A method and apparatus for processing traffic planning data

Abstract

This application provides a traffic planning data processing method and apparatus, relating to the field of traffic planning data processing technology. It extracts dynamic behavioral characteristics of traffic participants in designated road segments from traffic planning data; determines synchronization and following indicators corresponding to multiple traffic participation states; and replicates all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle. It performs planning deduction on traffic association information to obtain a traffic decision database; and determines the interaction constraint level of traffic participants in traffic planning by using the traffic decision database and the traffic linkage trends of traffic participants in designated road segments at different time periods. Based on the coordination planning cycle and interaction constraint level, it uses a traffic planning data sharing platform to execute traffic planning adjustments and synchronize them to a remote database. This application can achieve distributed decision-making under complex traffic planning data update delays, thereby improving the dynamic adaptability of traffic flow.

Description

Technical Field

[0001] This application relates to the field of traffic planning data processing technology, and more specifically, to a traffic planning data processing method and apparatus. Background Technology

[0002] Traffic planning data processing refers to the process of collecting, organizing, analyzing, and processing various types of data within the transportation system to support traffic planning, management, and optimization decisions. This process typically includes the comprehensive collection and analysis of data on traffic flow, traffic participant behavior, road conditions, and traffic facility configuration. By utilizing big data technology, artificial intelligence algorithms, and data mining techniques, traffic planning data processing can accurately predict traffic flow, evaluate the effectiveness of different traffic management strategies, and provide optimized traffic planning solutions based on traffic participant behavior patterns, road facility distribution, and traffic flow trends.

[0003] However, existing traffic planning data processing methods typically rely on centralized data storage and processing, leading to low data processing efficiency. This is especially true when dealing with large-scale, complex traffic data, which is prone to problems such as delayed data updates and insufficient real-time response. These methods fail to reflect changes in traffic flow and fluctuations in participant behavior in real time, making it difficult for traffic planning to synchronize with actual needs. Consequently, traffic management solutions often lag behind actual traffic conditions, impacting the smoothness and safety of urban traffic. Therefore, how to achieve distributed decision-making based on complex traffic planning data update delays to improve the dynamic adaptability of traffic flow is a challenge facing the industry. Summary of the Invention

[0004] This application provides a traffic planning data processing method and apparatus, which can realize distributed decision-making of complex traffic planning data under update delays, so as to improve the dynamic adaptability of traffic flow.

[0005] Firstly, this application provides a method for processing traffic planning data, the method comprising the following steps:

[0006] Traffic planning data for a specified road segment is obtained based on the traffic planning data platform, and dynamic behavioral characteristics of traffic participants in the specified road segment are extracted from the traffic planning data.

[0007] A distributed traffic planning database is constructed, and the dynamic behavioral characteristics are divided into distributed nodes according to traffic participation type to obtain the synchronization and car-following indicators corresponding to multiple traffic participation states. All synchronization and car-following indicators are replicated in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle.

[0008] Traffic association information of traffic participants traveling in the planned route is collected, and the traffic association information is used for planning and simulation to obtain a traffic decision database. The interaction constraint level of traffic participants in traffic planning is determined by the traffic decision database and the traffic linkage trend of traffic participants in a specified road segment at different time periods.

[0009] Based on the aforementioned coordination planning cycle and the aforementioned interaction constraint hierarchy, traffic planning adjustments are executed using the traffic planning data sharing platform and synchronized to the remote database.

[0010] In this embodiment, the traffic planning data represents a set of structured road and traffic flow information that supports traffic design, scheduling, and optimization.

[0011] In this embodiment, extracting the dynamic behavioral characteristics of traffic participants in a designated road segment from the traffic planning data specifically includes:

[0012] Based on the traffic planning data, a dynamic behavior parameter set for the specified road segment is constructed;

[0013] Set behavior pattern matching rules based on the dynamic behavior parameter set;

[0014] The behavioral trajectory data of traffic participants are reconstructed using the pattern matching rules to obtain the dynamic behavioral characteristics of traffic participants in a specified road segment.

[0015] In this embodiment, a distributed traffic planning database is constructed, and the dynamic behavioral characteristics are divided into distributed nodes according to traffic participation type to obtain synchronization and following indicators corresponding to multiple traffic participation states, specifically including:

[0016] In a distributed transportation planning database, data classification rules for distributed nodes are defined based on traffic participation type.

[0017] The dynamic behavioral features are assigned to corresponding nodes through the data classification rules, and dynamic synchronization nodes are established across nodes.

[0018] Based on the feature correlation in the dynamic synchronization node, state verification rules are defined for multiple types of traffic participation states.

[0019] The synchronization and following indicators corresponding to multiple traffic participation states are extracted from the state verification rules.

[0020] In this embodiment, the process of replicating all synchronization and tracking indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle specifically includes:

[0021] Set the synchronization trigger rules for all synchronized and trailing indicators;

[0022] The synchronization triggering rule is subjected to status detection to obtain a synchronization data copy;

[0023] The dynamic coordination planning cycle is output based on the update frequency of the synchronized data copy and the road segment coordination requirements of the specified road segment.

[0024] In this embodiment, collecting traffic association information of traffic participants traveling along the planned path specifically includes:

[0025] Obtain location data and timestamp information of traffic participants traveling along the planned route;

[0026] The location data and timestamp information are used to generate motion trajectory association features of traffic participants;

[0027] The overlap of the motion trajectory association features is verified to obtain the traffic association information of traffic participants traveling in the planned path.

[0028] In this embodiment, the coordination planning period refers to the time period that is dynamically adjusted based on real-time traffic data and road segment coordination requirements.

[0029] In this embodiment, determining the interaction constraint hierarchy of traffic participants in traffic planning through the traffic decision database and the traffic interaction trends of traffic participants in designated road segments at different time periods specifically includes:

[0030] Based on the risk prediction weights in the traffic decision database and the traffic linkage trend, the interactive behavior information of traffic participants is determined;

[0031] The planning synergy attributes in traffic planning are determined based on the interactive behavior information and the participation effect indicators at different times in the specified road segment;

[0032] Based on the aforementioned planning collaboration attributes, hierarchical constraint determination rules are established, and the interaction constraint hierarchy of traffic participants in traffic planning is generated.

[0033] In this embodiment, the process of adjusting traffic planning and synchronizing it with a remote database using a traffic planning data sharing platform, based on the coordination planning cycle and the interaction constraint hierarchy, specifically includes:

[0034] A traffic allocation strategy is generated based on the coordination planning cycle and the interaction constraint hierarchy.

[0035] The traffic allocation strategy is distributed to the roadside control equipment of the designated road section through the traffic planning data sharing platform, and a multi-device collaborative execution verification process is triggered.

[0036] By utilizing the data synchronization channel of the transportation planning data sharing platform, the verified adjustment results are compared with the remote database using spatiotemporal labels to complete incremental data synchronization and generate anomaly rollback instruction sets.

[0037] Secondly, this application provides a traffic planning data processing apparatus for executing a traffic planning data processing method, the data processing apparatus comprising:

[0038] The data acquisition module is used to acquire traffic planning data for a specified road segment based on the traffic planning data platform, and extract the dynamic behavioral characteristics of traffic participants in the specified road segment from the traffic planning data.

[0039] The data partitioning module is used to construct a distributed traffic planning database. It divides the dynamic behavioral characteristics into distributed nodes according to traffic participation type, obtains the synchronization and following indicators corresponding to multiple traffic participation states, and replicates all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle.

[0040] The decision-making and simulation module is used to collect traffic association information of traffic participants in the planned route, perform planning and simulation on the traffic association information to obtain a traffic decision database, and determine the interaction constraint level of traffic participants in traffic planning through the traffic decision database and the traffic linkage trend of traffic participants in a specified road segment at different time periods.

[0041] The data synchronization module is used to perform traffic planning adjustments and synchronize them to a remote database using the traffic planning data sharing platform, based on the coordination planning cycle and the interaction constraint level.

[0042] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0043] Traffic planning data for designated road segments is acquired through a traffic planning data platform. Dynamic behavioral characteristics of traffic participants within these segments are extracted from the traffic planning data. A distributed traffic planning database is constructed, and the dynamic behavioral characteristics are categorized into distributed nodes based on traffic participation type. Synchronization and following indicators corresponding to multiple traffic participation states are obtained, and all synchronization and following indicators are replicated in real-time via a data synchronization protocol, forming a dynamically updated coordination planning cycle. Traffic association information of participants traveling along planned routes is collected, and planning deductions are performed on this information to obtain a traffic decision database. The interaction constraint level of traffic participants in traffic planning is determined by using the traffic decision database and the traffic linkage trends of participants in designated road segments at different times. Based on the coordination planning cycle and the interaction constraint level, traffic planning adjustments are executed using a traffic planning data sharing platform and synchronized to a remote database.

[0044] Therefore, this application demonstrates its ability to improve urban traffic flow. Specifically, by constructing a dynamic behavioral parameter set and employing behavioral pattern matching rules to accurately extract the behavioral characteristics of traffic participants, traffic planning can be analyzed based on the actual dynamic behavior of participants, improving the accuracy of traffic analysis and the realism of behavioral modeling. By distributing and synchronizing dynamic behavioral characteristics in real time, the system possesses stronger data processing parallelism and real-time performance, enabling rapid response to changes in traffic conditions. This allows for the construction of a dynamically updated traffic coordination mechanism, enhancing the flexibility and accuracy of overall traffic scheduling. Furthermore, by introducing an overlapping verification and deduction mechanism for traffic association information, quantitative modeling of the spatiotemporal linkages among traffic participants is achieved, forming a hierarchical interactive constraint structure. Finally, through a shared platform and data synchronization mechanism, optimized traffic allocation strategies are distributed and transmitted back in real time, achieving data collaboration and feedback loops between cross-regional traffic management systems, thereby ensuring the consistency and stability of planning adjustments across multiple terminals and regions.

[0045] In summary, the technical solution adopted in this application can realize distributed decision-making based on complex traffic planning data update delays, thereby improving the dynamic adaptability of traffic flow. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is an exemplary flowchart of a traffic planning data processing method provided in this application;

[0048] Figure 2 This is a flowchart illustrating the process for determining the synchronization and following indicators provided in this application;

[0049] Figure 3 This is a flowchart illustrating the process of determining the traffic decision database provided in this application;

[0050] Figure 4 This is a modular structure diagram of a traffic planning data processing device provided in this application. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] This application provides a traffic planning data processing method and apparatus. Its core is to acquire traffic planning data for a designated road segment based on a traffic planning data platform, extract dynamic behavioral characteristics of traffic participants in the designated road segment from the traffic planning data, construct a distributed traffic planning database, classify the dynamic behavioral characteristics into distributed nodes according to traffic participation type to obtain synchronization and following indicators corresponding to multiple traffic participation states, and replicate all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle; collect traffic association information of traffic participants traveling along the planned path, perform planning deduction on the traffic association information to obtain a traffic decision database, determine the interaction constraint level of traffic participants in traffic planning through the traffic decision database and the traffic linkage trend of traffic participants in the designated road segment at different time periods; and, based on the coordination planning cycle and the interaction constraint level, execute traffic planning adjustments using a traffic planning data sharing platform and synchronize them to a remote database.

[0053] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown, this figure is an exemplary flowchart of a traffic planning data processing method according to this embodiment of the present application. The data processing method includes the following steps:

[0054] In step S1, traffic planning data for a specified road segment is obtained based on the traffic planning data platform, and dynamic behavioral characteristics of traffic participants in the specified road segment are extracted from the traffic planning data.

[0055] In practical implementation, obtaining traffic planning data for a specified road segment based on the traffic planning data platform can be achieved in the following way: Establish a standardized interface connection with the urban traffic sensing system, accessing multi-source data resources including high-precision maps, road network structure, signal timing, and real-time traffic flow. Through the unified data scheduling mechanism of the data platform, a query request containing the road segment number or geographical coordinates is sent to the platform. The platform then retrieves the corresponding road segment's traffic planning information from its distributed data warehouse, including lane configuration, traffic flow prediction, and control strategies. To ensure data accuracy and timeliness, the system employs a caching optimization and incremental update mechanism, periodically aggregating and updating information from the sensing front end and synchronizing it to the platform. The acquisition process is conducted through a unified data access interface, and the returned results are converted into a standardized data structure, which is then used as the traffic planning data for the specified road segment.

[0056] It should be noted that, in this application, the transportation planning data platform refers to the core platform that unifies the aggregation, management and scheduling of multi-source transportation planning data; and the transportation planning data refers to the structured road and traffic flow information set that supports traffic design, scheduling and optimization.

[0057] In this embodiment, extracting the dynamic behavioral characteristics of traffic participants in a designated road segment from the traffic planning data can be achieved through the following steps:

[0058] Based on the traffic planning data, a dynamic behavior parameter set for the specified road segment is constructed;

[0059] Set behavior pattern matching rules based on the dynamic behavior parameter set;

[0060] The behavioral trajectory data of traffic participants are reconstructed using the pattern matching rules to obtain the dynamic behavioral characteristics of traffic participants in a specified road segment.

[0061] In practical implementation, firstly, a dynamic parameter set describing changes in traffic participant behavior is constructed based on information about designated road segments obtained from the traffic planning data platform. This dynamic parameter set includes: spatial parameters (latitude and longitude coordinates, lane position, road geometry); temporal parameters (time of occurrence, duration, and time difference between adjacent behaviors); state parameters (speed, acceleration, direction angle, relative distance, and trajectory); and event parameters (labels for behavioral events such as lane changing, stopping, acceleration, yielding, and obstacle avoidance). To achieve high-precision construction of the dynamic behavior parameter set, multi-source raw data from the perception system needs to be integrated. Data cleaning methods and synchronous fusion algorithms are used to generate a time-continuous and structurally unified parameter record set, thus obtaining the dynamic behavior parameter set. Then, based on domain traffic behavior knowledge and the empirical results of machine learning models, a matching rule system for traffic participant behavior is formulated. The behavior pattern matching rules are defined through a hybrid of logical and model rules, mainly including: logical rules, which determine "deceleration behavior" when "acceleration is negative and speed change exceeds a threshold for more than 3 seconds"; and model rules, which use support vector machines, random forests, or long short-term memory networks to classify trajectory time-series data, train the model to output behavior categories, and use these categories as the behavior pattern matching rules. Finally, the traffic participant behavior trajectory data is processed based on the pattern matching rules. Specifically, the traffic participant's behavior trajectory is divided into equal-length segments according to time windows. Matching rules are applied to each segment for label determination, assigning a corresponding behavior label to each trajectory segment. Based on the assigned labels, similar behavior segments are recombined. This recombination process includes merging segments with similar behavioral characteristics to form a continuous dynamic behavior sequence. Through this recombination process, the dynamic behavioral characteristics of traffic participants in a specified road segment are finally extracted, including structured features such as behavior type, location, duration, and behavioral change trends. In the process of reorganization, behavioral graph models can be used to represent behavioral states with nodes and behavioral transition paths with edges, thereby presenting the dynamic behavioral characteristics of traffic participants more intuitively.

[0062] It should be noted that, in this application, traffic participants refer to individuals or units that generate traffic behavior in the road system, such as vehicles and pedestrians; the dynamic behavior parameter set refers to a structured data set describing the changes in the movement state of traffic participants in the spatiotemporal dimension; the behavior pattern matching rule refers to a set of rules used to identify the original trajectory data as a specific behavior type; the traffic participant's behavior trajectory data refers to a set of information on the spatiotemporal movement path and behavior changes of traffic participants in the road network; and the dynamic behavior characteristics refer to the typical behavior of traffic participants in a specific road segment.

[0063] In step S2, a distributed traffic planning database is constructed, and the dynamic behavioral characteristics are divided into distributed nodes according to traffic participation type to obtain the synchronization and car-following indicators corresponding to multiple traffic participation states. All synchronization and car-following indicators are copied in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle.

[0064] Preferably, in this embodiment, a distributed traffic planning database is constructed, and the dynamic behavioral characteristics are divided into distributed nodes according to traffic participation type to obtain synchronization and following indicators corresponding to multiple traffic participation states, for reference. Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining the synchronization index in some embodiments of this application. In this embodiment, the synchronization index can be determined by the following steps:

[0065] In step S21, in the distributed traffic planning database, data classification rules for distributed nodes are defined based on traffic participation type;

[0066] In step S22, the dynamic behavior features are directed to the corresponding nodes according to the data classification rules, and cross-node dynamic synchronization nodes are established.

[0067] In step S23, based on the feature correlation in the dynamic synchronization node, state verification rules corresponding to multiple types of traffic participation states are defined;

[0068] In step S24, the synchronization and following indicators corresponding to multiple traffic participation states are extracted from the state verification rules.

[0069] In practical implementation, firstly, a distributed traffic planning database is constructed, selecting a database system that supports high-concurrency read / write and data sharding mechanisms, such as Apache Cassandra or Amazon DynamoDB. Nodes are divided based on traffic participation type, with common types including motor vehicles, non-motor vehicles, and pedestrians. The data classification rules for distributed nodes are defined as follows: the main classification dimension is set to "participation type," enabling each type of data to be automatically routed to the corresponding type node; the sub-classification dimension is "spatial segment ID + time period," ensuring geographical and temporal consistency of data within each node; a consistent hashing algorithm is used to evenly map data across the cluster nodes, ensuring load balancing. Next, the cleaned and structured dynamic behavioral features are uploaded to each type of node according to the data classification rules: motor vehicle behavior data (such as speed fluctuations and following responses) are assigned to motor vehicle nodes; pedestrian dynamic data (such as stop-and-go transitions and crossing times) are assigned to pedestrian nodes; and non-motor vehicles are assigned based on riding paths and trajectory change directions. Identify road segments where different traffic participants interact (such as mixed pedestrian and vehicle areas and intersections), and establish dynamic synchronization nodes between these nodes: use message queue mechanisms or database triggers to synchronize the behavioral states between different nodes, thus establishing cross-node dynamic synchronization nodes; then, extract data with high coupling characteristics between traffic participants from the dynamic synchronization nodes, and use this data as feature correlation in the dynamic synchronization nodes. Data with high coupling characteristics includes: motor vehicle deceleration triggering non-motorized vehicle yielding; pedestrian crossing causing vehicle stopping; non-motorized vehicle changing direction causing vehicle trajectory deviation. Construct state verification rules corresponding to multiple traffic participation states: use statistical learning methods to extract high-frequency behavior combinations; construct a state transition graph to define the causal logic between preceding and following states in a specific traffic behavior sequence; introduce state influence indicators, such as behavior propagation delay and correlation weight, to describe the strength of relationships between multiple types of behaviors. Finally, extracting synchronization and car-following indicators corresponding to multiple traffic participation states allows us to extract synchronization delay time (the difference in behavioral reaction time between different types of participants), behavioral coordination degree (the degree of matching between different behavioral sequences), stability index (the fluctuation frequency of state switching in cross-type behavioral sequences), and spatiotemporal coupling factor (representing the degree of spatial overlap and duration of interactive behaviors). Data mining and clustering algorithms are then used to classify and reduce the extracted indicators, forming traceable and dynamically updated indicators, which are then used as synchronization and car-following indicators.

[0070] It should be noted that in this application, traffic participation type refers to the category of participants classified according to the mode of travel, including different types of traffic subjects such as motor vehicles, non-motor vehicles, and pedestrians; data classification rules refer to the logic and path used to determine the node to which traffic data belongs in the distributed system; dynamic synchronization node refers to the data transfer structure that spans multiple traffic participation type nodes and is used to record interactive events and state linkage relationships; feature correlation in dynamic synchronization node refers to the feature correspondence relationship that exists in the spatiotemporal dimension of synchronous changes in the behavior of different traffic participants; state verification rules refer to the calculation rule system used to confirm the correlation logic and state transition rationality between different traffic participation behaviors; and synchronization following index refers to the key performance indicator that measures the response consistency and coupling degree between different types of traffic participants in spatiotemporal and behavioral patterns.

[0071] In this embodiment, the real-time replication of all synchronization and tracking indicators through a data synchronization protocol to form a dynamically updated coordination planning cycle can be achieved through the following steps:

[0072] Set the synchronization trigger rules for all synchronized and trailing indicators;

[0073] The synchronization triggering rule is subjected to status detection to obtain a synchronization data copy;

[0074] The dynamic coordination planning cycle is output based on the update frequency of the synchronized data copy and the road segment coordination requirements of the specified road segment.

[0075] In practical implementation, firstly, the synchronization triggering rules ensure that the data of the synchronized car-following indicator is triggered and updated under specific conditions by setting conditions. These conditions include: time conditions, such as updating every 5 minutes, or triggering synchronization when the change in state exceeds a set threshold; behavioral conditions, such as triggering the replication of synchronized data when the relative position change between motor vehicles and non-motor vehicles exceeds a certain threshold; and spatial conditions, such as triggering data updates and replication when the behavior of traffic participants affects the overall traffic flow of a road segment. Synchronization triggering rules can also be set based on traffic flow, road segment lane conditions, participant types, and other traffic events (such as accidents, congestion, etc.). In other words, synchronization triggering rules for all synchronized car-following indicators are set through time, behavioral, and spatial conditions. Then, a monitoring module is established in the traffic planning system to detect in real time whether the synchronization triggering rules are met. This monitoring module can be implemented in the following way: a real-time data stream processing system is used in the state detection mechanism to continuously analyze traffic flow and behavior data, and to determine in real time whether the synchronization triggering conditions are met. The synchronization triggering conditions can be behaviors such as vehicle acceleration, deceleration, lane changing, or emergency braking. The system will detect these behavioral characteristics and compare them with preset rules. Once the synchronization triggering conditions are detected, the system automatically generates a synchronization data copy. Finally, the adjustment of the synchronization data copy update cycle and the collaborative planning cycle depends on the update frequency and the road segment collaboration requirements. The update frequency is usually set according to the frequency of changes in traffic flow and event types. For example, busy road segments may need to update synchronization data every 30 seconds, while relatively stable road segments can be updated every 5 minutes. The road segment collaboration requirements are based on the actual traffic conditions of the road segment, such as whether there are areas where multiple traffic participants intersect, or whether the road segment is a traffic bottleneck area, to dynamically adjust the frequency of the planning cycle. Based on the update frequency and road segment coordination requirements, a linear fitting method is used to fit the update frequency and road segment coordination requirements. The fitting result is used as the dynamic coordination planning cycle. This dynamic coordination planning cycle is the optimal response cycle for each road segment at the current moment. Specific adjustment strategies, such as adjusting signal cycles and optimizing traffic flow routes, are output through the coordination algorithm.

[0076] It should be noted that, in this application, the synchronization triggering rule refers to the set of rules that specify when and under what circumstances the data synchronization operation is triggered; the synchronized data copy refers to the traffic behavior data copy from the original data for dynamic updates; the road segment coordination requirement of a specified road segment refers to the degree to which a specified road segment needs to coordinate with other road segments or traffic participants in traffic planning; and the coordination planning cycle refers to the time period that is dynamically adjusted based on real-time traffic data and road segment coordination requirements.

[0077] In step S3, traffic association information of traffic participants traveling in the planned path is collected, and the traffic association information is used for planning and deduction to obtain a traffic decision database. The interaction constraint level of traffic participants in traffic planning is determined by the traffic decision database and the traffic linkage trend of traffic participants in the specified road segment at different time periods.

[0078] In this embodiment, collecting traffic association information of traffic participants traveling along the planned path can be achieved through the following steps:

[0079] Obtain location data and timestamp information of traffic participants traveling along the planned route;

[0080] The location data and timestamp information are used to generate motion trajectory association features of traffic participants;

[0081] The overlap of the motion trajectory association features is verified to obtain the traffic association information of traffic participants traveling in the planned path.

[0082] In practical implementation, firstly, the location data of traffic participants is acquired in real time through a positioning system. This acquired location data serves as the positioning data for traffic participants traveling along the planned path. This positioning data includes each participant's latitude and longitude coordinates, direction of travel, and speed. Each positioning data point should also carry a timestamp, recording the exact time the data point was captured. This timestamped positioning data serves as the timestamp information for traffic participants traveling along the planned path. Then, based on the acquired positioning data and timestamp information, the motion trajectory association features of traffic participants are calculated. This involves querying the time and spatial coordinates of each positioning data point, dynamic information such as speed, acceleration, and direction between different positioning data points, and the movement paths and driving patterns of traffic participants (such as going straight, changing lanes, stopping, etc.). A trajectory association feature extraction algorithm is used to extract interaction features with other traffic participants from the queried data. These interaction features can determine whether traffic participants are approaching, intersecting, or avoiding each other, and these interaction features are used as the motion trajectory association features of traffic participants. Finally, the spatial or temporal overlap of the motion trajectory features of multiple traffic participants is analyzed. Spatial or temporal overlap involves analyzing whether two traffic participants pass through the same area at the same time, or whether they exhibit intersection or avoidance behavior. An overlap calculation algorithm quantifies the degree of overlap between two trajectories. A threshold can be set to determine whether an overlap is "overlapping," and the traffic participants' behavior can be classified based on the overlap level. During classification, cross-analysis, combined with external traffic information (such as traffic light status and road conditions), is used to assist in verifying the overlap degree. The overlapping portion corresponding to the verified overlap degree is used as the traffic association information for traffic participants traveling within the planned path.

[0083] It should be noted that, in this application, the location data of traffic participants traveling in the planned path refers to the spatial location information of traffic participants; the timestamp information of traffic participants traveling in the planned path refers to the time information of recording specific data points; the motion trajectory association features represent the features related to behavior or path extracted based on the location and time data of traffic participants; the overlap verification verifies the similarity and intersection between the motion trajectories of different traffic participants through spatial and temporal matching; and the travel association information represents the association data formed by traffic participants based on the overlapping, interaction and other features of their behavioral trajectories during their travel on the same or adjacent road segments.

[0084] Preferably, in this embodiment, the traffic association information is used for planning and deduction to obtain a traffic decision database, which is then referenced. Figure 3 As shown in the figure, this is a flowchart illustrating the process of determining the traffic decision database in some embodiments of this application. In this embodiment, determining the traffic decision database can be achieved using the following steps:

[0085] In step S31, a traffic flow simulation model under spatiotemporal constraints is established based on the traffic association information table;

[0086] In step S32, dynamic events are injected into the traffic participant association data through the traffic flow inference model to generate an inference decision map;

[0087] In step S33, planning and deduction rules for traffic participants are established based on the deduction decision map;

[0088] In step S34, the traffic decision database is determined through the planning and deduction rules.

[0089] In practical implementation, firstly, a table is constructed based on traffic association information. This table contains the trajectory data, behavioral patterns, and overlap verification results of traffic participants. Spatiotemporal constraints are introduced into the traffic flow simulation model. These constraints include: spatial constraints, requiring traffic participants to interact or travel within the same physical area; and temporal constraints, defining the time range during the simulation process, such as peak or off-peak traffic periods. Microscopic and macroscopic traffic flow models are used to simulate traffic flow changes. The traffic flow simulation model predicts changes in traffic flow based on the behavioral data and interrelationships of traffic participants, as well as the external environment (such as traffic signals and road conditions). Based on the data in the traffic association information table, the parameters of the traffic flow simulation model are set and calibrated. Using the calibrated model, combined with the spatiotemporal constraints, changes in traffic flow are simulated. Finally, in the traffic flow simulation model, based on dynamic event injection technology and combined with traffic association data, the behavior of traffic participants is simulated in real time. Real-time simulation includes: changes in traffic signals, such as the impact of traffic light changes on traffic flow; changes in road conditions, such as traffic flow changes caused by traffic accidents, road construction, or weather changes; and changes in traffic participant behavior, such as acceleration, deceleration, and lane changes. An event-driven simulation system is then used to inject dynamic events into the model. Simulations are performed using the simulation system according to different scenarios and constraints, and the simulation results are used as a projection decision graph. Then, based on various traffic scenarios and behavioral results in the projection decision graph, planning projection rules for traffic participants are constructed, including: optimal travel strategies, such as choosing the optimal lane or route under specific traffic signals; behavior adjustment rules, such as reducing congestion by adjusting vehicle speed or changing lanes during traffic jams; and route optimization rules, automatically adjusting the travel routes of traffic participants according to traffic flow conditions. Effective traffic behavior patterns are extracted from the projection graph using data mining techniques, and projection rules adapted to different scenarios are formulated, which are then used as the planning projection rules for traffic participants. Finally, the planning and simulation rules are integrated into the traffic decision-making system. This system is typically based on database management technology to store and manage the planning and simulation rules and related data, ensuring rapid response in the decision-making process. Using a relational database or time-series database to manage the simulation rules and related data results in the traffic decision-making database. The data in the traffic decision-making database includes not only the behavior and decision-making rules of traffic participants, but also dynamic traffic flow, signal status, accident information, etc.

[0090] It should be noted that in this application, the traffic flow simulation model represents a mathematical model that simulates traffic flow and the behavior of traffic participants; the simulation decision graph represents a graph generated based on the traffic flow simulation model and the results of dynamic event injection; the planning simulation rules represent the decision-making process that guides traffic participants in different situations; and the traffic decision database represents a database used to store traffic planning, simulation rules, and real-time traffic data.

[0091] In this embodiment, determining the interaction constraint level of traffic participants in traffic planning through the traffic decision database and the traffic interaction trends of traffic participants in designated road segments at different time periods can be achieved through the following steps:

[0092] Based on the risk prediction weights in the traffic decision database and the traffic linkage trend, the interactive behavior information of traffic participants is determined;

[0093] The planning synergy attributes in traffic planning are determined based on the interactive behavior information and the participation effect indicators at different times in the specified road segment;

[0094] Based on the aforementioned planning collaboration attributes, hierarchical constraint determination rules are established, and the interaction constraint hierarchy of traffic participants in traffic planning is generated.

[0095] In practice, the process begins with traffic risk analysis based on historical and real-time data stored in the traffic decision-making database. This analysis involves predicting potential traffic accidents, congestion, or other anomalies. Regression analysis is applied using historical traffic flow, weather, and time period data to assess risk levels under different scenarios. Next, the analysis examines the traffic interaction trends of participants in a specified road segment across different time periods. These trends reflect the interactive relationships among multiple participants within the same timeframe. Interaction patterns in different time periods are identified based on traffic flow changes and participant behaviors (such as acceleration, braking, and lane changes). Finally, the behavioral data of each participant is compared with the corresponding risk predictions to extract their interactive behaviors. These interactive behaviors are then used as traffic participant interaction information, which includes the interaction relationships between a participant and other participants, risk coefficients, and behavioral characteristics. Then, linear correlation analysis is used to analyze the interaction behavior information and participation effect indicators. For example, a large amount of traffic congestion or accidents during a certain period may make the behavior of a certain traffic participant have a greater impact on the overall traffic flow. Based on the interaction behavior information and participation effect indicators, the planning coordination attributes of traffic participants in different scenarios are identified. The determination of planning coordination attributes includes the interaction patterns of multiple traffic participants within a certain period, such as group behavior patterns and traffic flow optimization behaviors. For example, during peak hours, multiple vehicles coordinate to adjust their speeds to maintain smooth traffic flow; when an accident occurs, vehicles may automatically adjust their routes to avoid congestion. In addition, cluster analysis or decision trees can be used to determine the planning coordination attributes in traffic planning, which will not be elaborated here. Finally, hierarchical constraint judgment rules for traffic participants are designed, namely: during high-volume periods, the driving speed of traffic participants is restricted, or priority is given to certain important traffic routes; when a traffic accident occurs, avoidance and detour rules for traffic participants are set. Based on hierarchical constraint decision rules, the restrictions and priorities of traffic participants in different scenarios are extracted according to actual traffic conditions. These restrictions and priorities are then used as interaction constraint levels. Based on these interaction constraint levels, the behavioral restrictions and priorities of traffic participants in specific traffic planning are updated. For example, in emergency situations, certain vehicles (such as ambulances) may have higher priority and be allowed to pass first. The hierarchical constraint decision rules can be implemented in a rule engine, and traffic signals or route selection strategies can be automatically generated through data-driven decision-making.

[0096] It should be noted that, in this application, risk prediction weight refers to the result of risk assessment and corresponding weighting of possible traffic events based on historical and real-time traffic data; traffic linkage trend at different time periods represents the interaction and behavior patterns of traffic participants in different time periods of a specified road segment; interactive behavior information represents the participation effect index at different time periods in a specified road segment, representing the degree of influence of traffic participants on overall traffic flow in a specific time period; planning coordination attribute represents the collaborative behavior characteristics of traffic participants in traffic planning; hierarchical constraint judgment rule is a multi-level behavior restriction rule formulated based on the coordination attributes and behavior patterns of traffic participants; interaction constraint level refers to the different constraint levels set in traffic planning according to the collaborative behavior and priority of traffic participants.

[0097] In step S4, based on the coordination planning cycle and the interaction constraint level, the traffic planning adjustment is performed using the traffic planning data sharing platform and synchronized to the remote database.

[0098] In this embodiment, the following steps can be used to perform traffic planning adjustments and synchronize them to a remote database using a traffic planning data sharing platform, based on the coordination planning cycle and the interaction constraint hierarchy:

[0099] A traffic allocation strategy is generated based on the coordination planning cycle and the interaction constraint hierarchy.

[0100] The traffic allocation strategy is distributed to the roadside control equipment of the designated road section through the traffic planning data sharing platform, and a multi-device collaborative execution verification process is triggered.

[0101] By utilizing the data synchronization channel of the transportation planning data sharing platform, the verified adjustment results are compared with the remote database using spatiotemporal labels to complete incremental data synchronization and generate anomaly rollback instruction sets.

[0102] In practical implementation, firstly, by combining the coordinated planning cycle with the interaction constraint hierarchy, traffic assignment strategies can be generated using linear programming, dynamic programming, and genetic algorithms. That is, by dynamically programming the coordinated planning cycle and the interaction constraint hierarchy, the output of the dynamic programming result indicates that certain road segments require traffic signal control or flow guidance to optimize traffic flow distribution during peak hours, while constraints can be appropriately relaxed during other times to improve overall traffic efficiency. The output of the dynamic programming result serves as the traffic assignment strategy. Then, the traffic planning data sharing platform is a centralized system with data storage, data exchange, and decision execution capabilities. It sends the traffic assignment strategy to the roadside control equipment (such as traffic lights, variable lane indicators, and intelligent traffic signs) on various road segments via network protocols. The roadside control equipment is responsible for adjusting signal timing, lane usage rules, etc., according to the issued traffic assignment strategy. For example, during peak hours, variable lanes may be added or signal cycles adjusted to prioritize traffic flow. In the multi-device collaborative execution verification, once the traffic assignment strategy is issued to each roadside control device, the traffic planning data sharing platform triggers a multi-device collaborative execution verification process to ensure the coordination of execution between the devices. For example, the timing of multiple traffic lights needs to be coordinated to avoid traffic flow conflicts at one intersection with that at an adjacent intersection. Finally, the traffic planning data sharing platform has a data synchronization function, which can synchronize the verified adjustment results with a remote database in real time through a data synchronization channel. Synchronized data includes adjusted traffic signal timings, lane usage status, and traffic flow data. To ensure data accuracy, the system performs spatiotemporal tag comparison on the synchronized data. Spatiotemporal tags refer to the markings of data in time and space. By comparing traffic adjustment data from different time periods and road segments, the system ensures that the information in the remote database is consistent with the current state; through an incremental data synchronization mechanism, only data that has changed is synchronized. If data anomalies or conflicts are detected during the synchronization process (e.g., traffic flow deviating significantly from expectations), the system generates an anomaly rollback instruction set to revert or correct the implemented adjustment strategy. The rollback instructions are automatically transmitted to each roadside control device to ensure the continuity and correctness of traffic management.

[0103] It should be noted that in this application, traffic assignment strategy refers to traffic flow and behavior control scheme; multi-device collaborative execution verification process refers to ensuring that multiple roadside control devices execute consistent traffic planning strategies within the same time period through a verification mechanism; and abnormal rollback instruction set refers to the reversal or correction command generated when data anomalies or conflicts are detected.

[0104] Therefore, this application demonstrates its ability to improve urban traffic flow. Specifically, by constructing a dynamic behavioral parameter set and employing behavioral pattern matching rules to accurately extract the behavioral characteristics of traffic participants, traffic planning can be analyzed based on the actual dynamic behavior of participants, improving the accuracy of traffic analysis and the realism of behavioral modeling. By distributing and synchronizing dynamic behavioral characteristics in real time, the system possesses stronger data processing parallelism and real-time performance, enabling rapid response to changes in traffic conditions. This allows for the construction of a dynamically updated traffic coordination mechanism, enhancing the flexibility and accuracy of overall traffic scheduling. Furthermore, by introducing an overlapping verification and deduction mechanism for traffic association information, quantitative modeling of the spatiotemporal linkages among traffic participants is achieved, forming a hierarchical interactive constraint structure. Finally, through a shared platform and data synchronization mechanism, optimized traffic allocation strategies are distributed and transmitted back in real time, achieving data collaboration and feedback loops between cross-regional traffic management systems, thereby ensuring the consistency and stability of planning adjustments across multiple terminals and regions.

[0105] In summary, the technical solution adopted in this application can realize distributed decision-making based on complex traffic planning data update delays, thereby improving the dynamic adaptability of traffic flow.

[0106] Example 2: This application provides a traffic planning data processing device, with reference to... Figure 4 As shown in the figure, this is a modular structure diagram of a traffic planning data processing device according to this embodiment of the present application. The data processing device includes:

[0107] The data acquisition module 100 is used to acquire traffic planning data for a specified road segment based on the traffic planning data platform, and extract the dynamic behavior characteristics of traffic participants in the specified road segment from the traffic planning data.

[0108] The data partitioning module 200 is used to construct a distributed traffic planning database, which divides the dynamic behavioral characteristics into distributed nodes according to traffic participation type, obtains the synchronization and following indicators corresponding to multiple traffic participation states, and replicates all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle.

[0109] The decision-making and simulation module 300 is used to collect traffic association information of traffic participants in the planned path, perform planning and simulation on the traffic association information to obtain a traffic decision database, and determine the interaction constraint level of traffic participants in traffic planning through the traffic decision database and the traffic linkage trend of traffic participants in a specified road segment at different time periods.

[0110] The data synchronization module 400 is used to perform traffic planning adjustments and synchronize them to a remote database using the traffic planning data sharing platform, based on the coordination planning cycle and the interaction constraint level.

[0111] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. This program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), on-time programmable read-only memory (OTPROM), electronically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0113] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A method for processing traffic planning data, characterized in that, The data processing method includes the following steps: Traffic planning data for a specified road segment is obtained based on the traffic planning data platform, and dynamic behavioral characteristics of traffic participants in the specified road segment are extracted from the traffic planning data. A distributed traffic planning database is constructed, and the dynamic behavioral characteristics are divided into distributed nodes according to traffic participation type to obtain the synchronization and car-following indicators corresponding to multiple traffic participation states. All synchronization and car-following indicators are replicated in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle. Traffic association information of traffic participants traveling in the planned route is collected, and the traffic association information is used for planning and simulation to obtain a traffic decision database. The interaction constraint level of traffic participants in traffic planning is determined by the traffic decision database and the traffic linkage trend of traffic participants in a specified road segment at different time periods. Based on the aforementioned coordination planning cycle and the aforementioned interaction constraint hierarchy, traffic planning adjustments are executed using the traffic planning data sharing platform and synchronized to the remote database; The specific steps involved constructing a distributed traffic planning database and classifying the dynamic behavioral characteristics into distributed nodes according to traffic participation types to obtain synchronization and car-following indices corresponding to multiple traffic participation states include: defining data classification rules for distributed nodes based on traffic participation types in the distributed traffic planning database; allocating the dynamic behavioral characteristics to corresponding nodes through the data classification rules and establishing cross-node dynamic synchronization nodes; defining state verification rules for multiple traffic participation states based on the feature correlations in the dynamic synchronization nodes; and extracting synchronization and car-following indices corresponding to multiple traffic participation states from the state verification rules. Specifically, the process of replicating all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle includes: setting synchronization trigger rules corresponding to all synchronization and following indicators; performing status checks on the synchronization trigger rules to obtain synchronization data copies; and outputting a dynamically updated coordination planning cycle based on the update frequency of the synchronization data copies and the road segment coordination requirements of the specified road segments. Specifically, determining the interaction constraint hierarchy of traffic participants in traffic planning through the traffic decision database and the traffic linkage trends of traffic participants in designated road segments at different time periods includes: determining the interactive behavior information of traffic participants based on the risk prediction weights in the traffic decision database and the traffic linkage trends; determining the planning coordination attributes in traffic planning based on the interactive behavior information and the participation effect indicators in designated road segments at different time periods; establishing hierarchical constraint judgment rules based on the planning coordination attributes, and generating the interaction constraint hierarchy of traffic participants in traffic planning. Specifically, the process of adjusting traffic planning and synchronizing it to a remote database using a traffic planning data sharing platform, based on the coordinated planning cycle and the interaction constraint hierarchy, includes: generating a traffic allocation strategy according to the coordinated planning cycle and the interaction constraint hierarchy; distributing the traffic allocation strategy to roadside control equipment on designated road sections through the traffic planning data sharing platform and triggering a multi-device collaborative execution verification process; and comparing the verified adjustment results with the remote database using the data synchronization channel of the traffic planning data sharing platform to complete incremental data synchronization and generate an anomaly rollback instruction set.

2. The traffic planning data processing method as described in claim 1, characterized in that, The aforementioned traffic planning data represents a set of structured road and traffic flow information that supports traffic design, scheduling, and optimization.

3. The traffic planning data processing method as described in claim 1, characterized in that, Extracting the dynamic behavioral characteristics of traffic participants in a designated road segment from the traffic planning data specifically includes: A dynamic behavior parameter set for a specified road segment is constructed based on the traffic planning data; Set behavior pattern matching rules based on the dynamic behavior parameter set; The behavioral trajectory data of traffic participants are reconstructed using the pattern matching rules to obtain the dynamic behavioral characteristics of traffic participants in a specified road segment.

4. The traffic planning data processing method as described in claim 1, characterized in that, The collection of traffic association information of traffic participants traveling along the planned route specifically includes: Obtain location data and timestamp information of traffic participants traveling along the planned route; The location data and timestamp information are used to generate motion trajectory association features of traffic participants; The overlap of the motion trajectory association features is verified to obtain the traffic association information of traffic participants traveling in the planned path.

5. The traffic planning data processing method as described in claim 1, characterized in that, The aforementioned coordination planning cycle refers to the time period that is dynamically adjusted based on real-time traffic data and road segment coordination needs.

6. A traffic planning data processing apparatus, used to execute a traffic planning data processing method as described in any one of claims 1 to 5, characterized in that, The data processing device includes: The data acquisition module is used to acquire traffic planning data for a specified road segment based on the traffic planning data platform, and extract the dynamic behavioral characteristics of traffic participants in the specified road segment from the traffic planning data. The data partitioning module is used to construct a distributed traffic planning database. It divides the dynamic behavioral characteristics into distributed nodes according to traffic participation type, obtains the synchronization and following indicators corresponding to multiple traffic participation states, and replicates all synchronization and following indicators in real time through a data synchronization protocol to form a dynamically updated coordination planning cycle. The decision-making and simulation module is used to collect traffic association information of traffic participants in the planned route, perform planning and simulation on the traffic association information to obtain a traffic decision database, and determine the interaction constraint level of traffic participants in traffic planning through the traffic decision database and the traffic linkage trend of traffic participants in a specified road segment at different time periods. The data synchronization module is used to perform traffic planning adjustments and synchronize them to a remote database using the traffic planning data sharing platform, based on the coordination planning cycle and the interaction constraint level.

Images