An automated highway toll management system

Abstract

The present invention relates to the technical field of transaction settlement, and specifically provides an automated highway toll management system. The system includes: a traffic status capture module that collects vehicle driving data, records vehicle positions, and updates them in a time series, analyzes vehicle speeds and directions, determines driving trajectories, uses the relative positions between vehicles to determine following and overtaking behaviors, and constructs the nodes and edges of a graph. In the present invention, through the comprehensive collection and real-time analysis of vehicle driving data, fine capture and dynamic update of traffic status are achieved, the interaction between vehicles is accurately evaluated, the key vehicles affecting traffic flow are timely identified. Based on this, toll standards are dynamically set to ensure reasonable allocation of road usage costs, reduce congestion risks, improve toll fairness and road usage efficiency, synchronize toll information in real time, make vehicle decisions more timely, avoid path selection errors caused by information lag, further optimize traffic flow distribution, improve traffic efficiency and effectively alleviate congestion problems.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction settlement, and particularly to an automated highway toll management system. Background Art

[0002] The technical field of transaction settlement involves various systems and methods for handling fund transfers, confirmations, and recordings in transactions. It is particularly crucial in financial and business environments, where these systems ensure the accuracy, transparency, and efficiency of transactions. Technologies in this field include automated settlement systems, electronic payment gateways, blockchain technology, and various security mechanisms for handling transactions ranging from simple retail transactions to complex cross-border financial transactions. Additionally, this technical field is constantly adapting to new market demands, such as contactless payments and cryptocurrency transactions, all aimed at increasing processing speed and reducing costs.

[0003] Among them, an automated highway toll management system refers to the use of electronic technology to automatically process the fees generated by vehicles during highway use. Such a system automatically identifies passing vehicles through electronic tags or license plate recognition technology, calculates the corresponding tolls, and eliminates the need for vehicles to stop and pay, greatly improving traffic flow and toll collection efficiency. The main purpose of the system is to simplify the toll collection process, reduce traffic congestion, and provide a more convenient and efficient road use experience.

[0004] In dealing with toll standards, existing technologies mostly adopt fixed standards, lacking flexible adjustment according to the real-time status of vehicles, unable to reflect traffic dynamic changes, easily leading to serious congestion on certain sections during peak periods and uneven traffic distribution. At the same time, there is a lack of identification of key vehicle behaviors, and the impact on traffic cannot be balanced through toll adjustments, resulting in increased congestion. In addition, the update of toll information lags behind, and vehicles cannot obtain accurate rates when choosing routes, affecting traffic efficiency and further exacerbating the imbalance and congestion of traffic flow. Summary of the Invention

[0005] The purpose of the present invention is to solve the drawbacks existing in the prior art and propose an automated highway toll management system.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An automated highway toll management system includes:

[0007] A traffic status capture module collects vehicle driving data, records vehicle positions, updates them in time series, analyzes vehicle speeds and directions, determines driving trajectories, determines following and overtaking behaviors using the relative positions between vehicles, constructs nodes and edges of a graph, continuously updates the characteristics of the nodes and edges of the graph, and generates a real-time traffic graph status;

[0008] Based on the real-time traffic map status, the data flow analysis module quantitatively analyzes node features, extracts driving patterns, calculates the interaction forces between vehicles, analyzes the impact of node connectivity on the network structure, and generates node influence scores.

[0009] Based on the node influence scores, the toll logic decision module sets toll standards for vehicle influence values, compares the influence differences between adjacent vehicles, dynamically adjusts toll strategies for vehicles at key nodes, determines the importance of driving routes and traffic flows, dynamically sets toll standards for multi-route vehicles, and generates optimized toll strategies.

[0010] Based on the optimized toll strategies, the toll rate adjustment and release module updates toll station parameters, sets toll rate values for toll devices, synchronizes the toll rate information of the vehicle-end system, issues notices on the update of vehicle tolls, records the log of toll rate changes at toll stations, and generates updated toll standard notices.

[0011] Based on the updated toll standard notices, the traffic flow reorganization module monitors the impact of toll changes on vehicle route selection, records the real-time driving trajectories of vehicles, analyzes the redistribution process of traffic flows, quantifies the changes in traffic flow density, calculates the route selection ratio after vehicle reorganization, and generates traffic flow dynamic results.

[0012] As a further solution of the present invention, the specific steps for obtaining the driving trajectory are as follows:

[0013] Based on the global positioning system, the geographical location coordinates of the vehicle are collected in real time, and the vehicle sends the position coordinate data to the data center every second to obtain real-time geographical location coordinate data.

[0014] Perform time serialization processing on the real-time geographical location coordinate data, mark each data point with a timestamp, and organize the data in chronological order to generate time-serialized geographical location coordinate data.

[0015] Extract the position at each time point from the time-serialized geographical location coordinate data, calculate the displacement between two adjacent time points, and use the formula:

[0016]

[0017] Generate a driving trajectory.

[0018] Where represents the abscissa of the geographical coordinate of the first time point, represents the ordinate of the geographical coordinate of the first time point, represents the abscissa of the geographical coordinate of the second time point, represents the ordinate of the geographical coordinate of the second time point, represents the straight-line distance between two adjacent time points.

[0019] As a further solution of the present invention, the steps for obtaining the real-time traffic map status are specifically as follows:

[0020] Through sensors and communication technologies, vehicles collect the geographical locations and speed data of themselves and surrounding vehicles, determine the relative motion states between vehicles including following or overtaking, and generate the relative position and behavior data between vehicles;

[0021] Using the relative position and behavior data between vehicles, construct the nodes and edges of the graph. Each vehicle serves as a node, and its relative motion behavior defines the direction and type of the edges, generating the basic structure of the graph;

[0022] Based on the basic structure of the graph, update the attributes of the nodes and edges in real time, including vehicle speed and vehicle spacing, using the formula:

[0023]

[0024] Generate the real-time traffic map status;

[0025] Wherein, represents the updated feature of the node or edge, represents the feature before update, represents the monitored feature change, is used to control the fusion degree of the previous data and the new data.

[0026] As a further solution of the present invention, the steps for obtaining the node influence score are specifically as follows:

[0027] Based on the real-time traffic map status, collect the feature data of multiple nodes, including vehicle speed, driving direction, and position. By analyzing the features, generate a node feature matrix, and call the feature matrix for node feature extraction to generate node feature data;

[0028] Using the node feature data, extract the driving mode, and by calculating the feature fitting degree, using the formula:

[0029]

[0030] Generate the node driving mode score;

[0031] Wherein, represents the driving mode score of node is the feature fitting degree between node and node and node is the feature dimension of node is node is the time factor, ​To avoid a constant with a denominator of zero;

[0032] Calculate the interaction force between vehicles according to the driving mode score of the nodes, using the formula:

[0033]

[0034] Generate data on the interaction force between vehicles;

[0035] Among them, represents the influence factor, indicating the interaction influence between node and node represents the driving mode score of node ; represents node and node The distance between them reflects the physical interval between the two nodes, is the proportionality coefficient of the interaction force, used to adjust the intensity of the interaction force;

[0036] Utilize the data on the interaction force between vehicles to analyze the impact of node connectivity on the network structure, and generate a node influence score by calculating the connectivity score.

[0037] As a further solution of the present invention, the steps for obtaining the optimized toll strategy are specifically as follows:

[0038] Based on the node influence score, analyze the impact of vehicles on traffic flow, identify key node vehicles, and set a toll benchmark for the vehicles to generate preliminary toll standard data;

[0039] Utilize the preliminary toll standard data to calculate the difference in influence scores between adjacent vehicles, using the formula:

[0040]

[0041] Generate influence difference data;

[0042] Among them, and respectively represent the influence scores of adjacent vehicles, used to measure the influence of differentiated vehicles in the traffic network, is a small positive number, used to ensure that the denominator is not zero when calculating the influence difference, represents the influence difference between adjacent vehicles, used to evaluate the gap in influence between the two vehicles;

[0043] Dynamically adjust the toll standard according to the influence difference data and the criticality of the vehicle's driving path, using the formula:

[0044]

[0045] Generate an adjusted toll strategy;

[0046] Among them, is the basic toll standard, reflecting the general toll standard when not referring to the target influence of individual vehicles, is an adjustment parameter used to adjust the toll standard according to the influence difference between vehicles, represents the current toll standard;

[0047] Combined with the adjusted toll strategy, referring to the criticality of traffic flow in multi-path selection, generate an optimized toll strategy.

[0048] As a further solution of the present invention, the specific steps for obtaining the updated toll standard notice are as follows:

[0049] Based on the optimized toll strategy, update the toll station parameters, collect the rate values of the current toll equipment, compare the difference between the current rate and the current adjustment standard, and generate the result of the rate value of the current toll equipment;

[0050] Using the result of the rate value of the current toll equipment, calculate the updated rate, using the formula:

[0051]

[0052] Generate the updated rate result;

[0053] Among them, represents the updated rate, represents the basic rate, represents the current rate, represents the adjustment coefficient, represents the additional factor coefficient;

[0054] Combined with the updated rate result, set the toll rate information of the vehicle end system, perform information synchronization and verification operations, and generate the result of the toll rate information of the vehicle end system;

[0055] According to the result of the toll rate information of the vehicle end system, issue a notice on the update of vehicle tolls, record the log of the toll rate change at the toll station, and generate an updated toll standard notice.

[0056] As a further solution of the present invention, the specific steps for obtaining the traffic flow dynamic result are as follows:

[0057] Based on the updated toll standard notice, monitor the real-time impact of toll changes on the vehicle passing path selection, record the changes in path selection, and generate vehicle path selection data;

[0058] Using the vehicle route selection data, record the real-time driving trajectory of the vehicle, analyze the data and monitor the vehicle flow trend on key sections, and generate the real-time driving trajectory result;

[0059] Extract data from the real-time driving trajectory result, analyze the redistribution process of traffic flow, and use the formula:

[0060]

[0061] Calculate and generate the traffic flow redistribution index;

[0062] Among them, represents the traffic volume of the th path, indicating the number of vehicles passing through the path, represents the distance of the th path, indicating the length of the path, represents the total traffic volume of all paths during the monitoring period, used to normalize the path data, represents the redistribution index, used to measure the utilization rate and mobility of multi-paths in the overall traffic flow;

[0063] Combined with the traffic flow redistribution index, quantify the change in traffic density and calculate the selection ratio of multi-paths, and use the dynamic analysis method to evaluate the change trend of path selection, and generate the traffic flow dynamic result.

[0064] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0065] In the present invention, through the comprehensive collection and real-time analysis of vehicle driving data, the fine capture and dynamic update of traffic conditions are realized, the interaction between vehicles is accurately evaluated, and the key vehicles affecting traffic flow are timely identified. Based on this, the toll standard is dynamically set to ensure the reasonable allocation of road use costs, reduce the congestion risk, and improve the toll fairness and road use efficiency. The toll information is synchronized in real time, making the vehicle decision-making more timely, avoiding path selection errors caused by information lag, further optimizing the traffic flow distribution, improving the traffic efficiency and effectively alleviating the congestion problem. Brief Description of the Drawings

[0066] Figure 1 is the system flow chart of the present invention;

[0067] Figure 2 is the flow chart of the acquisition steps of the driving trajectory of the present invention;

[0068] Figure 3 is the flow chart of the acquisition steps of the real-time traffic map state of the present invention;

[0069] Figure 4 is the flow chart of the acquisition steps of the node influence score of the present invention;

[0070] Figure 5 Flowchart of the acquisition steps for the optimized charging strategy of the present invention;

[0071] Figure 6 Flowchart of the acquisition steps for the updated charging standard notice of the present invention;

[0072] Figure 7 Flowchart of the acquisition steps for the traffic flow dynamic results of the present invention. Detailed implementation manners

[0073] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0074] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0075] Please refer to Figure 1 , an automated highway toll management system includes:

[0076] The traffic state capture module collects vehicle driving data, records the vehicle positions, updates them in time series, analyzes the vehicle speed and direction, determines the driving trajectory, determines the following and overtaking behaviors using the relative positions between vehicles, constructs the nodes and edges of a graph, continuously updates the features of the nodes and edges of the graph, and generates the real-time traffic graph state;

[0077] The data flow analysis module quantitatively analyzes the node features based on the real-time traffic graph state, extracts the driving patterns, calculates the interaction forces between vehicles, analyzes the influence of the connectivity between nodes on the network structure, and generates the node influence score;

[0078] The toll logic decision module sets the toll standards for the vehicle influence values based on the node influence score, compares the influence differences between adjacent vehicles, dynamically adjusts the toll strategy for the vehicles at key nodes, determines the importance of the driving path and traffic flow, dynamically sets the toll standards for multi-path vehicles, and generates the optimized toll strategy;

[0079] The rate adjustment and release module updates the toll station parameters based on the optimized charging strategy, sets the rate values of the toll collection equipment, synchronizes the passing rate information of the vehicle terminal system, releases the notice of vehicle passing fee update, records the toll rate change log of the toll station, and generates the updated toll standard notice;

[0080] Based on the updated toll standard notice, the traffic flow reorganization module monitors the impact of toll changes on vehicle passing route selection, records the real-time driving trajectories of vehicles, analyzes the redistribution process of traffic flow, quantifies the change in traffic flow density, calculates the route selection ratio after vehicle reorganization, and generates the traffic flow dynamic results.

[0081] The specific state of the real-time traffic map is node features and edge features. The node influence score includes node feature quantification, driving mode extraction, calculation of vehicle interaction forces, and node connectivity analysis. The optimized charging strategy specifically includes charging differentiation, key node pricing, and multi-path pricing. The updated toll standard notice includes toll rate setting, passing rate synchronization, and rate change record. The traffic flow dynamic results include traffic flow density change and vehicle route selection ratio.

[0082] Please refer to Figure 2 , and the steps for obtaining the driving trajectory are specifically as follows:

[0083] Based on the global positioning system, the geographical location coordinates of the vehicle are collected in real time. The vehicle sends the position coordinate data to the data center every second to obtain the real-time geographical location coordinate data;

[0084] Based on the geographical location coordinates collected in real time by the global positioning system, the vehicle uploads its current position coordinates to the data center every second. Through the real-time data, the position and movement path of the vehicle can be traced. By marking the timestamp of each data point, the data points can be organized into a time series. Such an organization method not only ensures the continuity of the data but also helps with subsequent position data processing and analysis. When performing route optimization and traffic flow analysis, time-series data can provide more information and insights. For example, by analyzing the moving speed and staying time of vehicles, the scheduling of traffic signals can be optimized to reduce traffic congestion. The obtained real-time geographical location coordinate data provides a basis for subsequent analysis.

[0085] Perform time serialization processing on the real-time geographical location coordinate data, mark each data point with a timestamp, and organize the data in chronological order to generate time-serialized geographical location coordinate data;

[0086] After performing time serialization processing on real-time geographical location coordinate data, each data point is marked with a timestamp, and the data is arranged in chronological order. This method of organizing data can track the driving path of a vehicle. By connecting the data points, a driving trajectory map of the vehicle is formed. This map not only helps to monitor the current position of the vehicle but also enables the analysis of its driving efficiency and route selection. In addition, the time-serialized data can be used to predict traffic patterns and optimize routes. By comparing the data in different time periods, peak hours and traffic bottlenecks can be identified, and then the operation of traffic lights can be adjusted or the scheduling of public transportation can be optimized. The generated time-serialized geographical location coordinate data provides an estimate for building a more effective traffic management system.

[0087] Extract the position at each time point from the time-serialized geographical location coordinate data, and calculate the displacement between two adjacent time points using the formula:

[0088]

[0089] Generate a driving trajectory;

[0090] Among them, represents the abscissa of the geographical coordinates of the first time point, represents the ordinate of the geographical coordinates of the first time point, represents the abscissa of the geographical coordinates of the second time point, represents the ordinate of the geographical coordinates of the second time point, represents the straight-line distance between two adjacent time points.

[0091] Formula:

[0092]

[0093] The advantage of the formula is that by calculating the distance between two time points, the moving speed and driving state of the vehicle can be monitored in real time, which helps the traffic management center to respond to estimated traffic accidents or congestion situations.

[0094] Detailed explanation of the formula and the derivation process of the formula calculation:

[0095] Set that at time point t1, the vehicle is at the geographical location , and at time point t2, it is at . Calculate the distance between these two time points:

[0096]

[0097] The results show that the vehicle has moved approximately 42.43 meters between two time points. If the time interval is 1 second, the vehicle's speed can be calculated to monitor whether its driving condition is normal. The calculation results provide basic data for subsequent traffic behavior analysis and traffic flow prediction.

[0098] Please refer to Figure 3 , and the steps to obtain the real-time traffic map status are specifically as follows:

[0099] Through sensors and communication technologies, the vehicle collects the geographical locations and speed data of itself and surrounding vehicles, determines the relative motion states between vehicles including following or overtaking, and generates relative position and behavior data between vehicles;

[0100] Through the sensors and communication technologies installed in the vehicle, the positions and speed information of the vehicle and its surrounding vehicles are collected in real time. Based on these data, data processing and analysis methods are used to determine the relative motion states between vehicles, including following and overtaking behaviors. This process includes obtaining raw data from sensors, identifying vehicle behavior patterns through algorithms, and classifying and storing behavior data to provide input data for subsequent traffic map construction, generating relative position and behavior data between vehicles.

[0101] Using the relative position and behavior data between vehicles, the nodes and edges of the graph are constructed. Each vehicle serves as a node, and its relative motion behavior defines the direction and type of the edge, generating the basic structure of the graph;

[0102] Utilizing the vehicle behavior data obtained from sensors and combining with the real-time position information of the vehicle, the nodes and edges of the traffic flow map are constructed. Each vehicle represents a node, and its relative behavior with other vehicles including following or overtaking defines the direction and type of the edge. This process not only includes data collection and analysis but also the implementation of a graph construction algorithm based on vehicle behavior patterns to dynamically describe the traffic conditions on the road and generate the basic structure of the traffic map.

[0103] Based on the basic structure of the graph, the attributes of the nodes and edges are updated in real time, including vehicle speed and vehicle spacing, using the formula:

[0104]

[0105] Generate the real-time traffic map status;

[0106] Among them, represents the updated characteristics of the node or edge, represents the characteristics before update, represents the monitored change in characteristics, is used to control the degree of fusion between the previous data and the new data.

[0107] Formula:

[0108]

[0109] The advantage of the formula is that it provides a method for dynamically updating the features of traffic map nodes and edges, making the traffic state more real-time and accurate. By adjusting , the influence of previous data and newly observed data can be balanced, thus optimizing the prediction and management of traffic flow.

[0110] Detailed explanation of the formula and the derivation process of formula calculation:

[0111] Set that in one data update cycle, the original speed feature value of a vehicle is 30 km / h, and the observed speed change is 5 km / h. The smoothing factor is set to 0.2, representing the weight of new data. According to the formula, the current speed feature value is calculated as follows:

[0112]

[0113] The result shows that referring to the combination of previous data and newly observed data, the updated speed of the vehicle is 25 km / h, which helps to adjust the state of the vehicle in the traffic map in real time, thus providing more accurate traffic flow information.

[0114] Please refer to Figure 4 , and the specific steps for obtaining the node influence score are as follows:

[0115] Based on the real-time traffic map state, collect the feature data of multiple nodes, including vehicle speed, driving direction and position. By analyzing the features, generate a node feature matrix, and call the feature matrix for node feature extraction to generate node feature data;

[0116] Based on the real-time traffic map state, the collection of node feature data involves the real-time monitoring of vehicle speed, driving direction and position. The data is continuously captured by the sensors of the traffic monitoring system and transmitted to the data processing center in real time through the wireless network. The data processing center uses high-performance servers to analyze and process the collected data, uses data mining techniques to identify driving patterns and behavior anomalies. The feature matrix of each node consists of a speed vector, a direction angle and a position coordinate. The features are merged through a data fusion algorithm to ensure the integrity and accuracy of the information. The system dynamically adjusts and optimizes the traffic flow prediction model by comparing the previous data and the real-time data, and the generated node feature data is used for traffic management and control decision support.

[0117] Using the node feature data, extract the driving pattern. By calculating the feature fitting degree, use the formula:

[0118]

[0119] Generate the driving mode score of the node;

[0120] Among them, represents the driving mode score of the node , is the feature fitting degree between the node and the node , is the feature dimension of the node , is the time factor, is a constant to avoid a zero denominator;

[0121] Formula:

[0122]

[0123] Detailed explanation of the formula and the derivation process of the formula calculation:

[0124] This formula is used to evaluate the driving mode score of the vehicle , based on the fitting degree between other vehicles and the vehicle and the time factor . Standardization is achieved through the feature dimension and a decimal number to avoid division-by-zero errors.

[0125] : The feature fitting degree between vehicle and vehicle is obtained by calculating the cosine fitting degree of the feature vectors of the two vehicles. If the speed of vehicle is 60 km / h and the direction is north, while the speed of vehicle j is 62 km / h and the direction is also north, then is close to 1, indicating a high degree of similarity.

[0126] : The time factor reflects the proximity of the data time point of vehicle to the scoring calculation time, and is calculated from the reciprocal of the time difference. If the data is 1 hour from now, is 1, and if the data is 2 hours from now, is 0.5.

[0127] : The feature dimension of vehicle includes speed, direction, and behavior. If vehicle has three features, then .

[0128] : A small constant, 0.01, is used to ensure that the denominator is not zero.

[0129] There are two vehicles set = 1 and = 2 are compared with the vehicles to obtain the following parameter values:

[0130] (similar in height to vehicle 1)

[0131] (moderately similar to vehicle 2)

[0132] (data from 1 hour ago)

[0133] (data from 2 hours ago)

[0134] (vehicle has three characteristic dimensions)

[0135] (a small constant to avoid division by zero)

[0136] Formula calculation process:

[0137]

[0138] The results show that the driving pattern score of the vehicle is 0.424, which reflects the weighted fitness of other vehicles with the most similar characteristics in terms of time and behavior. This score helps to determine the behavior pattern of the vehicle in the traffic network and is the basis for iterative analysis of vehicle interactions and mobility.

[0139] According to the driving pattern scores of the nodes, calculate the mutual forces between vehicles using the formula:

[0140]

[0141] Generate data on the mutual forces between vehicles;

[0142] Among them, represents the influence factor, indicating the interaction influence between node and node ; represents the driving pattern score of node ; represents node and the distance between node reflecting the physical interval between the two nodes; is the proportionality coefficient of the mutual force, used to adjust the intensity of the mutual force;

[0143] Formula:

[0144]

[0145] Detailed Explanation of the Formula and Derivation Process of Formula Calculation:

[0146] This formula is used to calculate the between the vehicle and the vehicle The mutual force between them is a key indicator reflecting the degree of mutual influence of the behaviors between the two vehicles. The parameter definitions in the formula are as follows:

[0147] and : The driving mode scores of vehicle and vehicle These scores reflect the behavioral characteristics of the vehicles. The has been calculated in the previous steps. Set to 0.5.

[0148] : Influence factor, characterizing the and The strength of the interaction between them. If the two vehicles often drive on the same section of the road, the value is relatively high, set to 0.8.

[0149] : The actual distance between vehicle and is in meters. Set the distance between the two vehicles to 100 meters.

[0150] : Proportional coefficient, determined according to vehicle density and traffic flow, set to 0.05. This value is obtained based on real-time traffic conditions and data analysis.

[0151] Let the numbers in the formula calculation process be as follows: , , , , (meters)

[0152] Calculation process:

[0153]

[0154] The result shows that the mutual force between vehicle and vehicle is 0.000848. This value is relatively small, indicating that although the two vehicles are relatively similar and relatively close, due to high traffic mobility or similar vehicle speeds, the mutual force is not large.

[0155] Using the data of the interaction forces between vehicles, analyze the impact of the connectivity between nodes on the network structure, and generate node influence scores by calculating connectivity scores.

[0156] Analyze the connectivity between nodes using the data of the interaction forces between vehicles. This process involves comparing the actual monitored vehicle behaviors with the predictions in the traffic model, calculating the influence score of each node in the traffic network, which refers to the geographical location, speed of the vehicle, and the interaction forces of the surrounding vehicles. Calculate the connectivity of multiple nodes through a mathematical model, and iteratively analyze how these connectivities affect the fluidity and stability of the entire network. The model will output the influence scores of each node, and these scores assist the traffic management system in identifying key road sections and traffic congestion points, optimizing the allocation of traffic signals and route planning. The results are directly used to adjust traffic lights and issue traffic warnings to improve road usage efficiency and reduce congestion.

[0157] Please refer to Figure 5 , and the specific steps for obtaining the optimized toll strategy are as follows:

[0158] Based on the node influence scores, analyze the impact of vehicles on the traffic flow, identify the vehicles at key nodes, set a toll benchmark for the vehicles, and generate preliminary toll standard data;

[0159] By analyzing the vehicle influence scores, determine which vehicles belong to key nodes. Vehicles at key nodes usually have greater influence, and their impact on the traffic flow is particularly significant. Therefore, it is crucial to consider this factor when setting toll standards. By collecting influence data, set higher toll standards for vehicles with greater influence, which can more fairly allocate the road usage costs, and at the same time encourage drivers to choose more reasonable travel times and routes, thereby optimizing traffic fluidity and reducing congestion.

[0160] Using the preliminary toll standard data, calculate the difference in influence scores between adjacent vehicles, using the formula:

[0161]

[0162] Generate influence difference data;

[0163] Among them, and respectively represent the influence scores of adjacent vehicles, used to measure the influence of different vehicles in the traffic network, is a small positive number, used to ensure that the denominator is not zero when calculating the influence difference, represents the influence difference between adjacent vehicles, used to evaluate the gap in influence between two vehicles;

[0164] Formula:

[0165]

[0166] The benefit of the formula is that it quantifies the difference in influence between two vehicles, provides an actual numerical difference, which is convenient for adjusting the toll strategy and is crucial when referring to the fairness of the toll strategy and the effectiveness of traffic management.

[0167] Detailed explanation of the formula and the derivation process of the formula calculation:

[0168] Let , This represents the influence scores of two vehicles, where To ensure that the calculation can still proceed stably when the difference in influence scores is very small. The calculation process is as follows:

[0169]

[0170]

[0171]

[0172]

[0173]

[0173] The result shows that the difference in the influence scores of the two vehicles is 10.05. This difference will be used for subsequent adjustment of the toll standard, so as to ensure that the vehicle with greater influence bears more traffic costs. In this way, it encourages drivers to avoid peak hours or choose alternative routes, thus helping to relieve the traffic pressure on key roads.

[0174] According to the influence difference data and the criticality of the vehicle's driving path, dynamically adjust the toll standard, using the formula:

[0175]

[0176] Generate the adjusted toll strategy;

[0177] Among them, is the basic toll standard, reflecting the general toll standard when not referring to the target influence of individual vehicles, is the adjustment parameter, used to adjust the toll standard according to the influence difference between vehicles, represents the current toll standard;

[0178] Formula:

[0179]

[0180] The benefit of the formula is that by adding to the basic toll depending on the influence difference Adjustment items are used to flexibly adjust the charging strategy to match the actual influence of different vehicles, so as to more fairly allocate the road use cost, and use economic means to encourage drivers to optimize their driving routes and times, thereby reducing traffic congestion.

[0181] Detailed formula explanation and formula calculation derivation process:

[0182] Set The basic charging standard per unit, obtained from the above results , set the adjustment coefficient , the calculation process is as follows:

[0183]

[0184]

[0185]

[0186]

[0187]

[0188] The results show that after referring to the influence difference between adjacent vehicles, the current charging standard should be adjusted to 50.52 units, which reflects the fair charging principle based on the actual influence of vehicles, and through this differential charging, it encourages drivers to choose driving times and routes with less impact on traffic flow, aiming to optimize traffic flow and reduce congestion.

[0189] Combined with the adjusted charging strategy, referring to the criticality of traffic flow in multi-path selection, an optimized charging strategy is generated.

[0190] Based on referring to the criticality of traffic flow on multiple driving routes, combined with the adjusted charging strategy, the overall charging strategy is iteratively optimized to ensure that the charging standard can dynamically reflect various driving conditions and traffic loads. This optimization refers to multiple variables, including the driving route of the vehicle, traffic density, and time period. By comprehensively considering these factors through an algorithm model, the generated optimized charging strategy aims to regulate traffic flow through economic means to make it smoother, reduce traffic congestion during peak hours, and the optimized strategy supports its effectiveness through real-time traffic data, so as to achieve the optimal charging effect in different traffic situations, improve the use efficiency of road resources, and implementing this strategy can significantly improve the adaptability and predictability of traffic management, making the traffic system more efficient and sustainable.

[0191] Please refer to Figure 6 , the specific steps to obtain the updated charging standard notice are as follows:

[0192] Based on the optimized charging strategy, update the toll station parameters, collect the rate values of the current toll collection equipment, compare the difference between the current rate and the current adjustment standard, and generate the rate value result of the current toll collection equipment;

[0193] When updating the toll station parameters, first collect the current rate values of the equipment. The data collection work is completed by accessing the management system of each toll station. The system records the settings and adjustment records of multiple devices. By comparing the data with the current standards of the policy orientation, it is determined which devices need to adjust the rate values to comply with the current toll collection policy. This comparison process involves data extraction, analysis, and comparison, ensuring the accuracy and timeliness of the rate adjustment and generating the rate value result of the current toll collection equipment.

[0194] Using the rate value result of the current toll collection equipment, calculate the updated rate using the formula:

[0195]

[0196] Generate the updated rate result;

[0197] Where, represents the updated rate, represents the base rate, represents the current rate, represents the adjustment coefficient, represents the additional factor coefficient;

[0198] Formula:

[0199]

[0200] The advantage of the formula is that by introducing the adjustment coefficient and the additional factor coefficient , the rate is dynamically adjusted based on market and policy changes, improving the adaptability and flexibility of the toll collection model.

[0201] Detailed explanation of the formula and the derivation process of the formula calculation:

[0202] Assume (base rate, set to 1 yuan per kilometer of passage), (current rate, already increased by 20%), (adjustment coefficient, indicating an adjustment range of 50% of the difference between the base rate and the current rate), (additional factor coefficient, indicating an additional increase of 5%).

[0203] The calculation process is as follows:

[0204] 1. Calculate the differential adjustment:

[0205] 2. Apply adjustment factors:

[0206] 3. Calculate the new base rate:

[0207] 4. Apply additional factor coefficients:

[0208] The updated rate Yuan.

[0209] The results show that, with reference to the current market conditions and policy requirements, the current prevailing rate is adjusted to 1.155 yuan per kilometer, ensuring the fairness of the rate and the consistency of the policy.

[0210] Combined with the updated rate results, set the prevailing rate information of the vehicle-end system, perform information synchronization and verification operations, and generate the vehicle-end system prevailing rate information results;

[0211] When setting the prevailing rate information of the vehicle-end system, the operator needs to extract the associated values from the updated rate data, input the values through vehicle management, perform format verification and logical checks on these data to avoid data errors or inconsistencies, and ensure that the current rate can be accurately synchronized to each passing vehicle. Including data upload, processing, and distribution, the operator needs to monitor the data transmission process and promptly handle any synchronization errors that occur, generate the vehicle-end system prevailing rate information results, and the data will be used to calculate the actual passing fees of the vehicle.

[0212] According to the vehicle-end system prevailing rate information results, issue a notice on the update of vehicle passing fees, record the toll rate change log at the toll station, and generate an updated toll standard notice.

[0213] Issuing a notice on the update of vehicle passing fees and recording the toll rate change log at the toll station involve extracting the current rate from the vehicle-end system prevailing rate information and publishing the change information to the public and related departments through the network broadcast system. At the same time, the operator needs to update the log in the internal management system, record the details of each toll rate change, including the change time, the equipment involved, the toll rates before and after the change, as well as the reasons and expected impacts of the change. These records are crucial for subsequent data review, policy evaluation, and compliance checks, ensuring the transparency and traceability of the toll policy and generating an updated toll standard notice.

[0214] Please refer to Figure 7 , the specific steps for obtaining the traffic flow dynamic results are as follows:

[0215] Based on the updated toll standard notice, monitor the real-time impact of toll changes on vehicle passing route selection, record the changes in route selection, and generate vehicle route selection data;

[0216] Based on the updated toll standard notice, record the changes in vehicle route selections on key sections. Capture data through the real-time traffic monitoring system, use GPS tracking technology to determine the actual driving routes of vehicles, and compare with the data before the notice was issued. Analyze the preference differences in vehicle travel routes before and after the toll change, and display the sensitivity of vehicles to the differential toll sections in the form of charts and percentages. This real-time monitoring not only assists urban traffic management departments in evaluating the actual impact of toll strategies but also provides data support for adjusting future toll policies.

[0217] Utilize vehicle route selection data to record the real-time driving trajectories of vehicles, analyze the data, and monitor the vehicle flow trends on key sections to generate real-time driving trajectory results;

[0218] Based on vehicle route selection data, implement a trajectory recording program. Cameras and sensors deployed at multiple key traffic nodes collect vehicle passing data, use big data analysis technology to process the collected information, identify frequently occurring routes and traffic congestion points through algorithm models, and the analysis model will predict traffic flow changes based on time series, thereby providing a scientific basis for traffic dispatching and effectively predicting and managing urban traffic flow.

[0219] Extract data from the real-time driving trajectory results, analyze the redistribution process of traffic flow, and use the formula:

[0220]

[0221] Calculate and generate traffic flow redistribution indicators;

[0222] Among them, represents the traffic volume of the th route, indicating the number of vehicles passing through the route, represents the distance of the th route, indicating the length of this route, represents the total traffic volume of all routes during the monitoring period, used to normalize the route data, represents the redistribution indicator, used to measure the utilization rate and mobility of multiple routes in the overall traffic flow;

[0223] Formula:

[0224]

[0225] The benefit of the formula is that it provides an indicator to quantify the traffic flow redistribution and can calculate the impact of traffic flow changes on route selection,

[0226] Detailed explanation of the formula and the derivation process of formula calculation:

[0227] Set that there are three route branches on a key road, and the traffic volumes are respectively , , , the corresponding path distances are respectively , , , and the total traffic flow , and the calculation process is as follows:

[0228]

[0229] The results show that on average each vehicle travels nearly 2 kilometers, which reflects that after the toll change, vehicles tend to choose shorter routes to reduce costs.

[0230] Combined with the traffic flow redistribution index, quantify the change in traffic flow density and calculate the selection ratio of multiple paths, and use the dynamic analysis method to evaluate the change trend of path selection to generate the traffic flow dynamic results.

[0231] Use the dynamic analysis method to evaluate the change trend of path selection, record the selection of each vehicle and the corresponding time points, input the data into the computer simulation program for processing, simulate the traffic flow distribution under different scenarios by setting different traffic volume and time parameters, calculate the routes preferentially selected by vehicles under different toll standards, and form a report, which includes the impact of various toll changes on traffic flow density and path selection ratio, providing data for urban traffic planning and toll policy adjustment.

[0232] The above is only the preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. An automated highway toll management system, characterized in that, The system includes: The traffic state capture module collects vehicle driving data, records vehicle positions, updates them in time series, analyzes vehicle speeds and directions, determines driving trajectories, determines following and overtaking behaviors using the relative positions between vehicles, constructs the nodes and edges of a graph, continuously updates the characteristics of the nodes and edges of the graph, and generates the real-time traffic graph state; The data flow analysis module quantifies and analyzes node characteristics, extracts driving patterns, calculates the interaction forces between vehicles, analyzes the impact of node connectivity on the network structure based on the real-time traffic graph state, and generates node influence scores; The toll logic decision module sets toll standards for vehicle influence values based on the node influence scores, compares the influence differences between adjacent vehicles, dynamically adjusts toll strategies for vehicles at key nodes, determines the importance of driving paths and traffic flows, dynamically sets toll standards for multi-path vehicles, and generates optimized toll strategies; The rate adjustment and release module updates toll station parameters, sets the rate values of toll devices, synchronizes the toll rate information of the vehicle-side system, issues announcements on vehicle toll updates, records the toll rate change logs of toll stations, and generates updated toll standard announcements based on the optimized toll strategies; The traffic flow reorganization module monitors the impact of toll changes on vehicle passing path selections, records the real-time driving trajectories of vehicles, analyzes the redistribution process of traffic flows, quantifies the changes in traffic flow density, calculates the path selection ratios of vehicles after reorganization, and generates traffic flow dynamic results based on the updated toll standard announcements; The specific steps for obtaining the optimized toll strategy are as follows: Based on the node influence scores, analyze the impact of vehicles on traffic flows, identify key node vehicles, and set toll baselines for vehicles to generate preliminary toll standard data; Using the preliminary toll standard data, calculate the influence score differences between adjacent vehicles, using the formula: ； Generate influence difference data; Among them, and respectively represent the influence scores of adjacent vehicles, which are used to measure the influence of differentiated vehicles in the traffic network. is a small positive number used to ensure that the denominator is not zero when calculating the influence difference. represents the influence difference between adjacent vehicles and is used to evaluate the gap in influence between two vehicles. According to the influence difference data and the criticality of the vehicle driving paths, dynamically adjust the toll standards, using the formula: ； Generate the adjusted toll strategy; Among them, is the basic charging standard, reflecting the general charging standard when not referring to the target influence of individual vehicles, is an adjustment parameter used to adjust the charging standard according to the influence difference between vehicles, represents the current charging standard; Combine the adjusted toll strategy and refer to the criticality of traffic flows with multi-path selections to generate the optimized toll strategy.

2. The automated highway toll management system according to claim 1, wherein The real-time traffic graph state specifically refers to node characteristics and edge characteristics. The node influence scores include node characteristic quantification, driving pattern extraction, calculation of interaction forces between vehicles, and node connectivity analysis. The optimized toll strategy specifically refers to toll differentiation, pricing for key nodes, and multi-path pricing. The updated toll standard announcements include toll rate setting, synchronization of passing toll rates, and recording of rate changes. The traffic flow dynamic results include changes in traffic flow density and vehicle path selection ratios.

3. The automated highway toll management system according to claim 2, wherein The specific steps for obtaining the driving trajectory are as follows: Based on the Global Positioning System, collect the geographical location coordinates of vehicles in real time. Vehicles send the position coordinate data to the data center every second to obtain real-time geographical location coordinate data; Perform time serialization processing on the real-time geographical location coordinate data, mark each data point with a timestamp, and organize the data in chronological order to generate time-serialized geographical location coordinate data; Extract the location at each time point from the time - serialized geographic location coordinate data, calculate the displacement between two adjacent time points, using the formula: ； Generate a driving trajectory; Among them, represents the abscissa of the geographical coordinates at the first time point, represents the ordinate of the geographical coordinates at the first time point, represents the abscissa of the geographical coordinates at the second time point, represents the ordinate of the geographical coordinates at the second time point, represents the straight-line distance between two adjacent time points.

4. The automated highway toll management system according to claim 3, characterized in that, The specific steps for obtaining the real - time traffic map status are as follows: Through sensors and communication technologies, the vehicle collects the geographic locations and speed data of itself and surrounding vehicles, determines the relative motion states between vehicles including following or overtaking, and generates relative position and behavior data between vehicles; Use the relative position and behavior data between vehicles to construct the nodes and edges of a graph. Each vehicle serves as a node, and its relative motion behavior defines the direction and type of the edge, generating the basic structure of the graph; Based on the basic structure of the graph, update the attributes of nodes and edges in real - time, including vehicle speed and vehicle spacing, using the formula: ； Generate the real - time traffic map status; Among them, represents the features of the updated nodes or edges, represents the features before the update, represents the monitored feature changes, is used to control the degree of fusion of the previous data and the new data.

5. The automated highway toll management system according to claim 4, wherein The specific steps for obtaining the node influence score are as follows: Based on the real - time traffic map status, collect the feature data of multiple nodes, including vehicle speed, driving direction, and location. By analyzing the features, generate a node feature matrix, and call the feature matrix for node feature extraction to generate node feature data; Use the node feature data to extract the driving pattern, and calculate the feature fitting degree, using the formula: ； Generate the node driving pattern score; Among them, represents the driving mode score of the node , is the feature fitting degree between the node and the node , is the feature dimension of the node , is the time factor, is a constant to avoid a zero denominator; According to the node driving pattern score, calculate the mutual force between vehicles, using the formula: ； Generate the mutual force data between vehicles; Among them, represents the influence factor, indicating the node and the node The interactive influence between them, represents the driving mode score of the node ; represents the node and the node The distance between them reflects the physical interval between the two nodes, is the proportionality coefficient of the interaction force, used to adjust the intensity of the interaction force; Utilize the mutual force data between vehicles to analyze the impact of node connectivity on the network structure. By calculating the connectivity score, generate the node influence score.

6. The automated highway toll management system according to claim 5, wherein The specific steps for obtaining the updated toll standard notice are as follows: Based on the optimized toll strategy, update the toll station parameters, collect the rate values of current toll collection equipment, compare the difference between the current rate and the current adjustment standard, and generate the result of the rate value of current toll collection equipment; Use the result of the rate value of current toll collection equipment to calculate the updated rate, using the formula: ； Generate the updated rate result; Among them, represents the updated rate, represents the base rate, represents the current rate, represents the adjustment coefficient, represents the additional factor coefficient; Combined with the updated rate result, set the toll rate information of the vehicle - end system, perform information synchronization and verification operations, and generate the result of the toll rate information of the vehicle - end system; According to the result of the toll rate information of the vehicle - end system, issue a notice on the update of vehicle tolls, record the log of toll rate changes at the toll station, and generate the updated toll standard notice.

7. The automated highway toll management system according to claim 6, characterized in that, The specific steps for obtaining the traffic flow dynamic result are as follows: Based on the updated toll standard notice, monitor the real - time impact of toll changes on vehicle travel path selection, record the changes in path selection, and generate vehicle path selection data; Use the vehicle path selection data to record the real - time driving trajectory of vehicles, analyze the data and monitor the vehicle flow trend at key sections, and generate the real - time driving trajectory result; Extract data from the real - time driving trajectory result, analyze the redistribution process of traffic flow, using the formula: ； Calculate and generate traffic flow redistribution indicators; Among them, represents the traffic volume of the th path, indicating the number of vehicles passing through the path, represents the distance of the th path, indicating the length of the path, represents the total traffic volume of all paths during the monitoring period, used to normalize the path data, represents the redistribution index, used to measure the utilization rate and mobility of multi-paths in the overall traffic flow; Combined with the traffic flow redistribution indicators, quantify the change in traffic flow density and calculate the selection ratio of multiple paths, and use dynamic analysis methods to evaluate the change trend of path selection, generating the traffic flow dynamic result.

Images