Expressway quasi-free flow pre-transaction charging lane configuration method

Abstract

The invention discloses an expressway quasi-free flow pre-transaction toll lane configuration method, which belongs to the technical field of expressways, and comprises the following steps: S1, carrying out the preprocessing and analysis of vehicle passing big data, and setting a toll standard for each lane of an expressway; s2, based on a path planning technology, guiding the vehicle to run on a lane with the minimum traffic flow all the time, performing automatic identification on the vehicle, and automatically settling vehicle fees to enable the vehicle to pass rapidly; and S3, vehicle traffic condition prediction and early warning: carrying out fault prediction and health management on the vehicle traffic condition of each lane on the expressway. According to the invention, the problems that the lane cannot be intelligently optimized, the quasi-free flow of vehicle passing cannot be realized, the road utilization rate is reduced, and the traffic jam is caused in the prior art are solved. According to the invention, through intelligent optimization of the lanes, quasi-free flow in the vehicle passing process is realized, the purposes of improving the road utilization rate and reducing congestion are achieved, and the requirements of modern society for efficient and rapid traffic can be met.

Description

Technical Field

[0001] The invention relates to the technical field of expressways, and in particular to a method for configuring quasi-free-flow pre-transaction toll lanes on expressways. Background Art

[0002] During special time periods such as peak hours and holidays, highway toll stations become major bottlenecks, causing large-scale congestion; traditional toll collection methods can no longer meet the modern society's demand for efficient and fast transportation.

[0003] The Chinese patent with publication number CN114826786A discloses a highway toll audit system, including: a head office system, a provincial center system and a branch company system, which makes full use of the head office system resources, uses the Internet, cloud storage and other advanced information technologies, builds a parallel reconciliation system for highway toll revenue based on big data, realizes in-depth mining and scientific analysis of business data, intelligent integration of internal and external information resources, decentralized sharing, and vertical linkage and horizontal collaboration between the company's functional departments and branches; however, the patent has the following defects:

[0004] When existing vehicles pass, lanes cannot be intelligently optimized, and quasi-free flow cannot be achieved during the passage of vehicles, which reduces road utilization, causes traffic congestion, and cannot meet the needs of modern society for efficient and fast transportation. Summary of the invention

[0005] The purpose of the present invention is to provide a method for configuring quasi-free-flow pre-transaction toll lanes on highways, which can achieve quasi-free flow during vehicle passage by intelligently optimizing lanes, thereby improving road utilization and reducing congestion, meeting the needs of modern society for efficient and fast transportation, and solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The method for configuring a quasi-free flow pre-transaction toll lane on a highway includes the following steps:

[0008] S1. Vehicle traffic big data collection and preprocessing:

[0009] Carry out real-time monitoring and continuous collection of vehicle flow, vehicle type, driving speed and driving time of each lane on the highway, determine the vehicle traffic big data of each lane on the highway, pre-process and analyze the vehicle traffic big data, and set charging standards for each lane of the highway;

[0010] S2. Automatic vehicle identification and fast passage:

[0011] According to the traffic flow information of each lane during the vehicle's passage, based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the lane with the least traffic flow. When the vehicle passes, based on the vehicle recognition technology, the vehicle is automatically identified and the vehicle fee is automatically settled, so that the vehicle can pass quickly;

[0012] S3. Vehicle traffic situation prediction and warning:

[0013] Based on machine learning technology, fault prediction and health management are carried out on the vehicle traffic conditions in each lane on the highway, the vehicle traffic demand and conditions are predicted, the quasi-free-flow vehicle traffic results on the highway are determined, and based on the quasi-free-flow vehicle traffic results on the highway, early warning and health management of vehicle traffic conditions are carried out to adapt to traffic needs in different scenarios.

[0014] Preferably, in S1, the vehicle traffic big data of each lane on the highway is determined, and the following operations are performed:

[0015] Based on the high-definition cameras installed on the highway, the traffic flow and vehicle type of each lane on the highway are monitored and collected continuously in real time to obtain traffic flow and vehicle type information;

[0016] Based on the on-board sensors installed on the vehicles, the vehicle speed and driving time of each lane on the highway are monitored and collected continuously in real time to obtain the vehicle speed and driving time information;

[0017] Among them, the vehicle traffic big data of each lane on the highway is determined based on the traffic flow and vehicle model information, vehicle speed and driving time information.

[0018] Preferably, in S1, a suitable charging standard is set for each lane of the expressway, and the following operations are performed:

[0019] Obtain big data on vehicle traffic in each lane on the highway;

[0020] Clean the big data of vehicle traffic in each lane on the highway;

[0021] Remove inconsistent data, invalid values ​​and missing values ​​that are useless for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway from the big data of vehicle traffic in each lane on the expressway, and determine the big data of vehicle traffic in each lane on the expressway that is useful for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway;

[0022] The traffic volume and vehicle type information in the big data of vehicle traffic in each lane on the highway are analyzed, and the charging standards are set for each lane of the highway in combination with the vehicle speed and driving time information.

[0023] Preferably, the data quality detection is performed on the vehicle traffic big data of each lane on the expressway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the expressway, including:

[0024] Extract and classify the vehicle traffic big data of each lane on the highway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the highway, and obtain a data set corresponding to each data type, wherein the data type includes vehicle flow, vehicle type, driving speed and driving time;

[0025] Extract the number of data contained in the data set corresponding to the traffic flow data;

[0026] Comparing the number of data contained in the data set corresponding to the vehicle flow data with a preset first data number threshold;

[0027] When the number of data contained in the data set corresponding to the vehicle flow data is lower than a preset first data number threshold, the missing value position corresponding to the vehicle flow data is retrieved;

[0028] For each missing value position corresponding to the vehicle flow data, extract the two valid data with the most recent data collection time as a reference valid data group;

[0029] Compare the data average value corresponding to the reference valid data group with the middle value of the data set corresponding to the vehicle flow data, and use the difference data between the data average value corresponding to the reference valid data group and the middle value of the data set corresponding to the vehicle flow data as the first difference data;

[0030] The first difference data corresponding to each missing value of the vehicle flow data is combined with the valid data in the data set corresponding to the vehicle flow data to obtain the filling value corresponding to each missing value contained in the vehicle flow data, wherein the filling value corresponding to each missing value of the vehicle flow data is obtained by the following formula:

[0031]

[0032] Among them, R t Indicates the filling value corresponding to each missing value of the traffic flow data; X 01 and X 02 Respectively represent the two valid data values ​​contained in the reference valid data group; X c01 represents the first difference data; n represents the total number of valid data in the data set corresponding to the traffic flow data; X i Indicates the data value of the i-th valid data in the data set corresponding to the traffic flow data;

[0033] The missing value position is filled with data using the filling value corresponding to each missing value of the vehicle flow data.

[0034] Preferably, the data quality detection of the vehicle traffic big data of each lane on the expressway where the quasi-free flow pre-transaction toll lane configuration is useful also includes:

[0035] Extract the number of data contained in the data set corresponding to the driving speed data;

[0036] Comparing the number of data contained in the data set corresponding to the driving speed data with a preset second data number threshold;

[0037] When the number of data contained in the data set corresponding to the driving speed data is lower than a preset second data number threshold, retrieving the missing value position corresponding to the driving speed data;

[0038] For each missing value position corresponding to the driving speed data, extract the two valid data with the closest data collection time as the observed valid data group;

[0039] A driving data reference value is obtained by performing a weighted average of the data average value corresponding to the observed valid data group, the middle value of the data set corresponding to the driving speed data, and the data maximum value of the data set corresponding to the driving speed data, and a difference data between the data average value corresponding to the observed valid data group and the driving data reference value is used as the second difference data;

[0040] The filling value corresponding to each missing value contained in the driving speed data is obtained by using the second difference data corresponding to each missing value of the driving speed data in combination with the valid data in the data set corresponding to the driving speed data, wherein the filling value corresponding to each missing value of the driving speed data is obtained by the following formula:

[0041]

[0042] Among them, K t Indicates the fill value corresponding to each missing value of the driving speed data; Y 01 and Y 02 Respectively represent the two valid data values ​​contained in the reference valid data group; Y c02 represents the second difference data; m represents the total number of valid data in the data set corresponding to the driving speed data; Y i Indicates the data value of the ith valid data in the data set corresponding to the driving speed data; Y z Indicates the middle value of the valid data in the data set corresponding to the driving speed data; Y p Indicates the average value of valid data in the data set corresponding to the driving speed data;

[0043] The missing value position is filled with data using the filling value corresponding to each missing value of the driving speed data.

[0044] Preferably, in S2, the vehicle is automatically identified and passes quickly, and the following operations are performed:

[0045] Real-time monitoring of the traffic flow of each lane of the quasi-free flow pre-transaction toll collection on the expressway to determine the traffic flow information of each lane during the vehicle passage process;

[0046] According to the traffic flow information of each lane during the vehicle's passage, the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow is selected. Based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow;

[0047] When a vehicle passes, it is automatically identified based on vehicle recognition technology, and the vehicle fees are automatically settled, allowing the vehicle to pass quickly.

[0048] Preferably, in S2, the navigation system intelligently guides the vehicle to travel on a lane with the least traffic volume, and performs the following operations:

[0049] Get the lane information of the vehicle;

[0050] Monitor the traffic flow of the lane where the vehicle is located and other lanes in real time to determine the traffic flow information of all lanes;

[0051] Analyze the traffic flow information of all lanes, and determine the lane with the least traffic flow based on the lane information of the vehicles during the passage process;

[0052] The route is planned for the lane with the least traffic flow, and the navigation system is used to intelligently guide vehicles to the lane with the least traffic flow, allowing vehicles to pass quickly.

[0053] Preferably, in S3, the vehicle traffic condition prediction and warning are performed by performing the following operations:

[0054] Collect big data on vehicle traffic in each lane on the highway;

[0055] Based on machine learning technology, the big data of vehicle traffic in each lane on the highway is divided and trained to build the optimal highway quasi-free flow vehicle traffic prediction model;

[0056] The optimal highway quasi-free-flow vehicle traffic prediction model is applied to the actual highway quasi-free-flow environment. According to the optimal highway quasi-free-flow vehicle traffic prediction model, the vehicle traffic conditions of each lane on the highway are predicted to have faults and health management, the vehicle traffic demand and conditions are predicted, the highway quasi-free-flow vehicle traffic results are determined, and the vehicle traffic conditions are warned and health managed according to the highway quasi-free-flow vehicle traffic results.

[0057] Preferably, in S3, an optimal highway quasi-free flow vehicle traffic prediction model is constructed, and the following operations are performed:

[0058] Obtain big data on vehicle traffic in each lane on the highway;

[0059] Classify the vehicle traffic big data of each lane on the highway, and divide the vehicle traffic big data of each lane on the highway into a training set and a test set;

[0060] Based on the training set, the machine learning model is trained and iteratively optimized to build a highway quasi-free-flow vehicle traffic prediction model;

[0061] Based on the test set, the performance of the highway quasi-free-flow vehicle traffic prediction model is tested to determine whether the highway quasi-free-flow vehicle traffic prediction model achieves the expected effect and to determine the optimal highway quasi-free-flow vehicle traffic prediction model.

[0062] Preferably, in S3, early warning and health management of vehicle traffic conditions are performed according to the traffic results of quasi-free-flow vehicles on the expressway, and the following operations are performed:

[0063] When it is predicted that a lane will have a large traffic volume and will be congested, timely warnings will be issued and toll collection strategies and services will be adjusted. Congestion can be alleviated by adjusting toll standards or guiding vehicles to choose other lanes, and dynamic adjustments can be made to vehicle tolls and routes to meet traffic needs in different scenarios.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] 1. The present invention determines the vehicle traffic big data of each lane on the expressway by real-time monitoring and continuous collection of the vehicle flow, vehicle type, driving speed and driving time of each lane on the expressway, performs data analysis on the vehicle flow and vehicle type information in the vehicle traffic big data of each lane on the expressway, and sets a charging standard for each lane of the expressway in combination with the vehicle driving speed and driving time information.

[0066] 2. The present invention uses the traffic flow information of each lane during the vehicle's passage and is based on path planning technology. The navigation system intelligently guides the vehicle to travel on the lane with the least traffic flow. When the vehicle passes, the vehicle is automatically identified and the vehicle fee is automatically settled based on vehicle identification technology, so that the vehicle can pass quickly. It is used in a quasi-free flow charging mode. By intelligently optimizing the lanes, the quasi-free flow in the vehicle's passage process is achieved, thereby achieving the purpose of improving road utilization and reducing congestion, and can meet the needs of modern society for efficient and fast transportation.

[0067] 3. Based on machine learning technology, the present invention performs fault prediction and health management on the vehicle traffic conditions in each lane on the highway, predicts vehicle traffic demand and conditions, determines the traffic results of quasi-free-flow vehicles on the highway, and performs early warning and health management on the vehicle traffic conditions based on the traffic results of quasi-free-flow vehicles on the highway. It alleviates congestion by adjusting toll standards or guiding vehicles to choose other lanes, and realizes dynamic adjustment of vehicle tolls and routes to adapt to traffic needs in different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 The present invention is a flow chart of the method for configuring a quasi-free-flow pre-transaction toll lane on a highway. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In order to solve the problem that the existing vehicles cannot optimize the lanes intelligently, cannot achieve quasi-free flow during the vehicle passage process, reduce the road utilization rate, cause traffic congestion, and cannot meet the needs of modern society for efficient and fast transportation, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0071] The method for configuring a quasi-free flow pre-transaction toll lane on a highway includes the following steps:

[0072] S1. Vehicle traffic big data collection and preprocessing:

[0073] Carry out real-time monitoring and continuous collection of vehicle flow, vehicle type, driving speed and driving time of each lane on the highway, determine the vehicle traffic big data of each lane on the highway, pre-process and analyze the vehicle traffic big data, and set charging standards for each lane of the highway;

[0074] In this embodiment, as a preferred technical solution of the present invention, the vehicle traffic big data of each lane on the highway is determined by performing the following operations:

[0075] Based on the high-definition cameras installed on the highway, the traffic flow and vehicle type of each lane on the highway are monitored and collected continuously in real time to obtain traffic flow and vehicle type information;

[0076] Based on the on-board sensors installed on the vehicles, the vehicle speed and driving time of each lane on the highway are monitored and collected continuously in real time to obtain the vehicle speed and driving time information;

[0077] Among them, the vehicle traffic big data of each lane on the highway is determined based on the traffic flow and vehicle model information, vehicle speed and driving time information.

[0078] It should be noted that high-definition cameras refer to HD 1080P, HD 960P or HD 720P cameras, 1080P is full HD, and high-definition cameras are the standards achieved by the combination of camera and clarity. High-definition cameras can be used to monitor and continuously collect traffic flow and vehicle model conditions in each lane on the highway in real time, thereby obtaining traffic flow and vehicle model information.

[0079] It should be noted that, in this embodiment, the on-board sensors include a speed sensor and a driving recorder, wherein the speed sensor can be used to monitor and continuously collect the vehicle speeds of each lane on the highway in real time to obtain vehicle speed information; the driving recorder can be used to monitor and continuously collect the vehicle driving time of each lane on the highway in real time to obtain vehicle driving time information.

[0080] In this embodiment, as a preferred technical solution of the present invention, a suitable charging standard is set for each lane of the expressway, and the following operations are performed:

[0081] Obtain big data on vehicle traffic in each lane on the highway;

[0082] Clean the big data of vehicle traffic in each lane on the highway;

[0083] Remove inconsistent data, invalid values ​​and missing values ​​that are useless for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway from the big data of vehicle traffic in each lane on the expressway, and determine the big data of vehicle traffic in each lane on the expressway that is useful for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway;

[0084] It should be noted that data cleaning is one of the important links in data analysis, data mining and application, aiming to improve data quality and the accuracy of analysis results.

[0085] Among them, the big data of vehicle traffic in each lane on the highway is cleaned, including:

[0086] Conduct consistency checks on the big data of vehicle traffic in each lane on the highway;

[0087] According to the data consistency requirements, check whether there is inconsistent data in the vehicle traffic big data of each lane on the expressway that is useless for the configuration of the quasi-free flow pre-transaction toll lanes on the expressway, and remove the inconsistent data in the vehicle traffic big data of each lane on the expressway;

[0088] Check invalid and missing values ​​for the vehicle traffic big data of each lane on the highway;

[0089] According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​in the big data of vehicle traffic in each lane on the expressway that are useless for the configuration of the quasi-free flow pre-transaction toll lanes on the expressway, and remove the invalid values ​​and missing values ​​in the big data of vehicle traffic in each lane on the expressway;

[0090] Then, the vehicle traffic big data of each lane on the highway which is useful for the configuration of quasi-free flow pre-transaction toll lanes on the highway is determined.

[0091] It should be noted that by cleaning the vehicle traffic big data of each lane on the highway, inconsistent data, invalid values ​​and missing values ​​that are useless for the configuration of quasi-free flow pre-transaction toll lanes on the highway can be removed from the vehicle traffic big data of each lane on the highway, and the vehicle traffic big data of each lane on the highway that is useful for the configuration of quasi-free flow pre-transaction toll lanes on the highway can be determined, which can improve the subsequent processing accuracy and analysis efficiency of the vehicle traffic big data of each lane on the highway.

[0092] The traffic volume and vehicle type information in the big data of vehicle traffic in each lane on the highway are analyzed, and the charging standards are set for each lane of the highway in combination with the vehicle speed and driving time information.

[0093] S2. Automatic vehicle identification and fast passage:

[0094] According to the traffic flow information of each lane during the vehicle's passage, based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the lane with the least traffic flow. When the vehicle passes, based on the vehicle recognition technology, the vehicle is automatically identified and the vehicle fee is automatically settled, so that the vehicle can pass quickly;

[0095] Specifically, the data quality test is performed on the big data of vehicle traffic in each lane of the expressway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the expressway, including:

[0096] Extract and classify the vehicle traffic big data of each lane on the highway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the highway, and obtain a data set corresponding to each data type, wherein the data type includes vehicle flow, vehicle type, driving speed and driving time;

[0097] Extract the number of data contained in the data set corresponding to the traffic flow data;

[0098] Comparing the number of data contained in the data set corresponding to the vehicle flow data with a preset first data number threshold;

[0099] When the number of data contained in the data set corresponding to the vehicle flow data is lower than a preset first data number threshold, the missing value position corresponding to the vehicle flow data is retrieved;

[0100] For each missing value position corresponding to the vehicle flow data, extract the two valid data with the most recent data collection time as a reference valid data group;

[0101] Compare the data average value corresponding to the reference valid data group with the middle value of the data set corresponding to the vehicle flow data, and use the difference data between the data average value corresponding to the reference valid data group and the middle value of the data set corresponding to the vehicle flow data as the first difference data;

[0102] The first difference data corresponding to each missing value of the vehicle flow data is combined with the valid data in the data set corresponding to the vehicle flow data to obtain the filling value corresponding to each missing value contained in the vehicle flow data, wherein the filling value corresponding to each missing value of the vehicle flow data is obtained by the following formula:

[0103]

[0104] Among them, R t Indicates the filling value corresponding to each missing value of the traffic flow data; X 01 and X 02 Respectively represent the two valid data values ​​contained in the reference valid data group; X c01 represents the first difference data; n represents the total number of valid data in the data set corresponding to the traffic flow data; X i Indicates the data value of the i-th valid data in the data set corresponding to the traffic flow data;

[0105] The missing value position is filled with data using the filling value corresponding to each missing value of the vehicle flow data.

[0106] The technical effect of the above technical solution is: by classifying and extracting the vehicle traffic big data of each lane on the highway, especially for key data types such as traffic volume, vehicle model, driving speed and driving time, the comprehensiveness and pertinence of the data are ensured. By detecting the integrity of the number of data in the traffic volume data set and comparing it with the preset first data number threshold, the problem of missing data can be discovered in time, thereby triggering the subsequent data filling process. When it is detected that the traffic volume data is missing, these missing values ​​are not simply ignored or deleted, but filled with valid data near the missing value position, which ensures the continuity and consistency of the data. By calculating the difference between the data mean value of the reference valid data group and the median value of the data set (first difference data), and combining the valid data in the data set, a complex formula is used to estimate the filling value of the missing value. This method takes into account the overall distribution and local characteristics of the data, so that the filling value is closer to the true value, and the accuracy and credibility of the data are improved. By performing quality inspection and data filling on the vehicle traffic big data, the data required for the configuration of the toll lane can be ensured to be complete and accurate, thereby supporting more accurate traffic flow prediction, vehicle model classification and toll strategy formulation. The accuracy and completeness of data are crucial to the realization of quasi-free-flow pre-transaction toll collection on highways, as it relies on real-time, accurate information on vehicle volume and vehicle type to optimize the toll collection process and improve traffic efficiency. Through automated data quality detection and data filling processes, manual intervention and error rates can be reduced, and the efficiency and accuracy of data processing can be improved. Accurate data can support smarter traffic management and resource allocation decisions, thereby optimizing highway operation and maintenance costs.

[0107] In summary, this technical solution not only improves the integrity and accuracy of highway vehicle traffic big data through refined data quality detection and data filling strategies, but also provides strong support for improving the operating efficiency of highway toll lanes, optimizing resource allocation and reducing operation and maintenance costs.

[0108] Specifically, the data quality detection is performed on the vehicle traffic big data of each lane on the expressway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the expressway, and also includes:

[0109] Extract the number of data contained in the data set corresponding to the driving speed data;

[0110] Comparing the number of data contained in the data set corresponding to the driving speed data with a preset second data number threshold;

[0111] When the number of data contained in the data set corresponding to the driving speed data is lower than a preset second data number threshold, retrieving the missing value position corresponding to the driving speed data;

[0112] For each missing value position corresponding to the driving speed data, extract the two valid data with the closest data collection time as the observed valid data group;

[0113] A driving data reference value is obtained by performing a weighted average of the data average value corresponding to the observed valid data group, the middle value of the data set corresponding to the driving speed data, and the data maximum value of the data set corresponding to the driving speed data, and a difference data between the data average value corresponding to the observed valid data group and the driving data reference value is used as the second difference data;

[0114] The filling value corresponding to each missing value contained in the driving speed data is obtained by using the second difference data corresponding to each missing value of the driving speed data in combination with the valid data in the data set corresponding to the driving speed data, wherein the filling value corresponding to each missing value of the driving speed data is obtained by the following formula:

[0115]

[0116] Among them, K t Indicates the fill value corresponding to each missing value of the driving speed data; Y 01 and Y 02 Respectively represent the two valid data values ​​contained in the reference valid data group; Y c02 represents the second difference data; m represents the total number of valid data in the data set corresponding to the driving speed data; Y i Indicates the data value of the ith valid data in the data set corresponding to the driving speed data; Y z Indicates the middle value of the valid data in the data set corresponding to the driving speed data; Y p Indicates the average value of valid data in the data set corresponding to the driving speed data;

[0117] The missing value position is filled with data using the filling value corresponding to each missing value of the driving speed data.

[0118] The technical effect of the above technical solution is: by classifying and extracting the vehicle traffic big data of each lane on the highway, especially for key data types such as traffic volume, vehicle model, driving speed and driving time, the comprehensiveness and pertinence of the data are ensured. By detecting the integrity of the number of data in the traffic volume data set and comparing it with the preset first data number threshold, the problem of missing data can be discovered in time, thereby triggering the subsequent data filling process. When it is detected that the traffic volume data is missing, these missing values ​​are not simply ignored or deleted, but filled with valid data near the missing value position, which ensures the continuity and consistency of the data. By calculating the difference between the data mean value of the reference valid data group and the median value of the data set (first difference data), and combining the valid data in the data set, a complex formula is used to estimate the filling value of the missing value. This method takes into account the overall distribution and local characteristics of the data, so that the filling value is closer to the true value, and the accuracy and credibility of the data are improved. By performing quality inspection and data filling on the vehicle traffic big data, the data required for the configuration of the toll lane can be ensured to be complete and accurate, thereby supporting more accurate traffic flow prediction, vehicle model classification and toll strategy formulation. The accuracy and completeness of data are crucial to the realization of quasi-free-flow pre-transaction toll collection on highways, as it relies on real-time, accurate information on vehicle volume and vehicle type to optimize the toll collection process and improve traffic efficiency. Through automated data quality detection and data filling processes, manual intervention and error rates can be reduced, and the efficiency and accuracy of data processing can be improved. Accurate data can support smarter traffic management and resource allocation decisions, thereby optimizing highway operation and maintenance costs.

[0119] In summary, this technical solution not only improves the integrity and accuracy of highway vehicle traffic big data through refined data quality detection and data filling strategies, but also provides strong support for improving the operating efficiency of highway toll lanes, optimizing resource allocation and reducing operation and maintenance costs.

[0120] In this embodiment, as a preferred technical solution of the present invention, the automatic identification and rapid passage of vehicles are performed by performing the following operations:

[0121] Real-time monitoring of the traffic flow of each lane of the quasi-free flow pre-transaction toll collection on the expressway to determine the traffic flow information of each lane during the vehicle passage process;

[0122] According to the traffic flow information of each lane during the vehicle's passage, the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow is selected. Based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow;

[0123] When a vehicle passes, it is automatically identified based on vehicle recognition technology, and the vehicle fees are automatically settled, allowing the vehicle to pass quickly.

[0124] In this embodiment, as a preferred technical solution of the present invention, the navigation system intelligently guides the vehicle to drive on the lane with the least traffic flow, and performs the following operations:

[0125] Get the lane information of the vehicle;

[0126] Monitor the traffic flow of the lane where the vehicle is located and other lanes in real time to determine the traffic flow information of all lanes;

[0127] Analyze the traffic flow information of all lanes, and determine the lane with the least traffic flow based on the lane information of the vehicles during the passage process;

[0128] The route is planned for the lane with the least traffic flow, and the navigation system is used to intelligently guide vehicles to the lane with the least traffic flow, allowing vehicles to pass quickly.

[0129] S3. Vehicle traffic situation prediction and warning:

[0130] Based on machine learning technology, fault prediction and health management are carried out on the vehicle traffic conditions in each lane on the highway, the vehicle traffic demand and conditions are predicted, the quasi-free-flow vehicle traffic results on the highway are determined, and based on the quasi-free-flow vehicle traffic results on the highway, early warning and health management of vehicle traffic conditions are carried out to adapt to traffic needs in different scenarios.

[0131] In this embodiment, as a preferred technical solution of the present invention, vehicle traffic condition prediction and warning, the following operations are performed:

[0132] Collect big data on vehicle traffic in each lane on the highway;

[0133] Based on machine learning technology, the big data of vehicle traffic in each lane on the highway is divided and trained to build the optimal highway quasi-free flow vehicle traffic prediction model;

[0134] The optimal highway quasi-free-flow vehicle traffic prediction model is applied to the actual highway quasi-free-flow environment. According to the optimal highway quasi-free-flow vehicle traffic prediction model, the vehicle traffic conditions of each lane on the highway are predicted to have faults and health management, the vehicle traffic demand and conditions are predicted, the highway quasi-free-flow vehicle traffic results are determined, and the vehicle traffic conditions are warned and health managed according to the highway quasi-free-flow vehicle traffic results.

[0135] In this embodiment, as a preferred technical solution of the present invention, an optimal highway quasi-free flow vehicle traffic prediction model is constructed, and the following operations are performed:

[0136] Obtain big data on vehicle traffic in each lane on the highway;

[0137] Classify the vehicle traffic big data of each lane on the highway, and divide the vehicle traffic big data of each lane on the highway into a training set and a test set;

[0138] Based on the training set, the machine learning model is trained and iteratively optimized to build a highway quasi-free-flow vehicle traffic prediction model;

[0139] Based on the test set, the performance of the highway quasi-free-flow vehicle traffic prediction model is tested to determine whether the highway quasi-free-flow vehicle traffic prediction model achieves the expected effect and to determine the optimal highway quasi-free-flow vehicle traffic prediction model.

[0140] In this embodiment, as a preferred technical solution of the present invention, early warning and health management of vehicle traffic conditions are performed according to the traffic results of quasi-free flow vehicles on the expressway, and the following operations are performed:

[0141] When it is predicted that a lane will have a large traffic volume and will be congested, timely warnings will be issued and toll collection strategies and services will be adjusted. Congestion can be alleviated by adjusting toll standards or guiding vehicles to choose other lanes, and dynamic adjustments can be made to vehicle tolls and routes to meet traffic needs in different scenarios.

[0142] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0143] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for configuring a quasi-free flow pre-transaction toll lane on a highway, characterized in that: The steps include: S1. Vehicle traffic big data collection and preprocessing: Carry out real-time monitoring and continuous collection of vehicle flow, vehicle type, driving speed and driving time of each lane on the highway, determine the vehicle traffic big data of each lane on the highway, pre-process and analyze the vehicle traffic big data, and set charging standards for each lane of the highway; S2. Automatic vehicle identification and fast passage: According to the traffic flow information of each lane during the vehicle's passage, based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the lane with the least traffic flow. When the vehicle passes, based on the vehicle recognition technology, the vehicle is automatically identified and the vehicle fee is automatically settled, so that the vehicle can pass quickly; S3. Vehicle traffic situation prediction and warning: Based on machine learning technology, fault prediction and health management are carried out on the vehicle traffic conditions in each lane on the highway, the vehicle traffic demand and conditions are predicted, the quasi-free-flow vehicle traffic results on the highway are determined, and based on the quasi-free-flow vehicle traffic results on the highway, early warning and health management of vehicle traffic conditions are carried out to adapt to traffic needs in different scenarios.

2. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 1, characterized in that: In S1, the vehicle traffic big data of each lane on the highway is determined, and the following operations are performed: Based on the high-definition cameras installed on the highway, the traffic flow and vehicle type of each lane on the highway are monitored and collected continuously in real time to obtain traffic flow and vehicle type information; Based on the on-board sensors installed on the vehicles, the vehicle speed and driving time of each lane on the highway are monitored and collected continuously in real time to obtain the vehicle speed and driving time information; Among them, the vehicle traffic big data of each lane on the highway is determined based on the traffic flow and vehicle model information, vehicle speed and driving time information.

3. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 2, characterized in that: In S1, a suitable charging standard is set for each lane of the expressway, and the following operations are performed: Obtain big data on vehicle traffic in each lane on the highway; Clean the big data of vehicle traffic in each lane on the highway; Remove inconsistent data, invalid values ​​and missing values ​​that are useless for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway from the big data of vehicle traffic in each lane on the expressway, and determine the big data of vehicle traffic in each lane on the expressway that is useful for the configuration of quasi-free-flow pre-transaction toll lanes on the expressway; The traffic volume and vehicle type information in the big data of vehicle traffic in each lane on the highway are analyzed, and the charging standards are set for each lane of the highway in combination with the vehicle speed and driving time information.

4. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 3, characterized in that: Data quality detection is performed on the big data of vehicle traffic in each lane of the expressway that is useful for the configuration of quasi-free flow pre-transaction toll lanes on the expressway, including: Extract and classify the vehicle traffic big data of each lane on the highway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the highway, and obtain a data set corresponding to each data type, wherein the data type includes vehicle flow, vehicle type, driving speed and driving time; Extract the number of data contained in the data set corresponding to the traffic flow data; Comparing the number of data contained in the data set corresponding to the vehicle flow data with a preset first data number threshold; When the number of data contained in the data set corresponding to the vehicle flow data is lower than a preset first data number threshold, the missing value position corresponding to the vehicle flow data is retrieved; For each missing value position corresponding to the vehicle flow data, extract the two valid data with the most recent data collection time as a reference valid data group; Compare the data average value corresponding to the reference valid data group with the middle value of the data set corresponding to the vehicle flow data, and use the difference data between the data average value corresponding to the reference valid data group and the middle value of the data set corresponding to the vehicle flow data as the first difference data; The first difference data corresponding to each missing value of the vehicle flow data is combined with the valid data in the data set corresponding to the vehicle flow data to obtain the filling value corresponding to each missing value contained in the vehicle flow data, wherein the filling value corresponding to each missing value of the vehicle flow data is obtained by the following formula: Among them, R t Indicates the filling value corresponding to each missing value of the traffic flow data; X 01 and X 02 Respectively represent the two valid data values ​​contained in the reference valid data group; X c01 represents the first difference data; n represents the total number of valid data in the data set corresponding to the traffic flow data; X i Indicates the data value of the i-th valid data in the data set corresponding to the traffic flow data; The missing value position is filled with data using the filling value corresponding to each missing value of the vehicle flow data.

5. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 4, characterized in that: Data quality detection is performed on the big data of vehicle traffic in each lane of the expressway that is useful for the configuration of the quasi-free flow pre-transaction toll lane on the expressway, including: Extract the number of data contained in the data set corresponding to the driving speed data; Comparing the number of data contained in the data set corresponding to the driving speed data with a preset second data number threshold; When the number of data contained in the data set corresponding to the driving speed data is lower than a preset second data number threshold, retrieving the missing value position corresponding to the driving speed data; For each missing value position corresponding to the driving speed data, extract the two valid data with the closest data collection time as the observed valid data group; A driving data reference value is obtained by performing a weighted average of the data average value corresponding to the observed valid data group, the middle value of the data set corresponding to the driving speed data, and the data maximum value of the data set corresponding to the driving speed data, and a difference data between the data average value corresponding to the observed valid data group and the driving data reference value is used as the second difference data; The filling value corresponding to each missing value contained in the driving speed data is obtained by using the second difference data corresponding to each missing value of the driving speed data in combination with the valid data in the data set corresponding to the driving speed data, wherein the filling value corresponding to each missing value of the driving speed data is obtained by the following formula: Among them, K t Indicates the fill value corresponding to each missing value of the driving speed data; Y 01 and Y 02 Respectively represent the two valid data values ​​contained in the reference valid data group; Y c02 represents the second difference data; m represents the total number of valid data in the data set corresponding to the driving speed data; Y i Indicates the data value of the ith valid data in the data set corresponding to the driving speed data; Y z Indicates the middle value of the valid data in the data set corresponding to the driving speed data; Y p Indicates the average value of valid data in the data set corresponding to the driving speed data; The missing value position is filled with data using the filling value corresponding to each missing value of the driving speed data.

6. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 3, characterized in that: In S2, the vehicle is automatically identified and passes quickly, and the following operations are performed: Real-time monitoring of the traffic flow of each lane of the quasi-free flow pre-transaction toll collection on the expressway to determine the traffic flow information of each lane during the vehicle passage process; According to the traffic flow information of each lane during the vehicle's passage, the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow is selected. Based on the path planning technology, the navigation system intelligently guides the vehicle to drive on the quasi-free-flow pre-trading toll lane on the expressway with the least traffic flow; When a vehicle passes, it is automatically identified based on vehicle recognition technology, and the vehicle fees are automatically settled, allowing the vehicle to pass quickly.

7. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 6, characterized in that: In S2, the navigation system intelligently guides the vehicle to drive on the lane with the least traffic volume, and performs the following operations: Get the lane information of the vehicle; Monitor the traffic flow of the lane where the vehicle is located and other lanes in real time to determine the traffic flow information of all lanes; Analyze the traffic flow information of all lanes, and determine the lane with the least traffic flow based on the lane information of the vehicles during the passage process; The route is planned for the lane with the least traffic flow, and the navigation system is used to intelligently guide vehicles to the lane with the least traffic flow, allowing vehicles to pass quickly.

8. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 7, characterized in that: In S3, the vehicle traffic condition prediction and warning are performed by performing the following operations: Collect big data on vehicle traffic in each lane on the highway; Based on machine learning technology, the big data of vehicle traffic in each lane on the highway is divided and trained to build the optimal highway quasi-free flow vehicle traffic prediction model; The optimal highway quasi-free-flow vehicle traffic prediction model is applied to the actual highway quasi-free-flow environment. According to the optimal highway quasi-free-flow vehicle traffic prediction model, the vehicle traffic conditions of each lane on the highway are predicted to have faults and health management, the vehicle traffic demand and conditions are predicted, the highway quasi-free-flow vehicle traffic results are determined, and the vehicle traffic conditions are warned and health managed according to the highway quasi-free-flow vehicle traffic results.

9. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 8, characterized in that: In S3, an optimal highway quasi-free flow vehicle traffic prediction model is constructed, and the following operations are performed: Obtain big data on vehicle traffic in each lane on the highway; Classify the vehicle traffic big data of each lane on the highway, and divide the vehicle traffic big data of each lane on the highway into a training set and a test set; Based on the training set, the machine learning model is trained and iteratively optimized to build a highway quasi-free-flow vehicle traffic prediction model; Based on the test set, the performance of the highway quasi-free-flow vehicle traffic prediction model is tested to determine whether the highway quasi-free-flow vehicle traffic prediction model achieves the expected effect and to determine the optimal highway quasi-free-flow vehicle traffic prediction model.

10. The method for configuring quasi-free flow pre-transaction toll lanes on expressways according to claim 9, characterized in that: In S3, early warning and health management of vehicle traffic conditions are performed according to the quasi-free flow vehicle traffic results on the expressway, and the following operations are performed: When it is predicted that a lane will have a large traffic volume and will be congested, timely warnings will be issued and toll collection strategies and services will be adjusted. Congestion can be alleviated by adjusting toll standards or guiding vehicles to choose other lanes, and dynamic adjustments can be made to vehicle tolls and routes to meet traffic needs in different scenarios.

Images