updated phase control requirements details, i.e., the time span requirements of the updated phase, control resources that meet the response time requirements are selected from the updated phase spatial adaptation resource pool. The calculation method for response time is the same as in step S134. A subset of updated phase timing adaptation resources is generated.

[0191] Step S1574: Combining the control intensity requirements in the updated stage control demand details, detect the control capability boundaries of each resource in the updated stage time-series adaptation resource subset, screen control resources whose control capabilities can meet the control intensity requirements of the updated stage, and generate a set of candidate control resources for the updated stage.

[0192] The control capability boundaries of each resource in the time-adapted resource subset of the updated stage are detected to determine whether they can achieve the control effect specified in the control intensity requirements of the updated stage. Similar to step S135, but the control intensity requirements may have been adjusted at this time. A candidate control resource set for the updated stage is generated.

[0193] Step S1575: Based on the coordination requirements in the updated stage control requirements details, re-examine the control function compatibility and action coordination of each resource in the updated stage candidate control resource set, set new resource coordination logic, and generate updated stage resource coordination logic.

[0194] Following the method in step S136, the compatibility of regulatory functions and the coordination of actions of each resource in the candidate regulatory resource set for the updated stage are re-examined, and new resource coordination logic is set. Since the regulatory requirements and resource set may change, it is necessary to re-examine and set the logic to generate the resource coordination logic for the updated stage.

[0195] Step S1576: Based on the node distribution and path direction in the updated stage flow link information, regroup the resources in the updated stage candidate control resource set according to the correspondence between deployment location and updated link nodes, adjust the composition of distributed resource response units, and generate the updated stage distributed resource unit configuration.

[0196] Based on the node distribution and path direction in the updated stage flow link information, the resources in the updated stage candidate control resource set are re-matched and grouped with the link nodes. It may be necessary to add, reduce, or adjust the composition of distributed resource response units to adapt to the new flow link. The updated stage distributed resource unit configuration is then generated.

[0197] Step S1577: Reset the control roles and task assignments of each resource within each updated distributed resource response unit, adjust the master-slave collaboration relationship of resources within the unit, and generate the updated resource collaboration configuration within the unit.

[0198] For each updated distributed resource response unit, the control roles and task assignments of each resource are redefined based on the resource type, function, and new control requirements. The master-slave collaboration relationship is adjusted to ensure efficient collaboration among resources within the unit. The updated resource collaboration configuration within the unit is then generated.

[0199] Step S1578: Set the collaborative linkage relationship between each updated distributed resource response unit, rebuild the information interaction channel and control action synchronization mechanism between units, and generate the updated collaborative linkage configuration between units.

[0200] Based on the updated stage flow information and distributed resource unit configuration, the collaborative linkage relationships between each distributed resource response unit are redefined. A new information exchange channel is established to ensure real-time information exchange between units; a new control action synchronization mechanism is established to ensure coordinated and consistent actions. The updated inter-unit collaborative linkage configuration is generated.

[0201] Step S1579: Integrate the updated phase distributed resource unit configuration, the updated intra-unit resource collaboration configuration, the updated inter-unit collaborative linkage configuration, and the updated phase resource collaboration logic to generate an updated resource collaboration response configuration fragment.

[0202] The updated phase distributed resource unit configuration, updated intra-unit resource collaboration configuration, updated inter-unit collaborative linkage configuration, and updated phase resource collaboration logic are integrated to form an updated resource collaboration response configuration fragment. This updated resource collaboration response configuration fragment is a partial update of the original resource collaboration response configuration information.

[0203] Step S15710: By simulating the resource collaborative execution process, detect the timing connection and spatial overlap of each resource action in the updated resource collaborative response configuration fragment, record the detected timing conflicts and spatial conflicts, and complete the generation of the updated resource collaborative response configuration fragment.

[0204] Using traffic simulation software or mathematical models, the collaborative execution process of each resource in the updated resource collaborative response configuration segment is simulated. During the simulation, the focus is on detecting the smoothness of the timing sequence of resource actions, and whether there are any overlapping or gaps in actions; whether there is any overlap in the spatial scope of action, and whether this will lead to mutual interference in the control effects. Detected timing and spatial conflicts are recorded, and the configuration segment is adjusted and optimized until the conflicts are eliminated. The updated resource collaborative response configuration segment is then generated.

[0205] Step S158: Integrate the updated stage flow link information and the updated resource collaborative response configuration fragment into the original traffic event flow link reconstruction information and resource collaborative response configuration information to complete the overall information update and generate iteratively updated flow link and resource configuration information.

[0206] Replace the corresponding parts of the original traffic event flow link reconstruction information with the updated stage flow link information, and replace the corresponding parts of the original resource collaborative response configuration information with the updated resource collaborative response configuration fragments. Integrate and perform consistency checks on the overall information to ensure that the updated information is logically coherent and the data is accurate. Generate iteratively updated flow link and resource configuration information.

[0207] Step S159: Drive the distributed control node group to execute a new round of phased collaborative control actions according to the iteratively updated flow link and resource configuration information, collect the new round of traffic event flow control collaborative execution information and corresponding traffic event evolution correction data and traffic network operation optimization data, and generate iterative control feedback data.

[0208] Using the iteratively updated traffic flow links and resource configuration information, the distributed control node group is driven to execute a new round of phased collaborative control actions according to step S140. New round of traffic event flow control collaborative execution information is collected, and traffic event evolution correction data and traffic network operation optimization data are extracted from it. Iterative control feedback data is generated to evaluate the control effect after the iterative update.

[0209] Step S1510: Compare the traffic event evolution correction data in the iterative control feedback data with the preset evolution deviation threshold, compare the traffic network operation optimization data with the preset improvement target threshold, and determine whether to generate a control completion flag based on the comparison result; if so, integrate the final iteratively updated flow link and resource configuration information, all iterative control process data and final control effect data to generate traffic event flow control completion information.

[0210] The system presets an evolutionary deviation threshold and an improvement target threshold. The evolutionary deviation threshold is the maximum allowable deviation between the actual evolutionary trajectory and the predicted trajectory; the improvement target threshold is the minimum improvement effect that the control action needs to achieve. The system compares the traffic event evolution correction data in the iterative control feedback data with the evolutionary deviation threshold. If the deviation is less than or equal to the threshold, it indicates that the event evolution has been effectively controlled. The system also compares the traffic network operation optimization data with the improvement target threshold. If the actual improvement effect reaches or exceeds the threshold, it indicates that the control has achieved its expected goals.

[0211] If both comparison results meet the requirements, a control completion flag is generated. The final iteratively updated flow link and resource configuration information, all iterative control process data (such as control instructions, execution data, and coordination status data for each round), and the final control effect data (such as final traffic flow, vehicle speed, and carbon emission levels) are integrated to generate traffic event flow control completion information. This traffic event flow control completion information comprehensively summarizes the control process and effects of the traffic event. If the comparison results do not meet the requirements, the process returns to step S151 to continue iterative updates and control until the requirements are met.

[0212] Based on the same inventive concept, please refer to Figure 2 The diagram shows a schematic block diagram of an intelligent event flow control system 100 applied to traffic scenarios provided in an embodiment of this application. The intelligent event flow control system 100 applied to traffic scenarios may include a communication unit 110, a machine-readable storage medium 120, and a processor 130.

[0213] In this embodiment, both the machine-readable storage medium 120 and the processor 130 are located in the intelligent event flow control system 100 applied to traffic scenarios and are separately configured. However, it should be understood that the machine-readable storage medium 120 may also be independent of the intelligent event flow control system 100 applied to traffic scenarios and may be accessed by the processor 130 through a bus interface. Alternatively, the machine-readable storage medium 120 may be integrated into the processor 130 and may communicate and interact with external systems through the communication unit 110. The machine-readable storage medium 120 is used to store machine-executable instructions for executing the scheme of this application, and the processor 130 is used to execute the machine-executable instructions stored in the machine-readable storage medium 120 to implement the intelligent event flow control method for traffic scenarios provided in the aforementioned method embodiments.

[0214] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. An intelligent event flow regulation method applied to a traffic scene, characterized in that, The method includes: Receive comprehensive perception information on traffic incidents and dynamic correlation information of the traffic network, and generate benchmark information for the flow of traffic incidents; Based on the traffic incident flow benchmark information, the traffic incident flow stages are divided, the traffic incident flow links corresponding to each flow stage are reconstructed, and traffic incident flow stage division and link reconstruction information are generated. Based on the traffic incident flow stage division and link reconstruction information, a distributed collaborative response rule set for regulation resources is constructed, and resource collaborative response configuration information is generated; Driven by resource collaborative response configuration information, the distributed control node group executes phased collaborative control actions to generate traffic event flow control collaborative execution information. Based on the feedback of traffic event evolution correction data and traffic network operation optimization data from the collaborative execution information of traffic event flow control, the traffic event flow link reconstruction information and resource collaborative response configuration information are iteratively updated to generate traffic event flow control completion information. 2.The intelligent event flow regulation method applied to a traffic scene according to claim 1, wherein, The process involves dividing traffic events into stages based on traffic event flow benchmark information, reconstructing the traffic event flow links corresponding to each stage, and generating traffic event flow stage division and link reconstruction information, including: The core feature information of traffic events is extracted from the traffic event flow benchmark information, and the road network topology, road traffic status and traffic flow evolution trend are extracted from the traffic road network dynamic correlation information to generate a set of core information of events and road networks. The core feature information of traffic events includes event triggering type, initial impact range, diffusion rate and associated road network elements. Based on the historical traffic incident database, historical incident data that matches the core feature information of the current traffic incident is extracted. Key time nodes and corresponding changes in the scope of impact and road network status response data in the historical incident flow process are screened to generate historical flow reference data. Based on historical traffic flow reference data and the current traffic incident diffusion rate, characteristic change critical points in the traffic incident flow process are extracted to generate event flow characteristic critical point data. The characteristic change critical points are the time nodes when the event diffusion rate, the type of impact range, or the road network response mode changes significantly. Based on the critical point data of event flow characteristics, the traffic event flow process is divided into multiple continuous flow stages. The time span, core evolution target and corresponding road network impact area of ​​each flow stage are defined to generate traffic event flow stage division information. For each transition stage, based on the core evolution goals and road network impact area of ​​that transition stage, the corresponding road network node information is extracted from the dynamic correlation information of the traffic road network to generate a stage road network node set. The road network node information includes road intersections, traffic hubs, road network connection points, and endpoints of key traffic sections. Based on the set of road network nodes in a given stage and the road network topology of that transition stage, the connectivity between each road network node is detected, feasible connection paths between road network nodes are filtered, paths with interrupted connectivity are eliminated, and feasible node connection path information for that stage is generated. Combining the spread rate and core evolution objectives of traffic incidents in this transition phase, the expansion trend of the traffic incident's transition range within this transition phase is predicted. The road network spatial range covered by the expansion trend of the transition range is matched with the road network spatial range associated with the feasible node connection path information of the phase. Node connection paths whose spatial locations are included in the expansion trend of the transition range are selected to generate the initial transition link information of the phase. Extract road traffic status and traffic flow evolution trend data for this transition phase, detect the carrying capacity of each node connection path in the initial transition link information of the phase, identify path segments that are at risk of exceeding the preset congestion threshold due to predicted traffic flow convergence, and generate phase transition obstruction risk path information. For the risk path information of the stage flow obstruction, the surrounding road network node information is retrieved again, alternative node connection paths are planned, the obstruction risk path segments in the initial flow link of the stage are replaced, and the activation conditions and switching process of the alternative paths are set to generate stage-optimized flow link information. Integrate the stage division information of all circulation stages and the corresponding stage optimization circulation link information, set the connection rules and switching trigger conditions between circulation links of each stage, and generate traffic event circulation stage division and link reconstruction information. 3.The intelligent event flow regulation method applied to a traffic scene according to claim 1, wherein, The process involves constructing a distributed collaborative response rule set for regulating resources based on traffic event flow stages and link reconstruction information, and generating resource collaborative response configuration information, including: Extract the optimized flow link information, core evolution goals, and road network impact areas of each stage from the traffic incident flow stage division and link reconstruction information, break down the control requirements of each flow stage, and generate a staged control requirement list. The control requirements include spatial coverage requirements, temporal response requirements, control intensity requirements, and coordination requirements. Collect detailed information on traffic control resources across the entire region and generate a resource ledger for the entire region. The detailed information includes resource type, control function, control coverage, response time, control capacity boundary, deployment location, and resource operation status. Based on the spatial coverage requirements in the phased regulation demand list, regulation resources that can cover the road network impact area of ​​the corresponding phase are selected from the overall regulation resource ledger to generate a phased spatial adaptation resource pool. For the timing response requirements of each stage, control resources that can meet the time span requirements of the transition stage are selected from the stage space adaptation resource pool, and a stage timing adaptation resource subset is generated. Based on the needs of phased regulation intensity, the regulation capability boundary of each resource in the phased time-series adaptation resource subset is detected, and regulation resources whose regulation capabilities can meet the phased regulation intensity requirements are selected to generate a phased candidate regulation resource set. Based on the stage coordination requirements, the compatibility of the control functions and the coordination of actions of each resource in the stage candidate control resource set are tested, the control action connection logic between different resources is set, and the control actions under the set connection logic are tested to see if there are mutual conflicts, and stage resource coordination logic is generated. Based on the node distribution and path direction in the phase optimization flow link information, the resources in the phase candidate control resource set are grouped according to the correspondence between deployment location and link node to form multiple distributed resource response units, and a phase distributed resource unit configuration is generated. Each distributed resource response unit undertakes the control task of the corresponding link node and surrounding area. Define the control roles and task assignments of each resource within each distributed resource response unit, define the master-slave collaboration relationship of resources within the distributed resource response unit, with the master resource undertaking the overall coordination task, and the slave resources cooperating to execute specific control actions, thereby generating the resource collaboration configuration within the unit; Establish the collaborative linkage relationship between each distributed resource response unit, build an information exchange channel and control action synchronization mechanism between distributed resource response units, and generate collaborative linkage configuration between units. It integrates the distributed resource unit configuration, intra-unit resource collaboration configuration, inter-unit collaborative linkage configuration, and stage resource collaboration logic of each circulation stage, sets resource scheduling paths, communication protocols, and data transmission standards, and generates resource collaboration response configuration information. 4.The intelligent event flow regulation method applied to a traffic scene according to claim 1, wherein, The process of driving a distributed control node group to execute phased coordinated control actions according to resource coordinated response configuration information, and generating traffic event flow control coordinated execution information, includes: Extract the distributed resource unit configuration, intra-unit resource collaboration configuration, inter-unit collaborative linkage configuration, and phased control requirements list from the resource collaborative response configuration information, determine the traffic control node corresponding to each distributed resource response unit, and integrate all traffic control nodes to form a distributed control node group. The control requirements and resource collaboration configurations of each flow stage are converted into control instructions that can be executed by each control node, generating a staged node control instruction set. The control instructions include action type, execution sequence, control range, control parameters and collaborative feedback requirements. Based on the phase transition rules in the traffic event flow phase division and link reconstruction information, the timing of the issuance of control instruction sets for each phase node is set, the feedback conditions for the completion of the previous phase instruction execution and the trigger conditions for the issuance of the next phase instruction are set, and the instruction issuance timing plan is generated. According to the instruction issuance sequence plan, the corresponding phased node control instructions are issued to each traffic control node in the distributed control node group in sequence. The issuance time, instruction content, receiving node identifier and instruction issuance channel of each phased node control instruction are recorded to generate a detailed instruction issuance ledger. During the instruction issuance process, instruction reception status data of each traffic control node is collected to generate node instruction reception status records. The instruction reception status data includes instruction reception confirmation signals, instruction parsing progress, and action preparation data. Once a traffic control node initiates a control action, it continuously collects data on the execution process of the action. This data includes the execution progress, real-time changes in control parameters, resource operation status data, and local operation status changes of the road network surrounding the node, generating a real-time data stream of the node's action execution. Based on the resource collaboration configuration within the unit, and combined with the real-time data stream of the action execution of each traffic control node within the same distributed resource response unit, the real-time data of the action execution of each traffic control node is compared with the preset action timing and parameter coordination requirements in the resource collaboration configuration within the unit to generate collaborative execution status data within the unit. Based on the inter-unit collaborative linkage configuration, and combined with the information interaction data and control action synchronization data between different distributed resource response units, the information interaction data and control action synchronization data are compared with the preset information interaction rules and action synchronization requirements in the inter-unit collaborative linkage configuration to generate the collaborative linkage status data between the distributed resource response units. Once the control action of a flow phase is completed, the action completion data of all traffic control nodes in that flow phase is collected to generate phase control completion data. The action completion data includes final control effect data, resource remaining status data, node operation status data, and control process log. By integrating detailed ledgers of instructions issued at all stages of the process, records of node instruction reception status, real-time data streams of node action execution, intra-unit collaborative execution status data, inter-unit collaborative linkage status data, and stage control completion data, traffic incident flow control and collaborative execution information is generated.

5. The intelligent event flow regulation method for traffic scenarios as claimed in claim 1 wherein, The traffic event evolution correction data and traffic network operation optimization data based on the feedback of traffic event flow control and collaborative execution information are used to iteratively update traffic event flow link reconstruction information and resource collaborative response configuration information, generating traffic event flow control completion information, including: Extract the stage control completion data from the traffic event flow control and coordination execution information, and separate the traffic event evolution correction data and traffic network operation optimization data. The traffic event evolution correction data includes the deviation between the actual evolution trajectory and the predicted trajectory, and the difference between the actual impact range and the predicted range. The traffic network operation optimization data includes actual traffic efficiency improvement data, traffic flow density change data, and congestion point dissipation data. Detect traffic incident evolution correction data, identify key transition stages and corresponding road network nodes that cause deviations in the evolution trajectory, record the specific manifestations and impact range of the deviations, and generate key nodes and stage information of the evolution deviations. By combining traffic network operation optimization data, we can identify road network sections where the improvement effect has not met expectations and the corresponding control phase, record the core reasons for the failure to meet expectations, and generate information on road network sections with insufficient improvement and the reasons for the failure. For key nodes and stage information of evolution deviation, the core feature information of traffic events, dynamic road network correlation information and historical flow reference data corresponding to the flow stage are retrieved again, the event evolution trend prediction parameters of the flow stage are corrected, and the corrected stage evolution trend data is generated. Based on the revised stage evolution trend data and information on road network improvement deficiencies and their causes, the set of road network nodes and feasible connection paths for this transition stage are re-examined, the node associations and alternative path configurations in the stage optimization transition link information are adjusted, and updated stage transition link information is generated. Based on the updated stage flow link information, the control requirements of this flow stage are re-splittered, compared with the original staged control requirement list, and the spatial coverage, timing response requirements and control intensity standards of the control requirements are revised to generate an updated staged control requirement list. Based on the updated phased regulation and control demand list, the regulation and control resources for this circulation phase are re-selected, the composition and configuration of the distributed resource response units are adjusted, the resource cooperation relationship within the unit and the collaborative linkage mechanism between units are optimized, and the updated resource collaborative response configuration fragment is generated. The updated stage flow link information and the updated resource collaborative response configuration fragment are integrated into the original traffic event flow link reconstruction information and resource collaborative response configuration information to complete the overall information update and generate iteratively updated flow link and resource configuration information. Driven by the iteratively updated flow link and resource allocation information, the distributed control node group executes a new round of phased collaborative control actions, collects the new round of traffic event flow control collaborative execution information and corresponding traffic event evolution correction data and traffic network operation optimization data, and generates iterative control feedback data; The traffic event evolution correction data in the iterative control feedback data is compared with the preset evolution deviation threshold, and the traffic network operation optimization data is compared with the preset improvement target threshold. Based on the comparison results, it is determined whether to generate a control completion flag. If so, the final iteratively updated flow link and resource configuration information, all iterative control process data, and final control effect data are integrated to generate traffic event flow control completion information.

6. The intelligent event flow control method applied to traffic scenarios according to claim 2, characterized in that, The method, based on historical traffic flow reference data and the current spread rate of traffic incidents, extracts the characteristic change critical points in the traffic incident flow process, generating incident flow characteristic critical point data, including: Extract historical event diffusion rate change curves, impact range expansion curves, and road network response mode conversion time points from historical flow reference data to establish a historical event flow characteristic database; Feature extraction is performed on the diffusion rate change curve in the historical event flow feature database to identify the rate abrupt change point in the diffusion rate change curve of the historical event and generate a set of historical rate abrupt change points. The rate abrupt change point is the time point when the rate of change of diffusion rate exceeds a preset rate of change threshold. Extract the influence range expansion curve from the historical event flow feature database, identify the range expansion mode transition point in the influence range expansion curve, and generate a set of historical range transition points. The range expansion mode transition point is the time point when the direction or rate of influence range expansion changes. By associating and matching the set of historical rate mutation points with the set of historical range transition points, and combining the road network response mode transition time points of historical events, the time points that simultaneously satisfy rate mutation, range transition and road network response mode change are selected to generate a set of historical characteristic change critical points. Detect the core features of historical events corresponding to each critical point in the set of critical points for changes in historical features, establish the correlation mapping relationship between historical features and critical points, and generate a feature-critical point mapping model. Extract the current traffic incident's spread rate data, construct the current traffic incident's spread rate change curve, and combine it with the core feature information of the current traffic incident. Input the feature-critical point mapping model to preliminarily predict the possible feature change critical points of the current traffic incident and generate initial prediction critical point data. Collect real-time evolution data at the initial stage of the current traffic incident. The real-time evolution data includes real-time spread rate, real-time impact range and real-time road network response data, and verify the initial predicted critical point data. Based on the deviation between real-time evolution data and initial predicted critical point data, the prediction parameters of the feature-critical point mapping model are adjusted to correct the initial predicted critical point data and generate corrected predicted critical point data. Continuously collect real-time evolution data of current traffic events, dynamically update and correct the predicted critical point data, until the critical points of all characteristic changes in the current traffic event process are determined. By integrating the time nodes corresponding to all identified characteristic change critical points, the corresponding diffusion rate change data, the influence range change data, and the road network response change data, event flow characteristic critical point data is generated.

7. The intelligent event flow control method applied to traffic scenarios according to claim 3, characterized in that, Based on the stage-based coordination requirements, the system detects the compatibility and synergy of the control functions of each resource in the stage-based candidate control resource set, sets the control action connection logic between different resources, and detects whether there are mutual conflicts in control actions under the set connection logic, generating stage-based resource coordination logic, including: The process involves extracting detailed descriptions of the regulation functions of each resource in the candidate regulation resource set, the types of regulation actions, the execution process of the actions, the mechanism of action, and the road network parameters affected by the actions, and generating a ledger of resource regulation functions and action characteristics. Based on the stage-specific coordination requirements, the coordination objectives to be achieved during the control process of this transition stage are set. The coordination objectives include smooth action sequence connection, superimposed and enhanced control effect, comprehensive control scope coverage, and avoidance of mutual interference between actions, and a stage-specific coordination objective list is generated. The resources in the candidate control resource set are paired up, and the compatibility of the control functions of each pair of resources is tested. It is determined whether the control functions of the two can complement or synergistically enhance each other. If the control functions of the two are for the same road network parameter but have opposite directions of action, they are marked as incompatible and the resource function compatibility test results are generated. For resource pairs with compatible functions, further test the execution timing compatibility of their control actions, determine whether the action execution cycle of the former resource can be connected with the action start cycle of the latter resource, and generate action timing compatibility test results. Based on the resource function compatibility test results and action timing compatibility test results, resource combinations that are both functionally and timing compatible are selected to generate a basic collaborative resource combination set. The scope of the control actions of each combination in the basic collaborative resource combination set is detected, and it is determined whether the control scope of the resources within the combination can cover the affected area of ​​the stage road network, and the scope coverage detection results are generated. For resource combinations that pass the scope coverage test, the mechanism of the control action of each resource in the resource combination is detected, the connection logic between actions is set, the completion flag of the previous resource action is set as the trigger condition for the start of the next resource action, and the action connection logic rules are generated. Based on the action connection logic rules, the execution process of the control action of the resource combination is simulated, the superposition result of the control effect generated by the simulation is calculated, and the matching degree of the superposition result of the control effect is evaluated with the quantified target value in the stage collaboration target list. If the matching degree is higher than the preset effective threshold, the action connection logic rule is marked as effective and an effective connection logic set is generated. Integrate the action connection rules, resource function compatibility requirements, action timing compatibility requirements and scope coverage requirements in the effective connection logic set, set the collaborative cooperation method and action execution order of each resource within the stage, and generate the stage resource collaboration logic framework. The exception handling mechanism in the supplementary stage resource coordination logic framework is defined, and the coordination adjustment method of other resources is set when a certain resource action is executed abnormally, thereby improving the stage resource coordination logic and generating the final stage resource coordination logic.

8. The intelligent event flow control method applied to traffic scenarios according to claim 4, characterized in that, The method, based on intra-unit resource collaboration configuration, combines the real-time data streams of traffic control nodes within the same distributed resource response unit with the preset action timing and parameter coordination requirements in the intra-unit resource collaboration configuration to generate intra-unit collaborative execution status data, including: Extract the master-slave collaboration relationship, the division of control roles and the requirements for action coordination in the resource collaboration configuration within the unit, set the action connection sequence, synchronous execution requirements and mutual feedback mechanism of each traffic control node in the distributed resource response unit, and generate the unit collaboration specification. Key action time series data are extracted from the real-time data stream of traffic control nodes within the same distributed resource response unit. The key action time series data includes the action start time, key action node completion time, action execution cycle, and action end time, generating a node time series dataset within the unit. Based on the action connection sequence in the unit's collaborative specification, the action start time of adjacent nodes in the unit's node time series dataset is compared with the completion time of the key action node of the previous node. The action connection time difference is calculated, the connection status is detected, and time series connection detection data is generated. Extract real-time change data of control parameters and local operation status change data of surrounding road network from the real-time data stream of each node's action execution. Based on the synchronous execution requirements in the intra-unit coordination specification, detect the synchronous status of changes in control parameters of each node and the coordinated enhancement status of changes in road network status, and generate synchronous coordination detection data. The mutual feedback data between traffic control nodes within the collection unit is combined with the mutual feedback mechanism in the unit's collaborative specifications to generate feedback collaborative detection data. The mutual feedback data includes the sending time, receiving time, completeness of feedback content, and timeliness of feedback response of the feedback information. Based on temporal connection detection data, synchronous collaboration detection data, and feedback collaboration detection data, an evaluation index system for intra-unit collaboration effect is constructed. The intra-unit collaboration effect evaluation index system includes temporal connection smoothness, synchronous collaboration accuracy, feedback response efficiency, and control effect superposition degree. The evaluation index values ​​of each evaluation index are calculated. The smoothness of the time sequence connection is determined based on the ratio of the connection time difference to the preset connection threshold. The synchronization and coordination accuracy is determined based on the difference between the real-time change data of the same control parameter at different traffic control nodes. The feedback response efficiency is determined based on the feedback time difference. The superposition degree of the control effect is determined based on the ratio of the actual superposition effect to the expected superposition effect. By integrating the values ​​of various evaluation indicators, a comprehensive score for the collaborative effect within the unit is generated. The comprehensive score reflects the overall level of collaboration and cooperation among the nodes within the unit. Identify evaluation indicators whose scores in the overall collaborative effect score are lower than the set scoring threshold, locate the corresponding nodes and action links, record the specific reasons for poor collaborative effect, and generate collaborative deviation reason record data. By integrating time-series connection detection data, synchronous collaborative detection data, feedback collaborative detection data, evaluation index values, comprehensive score of collaborative effect, and records of collaborative deviation reasons, data on collaborative execution status within the unit is generated.

9. The intelligent event flow control method applied to traffic scenarios according to claim 5, characterized in that, The process involves re-selecting control resources for the current phase based on the updated phased control demand list, adjusting the composition and configuration of distributed resource response units, optimizing resource collaboration relationships within units and inter-unit collaborative linkage mechanisms, and generating updated resource collaborative response configuration fragments, including: Extract spatial coverage requirements, temporal response requirements, regulatory intensity requirements, and coordination requirements from the updated phased regulation and control requirements list to generate an updated phased regulation and control requirements detail. Based on the spatial coverage requirements in the updated stage control demand details, control resources that can cover the affected area of ​​the updated road network are re-selected from the overall control resource ledger to generate the updated stage spatial adaptation resource pool. For the timing response requirements in the updated phase control requirements details, control resources that can meet the time span requirements of the updated phase are selected from the updated phase spatial adaptation resource pool, and a subset of updated phase timing adaptation resources is generated. Based on the control intensity requirements in the updated stage control demand details, the control capability boundaries of each resource in the updated stage time-series adaptation resource subset are detected, and control resources whose control capabilities can meet the control intensity requirements of the updated stage are selected to generate a set of candidate control resources for the updated stage. Based on the coordination requirements in the updated stage control requirements details, the compatibility of control functions and the coordination of actions of each resource in the candidate control resource set of the updated stage are re-examined, new resource coordination logic is set, and updated stage resource coordination logic is generated. Based on the node distribution and path direction in the updated stage flow link information, the resources in the updated stage candidate control resource set are regrouped according to the correspondence between deployment location and updated link nodes, the composition of distributed resource response units is adjusted, and the updated stage distributed resource unit configuration is generated. Reset the control roles and task assignments of each resource within each updated distributed resource response unit, adjust the master-slave collaboration relationship of resources within the unit, and generate the updated resource collaboration configuration within the unit. Establish the collaborative linkage relationship between each updated distributed resource response unit, rebuild the information interaction channel and control action synchronization mechanism between units, and generate the updated collaborative linkage configuration between units. Integrate the updated phase distributed resource unit configuration, the updated unit intra-unit resource collaboration configuration, the updated unit inter-unit collaborative linkage configuration, and the updated phase resource collaboration logic to generate an updated resource collaboration response configuration fragment. By simulating the resource collaboration execution process, the timing connection and spatial overlap of each resource action in the updated resource collaboration response configuration fragment are detected, the detected timing conflicts and spatial conflicts are recorded, and the updated resource collaboration response configuration fragment is generated.

10. An intelligent event flow control system applied to traffic scenarios, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the intelligent event flow control method for traffic scenarios according to any one of claims 1 to 9 by executing the machine-executable instructions.

Images