Shunt induction control method and system for expressway unmanned toll station

Abstract

The invention discloses a shunting induction control method and system for a high-speed unmanned toll station, and relates to the technical field of traffic control, and the method comprises the steps: collecting real-time traffic flow data, and carrying out the preprocessing; constructing a machine learning model based on the preprocessed real-time traffic flow data, and predicting different types of traffic flows about to arrive at a toll station; calculating a current optimal lane allocation scheme according to different types of traffic flows about to arrive at the toll station; based on the optimal lane allocation scheme, the state of each lane is adjusted through an intelligent scheduling algorithm; generating high-dimensional data by using a data fusion algorithm according to the adjusted state of each lane; and obtaining a complete transaction record based on the high-dimensional data by using a distributed account book technology. The lane state is dynamically adjusted according to the optimal scheme through the intelligent scheduling algorithm, the flexibility and adaptability are enhanced, and the problems of resource waste and congestion are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control, and in particular to a method and system for controlling traffic diversion induction at an unmanned high-speed toll station. Background Art

[0002] Intelligent management of highway toll stations is an important part of the development of modern transportation. With the acceleration of urbanization and the continuous increase in the number of motor vehicles, traditional manual toll stations have gradually exposed problems such as low efficiency and frequent congestion. Smart toll stations mainly rely on electronic toll collection systems, which achieve rapid passage through vehicle identification technology and automatic payment methods. However, they are still unable to cope with traffic fluctuations during peak hours.

[0003] Existing lane allocation strategies at highway toll stations often lack flexibility and fail to make real-time adjustments based on dynamically changing traffic flows, which can easily cause some lanes to be overly congested while other lanes are underutilized. They are also difficult to handle with the fusion and analysis of high-dimensional, multi-source data, affecting the scientific nature and accuracy of overall decision-making. The security and immutability of transaction records have not received sufficient attention, posing potential risks to user trust. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a diversion induction control method for unmanned high-speed toll stations, which solves the problems of low prediction accuracy, rigid lane allocation, limited data processing capabilities and insufficient security of transaction records in high-speed toll stations.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for diversion induction control of a high-speed unmanned toll station, which includes collecting real-time traffic flow data and performing preprocessing; Build a machine learning model based on pre-processed real-time traffic flow data to predict different types of traffic that will arrive at the toll station; Calculate the current optimal lane allocation plan based on the different types of traffic that will arrive at the toll station; Adjust the status of each lane through intelligent scheduling algorithm based on the optimal lane allocation plan; According to the state of each lane being adjusted, high-dimensional data is generated using a data fusion algorithm; Based on high-dimensional data, distributed ledger technology is used to obtain complete transaction records.

[0007] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, wherein: the real-time traffic flow data includes vehicle type, license plate number, entry time, exit time and driving speed information; The preprocessing includes data cleaning, denoising and standardization.

[0008] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, wherein: building a machine learning model based on the pre-processed real-time traffic flow data to predict different types of vehicle flows that are about to arrive at the toll station includes the following steps: Extracting feature vectors from preprocessed traffic flow data; The input layer of the LSTM network model receives the extracted feature vectors, and the input layer predicts different types of traffic flow in the future, expressed as: ; in, is the predicted value of different types of traffic flow, is the timestamp, is the lane position, is the average speed, is the average of the timestamps, is the standard deviation of the timestamps, is the maximum value of the average speed, is the standard deviation, is the vehicle type, is the mean of vehicle types, is the standard deviation of vehicle type, To adjust the vehicle type is the average value, Lane position The weight coefficient of .

[0009] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, wherein: according to different types of vehicle flows that are about to arrive at the toll station, calculating the current optimal lane allocation solution includes the following steps: Based on the predicted values ​​of different types of traffic flow, the maximum traffic efficiency on all lanes is calculated, and the expression is: ; in, To maximize traffic efficiency, The total number of lanes, For the Different types of traffic flow predicted for each lane, For the The average travel time per lane, For the The capacity limit of the lanes, is the standard deviation of lane capacity, is the congestion penalty coefficient, is the index of the total number of lanes; A specific lane allocation plan is obtained based on maximizing traffic efficiency, and each type of vehicle is assigned to the corresponding lane.

[0010] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, the following steps are included in the process of adjusting the state of each lane through an intelligent scheduling algorithm based on the optimal lane allocation scheme: According to the maximum traffic efficiency, each vehicle type is assigned to the corresponding lane, the status information of all lanes is obtained, and the intelligent scheduling algorithm is used to optimize and adjust the status of each lane. The expression is: ; in, For the The optimization results of the lanes, For the Average waiting time per lane, is the coefficient of waiting time, is the nonlinear index, is a constant; According to the lane optimization results, the lane use authority of each lane is adjusted.

[0011] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, wherein: according to adjusting the state of each lane, generating high-dimensional data by using the data fusion algorithm includes the following steps: Extract the optimization result of each lane from the lane optimization results, and record the waiting time of each lane; Extract features from vehicle waiting time, average travel time, vehicle location and vehicle speed data; The Bayesian fusion algorithm is used to fuse the feature extraction data into high-dimensional data.

[0012] As a preferred solution of the diversion induction control method of the unmanned high-speed toll station of the present invention, wherein: using distributed ledger technology based on high-dimensional data to obtain a complete transaction record includes the following steps: Generate a high-dimensional data matrix using the fused high-dimensional data; Pack high-dimensional data matrices into transaction data; Sign the transaction using digital signature technology and add the verified transaction to the blockchain; Through distributed ledger technology, all participants can view the transaction history in the blockchain.

[0013] In a second aspect, the present invention provides a traffic diversion induction control system for a high-speed unmanned toll station, including a data acquisition module, real-time traffic flow data, and pre-processing; Traffic prediction module, which builds a machine learning model based on pre-processed real-time traffic flow data to predict different types of traffic that will arrive at the toll station; The lane allocation optimization module calculates the current optimal lane allocation plan based on the different types of traffic that are about to arrive at the toll station; Intelligent dispatching module, which adjusts the status of each lane through intelligent dispatching algorithm based on the optimal lane allocation plan; The data fusion module generates high-dimensional data using a data fusion algorithm based on the state of each lane; The distributed ledger recording module uses distributed ledger technology based on high-dimensional data to obtain complete transaction records.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the diversion induction control method for a high-speed unmanned toll station as described in the first aspect of the present invention.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the diversion induction control method for a high-speed unmanned toll station as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: by collecting and preprocessing real-time traffic flow, high-quality basic data input is ensured, and then the long short-term memory network model is used to extract and predict the features of the preprocessed traffic flow data, so as to achieve accurate estimation of different types of traffic flow in the future, and the maximum traffic efficiency of all lanes is calculated based on the prediction results, and the optimal lane allocation plan is generated, which reduces the waiting time of vehicles. The intelligent scheduling algorithm dynamically adjusts the lane status according to the optimal plan, enhances flexibility and adaptability, avoids resource waste and congestion problems, and then uses the Bayesian fusion algorithm to generate a high-dimensional data matrix to comprehensively reflect the lane status and traffic conditions, enhance data integrity and reliability, and finally through distributed ledger technology, package key features into transaction data to ensure the security and tamper-proofness of transaction records, and enhance transparency and user trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the diversion induction control method of the unmanned high-speed toll station in Example 1; Figure 2 This is a system diagram of the diversion induction control system of the unmanned high-speed toll station in Example 1. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for controlling the diversion induction of a high-speed unmanned toll station, comprising the following steps: S1. Real-time traffic flow data includes vehicle type, license plate number, entry and exit time, and driving speed information.

[0021] S1.1. Vehicle type: Identify and record the type of each vehicle; License plate number: read and record the license plate number to ensure the uniqueness of the vehicle identity; Entry time and exit time: record the entry and exit time of each vehicle to calculate the residence time and traffic efficiency; Driving Speed: Measure and record the vehicle's driving speed.

[0022] Furthermore, duplicate vehicle records within the same time period are checked and deleted to ensure the uniqueness and accuracy of the data.

[0023] S2. Build a machine learning model based on the preprocessed real-time traffic flow data to predict different types of traffic that will arrive at the toll station.

[0024] S2.1. Extract feature vectors from preprocessed traffic flow data.

[0025] Furthermore, the timestamp of each vehicle entering or leaving the toll booth is converted into a standard format using datetime and various time features are extracted to capture the changing patterns of traffic flow in different time periods; The lane number exists in the data set as a specific field, and the lane number of the vehicle is directly extracted from the data; The average speed can be calculated by dividing the total driving distance by the required time. The average speed is calculated and the statistical characteristics of the speed are extracted to reflect the changes in vehicle driving behavior; Reflect the distribution of different types of vehicles, classify vehicle types, cars, trucks, buses, use unique codes and statistical features to reflect the distribution of different types of vehicles; The dwell time is calculated from the time difference between entering and leaving the toll booth. For each parking record, its dwell time is calculated and the average dwell time and standard deviation statistical characteristics of the dwell time are calculated based on this to reflect the changes in parking behavior.

[0026] The input layer of the LSTM network model receives the extracted feature vectors and predicts different types of traffic flow in the future (e.g., in the next five minutes). The expression is: ; in, is the predicted value of different types of traffic flow, is the timestamp, is the lane position, is the average speed, is the average of the timestamps, is the standard deviation of the timestamps, is the maximum value of the average speed, is the standard deviation, is the vehicle type, is the mean of vehicle types, is the standard deviation of vehicle type, To adjust the vehicle type is the average value, Lane position The weight coefficient of .

[0027] Used to capture periodic changes in timestamps; Used to capture the changing trend of historical average speed; Used to enhance the influence of lane position and prevent excessively large values ​​from affecting the overall result; Used to capture the distribution characteristics of vehicle types; When predicting different types of traffic, predict the traffic volume in the next 5 minutes, 15 minutes and 30 minutes so that adjustments can be made.

[0028] S3. Calculate the current optimal lane allocation plan based on the different types of traffic that are about to arrive at the toll station.

[0029] S3.1. Based on the predicted values ​​of different types of traffic flow, the maximum traffic efficiency on all lanes is calculated. The expression is: ; in, To maximize traffic efficiency, The total number of lanes, For the Different types of traffic flow predicted for each lane, For the The average travel time per lane, For the The capacity limit of the lanes, is the standard deviation of lane capacity, is the congestion penalty coefficient, Index to the total number of lanes.

[0030] Furthermore, For the The product of the expected traffic volume on a lane and the average travel time of the lane represents the total travel time of the lane. This part is the congestion adjustment factor, which is used to adjust the impact on traffic efficiency when the traffic volume approaches or exceeds the lane capacity; The sum of all lane capacities represents the traffic efficiency of the entire toll station; Used to measure lane saturation; The traffic flow, travel time and capacity limit of each lane are determined based on the maximized traffic efficiency.

[0031] S3.2. Obtain a specific lane allocation plan based on the maximum traffic efficiency and allocate each vehicle type to the corresponding lane.

[0032] Furthermore, based on vehicle type, entry, exit time, average speed and dwell time; There are three lanes (A, B, C) on the road section before the toll station of the expressway. The most effective lanes need to be allocated to three types of vehicles (small cars, medium trucks, and heavy trucks) to improve traffic efficiency. Small cars: usually fast and agile, suitable for all lanes but prefer fast lanes; Medium trucks: The speed is between the two, and they may need more space to change lanes, so they are suitable for the middle lane; Heavy trucks: They are slower, have larger bodies, and have a greater impact on other vehicles. They are best suited for the right lane to reduce the impact on faster vehicles. It was detected that the number of small cars increased significantly within a period of time, so part of the B lane was temporarily opened to small cars, and some medium-sized trucks were directed to the C lane; During peak hours, if the proportion of heavy trucks is low, Lane C can also be opened to all vehicles to increase total capacity.

[0033] S4. Adjust the status of each lane through an intelligent scheduling algorithm based on the optimal lane allocation plan.

[0034] S4.1. Allocate each vehicle type to the corresponding lane according to the maximum traffic efficiency, obtain the status information of all lanes, and use the intelligent scheduling algorithm to optimize and adjust the status of each lane. The expression is: ; in, For the The optimization results of the lanes, For the Average waiting time per lane, is the coefficient of waiting time, is the nonlinear index, is a constant.

[0035] Furthermore, different types of vehicles that are about to enter the toll booth are classified, and different types of vehicles have different passing requirements or restrictions; Ordinary lane: suitable for all types of vehicles; ETC dedicated lane: prepared for vehicles equipped with ETC, which can usually pass faster; Special passage for large vehicles: Provide wider passage space for large vehicles to reduce the impact on other vehicles; Allocate vehicles based on maximizing traffic efficiency; Current traffic flow: how many cars are actually waiting in line to pass; Average travel time: the time it takes for a vehicle to enter a lane and leave it completely; Lane capacity: the maximum number of vehicles that the lane can accommodate at a specific time; Waiting time: the length of time it takes for a vehicle to arrive at the end of the queue and start moving; Get the status information of all vehicles on the lane; The intelligent scheduling algorithm is used to continuously evaluate and adjust the lane configuration. If an abnormal situation occurs in the current lane, the following vehicles are guided to change to the adjacent lane in advance. The strategy is adjusted in time to reallocate vehicles to ensure the maximization of overall traffic efficiency.

[0036] S4.1. Adjust the lane use authority of each lane according to the lane optimization result.

[0037] Furthermore, when there is heavy traffic in a lane, the green light time can be appropriately extended to improve traffic capacity; For lanes with low traffic volume, shorten the red light time appropriately to reduce unnecessary waiting; Temporarily convert ordinary lanes into special lanes or emergency lanes to meet special needs; Use electronic display screens to guide vehicles to choose the best lane and reduce congestion; When a lane is close to full, vehicles are temporarily restricted from entering the lane and are guided to choose other lanes.

[0038] S5. According to the status of each lane being adjusted, a data fusion algorithm is used to generate high-dimensional data.

[0039] S5.1 extracts the optimization result of each lane from the optimization results of the lanes and records the waiting time of each lane.

[0040] Furthermore, based on the lane status adjusted by the intelligent scheduling algorithm, the optimization result of each lane is extracted, reflecting the comprehensive optimization score of the lane under the current traffic conditions.

[0041] S5.2. Feature extraction is performed on the vehicle waiting time, average travel time, vehicle position and vehicle speed data.

[0042] Furthermore, the timestamps of each vehicle entering the toll booth and the timestamps of the vehicle starting to pass through are converted into a standard format, and the waiting time of each vehicle is calculated to extract the statistical characteristics of the waiting time (such as the maximum waiting time, the minimum waiting time, the standard deviation of the waiting time, etc.) to reflect the changes in the waiting time; The timestamp of each vehicle starting to pass and leaving the toll booth is converted into a standard format to ensure the accuracy of subsequent calculations. The travel time of each vehicle is calculated, and the travel time of all vehicles is averaged to obtain the average travel time.

[0043] Extract the statistical characteristics of travel time (such as maximum travel time, minimum travel time, standard deviation of travel time, etc.) to reflect the changes in travel time; The specific location information of the vehicle on the lane is directly extracted from the data, and the lane number and lane type are directly extracted from the data. The lane number is in the form of a string and needs to be converted into a numeric type. The characteristics of the lane type such as the main lane and the auxiliary lane are added to reflect the functional differences of different lanes. Record the vehicle's driving speed within the toll station area, calculate the average speed of the vehicle between the entrance and exit, and extract statistical characteristics of the speed (such as maximum speed, minimum speed, speed fluctuation, etc.) to reflect changes in vehicle driving behavior.

[0044] S5.3 uses the Bayesian fusion algorithm to fuse the feature extraction data into high-dimensional data.

[0045] S6. Use distributed ledger technology based on high-dimensional data to obtain complete transaction records.

[0046] S6.1 generates a high-dimensional data matrix using the fused high-dimensional data.

[0047] Furthermore, the features extracted from the multi-source data of lane optimization results, vehicle waiting time, average travel time, vehicle position and vehicle speed are used to obtain a high-dimensional data matrix; Each dimension represents a feature, such as vehicle waiting time, average travel time, vehicle location, driving speed, and vehicle type information.

[0048] S6.2 packs the high-dimensional data matrix into transaction data.

[0049] Furthermore, the high-dimensional data matrix is ​​packaged into a structured transaction data format.

[0050] S6.3. Sign the transaction using digital signature technology and add the verified transaction to the blockchain.

[0051] Furthermore, a pair of asymmetric keys is generated for each participant for digital signature and verification, and the transaction data is signed using the participant's private key. The digital signature ensures the authenticity and integrity of the transaction and prevents data tampering.

[0052] S6.4. Through distributed ledger technology, all participants can view the transaction history in the blockchain.

[0053] Furthermore, all verified transactions are permanently stored in the blockchain, forming an unalterable transaction history record, ensuring that only authorized parties can access and modify transaction records, protecting data security and privacy.

[0054] This embodiment also provides a traffic diversion induction control system for an unmanned high-speed toll station, including: a data acquisition module, real-time traffic flow data, and pre-processing; Traffic prediction module, which builds a machine learning model based on pre-processed real-time traffic flow data to predict different types of traffic that will arrive at the toll station; The lane allocation optimization module calculates the current optimal lane allocation plan based on the different types of traffic that are about to arrive at the toll station; Intelligent dispatching module, which adjusts the status of each lane through intelligent dispatching algorithm based on the optimal lane allocation plan; The data fusion module generates high-dimensional data using a data fusion algorithm based on the state of each lane; The distributed ledger recording module uses distributed ledger technology based on high-dimensional data to obtain complete transaction records.

[0055] This embodiment also provides a computer device, which is suitable for the diversion induction control method of the unmanned highway toll station, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the diversion induction control method of the unmanned highway toll station as proposed in the above embodiment.

[0056] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0057] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the diversion induction control of a high-speed unmanned toll station as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0058] In summary, the present invention ensures high-quality basic data input by collecting and preprocessing real-time traffic flow, and then uses the long short-term memory network model to extract and predict the features of the preprocessed traffic flow data, so as to achieve accurate estimation of different types of traffic flow in the future, and calculates the maximum traffic efficiency of all lanes based on the prediction results, and generates the optimal lane allocation plan, which reduces the waiting time of vehicles. The intelligent scheduling algorithm dynamically adjusts the lane status according to the optimal plan, enhances flexibility and adaptability, avoids resource waste and congestion problems, and then uses the Bayesian fusion algorithm to generate a high-dimensional data matrix, which comprehensively reflects the lane status and traffic conditions, and enhances data integrity and reliability. Finally, through the distributed ledger technology, the key features are packaged into transaction data to ensure the security and tamper-proofness of transaction records, and enhance transparency and user trust.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for controlling traffic diversion induction at a high-speed unmanned toll station, characterized in that: include: Collect real-time traffic flow data and perform pre-processing; Build a machine learning model based on pre-processed real-time traffic flow data to predict different types of traffic that will arrive at the toll station; Calculate the current optimal lane allocation plan based on the different types of traffic that will arrive at the toll station; Adjust the status of each lane through intelligent scheduling algorithm based on the optimal lane allocation plan; According to the state of each lane being adjusted, high-dimensional data is generated using a data fusion algorithm; Use distributed ledger technology based on high-dimensional data to obtain complete transaction records; The real-time traffic flow data includes vehicle type, license plate number, entry time, exit time and driving speed information; The preprocessing includes data cleaning, denoising and standardization; Building a machine learning model based on preprocessed real-time traffic flow data to predict different types of traffic that will arrive at the toll station includes the following steps: Extracting feature vectors from preprocessed traffic flow data; The input layer of the LSTM network model receives the extracted feature vectors, and the input layer predicts different types of traffic flow in the future, expressed as: ； in, is the predicted value of different types of traffic flow, is the timestamp, is the lane position, is the average speed, is the average of the timestamps, is the standard deviation of the timestamps, is the maximum value of the average speed, is the standard deviation, is the vehicle type, is the mean of vehicle types, is the standard deviation of vehicle type, To adjust the vehicle type item, is the average value, Lane position The weight coefficient of .

2. The method for controlling the flow diversion of an unmanned high-speed toll station according to claim 1, characterized in that: According to the different types of traffic that are about to arrive at the toll station, calculating the current optimal lane allocation plan includes the following steps: Based on the predicted values ​​of different types of traffic flow, the maximum traffic efficiency on all lanes is calculated, and the expression is: ； in, To maximize traffic efficiency, The total number of lanes, For the Different types of traffic flow predicted for each lane, For the The average travel time per lane, For the The capacity limit of the lanes, is the standard deviation of lane capacity, is the congestion penalty coefficient, is the index of the total number of lanes; A specific lane allocation plan is obtained based on maximizing traffic efficiency, and each type of vehicle is assigned to the corresponding lane.

3. The method for controlling the flow diversion of an unmanned high-speed toll station according to claim 2, characterized in that: Based on the optimal lane allocation scheme, the intelligent scheduling algorithm is used to adjust the status of each lane, including the following steps: According to the maximum traffic efficiency, each vehicle type is assigned to the corresponding lane, the status information of all lanes is obtained, and the intelligent scheduling algorithm is used to optimize and adjust the status of each lane. The expression is: ； in, For the The optimization results of the lanes, For the Average waiting time per lane, is the coefficient of waiting time, is the nonlinear index, is a constant; According to the lane optimization results, the lane use authority of each lane is adjusted.

4. The method for controlling the flow diversion of an unmanned high-speed toll station according to claim 3, characterized in that: According to adjusting the status of each lane, generating high-dimensional data using the data fusion algorithm includes the following steps: Extract the optimization result of each lane from the lane optimization results, and record the waiting time of each lane; Extract features from vehicle waiting time, average travel time, vehicle location and vehicle speed data; The Bayesian fusion algorithm is used to fuse the feature extraction data into high-dimensional data.

5. The method for controlling the flow diversion of unmanned high-speed toll booths according to claim 4, characterized in that: Using distributed ledger technology based on high-dimensional data, obtaining a complete transaction record includes the following steps: Generate a high-dimensional data matrix using the fused high-dimensional data; Pack high-dimensional data matrices into transaction data; Sign the transaction using digital signature technology and add the verified transaction to the blockchain; Through distributed ledger technology, all participants can view the transaction history in the blockchain.

6. A traffic diversion induction control system for an unmanned high-speed toll station, based on the traffic diversion induction control method for an unmanned high-speed toll station according to any one of claims 1 to 5, characterized in that: include: Data collection module, real-time traffic flow data, and pre-processing; Traffic prediction module, which builds a machine learning model based on pre-processed real-time traffic flow data to predict the different types of traffic that will arrive at the toll station; The lane allocation optimization module calculates the current optimal lane allocation plan based on the different types of traffic that are about to arrive at the toll station; Intelligent dispatching module, which adjusts the status of each lane through intelligent dispatching algorithm based on the optimal lane allocation plan; The data fusion module generates high-dimensional data using a data fusion algorithm based on the state of each lane; The distributed ledger recording module uses distributed ledger technology based on high-dimensional data to obtain complete transaction records.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the diversion induction control method for a high-speed unmanned toll station described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the diversion induction control method for a high-speed unmanned toll station described in any one of claims 1 to 5 are implemented.

Images