Unmanned self-adaptive charging method and system for expressway

Abstract

The invention discloses an unmanned self-adaptive toll collection method and system for a highway, relates to the technical field of self-adaptive toll collection, and solves the problems that in a highway toll collection system, a toll collection channel is difficult to open in time according to the congestion condition of a toll station, and the toll collection efficiency is high. And self-adaptive charging is difficult to carry out according to the potential risk of the driver on the road. According to the invention, the number of vehicles in a toll station and target data are obtained in real time; dividing a time period, and calculating a congestion factor of the next time period according to the number of vehicles in the current time period; dynamically adjusting the number of opened charging channels in the next time period based on the congestion factor; after the time reaches the next time period, the vehicles are distributed to the corresponding charging channels through the artificial intelligence model; determining a road influence factor of each vehicle based on the target data and accounting highway cost; according to the invention, the passing efficiency of vehicles at the toll station can be improved, a supervising and urging effect on safe driving of a driver is achieved, and the traffic safety is improved.

Description

Technical Field

[0001] The present invention belongs to the field of traffic management and relates to an adaptive charging technology, in particular to an unmanned adaptive charging method and system for highways. Background Art

[0002] To improve toll collection efficiency, reduce labor costs, and increase vehicle speed, technological advancements, particularly in automation, intelligent recognition, and information processing, have led to the emergence of unmanned toll collection systems. These systems automatically identify vehicle information and enable rapid billing and deduction, significantly reducing vehicle dwell time at toll booths and improving overall traffic efficiency.

[0003] At present, most unmanned adaptive toll collection methods and systems used on highways are unable to adaptively charge based on the potential risks brought by drivers to the road. Instead, they only charge in a fixed pattern based on the mileage of the car, ignoring the beneficial effect of indirectly urging drivers to drive safely brought about by adaptive charging based on the driver's driving behavior.

[0004] Therefore, the present invention discloses an unmanned adaptive toll collection method and system for highways, which are used to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an unmanned adaptive toll collection method and system for highways, which is used to solve the technical problems in the highway toll collection system that it is difficult to open toll channels in a timely manner according to the congestion situation of the toll station, and it is difficult to adaptively charge according to the potential risks brought by drivers to the road. The present invention solves the above problems by obtaining the number of vehicles and target data in the toll station in real time; dividing the time period, and calculating the congestion factor of the next time period according to the number of vehicles in the current time period; dynamically adjusting the number of toll channels opened in the next time period based on the congestion factor; after the time reaches the next time period, allocating the vehicle to the corresponding toll channel through an artificial intelligence model; determining the road impact factor of each vehicle based on the target data and calculating the highway fee.

[0006] To achieve the above objectives, a first aspect of the present invention provides an unmanned adaptive toll collection method for highways, comprising: Obtain the number of vehicles within the toll station's management area and target data for each vehicle; target data includes vehicle weight, speed, number of braking times, and number of driving violations; Divide the time period and determine the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period; Set the toll lanes open at the toll station in the next time period based on the congestion factor; When the time reaches the next time period, the vehicle is guided to each toll lane based on the set toll lanes through the artificial intelligence model; Determining a road impact factor for each vehicle based on the target data; Determine the highway toll for each vehicle based on road impact factors; Pay high-speed tolls using CPC cards or ETC cards.

[0007] Preferably, the obtaining of the number of vehicles within the management range of the toll station and target data of each vehicle includes: When a vehicle enters the toll station's management area, the number of vehicles present is obtained through video monitoring; when a vehicle reaches the area where the weighing equipment is located, the vehicle's weight is obtained. The management area is manually set. The number of braking times of the vehicle on the highway is obtained through on-board sensors, and the number of driving violations and speed of the vehicle at several moments on the highway are obtained through video monitoring technology. The speed V of the vehicle on the highway is determined based on the mode, average, and maximum values ​​of the speeds. The speed V satisfies the following formula: V = α1 × DD + α2 × ZD + α3 × PD; Among them, DD is the maximum value of the speed at several moments, ZD is the mode of the speed at several moments, and PD is the average value of the speed at several moments; α1, α2 and α3 are all manually set proportional adjustment coefficients, and α1+α2+α3=1, α1>α2>α3.

[0008] Preferably, the time division includes: When the time reaches 0:00 on a given day, the traffic volume at each time point on the current day is obtained, the traffic volume is divided into a number of traffic volume groups according to the time point, and the mode in each traffic volume group is marked as the characteristic traffic volume at the corresponding time point; wherein the traffic volume is the traffic volume within the management range of the current toll station; Marking the time point when the characteristic traffic flow is greater than the traffic flow threshold as a target time point, connecting consecutive target time points into a target time period, and connecting consecutive non-target time points into a non-target time period; wherein the traffic flow threshold is manually set; Target time periods or non-target time periods whose duration is longer than the defined duration are marked as management time periods, and target time periods or non-target time periods whose duration is not longer than the defined duration are merged into the smaller of the two adjacent management time periods; a day is divided into several time periods according to the time range of each management time period; wherein the defined duration is obtained by manual setting.

[0009] Preferably, determining the congestion factor of a toll station in a next time period based on the number of vehicles in a current time period includes: When the time reaches the last time point of the current time period, the number of vehicles in the current time period in several historical days is obtained, and the number of vehicles in the next time period in several historical days is obtained; The number of vehicles in the current time period over several historical days is integrated into the current time period quantity group; the number of vehicles in the next time period over several historical days is integrated into the next time period quantity group; Sequentially extract the quantity YL in the next period quantity group corresponding to each date in several historical days i and the quantity DL in the current period quantity group i , get the number YL of the same number i in turn i Subtract the quantity DL i The difference C i ; Based on the difference C i Determine the difference C between adjacent dates i The change ratio H i ; Where i is the number of each date in a certain number of historical days; The change ratio H i Satisfies the following formula: H i =(C i -C i-1 ) / C i-1 ; Get some change ratio H i The average value P i , based on the average value P i Determine the change ratio DH for the day; the change ratio DH satisfies the following formula: DH=β×ln(P i +1)+1; Among them, β is the manually set amplitude adjustment coefficient, and the value range of β is (0,1]; The number YC of vehicles in the next time period on the same day is determined based on the ratio DH, and the number YC satisfies the following formula: YC=(1+DH)×DC; Among them, DC is the number of vehicles in the current time period on that day; The congestion factor YZ for the next time period of the day is determined based on the quantity YC. The congestion factor YZ satisfies the following formula: YZ=BZ×YC / BYC; Among them, BYC is the manually set standard number, and BZ is the standard congestion factor corresponding to the manually set standard number.

[0010] Preferably, the setting of toll lanes to be opened at a toll station in the next time period based on the congestion factor includes: Extract the congestion factor YZ. When the congestion factor YZ is greater than congestion threshold 1, open all toll lanes of the current toll station. Congestion threshold 1 and congestion threshold 2 are both manually set, and congestion threshold 1 is greater than congestion threshold 2. When the congestion factor is not greater than the congestion threshold 1 and not less than the congestion threshold 2, the number of toll lanes TDL of the current toll station is extracted based on the formula KDL= TDL / 2 Determine the number KDL of open toll lanes of the current toll station, and open the toll lanes of the current toll station from left to right based on the number KDL; When the congestion factor is less than the congestion threshold 2, the leftmost toll lane among the toll lanes of the current toll station is opened.

[0011] Preferably, the toll lanes based on the settings guide vehicles to the toll lanes through an artificial intelligence model, including: Extracting the open toll lanes and the real-time number of vehicles in the corresponding time period, as well as the number of the toll lane through which each vehicle was directed from the historical reference data; wherein the historical reference data includes a number of open toll lanes and the real-time number of vehicles in the corresponding time period, and the number of the toll lane through which the expert directed each vehicle based on the toll lanes and the real-time number of vehicles in the corresponding time period; Integrate the open toll lanes, the real-time number of vehicles in the corresponding time period, and the toll lanes through which each vehicle is guided into several sets of training data and test data; use the training data to train the artificial intelligence model, use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model based on the test results; ultimately, obtain a channel guidance model whose input is the open toll lanes and the real-time number of vehicles, and whose output is the number of the toll lane through which each vehicle is guided; When the time arrives at the next time period, the open toll lanes and the real-time number of vehicles are input into the channel guidance model to obtain the number of the toll lane that each vehicle is guided to pass through.

[0012] Preferably, determining the road impact factor of each vehicle based on the target data includes: Extract the current vehicle's weight CZ, speed V, number of braking times BC, and number of driving violations WG; when the speed V exceeds a speed threshold VZ or the number of driving violations WG exceeds a violation threshold WGZ, set the road impact factor DZ to the maximum value within the impact factor limit range; wherein the speed threshold, violation threshold, and impact factor limit range are all manually set; When the speed V exceeds the speed threshold and the number of illegal driving times WG does not exceed the number of illegal driving times threshold, the road influence factor DZ of the current vehicle is determined based on the vehicle weight CZ, the speed V, the number of braking times BC, and the number of illegal driving times WG; the road influence factor DZ satisfies the following formula: ; Among them, BCZ is the manually set standard vehicle weight, and BCL is the manually set standard number of braking times; 、 、 and The proportional adjustment coefficients are set manually, and , ; When the road influence factor DZ is greater than the maximum value of the influence factor limit range, the road influence factor DZ is taken as the maximum value of the influence factor limit range; when the road influence factor DZ is less than the minimum value of the influence factor limit range, the road influence factor DZ is taken as the minimum value of the influence factor limit range.

[0013] Preferably, the determining of the highway fee for each vehicle based on the road impact factor includes: The mileage LC of the current vehicle during this highway travel is obtained, the road influence factor DZ is extracted, and the highway fee GY of the current vehicle is determined based on the road influence factor DZ and the mileage LC. The highway fee GY satisfies the following formula: GY=ZY×LC×DZ / YZ; Among them, ZY is the manually set base rate for one kilometer, and YZ is the middle value of the limited range of influencing factors.

[0014] Preferably, the charging of high-speed fees by CPC card or ETC card includes: When the vehicle reaches the CPC card toll booth or ETC card toll booth at the toll station, the highway toll for this trip is paid using the CPC card or ETC card.

[0015] A second aspect of the present invention provides an unmanned adaptive toll collection system for highways, comprising: an on-site dispatch module, and a data collection module and an adaptive toll collection module connected to the on-site dispatch module; The data collection module is used to obtain the number of vehicles within the toll station's management area and target data for each vehicle; wherein the target data includes vehicle weight, speed, number of braking times, and number of driving violations; The on-site dispatch module is used to divide time periods and determine the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period; set the toll lanes open at the toll station in the next time period based on the congestion factor; and when the time reaches the next time period, the vehicle is guided to each toll lane based on the set toll lanes through the artificial intelligence model; The adaptive charging module is used to determine the road impact factor of each vehicle based on the target data; determine the highway fee of each vehicle based on the road impact factor; and collect the highway fee through the CPC card or the ETC card.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention obtains the number of vehicles and target data in the toll station in real time; divides the time period and calculates the congestion factor of the next time period based on the number of vehicles in the current time period; dynamically adjusts the number of toll lanes open in the next time period based on the congestion factor; after the time reaches the next time period, the vehicle is assigned to the corresponding toll lane through an artificial intelligence model; determines the road impact factor of each vehicle based on the target data and calculates the highway fee, thereby solving the technical problems in the highway toll collection system that it is difficult to open the toll lane in time according to the congestion situation of the toll station, and it is difficult to charge adaptively according to the potential risks brought by the driver to the road; the present invention can improve the traffic efficiency of vehicles at the toll station, and has the function of urging drivers to drive safely, thereby improving traffic safety.

[0017] 2. The road impact factor calculated by the present invention is a factor for calculating the damage caused to the road and the potential traffic hazards caused by the current vehicle during this driving. It is used for the subsequent settlement of highway fees for the current vehicle. The weight of the vehicle and the driver's operation are combined with each other. On the basis of ensuring the rationality of highway fees, the highway fees are increased for vehicles with greater potential traffic hazards, and the highway fees are reduced for vehicles without potential traffic hazards. Through precise measurement, the principle of "high-risk drivers pay more" is realized, and a differentiated charging system is established. This can urge drivers to comply with driving safety rules more, so that the charging system has a certain driving supervision effect, and increases the adaptability of the charging system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 Schematic diagram of the operating steps of the present invention; Figure 2A schematic diagram of the operation steps for obtaining the congestion factor for the next time period according to the present invention; Figure 3 Schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0020] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] See also Figure 1 The first embodiment of the present invention provides an unmanned adaptive toll collection method for a highway, comprising: Obtain the number of vehicles within the toll station's management area and target data for each vehicle; target data includes vehicle weight, speed, number of braking times, and number of driving violations; Divide the time period, determine the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period, and set the toll lanes open at the toll station in the next time period based on the congestion factor; when the time reaches the next time period, the vehicles are guided to the toll lanes based on the set toll lanes through the artificial intelligence model; The road impact factor of each vehicle is determined based on the target data, the highway fee of each vehicle is determined based on the road impact factor, and the highway fee is collected through the CPC card or ETC card.

[0022] This application obtains the number of vehicles within the toll station's management area and the target data of each vehicle, including: When a vehicle enters the toll station's management area, the number of vehicles present is obtained through video monitoring; when a vehicle reaches the area where the weighing equipment is located, the vehicle's weight is obtained. The management area is manually set. The number of braking times of the vehicle on the highway is obtained through on-board sensors. The number of driving violations and the speed of the vehicle at certain moments on the highway are obtained through video monitoring technology. The speed V of the vehicle on the highway is determined based on the mode, average, and maximum values ​​of the speeds. The speed V satisfies the following formula: V = α1 × DD + α2 × ZD + α3 × PD; Among them, DD is the maximum value of the speed at several moments, ZD is the mode of the speed at several moments, and PD is the average value of the speed at several moments; α1, α2 and α3 are all manually set proportional adjustment coefficients, and α1+α2+α3=1, α1>α2>α3.

[0023] It should be noted that the number of driving violations is the sum of speeding, continuous lane changes and overtaking in the low-speed lane.

[0024] It should be noted that the proportional adjustment coefficient α1>α2>α3 is because: α1 is multiplied by the maximum value of the speed at several moments, α2 is multiplied by the mode of the speed at several moments, and α3 is multiplied by the average value of the speed at several moments; Regarding the hazards posed by vehicles traveling on highways, the higher the speed at a certain moment, the greater the potential hazard at that moment. Although the moment of maximum speed is instantaneous, the hazard is also the greatest. Therefore, the present invention sets the proportional adjustment coefficient corresponding to the maximum speed at several moments to the maximum. Furthermore, because the mode of the speeds at several moments can better reflect the speed at which the vehicle occupied the longest time during this driving, and can better reflect the characteristic conditions of the vehicle speed, compared with the average speed, the present invention sets the proportional adjustment coefficient of the mode of the speeds at several moments to be greater than the proportional adjustment coefficient of the average speed of the speeds at several moments.

[0025] The time periods in this application include: When the time reaches 0:00 on a given day, the traffic volume at each time point on the current day is obtained, the traffic volume is divided into several traffic volume groups according to the time point, and the mode in each traffic volume group is marked as the characteristic traffic volume at the corresponding time point; the traffic volume is the traffic volume within the management range of the current toll station; Mark the time point when the characteristic traffic flow is greater than the traffic flow threshold as the target time point, connect the consecutive target time points into the target time period, and connect the consecutive non-target time points into the non-target time period; wherein the traffic flow threshold is manually set; Target time periods or non-target time periods whose duration is longer than the defined duration are marked as management time periods, and target time periods or non-target time periods whose duration is not longer than the defined duration are merged into the smaller of the two adjacent management time periods; a day is divided into several time periods according to the time range of each management time period; wherein the defined duration is obtained by manual setting.

[0026] It should be noted that, in the present invention, the unit of time point can be 1 minute, 5 minutes or 10 minutes.

[0027] It should be noted that the management range is obtained through manual setting. For example, the management range can be within 500 meters before and after the toll station.

[0028] It should be noted that the traffic flow threshold is a manually set threshold used to determine whether the traffic flow within the management range of the toll station within a unit time is saturated. The traffic flow threshold can be set to 100 vehicles.

[0029] It should be noted that the non-target time point is a time point when the characteristic traffic flow is not greater than the traffic flow threshold.

[0030] It should be noted that the defined duration can be 2 hours, 4 hours, 6 hours or 8 hours.

[0031] See also Figure 2 In this application, the congestion factor of a toll station in the next time period is determined based on the number of vehicles in the current time period, including: When the time reaches the last time point of the current time period, the number of vehicles in the current time period in several historical days is obtained, and the number of vehicles in the next time period in several historical days is obtained; The number of vehicles in the current time period over several historical days is integrated into the current time period quantity group; the number of vehicles in the next time period over several historical days is integrated into the next time period quantity group; Sequentially extract the quantity YL in the next period quantity group corresponding to each date in several historical days i and the quantity DL in the current period quantity group i , get the number YL of the same number i in turn i Subtract the quantity DL i The difference C i ; Based on the difference C i Determine the difference C between adjacent dates i The change ratio H i ; Where i is the number of each date in a certain number of historical days; The change ratio H i Satisfies the following formula: H i =(C i -C i-1 ) / C i-1 ; Get some change ratio H i The average value P i , based on the mean value P i Determine the change ratio DH for the day; the change ratio DH satisfies the following formula: DH=β×ln(P i +1)+1; Among them, β is the manually set amplitude adjustment coefficient, and the value range of β is (0,1]; The number YC of vehicles in the next time period on the same day is determined based on the ratio DH, and the number YC satisfies the following formula: YC=(1+DH)×DC; Among them, DC is the number of vehicles in the current time period on that day; The congestion factor YZ for the next time period of the day is determined based on the quantity YC. The congestion factor YZ satisfies the following formula: YZ=BZ×YC / BYC; Among them, BYC is the manually set standard number, and BZ is the standard congestion factor corresponding to the manually set standard number.

[0032] It's worth noting that in modern traffic management, the efficiency of highway toll booths directly impacts regional traffic flow, user satisfaction, and overall logistics efficiency. By dynamically predicting toll booth congestion for the next time period and adjusting the number of toll lanes accordingly, it's possible to precisely match the number of lanes with traffic demand during peak hours or emergencies. For example, increasing the number of lanes during peak hours can effectively reduce queues, while reducing them during off-peak hours can avoid wasted resources. This flexibility not only reduces wasted lane resources but also reduces traffic delays caused by congestion, improving overall traffic efficiency.

[0033] It should be noted that the historical days in the present invention are several days close to today's date.

[0034] It should be noted that the number of vehicles in the current time period in several historical days is integrated into the current time period quantity group. For example, if the current time period is 15:00-19:00 and the number of historical days is 100 days, the number of vehicles from 15:00 to 19:00 on each of the 100 days is taken as one data and integrated into the current time period quantity group. Therefore, there are 100 vehicles from 15:00 to 19:00 in the current time period quantity group.

[0035] It should be noted that the amplitude adjustment coefficient β of the ln() function is used for several change ratios H i The average value P i The degree of influence on the change ratio DH; when other conditions remain unchanged, the larger β is, the greater the influence on the change ratio DH is, and the smaller β is, the smaller the influence on the change ratio DH is.

[0036] It should be noted that, in another embodiment, the congestion factor YZ may also be obtained through the following steps: When the time reaches the last time point of the current time period, the number of vehicles in the current time period in several historical days is obtained, and the number of vehicles in the next time period in several historical days is obtained; The number of vehicles in the current time period over several historical days is integrated into the current time period quantity group; the number of vehicles in the next time period over several historical days is integrated into the next time period quantity group; Extract the current period quantity group and the next period quantity group in sequence, and mark the extracted current period quantity group or the next period quantity group as the analysis quantity group; obtain the variance of the data in the analysis quantity group, and judge whether the variance is less than the corresponding variance limit value; if yes, calculate the average value of the data in the analysis quantity group to obtain the characteristic quantity; if not, remove the quantity with the largest difference from the quantity mode in the analysis quantity group, and re-judge the variance until the variance of the analysis quantity group is less than the variance limit value, and then calculate the average value of the remaining data in the analysis quantity group to obtain the characteristic quantity; When the analysis quantity group is the current time period quantity group, the corresponding feature quantity is marked as the feature quantity DTL; when the analysis quantity group is the next time period quantity group, the corresponding feature quantity is marked as the feature quantity YTL; based on the feature quantity DTL and the feature quantity YTL, the congestion factor YZ for the next time period of the day is determined; the congestion factor YZ satisfies the following formula: YZ=BZ×(DC×YTL / DTL) / BYC; Among them, BYC is the manually set standard number, BZ is the standard congestion factor corresponding to the manually set standard number, and DC is the number of vehicles in the current time period on that day.

[0037] In this application, the toll lanes open at the toll station in the next time period are set based on the congestion factor, including: Extract the congestion factor YZ. When the congestion factor YZ is greater than congestion threshold 1, open all toll lanes of the current toll station. Congestion threshold 1 and congestion threshold 2 are both manually set, and congestion threshold 1 is greater than congestion threshold 2. When the congestion factor is not greater than the congestion threshold 1 and not less than the congestion threshold 2, the number of toll lanes TDL of the current toll station is extracted based on the formula KDL= TDL / 2 Determine the number KDL of open toll lanes of the current toll station, and open the toll lanes of the current toll station from left to right based on the number KDL; When the congestion factor is less than the congestion threshold 2, the leftmost toll lane among the toll lanes of the current toll station is opened.

[0038] It should be noted that, when the present invention opens toll lanes, the number of open toll lanes obtained through analysis is the number of one-way lanes.

[0039] It should be noted that in the present invention, the toll lanes of the current toll station are opened from left to right, and the leftmost toll lane among the toll lanes of the current toll station is opened, and the left lane is mainly used. This setting is because: the leftmost lane generally has less overlap with the path of straight vehicles on the main road, avoiding accidents caused by frequent lane changes.

[0040] In this application, the artificial intelligence model is used to guide vehicles to various toll lanes based on the set toll lanes, including: Extracting the open toll lanes and the real-time number of vehicles in the corresponding time period, as well as the number of the toll lane through which each vehicle was directed from the historical reference data; wherein the historical reference data includes a number of open toll lanes and the real-time number of vehicles in the corresponding time period, and the number of the toll lane through which the expert directed each vehicle based on the toll lanes and the real-time number of vehicles in the corresponding time period; Integrate the open toll lanes, the real-time number of vehicles in the corresponding time period, and the toll lanes through which each vehicle is guided into several sets of training data and test data; use the training data to train the artificial intelligence model, use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model based on the test results; ultimately, obtain a channel guidance model whose input is the open toll lanes and the real-time number of vehicles, and whose output is the number of the toll lane through which each vehicle is guided; When the time arrives at the next time period, the open toll lanes and the real-time number of vehicles are input into the channel guidance model to obtain the number of the toll lane that each vehicle is guided to pass through.

[0041] It should be noted that the numbers of the toll channels used in data training are set by experts based on the open toll channels and the real-time number of vehicles in the corresponding time period; when the channel guidance model is built, the output numbers of the toll channels through which each vehicle is guided can be: when the real-time number of vehicles is less than the vehicle threshold, the toll channels through which each vehicle is guided are set according to the distance between the vehicle and each open channel; for example: if vehicle 1 is close to toll channel 1, vehicle 1 is guided to toll channel 1 for passage; when the real-time number of vehicles is not less than the vehicle threshold, the toll channels through which each vehicle is guided are set according to the order in which the vehicles enter the management scope of the toll station; for example: if 6 toll channels are opened, with 6 vehicles in a group, the toll channels through which each vehicle is guided are selected from left to right according to the order in which each group of vehicles enters the toll station; wherein, the vehicle threshold is obtained through manual setting.

[0042] Specifically, the trained artificial intelligence model is tested using test data, and the specific steps for adjusting the artificial intelligence model based on the test results are as follows: The open toll channels in the inspection data and the real-time number of vehicles in the corresponding time period are input into the trained artificial intelligence model to obtain the corresponding number of the toll channels through which each vehicle is guided to pass. The corresponding number of the toll channels through which each vehicle is guided to pass is compared with the corresponding number of the toll channels through which each vehicle is guided to pass in the inspection data. When the two are the same, no parameter adjustment is required, and the next set of inspection data is inspected; if the two numbers are different, the corresponding parameters are adjusted until the two numbers are the same, and then the next set of inspection data is inspected. When the number of inspection data with the same number obtained from all inspection data accounts for 90% or more of the total inspection data, a channel guidance model is obtained, whose input is the open toll channels and the real-time number of vehicles, and whose output is the number of the toll channels through which each vehicle is guided to pass.

[0043] In this application, the road impact factors of each vehicle are determined based on the target data, including: The vehicle's weight CZ, speed V, number of braking times BC, and number of driving violations WG are extracted. When the speed V exceeds a speed threshold VZ or the number of driving violations WG exceeds a violation threshold WGZ, the road impact factor DZ is set to the maximum value within the impact factor's limited range. The speed threshold, violation threshold, and impact factor limited range are all manually set. When the speed V exceeds the speed threshold and the number of illegal driving times WG does not exceed the number of illegal driving times threshold, the road influence factor DZ of the current vehicle is determined based on the vehicle weight CZ, the speed V, the number of braking times BC, and the number of illegal driving times WG; the road influence factor DZ satisfies the following formula: ; Among them, BCZ is the manually set standard vehicle weight, and BCL is the manually set standard number of braking times; 、 、 and The proportional adjustment coefficients are set manually, and , ; When the road influence factor DZ is greater than the maximum value of the influence factor limit range, the road influence factor DZ is taken as the maximum value of the influence factor limit range; when the road influence factor DZ is less than the minimum value of the influence factor limit range, the road influence factor DZ is taken as the minimum value of the influence factor limit range.

[0044] It is worth noting that the road impact factor calculated by the present invention is a factor for calculating the damage caused to the road and the potential traffic hazards caused by the current vehicle during this driving. It is used for the subsequent settlement of highway fees for the current vehicle. The weight of the vehicle and the driver's operation are combined with each other. On the basis of ensuring the reasonableness of highway fees, the highway fees for vehicles with greater potential traffic hazards are increased, and the highway fees for vehicles without potential traffic hazards are reduced. Through precise measurement, the principle of "high-risk drivers pay more" is realized, and a differentiated charging system is established. This can urge drivers to comply with driving safety rules more, so that the charging system has a certain driving supervision effect, and increases the adaptability of the charging system.

[0045] It is worth noting that the present invention takes into account the vehicle's weight, speed, number of braking times, and number of driving violations when calculating the vehicle's impact on other vehicles on the road and the road itself; The weight of the vehicle is taken into account because: the weight of the vehicle directly affects the degree of wear and tear on the road surface. Overloaded vehicles will accelerate damage such as collapse and cracking of the road surface, which will have long-term impacts on infrastructure; The reason for considering speed is that: the higher the speed, the greater the kinetic energy of the vehicle, the greater the load on the braking system, and the significantly increased braking distance, and the greater the potential harm to other vehicles; The number of braking times is taken into account because: braking increases friction between the tire and the road, causing damage to the road surface; The reason for considering the number of driving violations is that the number of violations will disrupt road traffic order, cause congestion or "broken window effect", and increase the risk of accidents.

[0046] It should be noted that, in the present invention, the speed threshold can be set to 120 km / h, and the violation number threshold can be set to 3 times.

[0047] It should be noted that the limiting range of the impact factor is a range used to limit the rationality of the road impact factor DZ, so as to avoid the subsequent calculated highway toll being too high or too low.

[0048] It should be noted that the proportional adjustment coefficient Because: What is affected is the data related to the number of illegal driving WG, The data used is the relevant data of the car weight CZ, The data multiplied by is the speed V. The data multiplied by the number of brakes BC is related to the number of times the vehicle violates traffic regulations during high-speed driving. This is the data that most directly reflects the potential risk of harm caused by the current vehicle. Therefore, the present invention adjusts the proportional adjustment coefficient corresponding to the number of illegal driving times WG. The maximum value set; the vehicle weight CZ is the main data that can affect the highway, therefore, the present invention adjusts the proportional coefficient corresponding to the vehicle weight CZ The value of is set to be ranked second from large to small; speed V is the core indicator of driving behavior, which directly affects safety and accident probability, but its influence may be offset by other factors, such as driving experience. Therefore, the present invention adjusts the proportional adjustment coefficient corresponding to speed V The value is set to the third from large to small; braking will increase the friction between the tire and the road, causing damage to the road, but if the proportional adjustment coefficient of the braking number BC is set If the value is too large, it may cause the driver to be unwilling to brake, which may lead to safety hazards. Therefore, the present invention adjusts the proportional adjustment coefficient corresponding to the number of braking times BC to The value is set to the minimum.

[0049] It should be noted that when the road influence factor DZ is set to the maximum value of the influence factor limit range, the vehicle weight CZ and the number of brakes BC are not limited. This is because: the vehicle weight CZ is generally screened at the toll station at the entrance of the highway, and generally does not exceed the load-bearing capacity of the highway itself, so there is no need to further limit the vehicle weight CZ; braking can reduce the speed to ensure the safety of the driver. If the number of brakes BC is limited, it may cause safety hazards caused by the driver's reluctance to brake; at the same time, when the present invention subsequently analyzes the number of brakes BC, the proportional adjustment coefficient set for it is very small, for example, the value range is [0,0.1]; this is to avoid the safety hazards caused by the driver's reluctance to brake due to the statistics of the number of brakes BC.

[0050] It should be noted that, in the present invention, the standard vehicle weight BCZ can be set to 49 tons, and the standard number of brakes BCL is obtained by analyzing the length of the route traveled, and the standard number of brakes is proportional to the route length. For example, when the route length is 100 kilometers, the standard number of brakes is 20 times, and when the route length is 200 kilometers, the standard number of brakes is 40 times.

[0051] This application determines the highway toll for each vehicle based on road impact factors, including: The mileage LC of the current vehicle during this highway driving is obtained, the road influence factor DZ is extracted, and the highway fee GY of the current vehicle is determined based on the road influence factor DZ and the mileage LC. The highway fee GY satisfies the following formula: GY=ZY×LC×DZ / YZ; Among them, ZY is the manually set base rate for one kilometer, and YZ is the middle value of the limited range of influencing factors.

[0052] In this application, the expressway fees charged by CPC card or ETC card include: When the vehicle reaches the CPC card toll booth or ETC card toll booth at the toll station, the highway toll for this trip is paid using the CPC card or ETC card.

[0053] See also Figure 3 , a second aspect of the present invention provides an unmanned adaptive toll collection system for highways, comprising: an on-site dispatching module, and a data collection module and an adaptive toll collection module connected to the on-site dispatching module; Data collection module: used to obtain the number of vehicles within the toll station's management area and target data for each vehicle; target data includes vehicle weight, speed, number of braking times, and number of driving violations; On-site dispatch module: This module divides time periods and determines the congestion factor of the toll station for the next time period based on the number of vehicles in the current time period. It also sets the toll lanes open at the toll station for the next time period based on the congestion factor. When the next time period arrives, vehicles are directed to the toll lanes based on the set toll lanes using an artificial intelligence model. Adaptive charging module: used to determine the road impact factor of each vehicle based on target data; determine the highway fee of each vehicle based on the road impact factor; collect highway fees through CPC cards or ETC cards.

[0054] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0055] Working principle of the present invention: Obtaining the number of vehicles within the toll station's management area and target data for each vehicle provides data support for subsequent analysis; dividing time periods provides personalized time periods for subsequent analysis; determining the toll station's congestion factor for the next time period based on the number of vehicles in the current time period; calculating the congestion situation at the toll station in the next time period, providing a theoretical basis for the subsequent opening of toll lanes; setting the toll lanes open at the toll station in the next time period based on the congestion factor; and when the time reaches the next time period, using the artificial intelligence model to guide vehicles to the various toll lanes based on the set toll lanes. Determine the road impact factor for each vehicle based on the target data. This step provides a dynamic road impact factor by analyzing the driver's driving behavior. Subsequent highway fees can be reasonably adjusted based on this road impact factor. Determine the highway fee for each vehicle based on the road impact factor. Collect highway fees through CPC cards or ETC cards.

[0056] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An unmanned adaptive toll collection method for highways, characterized in that: include: Obtain the number of vehicles within the toll station's management area and target data for each vehicle; target data includes vehicle weight, speed, number of braking times, and number of driving violations; Divide the time period and determine the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period; Set the toll lanes open at the toll station in the next time period based on the congestion factor; When the time reaches the next time period, the vehicle is guided to each toll lane based on the set toll lanes through the artificial intelligence model; Determining a road impact factor for each vehicle based on the target data; Determine the highway toll for each vehicle based on road impact factors; Pay high-speed tolls using CPC cards or ETC cards.

2. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The method of obtaining the number of vehicles within the management range of the toll station and target data of each vehicle includes: When a vehicle enters the toll station's management area, the number of vehicles currently in use is obtained through video monitoring; when a vehicle reaches the area where the weighing equipment is located, the vehicle's weight is obtained; The number of braking times of the vehicle on the highway is obtained through on-board sensors, and the number of driving violations and speed of the vehicle at several moments on the highway are obtained through video monitoring technology. The speed V of the vehicle on the highway is determined based on the mode, average, and maximum values ​​of the speeds. The speed V satisfies the following formula: V = α1 × DD + α2 × ZD + α3 × PD; Among them, DD is the maximum value of the speed at several moments, ZD is the mode of the speed at several moments, and PD is the average value of the speed at several moments; α1, α2 and α3 are all proportional adjustment coefficients, and α1+α2+α3=1, α1>α2>α3.

3. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The time period division includes: When the time reaches 0:00 on a given day, the traffic volume at each time point on the current day is obtained, the traffic volume is divided into a number of traffic volume groups according to the time point, and the mode in each traffic volume group is marked as the characteristic traffic volume at the corresponding time point; wherein the traffic volume is the traffic volume within the management range of the current toll station; Marking the time point when the characteristic traffic flow is greater than the traffic flow threshold as a target time point, connecting consecutive target time points into a target time period, and connecting consecutive non-target time points into a non-target time period; Target time periods or non-target time periods whose duration is longer than the defined duration are marked as management time periods, and target time periods or non-target time periods whose duration is not longer than the defined duration are merged into the smaller of the two adjacent management time periods; a day is divided into several time periods according to the time range of each management time period.

4. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The determining of the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period includes: When the time reaches the last time point of the current time period, the number of vehicles in the current time period in several historical days is obtained, and the number of vehicles in the next time period in several historical days is obtained; The number of vehicles in the current time period over several historical days is integrated into the current time period quantity group; the number of vehicles in the next time period over several historical days is integrated into the next time period quantity group; Sequentially extract the quantity YL in the next period quantity group corresponding to each date in several historical days i and the quantity DL in the current period quantity group i , get the number YL of the same number i in turn i Subtract the quantity DL i The difference C i ; Based on the difference C i Determine the difference C between adjacent dates i The change ratio H i ; Where i is the number of each date in a certain number of historical days; The change ratio H i Satisfies the following formula: H i =(C i -C i-1 ) / C i-1 ; Get some change ratio H i The average value P i , based on the average value P i Determine the change ratio DH for the day; the change ratio DH satisfies the following formula: DH=β×ln(P i +1)+1; Among them, β is the amplitude adjustment coefficient, and the value range of β is (0,1]; The number YC of vehicles in the next time period on the same day is determined based on the ratio DH, and the number YC satisfies the following formula: YC=(1+DH)×DC; Among them, DC is the number of vehicles in the current time period on that day; The congestion factor YZ for the next time period of the day is determined based on the quantity YC. The congestion factor YZ satisfies the following formula: YZ=BZ×YC / BYC; Among them, BYC is the standard quantity, and BZ is the standard congestion factor corresponding to the standard quantity.

5. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The setting of toll lanes to be opened at a toll station in the next time period based on the congestion factor includes: Extract the congestion factor YZ. When the congestion factor YZ is greater than a congestion threshold 1, open all toll lanes at the current toll station. The congestion threshold 1 is greater than the congestion threshold 2. When the congestion factor is not greater than the congestion threshold 1 and not less than the congestion threshold 2, the number of toll lanes TDL of the current toll station is extracted based on the formula KDL= TDL / 2 Determine the number KDL of open toll lanes of the current toll station, and open the toll lanes of the current toll station from left to right based on the number KDL; When the congestion factor is less than the congestion threshold 2, the leftmost toll lane among the toll lanes of the current toll station is opened.

6. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The toll lanes based on the settings guide vehicles to the toll lanes through the artificial intelligence model, including: Extracting the open toll lanes and the real-time number of vehicles in the corresponding time period, as well as the number of the toll lane through which each vehicle was directed from the historical reference data; wherein the historical reference data includes a number of open toll lanes and the real-time number of vehicles in the corresponding time period, and the number of the toll lane through which the expert directed each vehicle based on the toll lanes and the real-time number of vehicles in the corresponding time period; Integrate the open toll lanes, the real-time number of vehicles in the corresponding time period, and the toll lanes through which each vehicle is guided into several sets of training data and test data; use the training data to train the artificial intelligence model, use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model based on the test results; ultimately, obtain a channel guidance model whose input is the open toll lanes and the real-time number of vehicles, and whose output is the number of the toll lane through which each vehicle is guided; When the time arrives at the next time period, the open toll lanes and the real-time number of vehicles are input into the channel guidance model to obtain the number of the toll lane that each vehicle is guided to pass through.

7. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: Determining the road impact factor of each vehicle based on the target data includes: Extract the current vehicle's weight CZ, speed V, number of braking times BC, and number of driving violations WG; when the speed V exceeds a speed threshold VZ or the number of driving violations WG exceeds a violation threshold WGZ, set the road impact factor DZ to the maximum value within the impact factor limit range; When the speed V exceeds the speed threshold and the number of illegal driving times WG does not exceed the number of illegal driving times threshold, the road influence factor DZ of the current vehicle is determined based on the vehicle weight CZ, the speed V, the number of braking times BC, and the number of illegal driving times WG; the road influence factor DZ satisfies the following formula: ； Among them, BCZ is the standard vehicle weight, BCL is the standard number of braking times; 、 、 and are all adjusted by proportional coefficients, and , ; When the road influence factor DZ is greater than the maximum value of the influence factor limit range, the road influence factor DZ is taken as the maximum value of the influence factor limit range; when the road influence factor DZ is less than the minimum value of the influence factor limit range, the road influence factor DZ is taken as the minimum value of the influence factor limit range.

8. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The method of determining the highway fee for each vehicle based on the road impact factor includes: The mileage LC of the current vehicle during this highway travel is obtained, the road influence factor DZ is extracted, and the highway fee GY of the current vehicle is determined based on the road influence factor DZ and the mileage LC. The highway fee GY satisfies the following formula: GY=ZY×LC×DZ / YZ; Among them, ZY is the base rate for one kilometer, and YZ is the middle value of the range of impact factors.

9. The unmanned adaptive toll collection method for highways according to claim 1, characterized in that: The expressway fees charged by CPC card or ETC card include: When the vehicle reaches the CPC card toll booth or ETC card toll booth at the toll station, the highway toll for this trip is paid using the CPC card or ETC card.

10. An unmanned adaptive toll collection system for highways, operating based on the unmanned adaptive toll collection method for highways according to any one of claims 1 to 9, characterized in that: include: An on-site dispatching module, and a data collection module and an adaptive charging module connected to the on-site dispatching module; The data collection module is used to obtain the number of vehicles within the toll station's management area and target data for each vehicle; wherein the target data includes vehicle weight, speed, number of braking times, and number of driving violations; The on-site dispatch module is used to divide the time periods and determine the congestion factor of the toll station in the next time period based on the number of vehicles in the current time period; Set the toll lanes open at the toll station in the next time period based on the congestion factor; when the time reaches the next time period, the artificial intelligence model will be used to guide vehicles to the toll lanes based on the set toll lanes; The adaptive charging module is used to determine the road impact factor of each vehicle based on the target data; determine the highway fee of each vehicle based on the road impact factor; and collect the highway fee through the CPC card or the ETC card.

Images