A traffic control and protection method, device and equipment based on congestion prediction

Abstract

The present invention proposes a traffic control and protection method, device and equipment based on congestion prediction, which aims to accurately identify congestion patterns and predict propagation paths by constructing a feature vector set based on historical data and a congestion propagation path prediction mechanism, so as to realize the timely release of congestion warning information; adopt risk assessment hierarchical protection and dynamic optimization of the best intervention time to accurately grasp the protection time and match the corresponding protection intensity; introduce regional risk redistribution strategy and protection effect gradient analysis technology to coordinate risk transfer control among multiple regions and avoid the disorderly spread of congestion risks; combine cross-temporal and spatial effect retrospective analysis and strategy conflict detection mechanism to evaluate the actual contribution of each protection factor, and construct a weighted adaptive strategy set and protection capability matrix; finally, integrate multiple links such as prediction, evaluation, and coordination to form an adaptive comprehensive protection system to realize active prevention and intelligent control of urban traffic congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control, and in particular to a traffic control protection method, device and equipment based on congestion prediction. Background Art

[0002] Traffic congestion in modern cities is becoming increasingly severe. Traditional passive response management models are no longer able to meet the needs of improving traffic efficiency. Prediction-based active protection and control have become an important direction for the development of traffic management. Current congestion prediction and protection control technologies face many challenges: traffic flow changes are affected by multiple factors such as weather, events, and construction, making it difficult to ensure the accuracy of prediction models. The causes and evolution of congestion vary significantly across regions and time periods, and there is a lack of refined prediction mechanisms. Existing analysis methods have high computational complexity and cannot meet the timeliness requirements of real-time prediction. The timing and intensity of preventive control measures are difficult to grasp, which may cause unnecessary interference to normal traffic. There is a lack of effective risk transfer control and coordination mechanisms between multiple regions, and the delay in the transmission of early warning information affects the timely implementation of protection measures. The quality of historical data is uneven, with missing data and outliers affecting prediction accuracy, and the generalization ability of prediction models is limited. There is a lack of quantitative evaluation standards and adaptive optimization mechanisms for protection effects, making it impossible to achieve continuous improvement of protection strategies.

[0003] Therefore, building an intelligent protection and control method that integrates congestion prediction, risk assessment, timing optimization, and regional coordination is of great value to improving the resilience and management level of urban transportation systems. Summary of the Invention

[0004] The present invention provides a traffic control and protection method, device and equipment based on congestion prediction, which aims to achieve active prevention and intelligent management and control of urban traffic congestion. It integrates key technologies such as congestion prediction, risk assessment, timing optimization, regional coordination, and effect tracing, and conducts full-process intelligent control of traffic conditions and congestion risks. It realizes congestion warning, intelligent deployment of protection measures and multi-region coordinated linkage, forming a traffic congestion protection system with predictive capabilities, rapid response, effective coordination, and adaptive adjustment.

[0005] A first aspect of the present invention provides a traffic control and protection method based on congestion prediction, comprising the following steps:

[0006] Construct a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set;

[0007] Using the set of feature vectors to perform pattern learning to identify congestion patterns, constructing a congestion propagation path prediction mechanism based on the congestion patterns, and using the congestion propagation path prediction mechanism to generate congestion propagation warning information;

[0008] Conduct risk assessment on the congestion propagation warning information to mark the danger level, formulate preventive measures and form a protection plan based on the danger level;

[0009] Converting the protection plan into a control action to mark a potential intervention opportunity, constructing a dynamic optimization mechanism for the timing based on the potential intervention opportunity, using the dynamic optimization mechanism for the timing to determine the optimal intervention time point, and initiating protection control at the optimal intervention time point;

[0010] Performing a congestion risk transfer analysis on the protection control to mark the risk transfer direction, establishing a regional risk redistribution strategy based on the risk transfer direction, generating a multi-region risk balance plan using the regional risk redistribution strategy, and forming an overall protection strategy through the multi-region risk balance plan;

[0011] Based on the overall protection strategy, protection resources are allocated to generate a control status;

[0012] The control status is analyzed to form a protection capability matrix, and the protection capability matrix is used to implement protection to complete congestion prediction traffic control protection.

[0013] A second aspect of the present invention provides a traffic control and protection device based on congestion prediction, comprising:

[0014] A data storage module is used to build a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set;

[0015] an early warning generation module, configured to use the feature vector set to perform pattern learning to identify congestion patterns, construct a congestion propagation path prediction mechanism based on the congestion patterns, and generate congestion propagation early warning information using the congestion propagation path prediction mechanism;

[0016] A plan formulation module is used to perform risk assessment and mark the danger level of the congestion propagation warning information, and formulate preventive measures to form a protection plan based on the danger level;

[0017] A timing optimization module is used to convert the protection plan into a control action to mark a potential intervention opportunity, build a timing dynamic optimization mechanism based on the potential intervention opportunity, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control at the optimal intervention time point;

[0018] A regional coordination module is configured to perform a congestion risk transfer analysis on the protection control to mark the risk transfer direction, establish a regional risk redistribution strategy based on the risk transfer direction, generate a multi-region risk balance plan using the regional risk redistribution strategy, and form an overall protection strategy through the multi-region risk balance plan;

[0019] A resource allocation module, configured to allocate protection resources based on the overall protection strategy and generate a control status;

[0020] The protection implementation module is used to analyze the control status to form a protection capability matrix, use the protection capability matrix to implement protection, and complete congestion prediction traffic control protection.

[0021] The third aspect of the present invention proposes a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a traffic control and protection method based on congestion prediction disclosed in the first aspect are implemented.

[0022] The beneficial effects of the present invention are embodied in the following aspects:

[0023] 1. By constructing a feature vector set based on historical data and a congestion propagation path prediction mechanism, it is possible to accurately identify the occurrence patterns of congestion and predict the propagation path, thereby enabling the timely release of congestion warning information. By marking the danger level through risk assessment and formulating graded protection plans, a precise matching mechanism between risks and protection measures is established, automatically selecting the corresponding protection intensity and measure combination according to different danger levels, thereby improving the accuracy of congestion prediction, the timeliness of warnings, and the targeted nature of protection.

[0024] 2. Through dynamic optimization of the best intervention timing, multi-region risk balance schemes and protection effect gradient analysis, an intelligent protection mechanism with three-dimensional coordination of timing, region and intensity was established. It can start protection control at the best time, avoid the disorderly transfer of congestion risks between regions through regional risk redistribution strategies, and dynamically adjust the protection intensity according to the gradient transmission characteristics of the protection effect, so as to achieve accurate grasp of protection timing and coordinated linkage control between regions.

[0025] 3. Through the flexible reallocation of protection resources, cross-temporal and spatial effect tracing analysis, and strategy conflict detection mechanism, it is possible to dynamically optimize resource allocation according to the protection intensity, accurately evaluate the actual contribution of each protection element, build a weighted adaptive strategy set and a protection capability matrix, and realize intelligent management and control of the entire process from resource allocation to protection implementation, thus establishing an intelligent traffic protection system with adaptive allocation, scenario adaptation, and continuous optimization capabilities.

[0026] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings herein illustrate specific examples of the technical solutions described in the present invention, and together with the specific implementation methods constitute a part of the specification, and are used to explain the technical solutions, principles and effects of the present invention.

[0028] Unless otherwise specified or defined, the same reference numerals in different drawings represent the same or similar technical features, and the same or similar technical features may also be represented by different reference numerals.

[0029] Figure 1 It is a flow chart of a traffic control and protection method based on congestion prediction according to the present invention.

[0030] Figure 2 This is a structural block diagram of a traffic control and protection device based on congestion prediction according to the present invention.

[0031] Figure 3 It is a structural schematic diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0033] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0034] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0035] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0036] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0037] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0038] The technical solutions of the embodiments of this application are introduced below.

[0039] like Figure 1 As shown, an embodiment of the present invention provides a traffic control and protection method based on congestion prediction, including the following steps S110 to S170:

[0040] Step S110: construct a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set.

[0041] Specifically, a historical traffic data storage platform will be built to accumulate basic data. Data collection and storage infrastructure will be established within the target area of multi-intersection coordinated control. Detection equipment, including high-definition video detectors, electromagnetic induction coils, microwave radar flowmeters, and floating vehicle data receivers, will be deployed at every key intersection within the coordinated control area to form a data perception network. The detection equipment at each intersection will collect real-time vehicle traffic data, including parameters such as instantaneous traffic flow, average speed, headway, queue length, vehicle occupancy rate, and vehicle type classification for each lane. Signal control data will also be collected, recording information such as traffic light timing, phase switching times, green light duration, and red light duration. An environmental data collection module will be established to monitor environmental factors that affect traffic operations, such as weather conditions, visibility, and road conditions. A three-tiered data storage architecture will be designed. The bottom tier will be for real-time data storage, storing raw detection data at a 30-second interval. The middle tier will be for aggregated data storage, summarizing raw data at time granularities such as 5 minutes, 15 minutes, 1 hour, and 1 day, and calculating statistical indicators such as average flow, peak flow, standard deviation, and coefficient of variation. The upper layer is for archiving and storing historical data, preserving complete traffic operation records for at least three years and supporting long-term traffic pattern analysis. A data quality control mechanism is established to identify abnormal data by setting reasonable numerical range thresholds, time continuity tests and other methods. For data missing issues, linear interpolation, historical averages and other methods are used to complete the data. Unify the data formats for different intersections and different equipment types, and establish a standardized data dictionary and metadata management mechanism. Configure a data backup mechanism and use multi-site backup technology to ensure data security. Design data query and retrieval interfaces to support rapid data extraction based on multi-dimensional conditions such as time range, spatial area, and data type. Through the long-term and stable operation of this data platform, historical traffic basic data covering multiple intersection coordination areas, with sufficient time span and reliable data quality has been accumulated.

[0042] Feature mining is performed on the accumulated basic data to identify congestion characteristics. Quantitative identification criteria for congestion states are established. When the vehicle occupancy rate at any entrance to an intersection exceeds 85%, the average speed is less than 15 kilometers per hour, and this state lasts for more than 5 minutes, it is marked as congested. The basic data is used to mine the temporal characteristics of congestion, analyzing the frequency of congestion, duration distribution, dissipation patterns, and cyclical change patterns. Statistical analysis is used to identify peak congestion periods, such as the weekday morning rush hour (7:00-9:00 AM) and evening rush hour (5:00-7:00 PM). Spatial congestion characteristics are analyzed based on the basic data to study the propagation of congestion between adjacent intersections and calculate the directionality, speed, and impact range of congestion diffusion. For example, congestion on arterial roads typically propagates upstream at a speed of 150-200 meters per minute, while congestion at intersections can spread in multiple directions simultaneously. Basic data is used to identify precursory features of congestion, analyzing patterns of traffic parameter changes within the 10-15 minutes before congestion develops. These include early signs such as sudden increases in traffic volume, gradual decreases in speed, and sustained increases in occupancy. A congestion severity grading system is established, categorizing congestion into mild, moderate, and severe levels based on indicators such as duration, number of vehicles affected, degree of delay, and spread. Basic data is used to analyze the impact of external factors on congestion, studying the influence of weather conditions, special events, and holidays on congestion patterns. For example, congestion duration is typically prolonged by 20-30% during rainy weather. Basic data is used to study congestion recovery characteristics, analyzing the spatiotemporal order of congestion dissipation, the speed of recovery, and the key factors influencing recovery effectiveness. Based on basic data, correlation patterns in congestion are mined to identify causal relationships and interaction patterns between congestion at different intersections. Machine learning and data mining algorithms, including cluster analysis, association rule mining, and time series analysis, are used to automatically identify implicit congestion characteristic patterns and complex correlation patterns. Through this series of feature mining and analysis processing, the systematic marking of congestion-related features in the basic data was completed.

[0043] Based on the labeled congestion features, a feature database is established to output a set of feature vectors. The labeled congestion features are structured and numerically represented to construct a feature database that supports efficient query and similarity analysis. The temporal dimension of the congestion features is vector-encoded, converting the specific moment of congestion occurrence into hour and minute codes, the duration of congestion into minute values, and the time it takes for congestion to dissipate into relative time differences. Periodic encoding techniques are used to process the cyclical nature of time, using sine and cosine functions to convert periodic time information such as hours, weeks, and months into continuous numerical vectors. The spatial dimension of the congestion features is coordinate-encoded, converting the location of congestion occurrence into standardized two-dimensional coordinates, the congestion impact area into a radius value, and the congestion propagation direction into an angular vector representation. Congestion severity is numerically coded, with mild congestion assigned a value of 1, moderate congestion assigned a value of 2, and severe congestion assigned a value of 3. The continuous numerical encoding is refined based on the specific delay duration and number of affected vehicles. The causes and influencing factors of congestion are classified and encoded, including one-hot encoding representations of different cause types, such as traffic demand overload, traffic accidents, signal failures, and inclement weather. A dimensionality standardization processing mechanism for feature vectors is established, using methods such as Z-score standardization and maximum and minimum value normalization to ensure that different types of features have a reasonable weight distribution in the vector space. The storage structure and indexing mechanism of the feature vectors are designed, and multidimensional indexing technology is used to support fast retrieval, pattern matching, and clustering analysis operations based on similarity. A dynamic update mechanism for feature vectors is constructed, which can automatically expand the vector space dimension when new congestion feature types are identified. Vector compression and storage optimization algorithms are designed, and sparse vector representation and other technologies are used to reduce storage space usage while ensuring feature representation accuracy. A similarity measurement method between vectors is constructed, supporting vector similarity calculation based on multiple metrics such as Euclidean distance and cosine similarity. Ultimately, a set of feature vectors with complete congestion feature information and a unified structure is established.

[0044] Step S120 , using the feature vector set to perform pattern learning to identify congestion patterns, constructing a congestion propagation path prediction mechanism based on the congestion patterns, and using the congestion propagation path prediction mechanism to generate congestion propagation warning information.

[0045] Specifically, feature vector sets are used for pattern learning to identify congestion patterns. Deep learning and machine learning algorithms are used to mine and identify patterns in feature vectors. Feature vector sets are then fed into clustering algorithms, using methods such as K-means clustering, hierarchical clustering, and density clustering to identify similar congestion patterns and discover clustering characteristics across time, space, and severity. Recurrent neural networks and long-short-term memory networks are trained using feature vector sets to learn the time series patterns of congestion occurrence and identify cyclical patterns and trends. An association rule mining model is built based on feature vector sets to discover correlations between different congestion characteristics. For example, if a certain intersection experiences severe congestion during the morning rush hour on a weekday, the probability of moderate congestion occurring at adjacent intersections within 15 minutes is 78%. Causal analysis is performed using feature vector sets to identify the main causes and triggering conditions of congestion, establishing a causal chain from traffic demand, weather conditions, and event occurrence to congestion formation. Feature vector sets are used to train support vector machines and random forest models to learn classification patterns for congestion severity and establish a mapping from traffic parameters to congestion levels. Based on feature vector sets, spatiotemporal correlation analysis is performed to identify the spatial propagation patterns and temporal evolution of congestion, revealing the directionality and attenuation characteristics of congestion spread. A congestion recovery model is established using feature vector sets to analyze the temporal patterns and influencing factors of congestion dissipation. For example, the average recovery time for mild congestion is 8 minutes, for moderate congestion is 15 minutes, and for severe congestion is 25 minutes. Feature vector sets are used for anomaly detection to identify unconventional congestion patterns and sudden congestion characteristics, and to establish criteria for identifying abnormal congestion. Through deep learning and pattern mining of feature vector sets, congestion patterns reflecting the entire process of congestion onset, development, propagation, and recovery are identified.

[0046] In some embodiments, the congestion propagation path prediction mechanism is constructed based on the congestion law, including: using the congestion law to analyze the spatial diffusion characteristics of congestion and identify the congestion propagation path; analyzing the time evolution law based on the congestion propagation path to obtain the propagation timing characteristics; establishing propagation prediction parameters according to the propagation timing characteristics and the congestion propagation path; generating prediction nodes according to the propagation prediction parameters; and constructing the congestion propagation path prediction mechanism using the prediction nodes.

[0047] First, congestion patterns are used to analyze the spatial diffusion characteristics of congestion and identify congestion propagation paths. The spatial propagation patterns in the congestion patterns are used to study the directionality of congestion diffusion from the source intersection to adjacent intersections, identify primary and secondary congestion propagation paths, and determine the specific congestion propagation paths along the road network. Next, the temporal evolution patterns of the congestion propagation paths are analyzed to obtain propagation time series characteristics. For each identified congestion propagation path, the temporal evolution patterns of congestion along each path are analyzed. The time distribution of congestion from the starting point to the key node along each congestion propagation path is calculated. For example, the congestion propagation speed for a main road path is 150 meters per minute, while for a secondary road path it is 100 meters per minute. This yields the corresponding propagation time series characteristics for each congestion propagation path, including propagation initiation time, peak arrival time, and dissipation time. Furthermore, the propagation time series characteristics and congestion propagation paths are comprehensively analyzed to establish propagation prediction parameters. By combining the temporal information in the propagation time series characteristics with the spatial information of the congestion propagation paths, key prediction parameters such as the propagation speed coefficient, propagation attenuation coefficient, and propagation probability weight are set. For different combinations of congestion propagation paths and propagation time series characteristics, corresponding propagation prediction parameter configurations are determined. Prediction nodes are then generated based on the propagation prediction parameters. Prediction nodes are generated at key intersections. For example, at Intersection B, where the main arterial road meets the ring road in the city center, a prediction node B-Node is generated. The congestion arrival time is configured to be 12 minutes after the source congestion, and the congestion intensity is 0.8 times the source intensity. A prediction node C-Node is generated at Intersection C in the commercial district, with an arrival time of 8 minutes and an intensity of 0.6 times the source intensity. Each prediction node is responsible for predicting congestion propagation in a specific area. Finally, a congestion propagation path prediction mechanism is constructed using the prediction nodes. The prediction nodes are organized and connected according to the propagation path, establishing an information transmission and prediction coordination mechanism between nodes. When congestion occurs at the source intersection, the B-Node predicts that congestion will increase by 0.8 times at Intersection B 12 minutes later, and the C-Node predicts that congestion will increase by 0.6 times at Intersection C 8 minutes later. This forms a congestion propagation path prediction mechanism that covers multiple paths.

[0048] Congestion propagation path prediction mechanisms are used to generate congestion propagation warning information. Based on this mechanism, propagation paths are calculated for the current congestion situation, identifying the primary and secondary directions in which congestion may spread. The priorities of different propagation paths are analyzed, and paths are ranked according to their importance, arrival time, and impact. The temporal characteristics of each propagation path are calculated, including key time nodes such as propagation start time, arrival time, peak time, and dissipation time. The spatial characteristics of the propagation paths are analyzed, and spatial parameters such as the impact range, propagation distance, number of covered intersections, and number of affected lanes are calculated. Propagation intensity analysis is conducted to calculate the intensity variation and decay patterns of congestion along different paths, predicting the congestion severity at each intersection. Path intersection analysis is conducted to identify the convergence points and overlapping areas of multiple propagation paths and assess the cumulative effects of multiple congestion events. Bottleneck sections are identified, key nodes and weak links along the propagation paths are analyzed, and key control points for congestion propagation are determined. Alternative path analysis is conducted to predict alternative congestion spread directions and path shift patterns when the primary propagation path is blocked. Establish a risk assessment for transmission paths, classifying them into high, medium, and low risk levels based on transmission speed, impact range, and severity. Based on the results of the diffusion path analysis, generate hierarchical and categorized congestion transmission warning information, including warning level, warning time, warning area, and warning content. Develop differentiated warning strategies, issuing red warnings for high-risk transmission paths, orange warnings for medium-risk paths, and yellow warnings for low-risk paths. Design a time-series warning release mechanism, issuing early warnings 30 minutes before congestion transmission begins and updating warning information every 10 minutes during the transmission process. For example, when congestion is detected at intersection A in the city center, the prediction mechanism identifies that the congestion will spread along the main road to intersection B, with a propagation time of 12 minutes and a decay of 0.8 times. Simultaneously, it will spread to intersection C, with a propagation time of 8 minutes and a decay of 0.6 times. Based on this, an orange warning is issued, advising vehicles to detour to the outer ring road in advance. Generate a precise warning area, clearly defining the specific affected road sections, intersections, and lanes, and generate dynamic warning content, including practical information such as the expected congestion level, duration, impact range, and recommended detour routes. Establish a multi-channel release mechanism for early warning information, release early warning information in a timely manner through multiple channels such as traffic broadcasts, variable information boards, mobile applications, navigation software, etc., design a feedback and correction mechanism for early warning information, and adjust the warning content and warning level in a timely manner according to the actual development of congestion, and ultimately form timely, accurate, detailed and comprehensive congestion communication early warning information.

[0049] Step S130: Conduct risk assessment on the congestion propagation warning information to mark the danger level, formulate preventive measures according to the danger level and form a protection plan.

[0050] Specifically, a risk assessment is implemented based on congestion propagation warning information, and the risk level is marked. Based on the warning level of the congestion propagation warning information, red warning areas are assessed as extremely high risk, orange warning areas as high risk, and yellow warning areas as moderate risk. Based on the warning time of the congestion propagation warning information, the 30 minutes before the start of the transmission are analyzed as an urgent risk period, the 10 minutes before the start of the transmission are analyzed as an extremely urgent risk period, and the transmission process is analyzed as a continuous risk period. The warning area of the congestion propagation warning information is used to assess the risk level of specific affected intersections. Intersections involving main roads are marked as level 1 risk points, intersections involving secondary roads are marked as level 2 risk points, and intersections involving branch roads are marked as level 3 risk points. Based on the warning content of the congestion propagation warning information, areas with expected severe congestion levels are marked as high risk, areas with expected moderate congestion levels are marked as medium risk, and areas with expected mild congestion levels are marked as low risk. Based on the predicted duration of the congestion propagation warning information, congestion lasting more than one hour is marked as long-term risk, those lasting between 30 minutes and one hour are marked as medium-term risk, and those lasting less than 30 minutes are marked as short-term risk. Using data on the impact range of congestion warning information, we calculate the impact of over 1,000 vehicles as extremely high risk, 500-1,000 vehicles as high risk, 200-500 vehicles as medium risk, and fewer than 200 vehicles as low risk. A final risk level is assigned to each warning area based on factors such as the warning level, time urgency, spatial impact, and congestion level.

[0051] Preventive measures and emergency response plans are formulated based on the risk level. A Level 1 protection level is designed for extremely high-risk areas. Comprehensive traffic control is implemented, non-essential vehicles are prohibited from entering, the highest level of police are deployed for on-site command, and all backup signal control plans are activated. A Level 2 protection level is designed for high-risk areas. Traffic police are deployed at key intersections, signal timings are adjusted to increase green light duration in major directions, and variable lanes are opened to increase traffic capacity. A Level 3 protection level is designed for medium-risk areas. Traffic light coordination and control are optimized, intelligent guidance is activated to issue detour suggestions, and traffic monitoring is strengthened. A Level 4 protection level is designed for low-risk areas. Regular monitoring is maintained, emergency resources are prepared, and traffic information is released in a timely manner. The temporal characteristics of risk levels are utilized to develop a timeline for the implementation of preventive measures, and protective measures are immediately activated in areas with urgent risk periods. Based on the spatial distribution of risk levels, key locations for preventive measures are determined. Key police forces and equipment are deployed at Level 1 risk points, while key monitoring and routine management are implemented at Level 2 and Level 3 risk points, respectively. Resource allocation intensity will be allocated according to hazard level: extremely high-hazard areas will receive all available resources, high-hazard areas will receive 70%, medium-hazard areas will receive 40%, and low-hazard areas will receive 20%. Based on the tiered protective measures developed above for different hazard levels, these preventive measures will be organized and integrated to build a comprehensive emergency response plan framework and implementation system, establishing three levels: overall plan, specific plan, and on-site response plan. Develop regional divisions and responsibilities for the emergency response plan, dividing the protection area into core control areas, key monitoring areas, and general attention areas, clarifying the protection priorities and control requirements for each area. Design the activation process and execution sequence for the emergency response plan, establish a decision-making mechanism for activation, an information transmission process, and a sequence for implementing measures. Develop a resource support plan for the emergency response plan, including the organization and deployment of personnel, the deployment and maintenance of equipment and facilities, establish an organizational command system for the emergency response plan, and establish a emergency response command center. Develop a monitoring and evaluation mechanism for the emergency response plan, establish a real-time monitoring network, formulate effectiveness evaluation indicators, and develop a dynamic optimization mechanism, ultimately forming a comprehensive and operational emergency response plan that covers the entire process.

[0052] Step S140 , converting the protection plan into a control action to mark a potential intervention opportunity, building a dynamic optimization mechanism for the timing based on the potential intervention opportunity, using the dynamic optimization mechanism for the timing to determine the optimal intervention time point, and starting the protection control at the optimal intervention time point.

[0053] Specifically, protection plans are converted into control actions to identify potential intervention opportunities. Based on the protection plan, regional traffic control within the first-level protection system is converted into specific control actions, such as intersection closures, lane restrictions, and detour instructions. Traffic light optimization and adjustment are converted into operational instructions, such as timing parameter modification, phase adjustment, and coordinated control. The protection plan analyzes the earliest executable time, latest required execution time, and optimal execution window for each control action, establishing the time constraints for the control actions. The protection plan identifies the spatial dependencies and execution sequence of control actions, for example, whether diversion measures must be implemented at upstream intersections before signal timing adjustments are made at downstream intersections. The protection plan analyzes the resource requirements and available resource constraints of control actions, identifying resource conflicts and bottlenecks. The protection plan analyzes the interactions and synergies between control actions, identifying combinations of actions that require simultaneous execution and pairs of actions that must avoid conflict. The protection plan establishes expected effects and execution conditions for control actions, analyzing the cost-benefit ratio and risk level of the actions. The protection plan identifies the flexibility and adjustability of control actions, identifying action types whose parameters can be adjusted based on actual conditions. Establish a classification standard for intervention opportunities, dividing potential intervention opportunities into three types: preventive intervention, responsive intervention, and restorative intervention. Preventive intervention is implemented before congestion forms, responsive intervention is implemented when congestion occurs, and restorative intervention is implemented after congestion dissipates. Design quantitative indicators for intervention opportunities, including evaluation dimensions such as intervention urgency, intervention effectiveness, resource availability, and coordination complexity. Through this series of action decomposition and timing analysis, identify potential intervention opportunities corresponding to protective plans.

[0054] In some embodiments, the construction of a dynamic optimization mechanism for timing based on the potential intervention timing includes: performing a timing analysis on the potential intervention timing to determine the timing execution order; establishing a timing priority based on the priority relationship of the timing execution order; dynamically adjusting the timing priority to generate an optimization strategy; and constructing a dynamic optimization mechanism for timing based on the optimization strategy.

[0055] First, a temporal analysis of potential intervention opportunities is conducted to determine their execution order. By analyzing the temporal characteristics of potential intervention opportunities, the earliest possible execution time, the latest required execution time, and the optimal execution time window for each intervention measure are identified. Taking into account the temporal dependencies between intervention measures, the execution order of each intervention opportunity is determined. For example, if diversion measures at the upstream intersection must be initiated within 5 minutes of a congestion warning, and signal adjustments at the downstream intersection must be performed 10 minutes after the diversion measures are initiated, the execution order of each intervention opportunity is determined. Next, priority relationships are analyzed based on the execution order of the opportunities, and a priority order is established. Based on the determined execution order, the importance and urgency of different intervention opportunities are analyzed. Priority weights are assigned to each intervention opportunity by assessing the scope of the intervention effect, resource requirements, and time window constraints. For example, upstream diversion measures are assigned a first priority due to their preventive nature, downstream signal adjustments are assigned a second priority, and emergency lane openings are assigned a third priority. This establishes a priority order. Furthermore, the priority orders are dynamically adjusted to generate an optimization strategy. Based on the established priority orders, the priorities are dynamically adjusted in conjunction with real-time traffic conditions and resource availability. When traffic congestion worsens, the priority of responsive interventions is increased; when resources are scarce, the priority of resource-intensive interventions is decreased. For example, during the morning rush hour, signal adjustment measures are upgraded from a second-level priority to a first-level priority, generating optimization strategies adapted to different scenarios. Ultimately, the optimization strategies are used to construct a dynamic timing optimization mechanism. The optimization strategies are integrated into a unified timing selection mechanism, establishing a workflow for strategy matching, timing selection, and dynamic adjustment. When an intervention request is triggered, the mechanism matches the corresponding strategy based on the current traffic conditions, selects the optimal combination of intervention timings, and dynamically adjusts subsequent timings based on actual results during execution, forming a dynamic timing optimization mechanism.

[0056] A dynamic optimization mechanism is used to determine the optimal intervention time. This mechanism analyzes the current congestion spread in real time. Inputting information such as current traffic state parameters, congestion trends, and available resources, the optimization process is initiated. This mechanism performs multi-objective optimization calculations, searching for the optimal intervention time combination while satisfying various constraints. This mechanism performs multiple rounds of iterative calculations, continuously adjusting and optimizing the intervention timing until convergence conditions are met or the preset computational time limit is reached. The dynamic optimization mechanism selects appropriate optimization strategies and parameter settings based on the current situation, such as using a rapid response strategy during the morning rush hour and a precise optimization strategy during off-peak hours. The dynamic optimization mechanism identifies and resolves timing conflicts between different intervention actions, ensuring the feasibility of the final selected time combination. The dynamic optimization mechanism evaluates the sensitivity of the optimal time combination to changes in external conditions, ensuring the robustness of the selected time combination. The dynamic optimization mechanism analyzes the implementation effectiveness and potential subsequent impact of the optimal intervention time, assessing the rationality of the intervention decision. A dynamic optimization mechanism for timing is used to compare multiple scenarios and generate alternative intervention timing options, providing decision makers with a framework for selection and risk assessment. A confidence assessment for the optimal timing is established, providing a credibility indicator for the determined timing based on the convergence of the optimization process, the stability of the solution, and historical verification results. A dynamic adjustment mechanism for the timing is designed to promptly recalculate and adjust the optimal intervention timing when actual conditions deviate from expectations. Through this series of optimization calculations and scenario comparisons, a scientifically optimized optimal intervention timing is obtained.

[0057] Initiate protective controls based on the optimal intervention time. Develop a detailed protective control implementation plan based on the optimal intervention time, specifying the specific execution time, department, method, and standards for each control action. Establish a protective control activation mechanism based on the optimal intervention time, setting up automatic triggering conditions and manual confirmation procedures to ensure the precise initiation of appropriate protective measures at the optimal time. Organize the deployment of protective control resources based on the optimal intervention time, ensuring personnel, equipment, and information channels are in place in advance to ensure timely and high-quality implementation of protective controls. Design a protective control execution monitoring mechanism based on the optimal intervention time to track the implementation of each control measure in real time and promptly identify implementation deviations and issues. Establish a protective control effectiveness evaluation mechanism based on the optimal intervention time, conducting immediate effectiveness monitoring after control measures are implemented to assess the degree to which actual control results align with expected results. Build a dynamic protective control adjustment mechanism based on the optimal intervention time. When unsatisfactory control results are detected or new circumstances arise, promptly adjust control intensity, expand control scope, or initiate backup control plans. Design a protective control information feedback mechanism based on the optimal intervention time to promptly collect and analyze various information during control execution. A coordinated control and prevention command mechanism was established using the optimal intervention time point to coordinate control actions across all departments and avoid duplication and interference. A quality assurance mechanism for control and prevention was established based on the optimal intervention time point, with standardized operating procedures and quality inspection procedures for control actions established. A protective control and prevention emergency response mechanism was designed to enable rapid activation of emergency plans and remedial measures in the event of emergencies during control execution. Ultimately, efficient protective control based on scientific timing was achieved.

[0058] Step S150: Perform congestion risk transfer analysis on the protection control to mark the risk transfer direction, establish a regional risk redistribution strategy based on the risk transfer direction, use the regional risk redistribution strategy to generate a multi-region risk balance plan, and form an overall protection strategy through the multi-region risk balance plan.

[0059] Specifically, a congestion risk transfer analysis is conducted for protective control, identifying the direction of risk transfer. Based on the intersection closures and lane restrictions implemented in protective control, the effects of these control actions on traffic diversion and diversion are analyzed, and the diversion paths and volume of restricted traffic are calculated. Signal timing adjustments implemented in protective control are used to analyze the biased impact of signal optimization on traffic flow in different directions, identifying directions with advantageous traffic flow and those with relatively limited traffic flow. Detour guidance implemented in protective control is used to analyze the carrying capacity and congestion risk tolerance of detour routes, and assess the impact of detour traffic on alternative routes. Based on the spatial coverage of protective control, the risk distribution changes between protected and unprotected areas are analyzed, and the volume and speed of risk transfer from protected areas to surrounding areas are calculated. The temporal implementation characteristics of protective control are used to analyze the differences in the impact of protective measures on risk transfer patterns during different time periods, identifying the time windows and peak periods for risk transfer. Based on the coordinated command arrangements of protective control, the impact of multi-intersection joint control on inter-regional risk redistribution is analyzed, and the risk concentration and release points generated by the joint control are calculated. A quantitative analysis model for risk transfer is developed, calculating the direction, angle, distance, intensity, and attenuation of risk transfer. A method for marking risk transfer directions was designed, using vector notation to mark the primary and secondary transfer directions and transfer weights for each risk source. Through this series of transfer analysis and direction identification, the risk transfer direction under the action of protective controls was marked.

[0060] In some embodiments, establishing a regional risk reallocation strategy based on the risk transfer direction includes: performing a flow analysis on the risk transfer direction to determine the risk flow distribution; evaluating the regional carrying capacity based on the risk flow distribution and establishing a carrying capacity configuration; balancing the carrying capacity configuration to generate a reallocation plan; and constructing a regional risk reallocation strategy based on the reallocation plan.

[0061] First, a flow analysis of risk transfer is conducted to determine the risk flow distribution. By analyzing the spatial characteristics and propagation paths of risk transfer, the flow patterns and final distribution of risk between different regions are identified. The risk transfer pattern from the source region to surrounding regions is analyzed, and the risk input and output for each region are calculated. For example, when traffic control is implemented in area A in the city center, 30% of the congestion risk shifts to area B in the east, 25% to area C in the west, and 20% to area D in the south. This determines the risk flow distribution between regions. Subsequently, the regional carrying capacity is assessed based on the risk flow distribution, and a carrying capacity configuration is established. Based on the determined risk flow distribution, the risk tolerance of each region is analyzed. Taking into account factors such as road capacity, traffic control capabilities, and emergency response capabilities, the upper limit of risk tolerance for each region is assessed. For example, if area B has a four-lane main road and a comprehensive signal control system, the risk tolerance limit is set at 1,000 vehicles per hour; if area C has a two-lane secondary road, the upper limit is set at 600 vehicles per hour. A carrying capacity configuration is established to reflect the risk tolerance of each region. Based on this, the carrying capacity configuration is balanced to generate a redistribution plan. Based on the established carrying capacity configuration and combined with the risk flow distribution, the risk balance between regions is adjusted. When the risk received by a certain area exceeds its carrying capacity, part of the risk will be reallocated to the area with surplus carrying capacity. For example, when the risk received by area B reaches 950 vehicles / hour and is close to the carrying limit, 200 vehicles / hour of risk will be reallocated to area E with surplus carrying capacity to generate a reallocation plan. Through the above steps, the redistribution plan is used to construct a regional risk reallocation strategy. The reallocation plan is converted into specific regional control guidance, and the control measures of each area are automatically adjusted when risk transfer occurs. For example, when it is detected that the risk is transferred from area A to area B, the strategy automatically adds 2 temporary signal control points in area B and extends the green light time by 15 seconds. At the same time, the control intensity in area A is moderately relaxed to form a regional risk reallocation strategy.

[0062] A regional risk redistribution strategy is used to generate a multi-regional risk balancing plan. This strategy comprehensively analyzes the current inter-regional risk distribution, identifying high-risk areas with excessively concentrated risk and low-risk areas with relatively less risk. Based on this strategy, specific risk adjustment measures are formulated to achieve an orderly transfer and balanced distribution of risk across regions through traffic flow guidance, signal coordination optimization, and temporary control measures. A multi-tiered balancing plan architecture is designed using this strategy: a city-level balancing plan coordinates citywide risk distribution, a district-level balancing plan coordinates intra-regional risks, and a road-section-level balancing plan addresses local risk adjustments. A timeline for risk balancing is developed based on the regional risk redistribution strategy, prioritizing risk reduction in high-risk areas and gradually guiding risk transfer to areas with greater carrying capacity, ultimately achieving global risk balance. For example, when severe congestion risk arises in the city center, the Outer Ring Expressway is first opened to increase capacity, then 30% of transit traffic is diverted to the Outer Ring Expressway. Simultaneously, temporary signal controls are added on secondary arterial roads to divert 20% of local traffic, ultimately reducing the city center's risk level from extremely high to moderate. Based on the regional risk reallocation strategy, a resource allocation plan for the balancing plan is established, clarifying the amount of human resources, equipment, technology, and other resources required in each region and the allocation schedule. The regional risk reallocation strategy is used to design an execution monitoring mechanism for the balancing plan, tracking the actual effects of risk transfer and changes in regional risk levels in real time. A performance evaluation system for the balancing plan is established based on the regional risk reallocation strategy, setting key indicators such as regional risk balance, transfer success rate, and control efficiency. A dynamic optimization mechanism for the balancing plan is constructed based on the regional risk reallocation strategy. When monitoring reveals that risks are re-accumulating in certain regions, balancing measures are adjusted and the plan configuration is re-optimized in a timely manner. Through this series of plan formulation and implementation arrangements, a coordinated and unified risk balancing plan covering multiple regions is generated.

[0063] A comprehensive protection strategy is formulated through a multi-regional risk balance plan. Based on this plan, local protection measures in each region are integrated into a comprehensive, overarching protection strategy framework. A unified command system for the protection strategy is established using this plan, with a city-level protection command center as the highest decision-making level, district-level protection sub-centers as the execution and coordination level, and intersections as the operational implementation level, forming a three-tiered command structure. A resource coordination plan for the protection strategy is formulated based on the multi-regional risk balance plan, centrally allocating citywide protection resources such as traffic police, signal control equipment, and information distribution channels to achieve optimal resource allocation and efficient utilization. A coordination mechanism for the protection strategy is designed based on the multi-regional risk balance plan, establishing a workflow for information sharing, decision-making consultation, and synchronized actions across regions to ensure coordinated and consistent protection actions across all regions. For example, when Dongcheng District initiates a Level 2 protection response, it automatically notifies the neighboring Xicheng District and Nancheng District to prepare for Level 3 protection, while also coordinating to increase traffic capacity in the outer ring area to accommodate diverted traffic. A comprehensive evaluation system for the protection strategy is constructed using this plan, assessing the overall effectiveness of the protection strategy based on city-wide traffic efficiency, regional risk levels, and resource utilization efficiency. A dynamic adjustment mechanism for the protection strategy was established based on a multi-regional risk balancing plan. The focus and implementation intensity of the overall protection strategy were adjusted in real time based on changes in the city's traffic situation and the evolution of regional risks. A tiered response mechanism for the protection strategy was developed based on the multi-regional risk balancing plan, with the corresponding level of overall protection strategy activated based on the city's congestion risk level. Ultimately, a comprehensive, coordinated, and dynamically optimized overall protection strategy was established.

[0064] Step S160: Allocate protection resources based on the overall protection strategy to generate a control status.

[0065] Specifically, after the overall protection strategy is determined, it is necessary to convert the strategy into specific resource allocation and control measures. Based on the overall protection strategy, protection resources are allocated to generate the control status.

[0066] In some embodiments, the allocation of protection resources based on the overall protection strategy to generate a control status includes: conducting a protection effect gradient analysis based on the overall protection strategy to obtain effect space distribution characteristics; constructing a gradient transfer tracking mechanism based on the effect space distribution characteristics; adjusting the protection intensity using the gradient transfer tracking mechanism; obtaining resource demand changes according to the protection intensity adjustment; and dynamically allocating resources based on the resource demand changes to generate a control status.

[0067] Based on the overall protection strategy, a gradient analysis of protection effectiveness was conducted to determine the spatial distribution characteristics of the effectiveness. Spatial differentiation analysis and gradient feature identification were performed based on the predicted effectiveness of the overall protection strategy after implementation. The overall protection strategy was used to analyze the transmission and attenuation patterns of protection measures at different levels, including the city, district, and intersection, and to calculate the gradient variation of effectiveness across each level. The overall protection strategy was used to analyze the impact of the spatial density of resources, such as traffic police force, signal control equipment, and information dissemination channels, on protection effectiveness, identifying differences in effectiveness between resource-intensive and resource-sparse areas. The overall protection strategy was used to analyze the impact of inter-regional information sharing, decision-making consultation, and action synchronization on the spatial distribution of protection effectiveness, and to calculate the relationship between coordination and effectiveness. Based on the overall protection strategy, the spatial distribution patterns of protection strategies corresponding to different risk levels were analyzed, identifying the gradient of effectiveness across high-, medium-, and low-intensity protection areas. The overall protection strategy was used to analyze the real-time impact of policy adjustments on the spatial distribution of effectiveness, and to calculate the propagation speed and impact range of the adjusted measures. A spatial interpolation method for calculating protection effectiveness was developed, using monitoring point data to extrapolate the effect distribution continuum across the entire region, identifying areas with peak, valley, and transitional effects. A quantitative calculation method for the effect gradient was designed, using spatial derivatives and directional derivatives to calculate the rate of change of the effect in different directions, and a vector field representation of the effect gradient was established. A cluster analysis method for the spatial distribution of the effect was constructed, and spatial regions with similar effect characteristics were grouped to form a spatial division of homogeneous and heterogeneous effect areas. A distance attenuation law for effect transmission was established, and the attenuation characteristics of the protective effect with increasing distance were analyzed. For example, the effect intensity within 1 km from the core protection area remained above 80%, dropped to 60% within 2 km, and dropped to below 30% outside 3 km. Through this series of analyses, the spatial distribution characteristics of the effect under the action of the overall protection strategy were obtained.

[0068] A gradient transfer tracking mechanism is constructed based on the spatial distribution characteristics of the effect. To dynamically track the spatial transfer process of protective effects and adjust protection intensity in a timely manner, a mathematical algorithm for gradient transfer is developed using the spatial distribution characteristics of the effect. The transfer path, transfer speed, and change patterns of the protective effect in space are analyzed. A transfer tracking monitoring network is designed based on the spatial distribution characteristics of the effect. A dense monitoring point distribution is set in areas with significant gradient changes in the effect, and a sparse monitoring point distribution is set in areas with relatively uniform effects, forming an adaptive monitoring density distribution. A transfer boundary identification algorithm is developed based on the spatial distribution characteristics of the effect. This algorithm automatically identifies the effective boundary, attenuation boundary, and vanishing boundary of the effect transfer, thereby determining the scope of gradient transfer. A transfer path prediction algorithm is developed based on the spatial distribution characteristics of the effect. This algorithm analyzes the transfer patterns of the effect along different paths, such as road networks, administrative boundaries, and geographical features, and establishes a probability distribution for multi-path transfer. A real-time transfer intensity calculation method is designed based on the spatial distribution characteristics of the effect. The instantaneous and cumulative intensity of the effect transfer is calculated through time series analysis of monitoring data. A transfer anomaly detection mechanism is established based on the spatial distribution characteristics of the effect to identify anomalies such as effect transfer interruption, transfer reversal, and transfer acceleration, thereby promptly detecting gradient transfer problems. The spatial distribution characteristics of the effects were used to construct an evaluation index for transfer efficiency. The transfer efficiency of the effects generated by unit protection investment at different spatial locations was calculated, and areas of high and low transfer efficiency were identified. A visualization method for transfer tracking was designed based on the spatial distribution characteristics of the effects. The spatial process of gradient transfer was intuitively displayed through effect contour maps, transfer vector maps, gradient heat maps, and other methods. A data fusion algorithm for transfer tracking was established based on the spatial distribution characteristics of the effects. This algorithm integrated multi-source monitoring data, historical statistical data, and theoretical calculation data to improve the accuracy and reliability of tracking results. An early warning mechanism for transfer tracking was constructed using the spatial distribution characteristics of the effects. When an anomaly in gradient transfer or a significant decrease in transfer efficiency was detected, an early warning signal was automatically triggered. After completing the algorithm establishment, mechanism design, and early warning configuration, a gradient transfer tracking mechanism with real-time tracking and anomaly detection capabilities was constructed.

[0069] Use the gradient transfer tracking mechanism to adjust protection intensity. This mechanism identifies areas of unreasonable protection intensity distribution and key locations requiring adjustment. It also analyzes the impact of protection intensity adjustments on effectiveness transfer, predicting the spatial diffusion and temporal evolution of adjustment measures. It also identifies areas of redundant and insufficient protection resource allocation, enabling the development of adjustment plans for resource reallocation and intensity redistribution. The mechanism promptly identifies areas of interrupted or abnormal protection effect transfer, initiating targeted intensity reinforcement measures. For example, if monitoring reveals that the transfer efficiency of protection effects from a main road to a branch road is only 40% of the expected rate, two temporary signal control points are immediately added to that branch road, and an additional team of traffic police is deployed for on-site traffic control, increasing the transfer efficiency to 75%. The mechanism also adjusts the spatial scope of protection intensity, expanding coverage or narrowing key areas, optimizing the spatial allocation of protection intensity. The visualization capabilities of the mechanism provide intuitive decision support for protection intensity adjustments, helping managers quickly identify key areas and directions for adjustment. Develop a multi-source information-based protection intensity adjustment strategy based on the mechanism, enhancing the scientific nature and accuracy of adjustment decisions. A preventative adjustment mechanism for protection intensity is established through a gradient transfer tracking mechanism, enabling proactive adjustments before transmission issues arise. A verification method for intensity adjustments is established based on this mechanism, allowing for real-time evaluation of the effectiveness of adjustment measures and prompt secondary adjustments and optimization. This mechanism also enables a learning experience summary mechanism for intensity adjustments, documenting the effectiveness patterns of different adjustment strategies. Ultimately, this allows for dynamic adjustment of protection intensity based on scientific tracking and precise analysis.

[0070] Analyze resource demand changes based on protection intensity adjustments. Use protection intensity adjustments to analyze the demand for traffic police, signal control equipment, surveillance equipment, and other resources in areas with newly added resource demands, and calculate resource gaps and replenishment requirements. Use protection intensity adjustments to identify redundant resources that can be released in resource-released areas, including available personnel, reallocated equipment and facilities, and transferable technical support personnel. Analyze the temporal characteristics of resource demand based on protection intensity adjustments, identifying peak, stable, and low periods of resource demand, and establishing a correspondence between time windows and resource demand. Use protection intensity adjustments to calculate the direction and volume of resource flows between different areas, identify resource output areas, resource receiving areas, and resource transfer areas, and map inter-regional resource flows. Use protection intensity adjustments to analyze the distribution of urgent and general resource demands, and formulate resource allocation priority and classification management strategies. Develop a quantitative calculation method for resource demand, converting abstract intensity adjustments into specific resource quantity requirements, including personnel, equipment, vehicle configurations, and communication facilities, to create a detailed resource requirement list. Analyze changes in resource demand, differentiating between changes in demand for specialized technical personnel, general on-duty personnel, equipment and facilities, and information support. For example, when the security intensity of a business district is increased from Level 2 to Level 1, the number of traffic police officers required increases from 8 to 15, signal control points from 6 to 12, temporary control facilities from 2 to 5, and monitoring coverage from 2 kilometers to 3.5 kilometers. Through systematic demand analysis and change tracking, we can capture the comprehensive changes in resource demand caused by security intensity adjustments.

[0071] Dynamic resource allocation is performed based on changes in resource demand, generating a control status. For areas with new resource requirements due to changes in resource demand, a rapid resource replenishment mechanism is established, along with precise resource allocation plans and execution sequences. For example, if the demand for traffic police in a certain area increases from 8 to 15, 7 officers are immediately deployed from adjacent areas and equipped with appropriate on-duty equipment and communication tools. A redundant resource recovery and allocation mechanism is established, pooling released resources such as redeployable personnel and reallocated equipment. A resource inventory management and real-time scheduling system are established, prioritizing allocation to areas with the most urgent needs. A time-based allocation strategy is designed, with full allocation activated during peak periods, regular allocation implemented during stable periods, and resource recovery implemented during off-peak periods, optimizing resource allocation over time. A targeted allocation mechanism is established, establishing direct allocation channels between resource-sending and receiving areas, and defining point-to-point resource flow paths to ensure precise, on-demand resource flow. A dual-track allocation mechanism is implemented, with rapid allocation channels activated for urgent needs, ensuring deployment within 15 minutes, and planned allocation for general needs, completing deployment within 1 hour. Establish a specialized deployment system, with corresponding deployment libraries and management mechanisms for different types of resources. For example, during the morning rush hour, 15 traffic police officers in the city center were redeployed: 8 were assigned to major congested intersections for on-site traffic control, 4 to secondary arterial roads for diversion and guidance, and 3 to emergency standby points. Simultaneously, 6 sets of temporary signal equipment were deployed to bottleneck sections, and 2 sets of mobile monitoring equipment were deployed to key observation points, creating an enhanced control system covering core areas. Ultimately, this resulted in a comprehensive control system with rational resource allocation, rapid response, comprehensive coverage, and significant effectiveness.

[0072] Step S170: Analyze the control status to form a protection capability matrix, use the protection capability matrix to implement protection, and complete congestion prediction traffic control protection.

[0073] Specifically, the formation of a protection capability matrix requires systematic analysis to quantify the effects of each protection element.

[0074] In some embodiments, analyzing the control state to form a protection capability matrix includes: performing a cross-temporal and spatial effect retrospective analysis of the control state to obtain a protection factor contribution; constructing a weighted adaptive strategy set based on the protection factor contribution; and forming a protection capability matrix using the weighted adaptive strategy set.

[0075] Exemplarily, the cross-temporal and spatial retrospective analysis of the control status to obtain the contribution of protective factors includes: conducting a cross-temporal and spatial retrospective analysis of the control status to obtain historical execution data; analyzing the impact of each factor based on the historical execution data to establish a contribution evaluation; the various factors include congestion propagation warning information, optimal intervention time points and multi-regional risk balance plans; and quantifying the contribution evaluation to generate a protection factor contribution.

[0076] First, a cross-temporal and spatial retrospective analysis of the control status was conducted to obtain historical execution data. Based on the control status, the actual execution and effectiveness of the entire protection process were traced forward. A cross-temporal and spatial data collection framework was established, with a 5-minute collection interval for the temporal dimension and spatial coverage for all key nodes within the coordinated control area. Key execution data, such as the timeliness of warning issuance, records of intervention initiation timing, and regional coordination execution information, was collected through the control status. Indicators such as warning issuance time, coverage, and accuracy were recorded. The intervention timing selection process, initiation time, and delays were tracked. Information was collected on the scope of regional coordination participation, coordination success rate, and resource allocation. For example, during a weekday morning rush hour congestion prevention operation, retrospective analysis revealed that warning information was issued 25 minutes before the congestion and covered three major intersections. Intervention was accurately initiated 8 minutes after the warning. Regional coordination covered two eastern and western regions, achieving an 85% success rate. Historical execution data reflecting the actual execution status of the three core elements was obtained. Subsequently, the impact of each element was analyzed based on this historical execution data, and a contribution assessment was established. Using historical execution data, we analyze the actual impact of three key elements—congestion propagation warning information, optimal intervention timing, and multi-regional risk balancing solutions—on the ultimate control effectiveness. For congestion propagation warning information, we analyze the impact of warning accuracy, timeliness, and coverage on the success rate of congestion prevention, and assess the correlation between warning quality and prevention effectiveness. For the optimal intervention timing, we analyze the impact of timing accuracy and timely intervention initiation on resource allocation optimization and prevention efficiency, and assess the contribution of timing to overall prevention effectiveness. For the multi-regional risk balancing solution, we analyze the impact of the integrity and stability of regional coordination on risk transfer control and overall protection coordination, and assess the extent to which regional coordination improves prevention effectiveness. We establish evaluation criteria for the impact of these three elements, encompassing direct impact, synergistic impact, and sustained impact. For example, our analysis found that the direct impact of congestion propagation warning information on early warning was 18%, the direct impact of the optimal intervention timing on resource optimization was 20%, and the direct impact of the multi-regional risk balancing solution on overall coordination was 22%. We develop a contribution assessment that reflects the true impact of these three elements. On this basis, the contribution assessment is quantified to generate the contribution of the protection factors. The formula for calculating factor contribution is established: Ci = (Ei - E0) / (Emax - E0) × Wi × Fi, where Ci is the contribution of the i-th factor, Ei is the protection effect value when the factor is included, E0 is the baseline protection effect value, Emax is the theoretical maximum protection effect value, Wi is the weight adjustment factor, and Fi is the effect amplification factor. The formula for calculating the synergistic contribution between design factors is: Synergy_ij = Eij - (Ei + Ej - E0), which calculates the synergistic contribution of the factor combination.A comprehensive contribution calculation formula was established: TCi = αCi + β∑(Rij × Cj) + γTi, where TCi represents the comprehensive contribution of factor i, α represents the direct contribution weight coefficient, β represents the associated contribution weight coefficient, γ represents the time decay weight coefficient, Rij represents the factor correlation, and Ti represents the time decay factor. Specific contribution values for the three factors were calculated, such as 18.5% for the congestion propagation warning information, 20.8% for the optimal intervention time point, and 22.3% for the multi-regional risk balance plan. A dynamic contribution update mechanism was established to automatically trigger a recalculation of the contribution when the actual application effect deviated from the expected effect by more than 5%. For example, if the actual contribution of multi-regional coordination increased from 22.3% to 25.1% during three consecutive protection practices, the weight configuration for that factor would be automatically updated. This ultimately generates scientifically accurate, quantifiable, and operational protection factor contribution values.

[0077] Exemplarily, the construction of a weighted adaptive strategy set based on the contribution of the protection factors includes: using the contribution of the protection factors to identify strategy conflict points and establish a conflict detection mechanism; performing scene classification and matching based on the conflict detection mechanism to generate a weight configuration scheme for each scene; and constructing a weighted adaptive strategy set according to the weight configuration scheme for each scene.

[0078] First, the contribution of protective factors is used to identify strategic conflicts and establish a conflict detection mechanism. Based on the distribution of protective factor contributions, the authors analyze the strategic conflicts in the practical application of three key elements: congestion propagation warning information, optimal intervention timing, and multi-regional risk balancing solutions. They identify the timeliness conflicts between warning information and intervention timing. For example, during the morning rush hour, the warning information strategy requires immediate warning issuance upon detection of signs of congestion to gain time for resolution, while the intervention timing strategy requires precise analysis of the optimal intervention point to avoid premature intervention and resource waste. These conflicts conflict in response speed and accuracy. They also analyze the decision-making conflicts between intervention timing and regional coordination. When immediate intervention measures are required at an intersection, the regional coordination strategy requires prior communication and coordination with neighboring regions to avoid risk transfer, creating a conflict between decision-making timeliness and coordination integrity. They also identify resource conflicts between regional coordination and warning information. Given limited resources, regional coordination requires the deployment of a large number of personnel and equipment for multi-point coordinated control, while the issuance of warning information also consumes communication and monitoring resources, creating a resource competition conflict. A conflict intensity quantification method was established to calculate the degree of conflict between factors. For example, the conflict intensity between warning information and intervention timing was 0.15, and the conflict intensity between intervention timing and regional coordination was 0.12. A conflict detection mechanism was established to automatically identify and quantify strategic conflicts. Next, scenario classification and matching were performed based on the conflict detection mechanism to generate scenario-specific weighting schemes. Using this conflict detection mechanism, the characteristics and intensity of strategic conflicts were analyzed under different traffic scenarios. Analyzing conflict patterns under high-volume, high-density traffic conditions during the morning rush hour revealed a significant increase in the importance of regional coordination strategies, necessitating strengthened coordination among multiple regions. Its weight should be appropriately increased, while the weights of warning information and intervention timing were adjusted accordingly. Analyzing conflict patterns under unexpected, high-urgency circumstances revealed a significant importance of intervention timing strategies. Rapid and accurate intervention decisions became crucial, and their weight should be significantly increased. For example, when a traffic accident in a commercial district caused congestion on a main road, the weight of intervention timing was increased from the typical 20% to 30% to ensure rapid initiation of emergency diversion measures. For evening rush hour scenarios, it was found that the early prevention role of early warning information is more important, and its weight needs to be appropriately increased. For severe weather scenarios, the three elements need to be more balanced to cope with complex and changeable traffic conditions. Generate scenario-specific weight configuration schemes optimized for different scenarios. On this basis, construct a set of weight adaptive strategies based on the scenario-specific weight configuration schemes. Integrate the generated scenario-specific weight configuration schemes into a unified adaptive strategy system, and establish a complete workflow for scenario recognition, weight matching, and dynamic switching. Design a scene automatic recognition mechanism to automatically determine the current scene type through key indicators such as traffic flow density, time characteristics, weather conditions, and emergencies. Establish weight switching rules to automatically switch from the current weight configuration to the optimal weight configuration for the target scenario when the scene changes.A smooth transition mechanism is designed to prevent drastic changes in weight configuration from impacting protection effectiveness, and a step-by-step adjustment approach is used to gradually complete the weight switching. For example, when a transition from off-peak hours to morning rush hour is detected, the weight of the warning information is gradually adjusted, the weight of the intervention opportunity changes accordingly, and the weight of regional coordination is moderately increased. The entire switching process is completed smoothly within 8 minutes. A weight configuration verification mechanism is established to monitor the protection effect after weight adjustment in real time. When the effect does not meet expectations, the weight fine-tuning program is automatically initiated. Ultimately, a set of weight adaptive strategies is constructed that can automatically adjust the weight configuration according to scenario changes and resolve policy conflicts.

[0079] A protection capability matrix is formed using a weighted adaptive policy set. Based on the weighted adaptive policy set, individual policies are organized into a matrix structure based on functional dimensions and application scenarios, establishing a multi-dimensional protection capability expression framework. The protection capability matrix is constructed using the weighted adaptive policy set, with the rows representing different protection function categories and the columns representing different application scenario types. The weighted adaptive policy set is used to populate each cell of the protection capability matrix, with each cell containing a specific policy combination and weight configuration for the corresponding function and scenario. For example, in the "Warning Function × Morning Rush Scenario" cell, the congestion propagation warning strategy is assigned a weight of 0.18, and the data quality assurance strategy is assigned a weight of 0.08, resulting in a total warning capability value of 0.26. In the "Coordination Function × Emergency Scenario" cell, the multi-region coordination strategy is assigned a weight of 0.22, the resource allocation strategy is assigned a weight of 0.05, and the timing selection strategy is assigned a weight of 0.20, resulting in a total coordination capability value of 0.47. A dynamic update mechanism for the protection capability matrix is designed based on the weighted adaptive policy set. Whenever policy weights are adjusted, the values and configurations in the matrix are updated accordingly. A performance evaluation method for a protection capability matrix is established based on a set of weighted adaptive strategies. The overall protection capability index of the matrix and the distribution of protection strength in each dimension are calculated. The intelligent optimization function of the protection capability matrix is constructed using the set of weighted adaptive strategies. The protection efficiency of the matrix is improved through continuous learning and adjustment. The resource mapping relationship of the protection capability matrix is designed based on the set of weighted adaptive strategies, and the resource input and configuration requirements required for each protection capability are clarified. An effect tracking mechanism for the protection capability matrix is established based on the set of weighted adaptive strategies to monitor the degree of performance and effectiveness of each protection capability in real time. The scenario adaptation function of the protection capability matrix is designed based on the set of weighted adaptive strategies, and the matrix configuration is automatically adjusted according to different traffic conditions and protection needs. Finally, a comprehensive protection capability matrix that reflects the actual distribution of protection capabilities and supports dynamic adjustment and optimization is established.

[0080] Protective measures are implemented using a protective capability matrix. Based on the established protective capability matrix, the corresponding protective capability configuration within the matrix is automatically selected and corresponding protective measures are initiated, depending on the current traffic scenario and congestion risk. When a morning rush hour congestion risk is detected, protective measures such as warning information issuance, intervention timing selection, and regional coordination are automatically initiated based on the "warning function × morning rush hour scenario" configuration within the matrix. The protective capability matrix guides coordinated control across multiple intersections. Based on the weighting of each function within the matrix, warning, intervention, and coordination resources are uniformly dispatched, achieving synchronized response and coordinated linkage of protective measures at each intersection. For example, if congestion signs appear at three consecutive intersections in a commercial district, according to the configuration of the protective capability matrix, warning information issuance is simultaneously initiated at Intersection A, intervention timing is implemented at Intersection B, and regional coordination measures are implemented at Intersection C. Protective actions at all three intersections are coordinated under the guidance of the matrix, effectively preventing the further spread of congestion. The matrix's effectiveness tracking mechanism monitors the effectiveness and synergy of various protective measures in real time. Based on the scenario-adaptive capabilities of the protective capability matrix, the optimal protective configuration for each scenario is automatically switched to when the traffic scenario changes. Through the above-mentioned protection implementation, congestion-predictive traffic control and protection are complete. Leveraging the protection capability matrix, a complete closed-loop control system is implemented, encompassing congestion prediction, risk assessment, timing selection, regional coordination, and protection implementation. Based on varying traffic conditions and congestion risks, the system automatically selects the most appropriate combination of protection strategies, dynamically adjusts protection intensity and resource allocation, and achieves intelligent coordination and synchronized response across multiple intersections. For example, during a complete protection process, the system successfully predicted the risk of congestion on a major arterial road, issued a 20-minute advance warning, initiated diversion measures at the optimal time, and coordinated control at four adjacent intersections. Ultimately, a severe congestion that could have lasted 45 minutes was resolved within 15 minutes, restoring normal traffic flow. This system has established a multi-intersection coordinated traffic control and synchronized protection system with accurate prediction, timely response, effective coordination, and strong adaptability. This system enables proactive prevention and intelligent management of urban traffic congestion, significantly improving the overall efficiency and safety of the road network.

[0081] In order to implement the traffic control and protection method based on congestion prediction corresponding to the above method embodiment, so as to achieve the corresponding functions and technical effects. Figure 2 , Figure 2 The following is a block diagram of a traffic control and protection device 200 based on congestion prediction according to an embodiment of the present application. For ease of illustration, only the parts relevant to this embodiment are shown. The traffic control and protection device 200 based on congestion prediction according to an embodiment of the present application includes:

[0082] The data storage module 201 is used to build a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set;

[0083] an early warning generation module 202 for using the feature vector set to perform pattern learning to identify congestion patterns, constructing a congestion propagation path prediction mechanism based on the congestion patterns, and generating congestion propagation early warning information using the congestion propagation path prediction mechanism;

[0084] The emergency plan formulation module 203 is used to perform risk assessment on the congestion propagation warning information, mark the danger level, and formulate preventive measures to form a protection plan based on the danger level;

[0085] A timing optimization module 204 is configured to convert the protection plan into a control action to mark a potential intervention opportunity, establish a timing dynamic optimization mechanism based on the potential intervention opportunity, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control at the optimal intervention time point;

[0086] The regional coordination module 205 is configured to perform congestion risk transfer analysis on the protection control to mark the risk transfer direction, establish a regional risk redistribution strategy based on the risk transfer direction, generate a multi-region risk balance plan using the regional risk redistribution strategy, and form an overall protection strategy based on the multi-region risk balance plan;

[0087] A resource allocation module 206 is configured to allocate protection resources based on the overall protection strategy and generate a control status;

[0088] The protection implementation module 207 is used to analyze the control status to form a protection capability matrix, use the protection capability matrix to implement protection, and complete congestion prediction traffic control protection.

[0089] The aforementioned congestion prediction-based traffic control and protection device 200 can implement the congestion prediction-based traffic control and protection method of the aforementioned method embodiment. The optional options in the aforementioned method embodiment also apply to this embodiment and will not be described in detail here. The remaining contents of the embodiments of this application can be referenced to the contents of the aforementioned method embodiment and will not be further described in this embodiment.

[0090] like Figure 3 As shown, the third embodiment of the present invention further provides a computer device, including a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302, characterized in that when the processor 302 executes the program, the steps of a traffic control and protection method based on congestion prediction described in the first embodiment of the present invention are implemented.

[0091] The purpose of the above embodiments is to exemplify and deduce the technical solution of the present invention, and to fully describe the technical solution, purpose and effect of the present invention. Its purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosed content of the present invention, and it does not limit the scope of protection of the present invention.

[0092] The above embodiments are not exhaustive and may include many other embodiments not listed above. Any replacements and improvements made without violating the concept of the present invention are within the scope of protection of the present invention.

Claims

1. A traffic control and protection method based on congestion prediction, characterized in that: include: Construct a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set; Using the set of feature vectors to perform pattern learning to identify congestion patterns, constructing a congestion propagation path prediction mechanism based on the congestion patterns, and using the congestion propagation path prediction mechanism to generate congestion propagation warning information; Conduct risk assessment on the congestion propagation warning information to mark the danger level, formulate preventive measures and form a protection plan based on the danger level; Converting the protection plan into a control action to mark a potential intervention opportunity, constructing a dynamic optimization mechanism for the timing based on the potential intervention opportunity, using the dynamic optimization mechanism for the timing to determine the optimal intervention time point, and initiating protection control at the optimal intervention time point; Performing a congestion risk transfer analysis on the protection control to mark the risk transfer direction, establishing a regional risk redistribution strategy based on the risk transfer direction, generating a multi-region risk balance plan using the regional risk redistribution strategy, and forming an overall protection strategy through the multi-region risk balance plan; Based on the overall protection strategy, protection resources are allocated to generate a control status; The control state is analyzed to form a protection capability matrix, including: performing a cross-temporal and spatial effect retrospective analysis on the control state to obtain the contribution of protection factors; constructing a weighted adaptive strategy set based on the contribution of the protection factors; using the weighted adaptive strategy set to form a protection capability matrix, using the protection capability matrix to implement protection, and completing congestion prediction traffic control protection; the cross-temporal and spatial effect retrospective analysis of the control state to obtain the contribution of protection factors includes: performing a cross-temporal and spatial retrospective analysis on the control state to obtain historical execution data; analyzing the impact of each factor based on the historical execution data, and establishing a contribution degree assessment; the each factor includes congestion propagation warning information, the optimal intervention time point, and a multi-region risk balance plan; quantifying the contribution degree assessment to generate a protection factor contribution.

2. The method according to claim 1, characterized in that The congestion propagation path prediction mechanism is constructed based on the congestion rule, including: Analyze the spatial diffusion characteristics of congestion using the congestion law and identify the congestion propagation path; Analyzing the time evolution law based on the congested propagation path to obtain propagation time series characteristics; Establishing propagation prediction parameters based on the propagation time series characteristics and the congested propagation path; generating a prediction node according to the propagation prediction parameter; The prediction nodes are used to construct a congestion propagation path prediction mechanism.

3. The method according to claim 1, characterized in that The dynamic optimization mechanism for finding the optimal timing based on the potential intervention timing is constructed, including: Performing a timing analysis on the potential intervention opportunities to determine an execution order of the opportunities; Analyzing the priority relationship according to the timing execution order to establish the timing priority; Dynamically adjusting the timing priorities to generate an optimization strategy; A timing dynamic optimization mechanism is constructed according to the optimization strategy.

4. The method according to claim 1, wherein The establishing of a regional risk reallocation strategy based on the risk transfer direction includes: Conducting a flow analysis on the risk transfer direction to determine the risk flow distribution; Assess regional carrying capacity based on the risk flow distribution and establish carrying capacity configuration; Performing balancing processing on the carrying capacity configuration to generate a reallocation plan; A regional risk reallocation strategy is constructed based on the reallocation plan.

5. The method according to claim 1, wherein The generation of a control status by allocating protection resources based on the overall protection strategy includes: Based on the overall protection strategy, a protection effect gradient analysis is conducted to obtain the spatial distribution characteristics of the effect; Constructing a gradient transfer tracking mechanism based on the spatial distribution characteristics of the effect; Using the gradient transfer tracking mechanism to adjust the protection strength; Adjusting acquisition resource requirements according to the protection strength; Dynamic resource allocation is performed based on the changes in resource demand to generate a management and control status.

6. The method according to claim 1, characterized in that The step of constructing a weighted adaptive strategy set based on the contribution of the protection elements includes: Using the contribution of the protection elements to identify strategic conflict points, and establish a conflict detection mechanism; Perform scene classification and matching based on the conflict detection mechanism to generate a weight configuration scheme for each scene; A weight adaptation strategy set is constructed according to the scenario-specific weight configuration scheme.

7. A traffic control and protection device based on congestion prediction, characterized in that: include: A data storage module is used to build a historical traffic data storage platform to accumulate basic data, perform feature mining on the basic data to mark congestion features, and establish a feature database based on the congestion features to output a feature vector set; an early warning generation module, configured to use the feature vector set to perform pattern learning to identify congestion patterns, construct a congestion propagation path prediction mechanism based on the congestion patterns, and generate congestion propagation early warning information using the congestion propagation path prediction mechanism; A plan formulation module is used to perform risk assessment and mark the danger level of the congestion propagation warning information, and formulate preventive measures to form a protection plan based on the danger level; A timing optimization module is used to convert the protection plan into a control action to mark a potential intervention opportunity, build a timing dynamic optimization mechanism based on the potential intervention opportunity, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control at the optimal intervention time point; A regional coordination module is configured to perform a congestion risk transfer analysis on the protection control to mark the risk transfer direction, establish a regional risk redistribution strategy based on the risk transfer direction, generate a multi-region risk balance plan using the regional risk redistribution strategy, and form an overall protection strategy through the multi-region risk balance plan; A resource allocation module, configured to allocate protection resources based on the overall protection strategy and generate a control status; A protection implementation module is used to analyze the control state to form a protection capability matrix, including: performing a cross-temporal and spatial effect retrospective analysis on the control state to obtain the contribution of protection factors; constructing a weighted adaptive strategy set based on the contribution of the protection factors; using the weighted adaptive strategy set to form a protection capability matrix, using the protection capability matrix to implement protection and complete congestion prediction traffic control protection; the cross-temporal and spatial effect retrospective analysis of the control state to obtain the contribution of protection factors includes: performing a cross-temporal and spatial retrospective analysis on the control state to obtain historical execution data; analyzing the impact of each factor based on the historical execution data to establish a contribution degree assessment; the various factors include congestion propagation warning information, the optimal intervention time point and a multi-region risk balance plan; quantifying the contribution degree assessment to generate a protection factor contribution degree.

8. A computer device, characterized in that: The method comprises a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method according to any one of claims 1 to 6 when executing the computer program.

Images