Traffic control protection method, device and equipment based on congestion prediction

Abstract

The invention provides a traffic control protection method, device and equipment based on congestion prediction, and aims to accurately identify a congestion rule and predict a propagation path by constructing a feature vector set based on historical data and a congestion propagation path prediction mechanism so as to realize timely release of congestion early warning information. Risk assessment grading protection and optimal intervention opportunity dynamic optimization are adopted, the protection opportunity is accurately mastered, and corresponding protection intensity is matched; a regional risk redistribution strategy and a protection effect gradient analysis technology are introduced, risk transfer control among multiple regions is coordinated, and disordered diffusion of congestion risks is avoided; in combination with cross-space-time effect tracing analysis and a strategy conflict detection mechanism, the actual contribution degree of each protection element is evaluated, and a weight adaptive strategy set and a protection capability matrix are constructed; finally, multiple links such as prediction, evaluation and coordination are fused to form a self-adaptive comprehensive protection system, and active prevention and intelligent management and control of urban traffic congestion are realized.

Description

Technical Field

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

[0002] The problem of modern urban traffic congestion is becoming increasingly severe. The traditional passive response management mode has been difficult to meet the demand for improving traffic efficiency. Active protection control based on prediction has become an important direction for the development of traffic management. Currently, congestion prediction and protection control technologies face many challenges: traffic flow changes are affected by multiple factors such as weather, events, and construction, it is difficult to ensure the accuracy of prediction models, and the congestion formation and evolution laws vary significantly in different regions and time periods, lacking a refined prediction mechanism; the existing analysis methods have high computational complexity and are difficult to meet the timeliness requirements of real-time prediction; it is difficult to grasp the intervention timing and intensity of preventive control measures, 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 lag in warning information transmission affects the timely implementation of protection measures; the quality of historical data is uneven, data missing and outliers affect prediction accuracy, and the generalization ability of prediction models is limited; the protection effect lacks a quantitative evaluation standard and an adaptive optimization mechanism, and it is impossible to achieve continuous improvement of protection strategies.

[0003] Therefore, constructing an intelligent protection control method integrating congestion prediction, risk assessment, timing optimization, and regional coordination has important value for improving the resilience and management level of urban traffic systems. Summary of the Invention

[0004] The present invention provides a traffic control protection method, device and equipment based on congestion prediction, aiming to achieve active prevention and intelligent management and control of urban traffic congestion, integrating key technologies such as congestion prediction, risk assessment, timing optimization, regional coordination, and effect traceability, and performing full-process intelligent control on traffic conditions and congestion risks, realizing congestion early warning, intelligent deployment of protection measures, and multi-region coordinated linkage, forming a traffic congestion protection system with prediction ability, rapid response, effective coordination, and adaptive adjustment.

[0005] In the first aspect of the present invention, a traffic control protection method based on congestion prediction is proposed, including the following steps: 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 set of feature vectors; Use the set of feature vectors for pattern learning to identify congestion rules, construct a congestion propagation path prediction mechanism based on the congestion rules, and use the congestion propagation path prediction mechanism to generate congestion propagation warning information; Implement risk assessment for the congestion propagation warning information to mark the danger level, and formulate preventive measures based on the danger level to form a protection plan; Convert the protection plan into control actions to mark potential intervention times, build a timing dynamic optimization mechanism based on the potential intervention times, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control through the optimal intervention time point; Conduct congestion risk transfer analysis for the protection control to mark the risk transfer direction, establish a regional risk reallocation strategy based on the risk transfer direction, adopt the regional risk reallocation strategy to generate a multi-regional risk balance plan, and form an overall protection strategy through the multi-regional risk balance plan; Conduct protection resource allocation based on the overall protection strategy to generate a management and control status; Analyze the management and control status to form a protection capability matrix, and use the protection capability matrix to implement protection to complete congestion prediction traffic control protection.

[0006] The second aspect of the present invention proposes a traffic control protection device based on congestion prediction, including: A data storage module, used to build a historical traffic data storage platform to accumulate basic data, conduct 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, used to perform pattern learning using the feature vector set to identify congestion patterns, build a congestion propagation path prediction mechanism based on the congestion patterns, and generate congestion propagation warning information using the congestion propagation path prediction mechanism; A plan formulation module, used to implement risk assessment for the congestion propagation warning information to mark the danger level, and formulate preventive measures based on the danger level to form a protection plan; A timing optimization module, used to convert the protection plan into control actions to mark potential intervention times, build a timing dynamic optimization mechanism based on the potential intervention times, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control through the optimal intervention time point; A regional coordination module, used to conduct congestion risk transfer analysis for the protection control to mark the risk transfer direction, establish a regional risk reallocation strategy based on the risk transfer direction, adopt the regional risk reallocation strategy to generate a multi-regional risk balance plan, and form an overall protection strategy through the multi-regional risk balance plan; A resource allocation module, used to conduct protection resource allocation based on the overall protection strategy to generate a management and control status; A protection implementation module, used to analyze the management and control status to form a protection capability matrix, and use the protection capability matrix to implement protection to complete congestion prediction traffic control protection.

[0007] A third aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of a traffic control and protection method based on congestion prediction disclosed in the first aspect.

[0008] The beneficial effects of the present invention are reflected in the following aspects: 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 congestion occurrence pattern and predict the propagation path, realizing the timely release of congestion warning information; through risk assessment to mark the danger level and formulate a hierarchical protection plan, a precise matching mechanism between risks and protection measures is established, and corresponding protection intensities and measure combinations are automatically selected according to different danger levels, improving the accuracy of congestion prediction, the timeliness of early warning, and the pertinence of protection.

[0009] 2. Through the dynamic optimization of the best intervention timing, the multi-region risk balance scheme, and the gradient analysis of protection effects, an intelligent protection mechanism coordinated in three dimensions of timing-region-intensity is established, which can initiate protection control at the best timing, avoid the disorderly transfer of congestion risks between regions through the regional risk reallocation strategy, and dynamically adjust the protection intensity according to the gradient transfer characteristics of protection effects, realizing the precise grasp of protection timing and the coordinated linkage control between regions.

[0010] 3. Through the elastic reallocation of protection resources, the retrospective analysis of cross-time and space effects, and the strategy conflict detection mechanism, it is possible to dynamically optimize resource allocation according to the adjustment of protection intensity, accurately evaluate the actual contribution degrees of various protection elements, construct a weight self-adaptive strategy set and a protection ability matrix, realize the full-process intelligent control from resource allocation to protection implementation, and establish an intelligent traffic protection system with the capabilities of self-adaptive allocation, scenario adaptation, and continuous optimization.

[0011] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings herein show specific examples of the technical solutions of the present invention and form a part of the specification together with the specific implementation manners, and are used to explain the technical solutions, principles, and effects of the present invention.

[0013] Unless otherwise specifically stated or defined, in different drawings, the same reference numerals represent the same or similar technical features, and for the same or similar technical features, different reference numerals may also be used for representation.

[0014] Figure 1It is a schematic flowchart of a traffic control and protection method based on congestion prediction according to the present invention.

[0015] Figure 2 It is a structural block diagram of a traffic control and protection device based on congestion prediction according to the present invention.

[0016] Figure 3 It is a schematic structural diagram of a computer device according to the present invention. Detailed implementation manners

[0017] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also 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 unnecessary details from interfering with the description of the present application.

[0018] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0019] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0020] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if detecting [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detecting [the described condition or event]", or "in response to detecting [the described condition or event]" according to the context.

[0021] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0022] Reference to "an embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in some other embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0023] The technical solutions of the embodiments of this application will be introduced below.

[0024] As Figure 1 shown, an embodiment of the present invention provides a traffic control and protection method based on congestion prediction, including the following steps S110-step S170: 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 set of feature vectors.

[0025] Specifically, build a historical traffic data storage platform to accumulate basic data. Establish data collection and storage infrastructure in the multi-intersection coordinated control target area. Deploy detection devices at each important intersection within the coordinated control range, including high-definition video detectors, electromagnetic induction coils, microwave radar flow meters, and floating car data receiving devices, to form a data perception network. The detection devices at each intersection collect vehicle passing data in real time, including parameters such as the instantaneous flow rate, average driving speed, headway, queue length, vehicle occupancy rate, and vehicle type classification of each lane. At the same time, collect signal control data and record signal timing information such as the timing plan, phase switching moment, green light duration, and red light duration of the traffic lights. Establish an environmental data collection module to monitor environmental factors affecting traffic operation, such as weather conditions, visibility, and road surface conditions. Design a three-tier data storage architecture. The bottom layer is for real-time data storage, saving the original detection data at a 30-second collection interval. The middle layer is for aggregated data storage, statistically aggregating the original data according to time granularities such as 5 minutes, 15 minutes, 1 hour, and 1 day, and calculating statistical indicators such as average flow rate, peak flow rate, standard deviation, and coefficient of variation. The upper layer is for historical data archiving storage, saving at least 3 years of complete traffic operation records to support long-term traffic pattern analysis. Establish a data quality control mechanism to identify abnormal data through methods such as setting reasonable numerical range thresholds and time continuity checks. For data missing problems, use methods such as linear interpolation and historical mean to complete the data. Unify the data formats of different intersections and different device 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 fast data extraction according to multi-dimensional conditions such as time range, spatial area, and data type. Through the long-term stable operation of this data platform, historical traffic basic data covering the multi-intersection coordinated area, with sufficient time span and reliable data quality, has been accumulated.

[0026] Mine the features of the accumulated basic data to mark congestion features. Establish a quantitative recognition standard for the congestion state. When the vehicle occupancy rate in any import direction of an intersection exceeds 85%, and the average vehicle speed is lower than 15 kilometers per hour, and this state lasts for more than 5 minutes, it is marked as the congestion state. Use the basic data to mine the congestion time features, analyze the occurrence frequency of congestion, the duration distribution, the dissipation time pattern, and the periodic change pattern. Identify the peak congestion periods through statistical analysis, such as the morning peak from 7:00 to 9:00 and the evening peak from 17:00 to 19:00 on weekdays. Conduct congestion spatial feature analysis based on the basic data, study the propagation law of congestion between adjacent intersections, and calculate the directionality, propagation speed, and influence range of congestion diffusion. For example, congestion on the main road usually propagates upstream at a speed of 150-200 meters per minute, while intersection congestion may spread in multiple directions simultaneously. Use the basic data to identify the precursor features of congestion, and analyze the change pattern of traffic parameters within 10-15 minutes before the formation of congestion, including early signs such as a sudden increase in traffic flow, a gradual decrease in vehicle speed, and a continuous increase in occupancy rate. Establish a grading standard for the severity of congestion. According to indicators such as the duration of congestion, the number of affected vehicles, the degree of delay, and the diffusion range, congestion is divided into three levels: mild, moderate, and severe. Analyze the impact of external factors on congestion through basic data, and study the influence law of factors such as weather conditions, special events, and holidays on the congestion pattern. For example, the duration of congestion usually extends by 20-30% under rainy conditions. Conduct research on congestion recovery features using the basic data, analyze the spatio-temporal order of congestion dissipation, the recovery speed, and the key factors affecting the recovery effect. Mine the correlation law of congestion based on the basic data, and identify the causal relationship and mutual influence pattern between congestions at different intersections. Adopt machine learning and data mining algorithms, including clustering analysis, association rule mining, time series analysis, etc., to automatically identify implicit congestion feature patterns and complex correlation laws. Through this series of feature mining and analysis processing, the systematic marking of congestion-related features in the basic data is completed.

[0027] Build a feature database based on the marked congestion features and output a set of feature vectors. Structurally organize and numerically represent the marked congestion features to construct a feature database that supports efficient querying and similarity analysis. Perform vector encoding processing on the time dimension information in the congestion features, convert the specific moment when congestion occurs into hour encoding and minute encoding, convert the duration of congestion into a minute value, and convert the congestion dissipation time into a relative time difference. Use periodic encoding technology to process the periodic features of time, and use sine and cosine functions to convert periodic time information such as hours, weeks, and months into continuous numerical vectors. Coordinate the spatial dimension information in the congestion features, convert the location where congestion occurs into a standardized two-dimensional coordinate, convert the congestion impact range into a radius value, and convert the congestion propagation direction into an angle vector representation. Numerically classify and encode the severity of congestion, assign a value of 1 for mild congestion, 2 for moderate congestion, and 3 for severe congestion, and perform refined continuous numerical encoding according to the specific delay duration and the number of affected vehicles. Classify and encode the causes and influencing factors of congestion, including one-hot encoding representations of different cause types such as traffic demand overload, traffic accidents, signal failures, and bad weather. Establish a dimension standardization processing mechanism for feature vectors, and use methods such as Z-score standardization and maximum-minimum normalization to ensure a reasonable weight distribution of different types of features in the vector space. Design the storage structure and indexing mechanism of feature vectors, and use multi-dimensional indexing technology to support fast retrieval, pattern matching, and clustering analysis operations based on similarity. Construct a dynamic update mechanism for feature vectors, which can automatically expand the dimension of the vector space when a new type of congestion feature is identified. Design vector compression and storage optimization algorithms, and use sparse vector representation and other technologies to reduce the storage space occupancy while ensuring the accuracy of feature representation. Construct a similarity measurement method between vectors to support vector similarity calculation based on various measurement methods such as Euclidean distance and cosine similarity. Finally, a set of feature vectors containing complete congestion feature information and unified structural specifications is established.

[0028] In step S120, use the set of feature vectors to perform pattern learning to identify congestion patterns, construct a congestion propagation path prediction mechanism based on the congestion patterns, and generate congestion propagation warning information using the congestion propagation path prediction mechanism.

[0029] Specifically, a feature vector set is used for pattern learning to identify congestion patterns. Deep learning and machine learning algorithms are employed to conduct pattern mining and rule identification on the feature vectors. The feature vector set is input into clustering algorithms, and methods such as K-means clustering, hierarchical clustering, and density clustering are used to identify similar congestion patterns, and the clustering characteristics of congestion in terms of time, space, and severity are discovered. The feature vector set is used to train recurrent neural networks and long short-term memory networks to learn the time series patterns of congestion occurrence and identify the periodic patterns and trend changes of congestion occurrence. An association rule mining model is established based on the feature vector set to discover the association relationships between different congestion characteristics. For example, when a certain intersection experiences severe congestion during the morning rush hour on weekdays, the probability of moderate congestion occurring at adjacent intersections within 15 minutes is 78%. Causal relationship analysis is carried out through the feature vector set to identify the main causes and triggering conditions leading to congestion, and a causal chain from traffic demand, weather conditions, event occurrence to congestion formation is established. The feature vector set is used to train support vector machines and random forest models to learn the classification rules of congestion severity and establish a mapping relationship from traffic parameters to congestion levels. Spatiotemporal association analysis is performed based on the feature vector set to identify the spatial propagation pattern and temporal evolution law of congestion, and the directional and attenuation characteristics of congestion diffusion are discovered. A congestion recovery rule model is established through the feature vector set to analyze the time pattern 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. Anomaly detection is carried out using the feature vector set to identify unconventional congestion patterns and sudden congestion characteristics, and an identification criterion for abnormal congestion is established. Through the deep learning and pattern mining of the feature vector set, the congestion patterns reflecting the entire process of congestion occurrence, development, propagation, and recovery are identified.

[0030] In some embodiments, the congestion propagation path prediction mechanism constructed based on the congestion pattern includes: analyzing the spatial diffusion characteristics of congestion using the congestion pattern to identify the congestion propagation path; analyzing the temporal evolution law based on the congestion propagation path to obtain the propagation time series characteristics; establishing propagation prediction parameters according to the propagation time series characteristics and the congestion propagation path; generating prediction nodes according to the propagation prediction parameters; and constructing a congestion propagation path prediction mechanism using the prediction nodes.

[0031] First, analyze the spatial diffusion characteristics of congestion using congestion rules to identify congestion propagation paths. Through the spatial propagation patterns in congestion rules, study the diffusion directionality of congestion from the source intersection to adjacent intersections, identify the main and secondary paths of congestion propagation, and determine the specific congestion propagation paths that congestion may spread along the road network. Next, analyze the time evolution rules based on the congestion propagation paths to obtain propagation timing characteristics. For the identified congestion propagation paths, analyze the time evolution rules of congestion along each path. Calculate the time distribution of congestion reaching key nodes from the starting point along each congestion propagation path. For example, the congestion propagation speed on the main road propagation path is 150 meters per minute, and on the secondary road propagation path is 100 meters per minute. Thus, obtain the propagation timing characteristics corresponding to each congestion propagation path, including the propagation start time, peak arrival time, and dissipation time. Furthermore, conduct a comprehensive analysis of the propagation timing characteristics and congestion propagation paths to establish propagation prediction parameters. By combining the time information in the propagation timing characteristics with the spatial information of the congestion propagation paths, set key prediction parameters such as propagation speed coefficient, propagation attenuation coefficient, and propagation probability weight. For different combinations of congestion propagation paths and propagation timing characteristics, determine the corresponding propagation prediction parameter configurations. Then, generate prediction nodes based on the propagation prediction parameters. Generate prediction nodes at key intersection locations. For example, generate prediction node B-Node at intersection B where the main road in the city center intersects with the ring road, configure the congestion arrival time to be 12 minutes after the source congestion occurs, and the congestion intensity to be 0.8 times that of the source; generate prediction node C-Node at intersection C in the commercial area, configure the arrival time to be 8 minutes, and the intensity to be 0.6 times that of the source. Each prediction node undertakes the congestion propagation prediction task for a specific area. Finally, use the prediction nodes to construct a congestion propagation path prediction mechanism. Organize and connect the prediction nodes according to the propagation paths, and establish an information transfer and prediction coordination mechanism between the nodes. When congestion occurs at the source intersection, B-Node predicts that congestion with an intensity of 0.8 times will occur at intersection B after 12 minutes, and C-Node predicts that congestion with an intensity of 0.6 times will occur at intersection C after 8 minutes, forming a congestion propagation path prediction mechanism covering multiple paths.

[0032] Generate congestion propagation warning information by using the congestion propagation path prediction mechanism. Calculate the propagation paths based on the current congestion situation using the congestion propagation path prediction mechanism, identify the main and secondary directions in which congestion may spread, analyze the priorities of different propagation paths, and rank the paths according to propagation probability, arrival time, and impact degree. Calculate the time characteristics of each propagation path, including key time nodes such as propagation start time, arrival time, peak time, and dissipation time, analyze the spatial characteristics of the propagation path, and calculate spatial parameters such as influence range, propagation distance, number of covered intersections, and number of affected lanes. Conduct propagation intensity analysis, calculate the intensity change and attenuation law of congestion on different paths, predict the congestion severity at each intersection, conduct path convergence point analysis, identify the convergence points and overlapping areas of multiple propagation paths, and evaluate the superposition effect of multiple congestions. Identify bottleneck sections, analyze the key nodes and weak links on the propagation path, determine the control points of congestion propagation, conduct alternative path analysis, and when the main propagation path is blocked, predict the alternative diffusion direction and path transfer law of congestion. Establish a risk level assessment for the propagation path, and classify the propagation path into high-risk, medium-risk, and low-risk levels according to propagation speed, influence range, and severity. Based on the results of the diffusion path analysis, generate classified congestion propagation warning information, including warning level, warning time, warning area, and warning content. Develop differentiated warning strategies, issue red warnings for high-risk propagation paths, orange warnings for medium-risk paths, and yellow warnings for low-risk paths, and design a time-sequenced warning release mechanism to issue early warnings 30 minutes before the start of congestion propagation and update the warning information every 10 minutes during the propagation 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 the intensity attenuating to 0.8 times, and at the same time spread to intersection C with a propagation time of 8 minutes and the intensity attenuating to 0.6 times. Accordingly, an orange warning is issued, suggesting that vehicles detour around the outer ring road in advance. Generate an accurate warning area range, clarify the specific roads, intersections, and lanes affected, generate dynamic warning content, including practical information such as expected congestion level, duration, influence range, and recommended detour routes. Establish a multi-channel release mechanism for warning information, timely release warning information through various channels such as traffic radio, variable message signs, mobile applications, and navigation software, design a feedback and correction mechanism for warning information, and adjust the warning content and warning level in a timely manner according to the actual congestion development situation, and finally form timely, accurate, detailed, and comprehensive congestion propagation warning information.

[0033] In step S130, implement a risk assessment for the congestion propagation warning information to mark the danger level, and formulate preventive measures based on the danger level to form a protection plan.

[0034] Specifically, risk assessment is implemented for congestion propagation warning information to mark the danger level. According to the warning level of the congestion propagation warning information, extremely high-risk assessment is carried out for the red warning area, high-risk assessment for the orange warning area, and medium-risk assessment for the yellow warning area. Based on the warning time of the congestion propagation warning information, it is analyzed that the 30 minutes before the start of propagation is the emergency risk period, the 10 minutes before the start is the extremely urgent risk period, and the period during propagation is the continuous risk period. Using the warning area range of the congestion propagation warning information, the risk degree of specific affected intersections is evaluated. Those involving main road intersections are marked as first-level risk points, those involving secondary road intersections are marked as second-level risk points, and those involving branch road intersections are marked as third-level risk points. According to the warning content of the congestion propagation warning information, areas with an expected severe congestion level are marked as high danger level, areas with an expected moderate congestion level are marked as medium danger level, and areas with an expected mild congestion level are marked as low danger level. Based on the prediction of the duration of the congestion propagation warning information, those with a duration exceeding 1 hour are marked as long-term danger, those with a duration of 30 minutes to 1 hour are marked as medium-term danger, and those with a duration of less than 30 minutes are marked as short-term danger. Using the impact range data of the congestion propagation warning information, if the number of affected vehicles exceeds 1000, it is extremely high danger; if it is 500 - 1000, it is high danger; if it is 200 - 500, it is medium danger; and if it is less than 200, it is low danger. Considering factors such as warning level, time urgency, spatial impact, and congestion level, the final danger level is marked for each warning area to form the danger level marking result.

[0035] Formulate preventive measures according to the risk level to form a protection plan. Design a first-level protection level for extremely high-risk areas, implement comprehensive traffic control, prohibit non-essential vehicles from entering, dispatch the highest-level police force to command on-site, and activate all backup signal control plans. Design a second-level protection level for high-risk areas, deploy additional traffic police at key intersections, adjust signal timing to increase the green light time for the main directions, and activate variable lanes to increase traffic capacity. Design a third-level protection level for medium-risk areas, optimize the coordinated control of traffic lights in this area, start intelligent guidance to issue detour suggestions, and strengthen traffic monitoring. Design a fourth-level protection level for low-risk areas, maintain normal monitoring, prepare emergency resources, and promptly release traffic information. Utilize the time characteristics of the risk level to formulate the implementation sequence of preventive measures, and immediately activate protection measures for areas during emergency risk periods. Based on the spatial distribution of the risk level, determine the key deployment locations of preventive measures, deploy key police forces and equipment at first-level risk points, and implement key monitoring and routine management at second-level and third-level risk points respectively. Allocate corresponding resource investment intensities according to the risk level, invest all available resources in extremely high-risk areas, 70% of resources in high-risk areas, 40% of resources in medium-risk areas, and 20% of resources in low-risk areas. Based on the above hierarchical protection measures formulated for different risk levels, organize and integrate these preventive measures to construct a complete protection plan framework and implementation system, and establish three levels: the overall plan, the special plan, and the on-site disposal plan. Define the regional division and responsibility assignment of the protection plan, divide the protection area into the core control area, the key monitoring area, and the general concern area, and clarify the protection focus and control requirements for each area. Design the activation process and execution sequence of the protection plan, establish a decision-making mechanism for plan activation, an information transmission process, and a measure implementation order. Develop a resource guarantee plan for the protection plan, including the organization and deployment of personnel teams, the deployment and maintenance of equipment and facilities, establish an organizational command system for the protection plan, and set up a protection command center. Construct a monitoring and evaluation mechanism for the protection plan, establish a real-time monitoring network, formulate effect evaluation indicators and a dynamic optimization mechanism, and finally form a comprehensive protection plan covering the whole process and with strong operability.

[0036] In step S140, convert the protection plan into control actions to mark potential intervention times, build an opportunity dynamic optimization mechanism based on the potential intervention times, use the opportunity dynamic optimization mechanism to determine the best intervention time point, and activate the protection control through the best intervention time point.

[0037] Specifically, convert the protection plan into control actions to mark potential intervention times. Based on the protection plan, convert the area traffic control in the first-level protection into specific control actions such as intersection closure, lane restriction, and detour guidance, and convert the optimization adjustment of traffic lights into operation instructions such as modification of timing parameters, phase adjustment, and coordinated control. Analyze the earliest executable time, the latest mandatory execution time, and the optimal execution time window of each control action using the protection plan, and establish the time constraint conditions for the control actions. Identify the spatial dependence relationship and the execution sequence of control actions according to the protection plan. For example, it is necessary to implement the diversion measure at the upstream intersection first and then adjust the signal timing at the downstream intersection. Analyze the resource requirements of control actions and the available resource constraints based on the protection plan, and identify the resource conflict points and resource bottleneck links. Analyze the mutual influence and synergistic effect between control actions using the protection plan, and identify the action combinations that need to be executed synchronously and the action pairs that must avoid conflicts. Establish the expected effect and execution conditions of control actions according to the protection plan, and analyze the cost-benefit ratio and risk level of action execution. Identify the flexibility and adjustability of control actions through the protection plan, and mark the action types that can be adjusted according to the actual situation. Establish a classification standard for intervention times, and divide the potential intervention times 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 times, including evaluation dimensions such as intervention urgency, intervention effectiveness, resource availability, and coordination complexity. Through this series of action decompositions and timing analyses, mark the potential intervention times corresponding to the protection plan.

[0038] In some embodiments, constructing a timing dynamic optimization mechanism based on the potential intervention times includes: performing a timing analysis on the potential intervention times to determine the timing execution sequence; analyzing the priority relationship according to the timing execution sequence to establish a timing priority; performing a dynamic adjustment process on the timing priority to generate an optimization strategy; and constructing a timing dynamic optimization mechanism according to the optimization strategy.

[0039] First, conduct a timing analysis of potential intervention opportunities to determine the execution order of the opportunities. By analyzing the time characteristics of potential intervention opportunities, identify the earliest executable time, the latest mandatory execution time, and the optimal execution time window for each intervention measure. Considering the time-dependent relationships between intervention measures, arrange the sequential execution order of each intervention opportunity. For example, the diversion measure at the upstream intersection must be initiated within 5 minutes after the congestion warning is issued, and the signal adjustment at the downstream intersection needs to be executed 10 minutes after the diversion measure is initiated, to determine the execution order of each intervention measure's opportunity. Next, analyze the priority relationship based on the opportunity execution order to establish opportunity priorities. For the determined opportunity execution order, analyze the importance and urgency of different intervention opportunities. By evaluating the impact scope, resource requirements, and time window constraints of the intervention effects, assign priority weights to each intervention opportunity. For example, the upstream diversion measure is set as the first-level priority due to its preventive effect, the downstream signal adjustment is set as the second-level priority, and the emergency lane opening is set as the third-level priority, to establish opportunity priorities. Furthermore, perform dynamic adjustment processing on the opportunity priorities to generate an optimization strategy. According to the established opportunity priorities, combined with the real-time traffic conditions and available resources, dynamically adjust the priorities. When the traffic congestion level increases, raise the priority of responsive interventions; when resources are tight, lower the priority of resource-intensive interventions. For example, during the morning rush hour, raise the signal adjustment measure from the second level to the first level priority, to generate an optimization strategy suitable for different scenarios. Finally, use the optimization strategy to construct a dynamic opportunity optimization mechanism. Integrate the optimization strategy into a unified opportunity selection mechanism, and establish a workflow for strategy matching, opportunity selection, and dynamic adjustment. When the intervention demand is triggered, the mechanism matches the corresponding strategy according to the current traffic conditions, selects the optimal combination of intervention opportunities, and dynamically adjusts the subsequent opportunities according to the actual effects during the execution process, to form a dynamic opportunity optimization mechanism.

[0040] The optimal intervention time point is determined by using the opportunity dynamic optimization mechanism. Based on the opportunity dynamic optimization mechanism, the current congestion propagation situation is analyzed in real time. Information such as current traffic state parameters, congestion development trend, and available resource status is input, and the optimization calculation process is started. The opportunity dynamic optimization mechanism is used to perform multi-objective optimization calculations. Under the premise of meeting various constraint conditions, the time point combination that maximizes the intervention effect is searched. Through multiple rounds of iterative calculations using the opportunity dynamic optimization mechanism, the intervention time is continuously adjusted and optimized until the convergence condition is met or the preset calculation time limit is reached. The opportunity dynamic optimization mechanism is used to select corresponding optimization strategies and parameter settings according to the current specific situation. For example, a rapid response strategy is adopted during the morning rush hour, and an accurate optimization strategy is adopted during the off-peak period. The opportunity dynamic optimization mechanism is used to identify and resolve the timing conflicts between different intervention actions to ensure the executability of the finally determined time point combination. The opportunity dynamic optimization mechanism is used to evaluate the sensitivity of the determined optimal time point to changes in external conditions to ensure the robustness of the time point selection. Through the opportunity dynamic optimization mechanism, the execution effect and possible subsequent impacts of the optimal intervention time point are analyzed to evaluate the rationality of the intervention decision. The opportunity dynamic optimization mechanism is used to compare multiple scenarios, generate alternative intervention time point plans, and provide decision-makers with a choice space and risk assessment. A confidence evaluation of the optimal time point is established. According to the convergence situation of the optimization process, the stability of the solution, and the historical verification results, a credibility index is provided for the determined time point. A dynamic adjustment mechanism for the time point is designed. When the actual situation deviates from the expectation, the optimal intervention time point is recalculated and adjusted in a timely manner. Through this series of optimization calculations and scenario comparisons, the scientifically optimized optimal intervention time point is obtained.

[0041] Initiate protection control at the optimal intervention time point. Develop a detailed implementation plan for protection control according to the optimal intervention time point, specifying the specific execution time, execution department, execution method, and execution standard for each control action. Establish a protection control initiation mechanism using the optimal intervention time point, setting automatic trigger conditions and manual confirmation procedures to ensure the accurate initiation of corresponding protection measures at the optimal time. Organize the allocation of protection control resources based on the optimal intervention time point, arranging personnel in place, equipment ready, and information channels unblocked in advance to ensure the high-quality execution of protection control on time. Design a monitoring mechanism for the implementation of protection control based on the optimal intervention time point, tracking the implementation of various control measures in real time and promptly detecting implementation deviations and problems. Establish an evaluation mechanism for the effectiveness of protection control using the optimal intervention time point, immediately conducting effectiveness monitoring after the implementation of control measures to evaluate the degree of agreement between the actual control effect and the expected effect. Build a dynamic adjustment mechanism for protection control based on the optimal intervention time point. When it is found that the control effect is not ideal or new situation changes occur, promptly adjust the control intensity, expand the control scope, or initiate a backup control plan. Design an information feedback mechanism for protection control based on the optimal intervention time point, promptly collecting and analyzing various information during the control execution process. Establish a coordination and command mechanism for protection control using the optimal intervention time point, uniformly dispatching the control actions of each department to avoid duplicate control and mutual interference. Build a quality assurance mechanism for protection control based on the optimal intervention time point, establishing a standardized operation process and quality inspection procedures for control actions. Design an emergency response mechanism for protection control. When emergencies occur during the control execution process, be able to quickly initiate emergency plans and take remedial measures. Ultimately, efficient protection control based on scientific timing selection is achieved.

[0042] Step S150: Conduct congestion risk transfer analysis for protection control, mark the risk transfer direction, establish a regional risk reallocation strategy based on the risk transfer direction, generate a multi-region risk balance plan using the regional risk reallocation strategy, and form an overall protection strategy through the multi-region risk balance plan.

[0043] Specifically, congestion risk transfer analysis is carried out on protection control to mark the risk transfer direction. Based on the intersection closure and lane restriction measures in protection control, analyze the guiding and transfer effects of these control actions on traffic flow, and calculate the transfer paths and transfer volumes of the restricted vehicle flows. Utilize the signal timing adjustment measures in protection control to analyze the directional influence of signal optimization on traffic flows in different directions, and identify the directions with passing advantages and the relatively restricted directions. According to the detour guidance measures in protection control, analyze the carrying capacity and congestion risk tolerance level of the detour routes, and evaluate the impact intensity of the detour traffic on the alternative roads. Based on the spatial coverage of protection control, analyze the change in risk distribution between the protected area and the non-protected area, and calculate the transfer volume and transfer speed of risk from the protected area to the surrounding areas. Utilize the time implementation characteristics of protection control to analyze the difference in the impact of protection measures in different time periods on the risk transfer mode, and identify the time window and peak period of risk transfer. According to the coordinated command arrangement of protection control, analyze the impact of multi-intersection joint control on the redistribution of risks between regions, and calculate the risk concentration points and risk release points generated by the joint control. Establish a quantitative analysis model for risk transfer, and calculate the direction angle, transfer distance, transfer intensity, and attenuation law of risk transfer. Design a marking method for the risk transfer direction, and use the vector representation method to mark the main transfer direction, secondary transfer direction, and transfer weight allocation of each risk source. Through this series of transfer analyses and direction identifications, mark the risk transfer direction under the action of protection control.

[0044] In some embodiments, establishing a regional risk redistribution strategy based on the risk transfer direction includes: conducting a flow direction analysis on the risk transfer direction to determine the risk flow distribution; evaluating the regional carrying capacity according to the risk flow distribution and establishing a carrying capacity configuration; performing a balancing process on the carrying capacity configuration to generate a redistribution plan; and constructing a regional risk redistribution strategy according to the redistribution plan.

[0045] First, conduct a flow analysis of the risk transfer direction to determine the risk flow distribution. By analyzing the spatial characteristics and propagation paths of the risk transfer direction, identify the flow rules and final distribution states of risks among different regions. Analyze the transfer patterns of risks from the source region to the surrounding regions, and calculate the risk input and output amounts of each region. For example, when traffic control is implemented in area A in the city center, 30% of the congestion risk is transferred to area B in the east, 25% to area C in the west, and 20% to area D in the south, to determine the risk flow distribution among regions. Subsequently, based on the risk flow distribution, evaluate the regional carrying capacity and establish a carrying capacity configuration. For the determined risk flow distribution, analyze the risk tolerance of each region. Considering factors such as road capacity, traffic control ability, and emergency response ability, evaluate the upper limit of risk that each region can bear. For example, area B has a main road with 4 lanes and a perfect signal control system, and the risk carrying upper limit is set at 1000 vehicle trips per hour; area C is a secondary road with 2 lanes, and the carrying upper limit is set at 600 vehicle trips per hour. Establish a carrying capacity configuration that reflects the risk tolerance of each region. On this basis, perform a balancing process on the carrying capacity configuration to generate a reallocation plan. According to the established carrying capacity configuration, combined with the risk flow distribution, conduct risk balance adjustment among regions. When the risk received by a certain region exceeds its carrying capacity, reallocate some of the risks to regions with surplus carrying capacity. For example, when the risk received by area B reaches 950 vehicle trips per hour and is close to the carrying upper limit, reallocate 200 vehicle trips per hour of the risk to area E with surplus carrying capacity to generate a reallocation plan. Through the above steps, use the reallocation plan to construct a regional risk reallocation strategy. Convert the reallocation plan into specific regional control guidance, and automatically adjust the control measures of each region when risk transfer occurs. For example, when it is detected that risks are 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, and at the same time moderately relaxes the control intensity in area A to form a regional risk reallocation strategy.

[0046] Adopt the regional risk reallocation strategy to generate a multi-regional risk balance plan. Use the regional risk reallocation strategy to comprehensively analyze the current risk distribution among regions, identify high-risk regions with overly concentrated risks and low-risk regions with relatively lower risks. Based on the regional risk reallocation strategy, formulate specific risk adjustment measures, and achieve the orderly transfer and balanced distribution of risks among regions through means such as traffic flow guidance, signal coordination optimization, and temporary control settings. Use the regional risk reallocation strategy to design a multi-level balance plan framework, establish a municipal-level balance plan to overall coordinate the city's risk distribution, a district-level balance plan to coordinate the risks within the region, and a road-section-level balance plan to handle local risk adjustment. According to the regional risk reallocation strategy, formulate the timing arrangement for risk balance, prioritize the release of risks in high-risk regions, gradually guide the risks to transfer to regions with stronger carrying capacities, and ultimately achieve global risk balance. For example, when a severe congestion risk occurs in the city center, first open the outer ring expressway to increase the traffic capacity, then guide 30% of the transit traffic to transfer to the outer ring, and at the same time add temporary signal control on the secondary roads to divert 20% of the local traffic, finally reducing the risk level in the city center from extremely high danger to medium danger. Based on the regional risk reallocation strategy, establish the resource allocation plan for the balance plan, clarify the quantity and configuration timing of resources such as manpower, equipment, and technology required for each region. Use the regional risk reallocation strategy to design the execution monitoring mechanism for the balance plan, and real-time track the actual effect of risk transfer and the change of regional risk levels. According to the regional risk reallocation strategy, establish the effect evaluation system for the balance plan, and set key indicators such as regional risk balance degree, transfer success rate, and control efficiency. Based on the regional risk reallocation strategy, construct the dynamic optimization mechanism for the balance plan. When it is monitored that the risks in some regions re-aggregate, timely adjust the balance measures and re-optimize the plan configuration. Through this series of plan formulation and implementation arrangements, a risk balance plan covering multiple regions and coordinated and unified is generated.

[0047] Form an overall protection strategy through a multi-region risk balancing plan. Integrate the local protection measures in each region into an overall protection strategy framework for the whole city according to the multi-region risk balancing plan. Use the multi-region risk balancing plan to establish a unified command system for the protection strategy, set up a municipal protection command center as the highest decision-making level, district-level protection sub-centers as the execution and coordination level, and the intersection site as the operation and implementation level, forming a three-level linkage command structure. Based on the multi-region risk balancing plan, formulate a resource overall planning plan for the protection strategy, uniformly allocate protection resources such as the traffic police force, signal control equipment, and information release channels in the whole city, and achieve the optimal allocation and efficient utilization of resources. Design a coordinated linkage mechanism for the protection strategy according to the multi-region risk balancing plan, establish a workflow for information sharing, decision-making consultation, and action synchronization among regions, and ensure the coordination of protection actions in each region. For example, when the Second-level Protection Response is activated in Dongcheng District, it automatically notifies the adjacent Xicheng District and Nancheng District to make preparations for the Third-level Protection, and at the same time coordinates the outer ring area to increase traffic capacity to undertake the diverted traffic. Use the multi-region risk balancing plan to construct a comprehensive evaluation system for the protection strategy, and evaluate the overall protection effect from dimensions such as the traffic efficiency of the whole city, the regional risk level, and the resource utilization efficiency. Based on the multi-region risk balancing plan, establish a dynamic adjustment mechanism for the protection strategy, and according to the changes in the traffic situation of the whole city and the evolution of regional risks, timely adjust the key directions and implementation intensities of the overall protection strategy. Formulate a hierarchical response mechanism for the protection strategy according to the multi-region risk balancing plan, and activate the corresponding level of the overall protection strategy according to the congestion risk level of the whole city. Finally, an overall protection strategy that integrates the overall situation, is coordinated and orderly, and dynamically optimized is established.

[0048] Step S160, perform protection resource allocation based on the overall protection strategy to generate a control state.

[0049] Specifically, after the overall protection strategy is determined, it is necessary to transform the strategy into specific resource allocation and control measures. Perform protection resource allocation based on the overall protection strategy to generate a control state.

[0050] In some embodiments, the performing protection resource allocation based on the overall protection strategy to generate a control state includes: performing a gradient analysis of the protection effect based on the overall protection strategy to obtain the spatial distribution characteristics of the effect; constructing a gradient transfer tracking mechanism based on the spatial distribution characteristics of the effect; adjusting the protection intensity by using the gradient transfer tracking mechanism; obtaining the change in resource requirements according to the adjusted protection intensity; and performing dynamic resource allocation based on the change in resource requirements to generate a control state.

[0051] Conduct a gradient analysis of the protection effect based on the overall protection strategy to obtain the spatial distribution characteristics of the effect. Conduct a spatial differentiation analysis and gradient feature identification based on the predicted effect after the implementation of the overall protection strategy. Analyze the effect transmission and attenuation laws of protection measures at different levels of the city level, district level, and intersection level according to the overall protection strategy, and calculate the effect gradient changes between different levels. Use the overall protection strategy to analyze the impact of the spatial configuration density of resources such as traffic police forces, signal control equipment, and information release channels on the protection effect, and identify the effect differences between resource-intensive areas and resource-scarce areas. Analyze the impact of information sharing, decision-making consultation, and action synchronization between regions on the spatial distribution of the protection effect according to the overall protection strategy, and calculate the relationship between the coordination degree and the protection effect intensity. Analyze the effect distribution patterns of protection strategies corresponding to different risk levels in space based on the overall protection strategy, and identify the effect gradients of high-intensity protection areas, medium-intensity protection areas, and low-intensity protection areas. Use the overall protection strategy to analyze the real-time impact of strategy adjustment on the spatial distribution of the effect, and calculate the effect propagation speed and influence range of the adjustment measures. Establish a spatial interpolation calculation method for the protection effect, and deduce the continuous surface of the effect distribution of the entire area through the monitoring point data, and identify the effect peak area, effect valley area, and effect transition area. Design a quantitative calculation method for the effect gradient, calculate the change rate of the effect in different directions using spatial derivatives and directional derivatives, and establish a vector field representation of the effect gradient. Construct a clustering analysis method for the spatial distribution of the effect, group the spatial regions with similar effect characteristics, and form a spatial division of effect homogeneous areas and effect heterogeneous areas. Establish the distance attenuation law of effect transmission, and analyze the attenuation characteristics of the protection effect with the increase of distance. For example, the effect intensity remains above 80% within 1 kilometer of the protection core area, drops to 60% within 2 kilometers, and drops below 30% outside 3 kilometers. Obtain the spatial distribution characteristics of the effect under the action of the overall protection strategy through this series of analyses.

[0052] Construct a gradient transfer tracking mechanism based on the characteristics of the effect space distribution. To dynamically track the transfer process of the protection effect in space and adjust the protection intensity in a timely manner, a mathematical algorithm for gradient transfer is established using the characteristics of the effect space distribution, and the transfer path, transfer speed, and variation law of the transfer intensity of the protection effect in space are analyzed. A monitoring network for transfer tracking is designed according to the characteristics of the effect space distribution, with dense monitoring points set in areas where the effect gradient changes significantly and sparse monitoring points set in areas where the effect is relatively uniform, forming an adaptive monitoring density distribution. An identification algorithm for the transfer boundary is established based on the characteristics of the effect space distribution to automatically identify the effective boundary, attenuation boundary, and disappearance boundary of the effect transfer and determine the scope of action of the gradient transfer. A prediction algorithm for the transfer path is constructed using the characteristics of the effect space distribution to analyze the transfer law of the effect along different paths such as road networks, administrative boundaries, and geographical features, and establish the probability distribution of multi-path transfer. A real-time calculation method for the transfer intensity is designed according to the characteristics of the effect space distribution, and the instantaneous intensity and cumulative intensity of the effect transfer are calculated through the time series analysis of the monitoring data. A detection mechanism for transfer anomalies is established based on the characteristics of the effect space distribution to identify abnormal phenomena such as transfer interruption, reverse transfer, and accelerated transfer, and timely discover problems with gradient transfer. An evaluation index for transfer efficiency is constructed using the characteristics of the effect space distribution to calculate the transfer efficiency of the effect generated by unit protection investment at different spatial positions and identify the high-value and low-value areas of transfer efficiency. A visualization method for transfer tracking is designed according to the characteristics of the effect space distribution to intuitively display the spatial process of gradient transfer through methods such as effect contour maps, transfer vector maps, and gradient heat maps. A data fusion algorithm for transfer tracking is established based on the characteristics of the effect space distribution to integrate multi-source monitoring data, historical statistical data, and theoretical calculation data, improving the accuracy and reliability of the tracking results. A warning mechanism for transfer tracking is constructed using the characteristics of the effect space distribution, and when abnormal gradient transfer or a significant decrease in transfer efficiency is detected, a warning signal is automatically triggered. After completing the algorithm establishment, mechanism design, and warning configuration, a gradient transfer tracking mechanism with real-time tracking and anomaly detection capabilities is constructed.

[0053] Adjust the protection intensity by using the gradient transfer tracking mechanism. Identify unreasonable areas in the current protection intensity distribution and key positions that need to be adjusted based on the gradient transfer tracking mechanism. Analyze the impact of protection intensity adjustment on effect transfer using the gradient transfer tracking mechanism, and predict the spatial diffusion effect and temporal evolution process of adjustment measures. Identify redundant and insufficient areas in the allocation of protection resources through the gradient transfer tracking mechanism, and formulate adjustment plans for resource reallocation and intensity redistribution. Timely detect areas where the transfer of protection effects is interrupted or abnormal based on the gradient transfer tracking mechanism, and initiate targeted intensity reinforcement measures. For example, when it is monitored that the transfer efficiency of the protection effect of a certain main road to the branch road is only 40% of the expected value, immediately add 2 temporary signal control points to the branch road and dispatch 1 additional traffic police team for on-site guidance to increase the transfer efficiency to 75%. Adjust the spatial scope of the protection intensity based on the gradient transfer tracking mechanism, expand the protection coverage or shrink the protection focus, and optimize the spatial configuration of the protection intensity. Utilize the visualization function of the gradient transfer tracking mechanism to provide intuitive decision-making support for protection intensity adjustment, helping managers quickly identify adjustment priorities and directions. Develop a protection intensity adjustment strategy based on multi-source information according to the gradient transfer tracking mechanism to improve the scientificity and accuracy of adjustment decisions. Establish a preventive adjustment mechanism for protection intensity through the gradient transfer tracking mechanism and make intensity adjustments in advance before problems occur in effect transfer. Establish an effect verification method for intensity adjustment based on the gradient transfer tracking mechanism to evaluate the actual effects of adjustment measures in real time and make secondary adjustments and optimizations in a timely manner. Use the gradient transfer tracking mechanism to construct an experience summary mechanism for intensity adjustment and record the effect rules of different adjustment strategies. Ultimately, dynamic adjustment of protection intensity based on scientific tracking and precise analysis is achieved.

[0054] Adjust the resource acquisition requirements according to the protection intensity. Analyze the resource requirements of the newly added resource demand areas for resources such as traffic police forces, signal control equipment, and monitoring equipment by using the protection intensity adjustment, and calculate the resource gaps and replenishment requirements. Identify the redundant resources that can be released in the resource release areas according to the protection intensity adjustment, including the number of deployable personnel, the equipment and facilities that can be reallocated, and the technical support forces that can be transferred. Analyze the time-varying characteristics of resource requirements based on the protection intensity adjustment, identify the peak periods, stable periods, and trough periods of resource requirements, and establish the corresponding relationship between the time window and resource requirements. Calculate the resource flow direction and flow volume between different regions by using the protection intensity adjustment, determine the resource output areas, resource receiving areas, and resource transfer areas, and draw the resource flow map between regions. Analyze the distribution of emergency resource requirements and general resource requirements according to the protection intensity adjustment, and formulate the priority ranking and classification management strategies for resource allocation. Establish a quantitative calculation method for resource requirements, convert the abstract intensity adjustment into specific resource quantity requirements, including the number of personnel, the number of equipment, vehicle equipment, and communication facilities, etc., and form a detailed resource requirement list. Analyze the changes in resource type requirements, and distinguish the changes in different types of resources such as professional and technical personnel requirements, general duty personnel requirements, equipment and facility requirements, and information support requirements. For example, when the protection intensity of a business district is increased from level two to level one, the traffic police requirement increases from 8 to 15, the signal control points increase from 6 to 12, the temporary control facilities increase from 2 sets to 5 sets, and the monitoring coverage area expands from 2 kilometers to 3.5 kilometers. Through systematic demand analysis and change tracking, obtain the comprehensive resource requirement changes caused by the adjustment of the protection intensity.

[0055] Based on the changes in resource requirements, dynamic resource allocation is carried out to generate a control state. For the newly added resource requirement areas in the changes of resource requirements, a rapid resource replenishment mechanism is established, and precise resource allocation plans and execution timings are formulated. For example, when the traffic police requirement in a certain area increases from 8 to 15, immediately allocate 7 traffic police from adjacent areas to arrive at the scene, and equip them with corresponding duty equipment and communication tools. A redundant resource recycling and allocation mechanism is constructed to uniformly incorporate released resources such as deployable personnel and reallocable equipment into the allocation pool, establish a resource inventory management and real-time scheduling system, and preferentially allocate them to the areas with the most urgent needs. A time-period-based allocation strategy is designed. For peak hours, a full-power allocation mode is initiated; for stable hours, a conventional allocation mode is adopted; for off-peak hours, a resource recycling mode is implemented to achieve an optimized allocation of resources in the time dimension. A directional allocation mechanism is established to directly connect the resource output areas and resource receiving areas to form a direct allocation channel, and a point-to-point resource flow path is formulated to ensure the precise flow of resources as needed. A dual-track allocation mechanism is constructed. For urgent needs, a rapid allocation channel is activated to ensure arrival within 15 minutes; for general needs, a planned allocation method is adopted to complete the deployment within 1 hour. A professional allocation system is established, and corresponding allocation libraries and management mechanisms are established for different types of resources. For example, during the morning rush hour, 15 traffic police in the city center are redeployed. Among them, 8 are allocated to the main congested intersections for on-site guidance, 4 are allocated to the secondary arterial roads for diversion guidance, and 3 are allocated to the emergency standby points for standby. At the same time, 6 sets of temporary signal devices are allocated to the bottleneck sections, and 2 sets of mobile monitoring devices are deployed to key observation points to form an enhanced control state covering the core area. Finally, a comprehensive control state with reasonable resource allocation, rapid response, comprehensive coverage, and remarkable effects is generated.

[0056] Step S170: Analyze the control state to form a protection ability matrix, and use the protection ability matrix to implement protection to complete congestion prediction traffic control protection.

[0057] Specifically, the formation of the protection ability matrix requires systematic analysis to quantify the effect of each protection element.

[0058] In some embodiments, the analyzing the control state to form a protection ability matrix includes: performing cross-time and space effect traceability analysis on the control state to obtain the contribution degree of protection elements; constructing a weight adaptive strategy set based on the contribution degree of protection elements; using the weight adaptive strategy set to form a protection ability matrix; Exemplarily, the performing cross-time and space effect traceability analysis on the control state to obtain the contribution degree of protection elements includes: performing cross-time and space traceability analysis on the control state to obtain historical execution data; analyzing the influence effect of each element based on the historical execution data to establish a contribution degree evaluation; the elements include congestion propagation warning information, the best intervention time point, and a multi-region risk balance plan; quantifying the contribution degree evaluation to generate the contribution degree of protection elements.

[0059] First, conduct a cross - time - space traceability analysis of the control status to obtain historical execution data. Trace forward based on the control status the actual execution situation and performance of the entire protection process. Establish a cross - time - space data collection framework, set the collection interval of the time dimension to 5 minutes, and the collection scope of the space dimension to cover all key nodes within the coordinated control area. Collect key execution data such as the timeliness data of early warning release, the timing record of intervention start, and the execution information of regional coordination through the control status. Record indicators such as the release time, coverage range, and accuracy rate of early warning information, track data such as the selection process of intervention timing, start time, and delay situation, and collect information such as the participation scope of regional coordination, coordination success rate, and resource allocation situation. For example, during the congestion protection during a certain weekday morning rush hour, through traceability, the timeliness data that the early warning information was released 25 minutes before the congestion and covered 3 main intersections was obtained, the timing record that the intervention timing was accurately started 8 minutes after the early warning, and the execution information that the regional coordination involved the east and west regions and the coordination success rate reached 85%. Obtain historical execution data reflecting the true execution status of the three core elements. Subsequently, analyze the impact effects of each element based on the historical execution data and establish a contribution degree assessment. Use the obtained historical execution data to analyze the actual impact degrees of the three elements of congestion propagation early warning information, the best intervention time point, and the multi - regional risk balance plan on the final control effect respectively. For the congestion propagation early warning information, analyze the impacts of warning accuracy, timeliness, and coverage range on the congestion protection success rate, and evaluate the correlation degree between warning quality and protection effect. For the best intervention time point, analyze the impacts of the accuracy of timing selection and the timeliness of intervention start on resource allocation optimization and protection efficiency, and evaluate the contribution degree of timing grasp to the overall protection level. For the multi - regional risk balance plan, analyze the impacts of the integrity of regional coordination and the stability of coordination effect on risk transfer control and overall protection coordination, and evaluate the improvement degree of regional coordination on protection effectiveness. Establish an evaluation standard for the impact effects of the three elements, including three dimensions: direct impact degree, collaborative impact degree, and continuous impact degree. For example, through analysis, it is found that the direct impact degree of congestion propagation early warning information in early warning is 18%, the direct impact degree of the best intervention time point in resource optimization is 20%, and the direct impact degree of the multi - regional risk balance plan in overall coordination is 22%. Establish a contribution degree assessment reflecting the true impact value of the three elements. On this basis, conduct a quantitative processing of the contribution degree assessment to generate the contribution degree of protection elements. Establish a formula for calculating the contribution degree of elements: Ci = (Ei - E0) / (Emax - E0) × Wi × Fi, where Ci is the contribution degree of the i - th element, Ei is the protection effect value when the element is included, E0 is the benchmark protection effect value, Emax is the theoretical maximum protection effect value, Wi is the weight adjustment factor, and Fi is the effect amplification coefficient. Design a formula for calculating the collaborative contribution between elements: Synergy_ij = Eij - (Ei + Ej - E0), and calculate the collaborative contribution of element combinations.Establish a comprehensive contribution calculation formula: TCi = αCi + β∑(Rij × Cj) + γTi, where TCi is the comprehensive contribution of element i, α is the direct contribution weight coefficient, β is the associated contribution weight coefficient, γ is the time decay weight coefficient, Rij is the element correlation degree, and Ti is the time decay factor. The specific contribution values of the three elements are obtained through calculation. For example, the comprehensive contribution of the congestion propagation warning information is 18.5%, the comprehensive contribution of the optimal intervention time point is 20.8%, and the comprehensive contribution of the multi-region risk balance plan is 22.3%. Establish a dynamic update mechanism for the contribution. When the deviation between the actual application effect and the expectation exceeds 5%, the contribution recalculation is automatically triggered. For example, in three consecutive protection practices, when the actual contribution of multi-region coordination increases from 22.3% to 25.1%, the weight configuration of this element is automatically updated. Finally, a scientific, accurate, quantifiable and operable contribution of protection elements is generated.

[0060] Exemplarily, the constructing a weight adaptive strategy set based on the contribution of the protection element includes: identifying strategy conflict points by using the contribution of the protection element and establishing a conflict detection mechanism; performing scenario classification and matching based on the conflict detection mechanism to generate a sub-scenario weight configuration plan; and constructing a weight adaptive strategy set according to the sub-scenario weight configuration plan.

[0061] First, use the contribution degree of protection elements to identify the strategy conflict points and establish a conflict detection mechanism. Based on the obtained distribution of the contribution degree of protection elements, analyze the strategy conflict problems of three elements, namely congestion propagation warning information, the best intervention time, and the multi-region risk balance plan, in practical applications. Identify the timeliness conflict between warning information and intervention time. For example, during the morning rush hour, the warning information strategy requires immediate release of warnings after detecting the signs of congestion to gain disposal time, while the intervention time strategy requires precise analysis of the best intervention point to avoid waste of resources caused by premature intervention. There is a conflict between the two in terms of response speed and accuracy. Analyze the decision-making conflict between intervention time and regional coordination. When immediate intervention measures need to be initiated at a certain intersection, the regional coordination strategy requires prior communication and coordination with adjacent regions to avoid risk transfer, resulting in a conflict between decision-making timeliness and coordination integrity. Identify the resource conflict between regional coordination and warning information. In the case of limited resources, regional coordination needs to allocate a large number of personnel and equipment for multi-point collaborative control, and the release of warning information also requires communication and monitoring resources, resulting in a resource competition conflict. Establish a method for quantifying conflict intensity to calculate the degree of conflict between elements. For example, the conflict intensity between warning information and intervention time is 0.15, and the conflict intensity between intervention time and regional coordination is 0.12. Establish a conflict detection mechanism that can automatically identify and quantify strategy conflicts. Next, based on the conflict detection mechanism, perform scenario classification and matching to generate a sub-scenario weight configuration plan. Use the established conflict detection mechanism to analyze the performance characteristics and intensity changes of strategy conflicts in different traffic scenarios. For the morning rush hour scenario, analyze the conflict patterns under the traffic conditions of large traffic flow and high density. It is found that the importance of the regional coordination strategy is significantly improved, and multi-region collaborative cooperation needs to be strengthened, and its weight should be appropriately increased, while the weights of warning information and intervention time are adjusted accordingly. For the emergency scenario, analyze the conflict patterns under unexpected and highly urgent situations. It is found that the importance of the intervention time strategy is prominent, and quick and accurate intervention decisions become the key, and its weight should be significantly increased. For example, when a traffic accident occurs in a commercial area, causing congestion on the main road, the weight of the intervention time is increased from the conventional 20% to 30% to ensure that emergency diversion measures can be quickly initiated. For the evening rush hour scenario, it is found that the preventive role of warning information is more important, and its weight needs to be appropriately increased. For the bad weather scenario, the three elements need to be more evenly configured to cope with the complex and changeable traffic conditions. Generate a sub-scenario weight configuration plan optimized for different scenarios. On this basis, construct a weight adaptive strategy set according to the sub-scenario weight configuration plan. Integrate the generated sub-scenario weight configuration plans into a unified adaptive strategy system, and establish a complete workflow for scenario recognition, weight matching, and dynamic switching. Design a scenario automatic recognition mechanism to automatically identify the current scenario type through key indicators such as traffic flow density, time characteristics, weather conditions, and emergencies. Establish a weight switching rule. When the scenario changes, automatically switch from the current weight configuration to the optimal weight configuration of the target scenario.Design a smooth transition mechanism to avoid the impact of sharp changes in weight configuration on the protection effect, and adopt a step-by-step adjustment method to gradually complete the weight switch. For example, when it is detected that the peak period is converted to the morning rush hour scenario, the warning information weight is gradually adjusted, the intervention timing weight changes accordingly, and the regional coordination weight is moderately increased. The entire switching process is smoothly completed within 8 minutes. Build a weight configuration verification mechanism to monitor the protection effect after weight adjustment in real time, and automatically start the weight fine-tuning program when the effect does not meet the expectations. Finally, build a set of weight adaptive strategies that can automatically adjust the weight configuration according to scenario changes and resolve strategy conflicts.

[0062] Use the set of weight adaptive strategies to form a protection ability matrix. According to the set of weight adaptive strategies, organize each strategy in a matrix form according to the functional dimension and application scenario, and establish a multi-dimensional protection ability expression framework. Based on the set of weight adaptive strategies, construct the row and column structures of the protection ability matrix. The row dimension represents different protection function categories, and the column dimension represents different application scenario types. Use the set of weight adaptive strategies to fill each cell of the protection ability matrix. Each cell contains the specific strategy combination and weight configuration under the corresponding function and scenario. For example, in the "warning function × morning rush hour scenario" cell, configure the weight of the congestion propagation warning strategy to be 0.18, the weight of the data quality guarantee strategy to be 0.08, and the total warning ability value to be 0.26. In the "coordination function × emergency scenario" cell, configure the weight of the multi-region coordination strategy to be 0.22, the weight of the resource allocation strategy to be 0.05, and the weight of the timing selection strategy to be 0.20, and the total coordination ability value to be 0.47. According to the set of weight adaptive strategies, design a dynamic update mechanism for the protection ability matrix. When the strategy weight is adjusted, the values and configurations in the matrix are updated accordingly. Based on the set of weight adaptive strategies, establish a performance evaluation method for the protection ability matrix, and calculate the overall protection ability index of the matrix and the protection intensity distribution of each dimension. Use the set of weight adaptive strategies to construct the intelligent optimization function of the protection ability matrix, and improve the protection efficiency of the matrix through continuous learning and adjustment. According to the set of weight adaptive strategies, design the resource mapping relationship of the protection ability matrix, and clarify the resource input and configuration requirements for each protection ability. Based on the set of weight adaptive strategies, establish an effect tracking mechanism for the protection ability matrix, and monitor the exertion degree and effect of each protection ability in real time. According to the set of weight adaptive strategies, design the scenario adaptation function of the protection ability matrix, and automatically adjust the matrix configuration according to different traffic conditions and protection requirements. Finally, a comprehensive protection ability matrix that reflects the real protection ability distribution and supports dynamic adjustment and optimization is established.

[0063] Implement protection using the protection capability matrix. Based on the established protection capability matrix, according to the current traffic scenario and congestion risk status, automatically select the corresponding protection capability configuration plan in the matrix and initiate the corresponding protection implementation measures. When detecting the congestion risk during the morning rush hour, according to the configuration of "warning function × morning rush hour scenario" in the matrix, automatically initiate protection measures such as warning information release, intervention timing selection, and area coordination. Use the protection capability matrix to guide the coordinated control among multiple intersections. According to the weight configuration of each function in the matrix, uniformly dispatch warning resources, intervention resources, and coordination resources to achieve the synchronous response and coordinated linkage of protection measures at each intersection. For example, when congestion signs appear at three consecutive intersections in a commercial area, according to the configuration of the protection capability matrix, initiate warning information release at intersection A, implement intervention timing control at intersection B, and carry out area coordination measures at intersection C simultaneously. The protection actions at the three intersections are coordinated under the guidance of the matrix, effectively preventing the further spread of congestion. Use the effect tracking mechanism of the matrix to monitor the implementation effect and collaborative performance of each protection measure in real time. According to the scenario adaptation ability of the protection capability matrix, when the traffic scenario changes, automatically switch to the optimal protection configuration under the corresponding scenario. Through the above protection implementation, complete the traffic control protection for congestion prediction. The use of the protection capability matrix realizes a complete closed-loop control from congestion prediction, risk assessment, timing selection, area coordination to protection implementation. It can automatically select the most suitable combination of protection strategies according to different traffic conditions and congestion risks, dynamically adjust the protection intensity and resource allocation, and achieve intelligent coordination and synchronous response among multiple intersections. For example, during a complete protection process, successfully predicted the congestion risk on a certain main road, issued a warning 20 minutes in advance, initiated the diversion measure at the best timing, coordinated the linkage control of 4 adjacent intersections, and finally controlled the originally possible 45-minute severe congestion to be relieved within 15 minutes, and the traffic flow returned to normal. Established a multi-intersection coordinated traffic control synchronous protection system with accurate prediction, timely response, effective coordination, and strong adaptability, realized the proactive prevention and intelligent management and control of urban traffic congestion, and significantly improved the overall traffic efficiency and safety level of the road network.

[0064] To implement the traffic control protection method based on congestion prediction corresponding to the above method embodiments to achieve the corresponding functions and technical effects. Refer to Figure 2 , Figure 2 FIG. shows a structural block diagram of a traffic control protection device 200 based on congestion prediction provided by an embodiment of the present application. For the sake of convenience of description, only the parts related to this embodiment are shown. The traffic control protection device 200 based on congestion prediction provided by the embodiment of the present application includes: A data storage module 201, configured 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 set of feature vectors; The early warning generation module 202 is configured to perform pattern learning using the feature vector set to identify congestion rules, construct a congestion propagation path prediction mechanism based on the congestion rules, and generate congestion propagation early warning information by using the congestion propagation path prediction mechanism; The plan formulation module 203 is configured to perform risk assessment on the congestion propagation early warning information to mark the danger level, and formulate preventive measures according to the danger level to form a protection plan; The timing optimization module 204 is configured to convert the protection plan into control actions to mark potential intervention times, construct a timing dynamic optimization mechanism based on the potential intervention times, determine the optimal intervention time point by using the timing dynamic optimization mechanism, and initiate protection control through the optimal intervention time point; The area 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 reallocation strategy based on the risk transfer direction, generate a multi - area risk balance plan by using the regional risk reallocation strategy, and form an overall protection strategy through the multi - area risk balance plan; The resource allocation module 206 is configured to perform protection resource allocation based on the overall protection strategy to generate a control status; The protection implementation module 207 is configured to analyze the control status to form a protection capability matrix, and perform protection implementation by using the protection capability matrix to complete congestion prediction traffic control protection.

[0065] The above - mentioned traffic control protection device 200 based on congestion prediction can implement the traffic control protection method based on congestion prediction in the above - mentioned method embodiment. The optional items in the above - mentioned method embodiment also apply to this embodiment, which will not be elaborated here. The remaining content of the embodiment of the present application can refer to the content of the above - mentioned method embodiment, and will not be repeated in this embodiment.

[0066] As Figure 3 shown, the third embodiment of the present invention also 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. The characteristic is that when the processor 302 executes the program, it implements the steps of the traffic control protection method based on congestion prediction described in the first embodiment of the present invention.

[0067] The purpose of the above - mentioned embodiments is to reproduce and deduce the technical solutions of the present invention exemplarily, and to describe the technical solutions, purposes and effects of the present invention completely. The purpose is to make the public understand the disclosed content of the present invention more thoroughly and comprehensively, and does not limit the protection scope of the present invention.

[0068] The above embodiments are not an exhaustive list based on the present invention. In addition, there may be multiple other embodiments not listed. Any substitution and improvement made on the basis of not violating the concept of the present invention fall within the protection scope of the present invention.

Claims

1. A traffic control and protection method based on congestion prediction, characterized in that Including: Construct a historical traffic data storage platform to accumulate basic data, mine features of the basic data to mark congestion features, and establish a feature database based on the congestion features to output a set of feature vectors; Use the set of feature vectors for pattern learning to identify congestion rules, construct a congestion propagation path prediction mechanism based on the congestion rules, and generate congestion propagation warning information by using the congestion propagation path prediction mechanism; Implement risk assessment for the congestion propagation warning information to mark the danger level, and formulate preventive measures based on the danger level to form a protection plan; Convert the protection plan into control actions to mark potential intervention times, construct a timing dynamic optimization mechanism based on the potential intervention times, use the timing dynamic optimization mechanism to determine the optimal intervention time point, and initiate protection control through the optimal intervention time point; Conduct congestion risk transfer analysis for the protection control to mark the risk transfer direction, establish a regional risk redistribution strategy based on the risk transfer direction, generate a multi-regional risk balance plan by using the regional risk redistribution strategy, and form an overall protection strategy through the multi-regional risk balance plan; Conduct protection resource allocation based on the overall protection strategy to generate a management and control state; Analyze the management and control state to form a protection capability matrix, and use the protection capability matrix to implement protection to complete congestion prediction traffic control protection.

2. The method according to claim 1, wherein The congestion propagation path prediction mechanism constructed based on the congestion rules includes: Use the congestion rules to analyze the spatial diffusion characteristics of congestion and identify the congestion propagation path; Analyze the time evolution rule based on the congestion propagation path to obtain the propagation time series characteristics; Establish propagation prediction parameters according to the propagation time series characteristics and the congestion propagation path; Generate prediction nodes according to the propagation prediction parameters; Construct a congestion propagation path prediction mechanism by using the prediction nodes.

3. The method according to claim 1, characterized in that The timing dynamic optimization mechanism constructed based on the potential intervention times includes: Conduct timing analysis on the potential intervention times to determine the timing execution order; Analyze the priority relationship according to the timing execution order to establish a timing priority; Conduct dynamic adjustment processing on the timing priority to generate an optimization strategy; Construct a timing dynamic optimization mechanism according to the optimization strategy.

4. The method according to claim 1, characterized in that The regional risk redistribution strategy established based on the risk transfer direction includes: Conduct flow direction analysis on the risk transfer direction to determine the risk flow distribution; Evaluate the regional carrying capacity according to the risk flow distribution and establish a carrying capacity configuration; Conduct balance processing on the carrying capacity configuration to generate a redistribution plan; Construct a regional risk redistribution strategy according to the redistribution plan.

5. The method according to claim 1, characterized in that, The protection resource allocation based on the overall protection strategy to generate a management and control state includes: Conduct protection effect gradient analysis based on the overall protection strategy to obtain the effect space distribution characteristics; Construct a gradient transfer tracking mechanism based on the effect space distribution characteristics; Adjust the protection intensity by using the gradient transfer tracking mechanism; Obtain the resource demand change according to the adjusted protection intensity; Conduct dynamic resource allocation based on the resource demand change to generate a management and control state.

6. The method according to claim 1, wherein The analysis of the management and control state to form a protection capability matrix includes: Conduct cross - space - time effect traceability analysis on the control status to obtain the contribution degree of protection elements; Construct a weight adaptive strategy set based on the contribution degree of protection elements; Form a protection ability matrix by using the weight adaptive strategy set.

7. The method according to claim 6, characterized in that, The conduct of cross - space - time effect traceability analysis on the control status to obtain the contribution degree of protection elements includes: Conduct cross - space - time traceability analysis on the control status to obtain historical execution data; Based on the historical execution data, analyze the influence effects of each element, and establish a contribution degree evaluation; each of the elements includes congestion propagation warning information, the best intervention time point, and a multi - region risk balance plan; Quantify the contribution degree evaluation to generate the contribution degree of protection elements.

8. The method according to claim 6, wherein The construction of a weight adaptive strategy set based on the contribution degree of protection elements includes: Use the contribution degree of protection elements to identify strategy conflict points and establish a conflict detection mechanism; Based on the conflict detection mechanism, conduct scenario classification and matching to generate a sub - scenario weight configuration plan; Construct a weight adaptive strategy set according to the sub - scenario weight configuration plan.

9. A traffic control and protection device based on congestion prediction, characterized in that, Including: A data storage module, which is used to 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 set of feature vectors; An early warning generation module, which is used to perform pattern learning using the set of feature vectors to identify congestion rules, construct a congestion propagation path prediction mechanism based on the congestion rules, and generate congestion propagation warning information by using the congestion propagation path prediction mechanism; A pre - plan formulation module, which is used to perform risk assessment on the congestion propagation warning information to mark the danger level, and formulate preventive measures based on the danger level to form a protection pre - plan; An opportunity optimization module, which is used to convert the protection pre - plan into control actions to mark potential intervention opportunities, construct an opportunity dynamic optimization mechanism based on the potential intervention opportunities, use the opportunity dynamic optimization mechanism to determine the best intervention time point, and initiate protection control through the best intervention time point; A regional coordination module, which is used to conduct congestion risk transfer analysis on the protection control to mark the risk transfer direction, establish a regional risk re - allocation strategy based on the risk transfer direction, generate a multi - region risk balance plan by using the regional risk re - allocation strategy, and form an overall protection strategy through the multi - region risk balance plan; A resource allocation module, which is used to conduct protection resource allocation based on the overall protection strategy to generate a control status; A protection implementation module, which is used to analyze the control status to form a protection ability matrix, and perform protection implementation by using the protection ability matrix to complete congestion prediction traffic control protection.

10. A computer device, characterized in that, Including 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 8 when executing the computer program.

Images