Traffic diversion method based on hierarchical composite highway differentiated charging model

Abstract

The embodiment of the present invention discloses a diversion method based on a differentiated charging model for a layered composite highway, and relates to the field of intelligent transportation technology for highways. The method comprises: obtaining the vehicle speed of each layer of roads on a three-dimensional highway; inputting the vehicle speed and charging scheme of each layer of roads into a differentiated charging model, predicting the future traffic volume of each layer of roads by the differentiated charging model, and adjusting the charging scheme of each layer of roads according to the traffic volume to achieve traffic diversion induction between each layer of roads. This embodiment achieves diversion induction of upper and lower layer traffic volume by formulating differentiated charging strategies for the upper and lower layers of a three-dimensional highway.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of intelligent transportation technology for highways, and in particular to a diversion method based on a hierarchical composite highway differentiated charging model. Background Art

[0002] With the increasing traffic flow, there is a strong demand for highway expansion. However, in areas with a high degree of urbanization and a high proportion of mountainous areas, the expansion of highway capacity is limited and basically cannot be implemented. In response to this situation, three-dimensional expansion has gradually become a trend. Figure 1 This is a schematic diagram of a three-dimensional highway provided by an embodiment of the present invention, including upper and lower layers of roads (where the upper layer is shown in cross-section). However, in order to ensure the safety of the upper layer, generally only small vehicles are allowed to travel. At the same time, in order to improve the efficiency of operation, the flow of small vehicles on the upper layer cannot be greater than its threshold, otherwise it will cause congestion or accidents.

[0003] There are also some highway diversion methods in the prior art. For example, patent CN114333362B discloses a highway traffic detection device and diversion management method, and patent CN115424432A discloses an upstream diversion method under abnormal highway events based on multi-source data. However, they do not reflect the differentiated characteristics of each layer of a three-dimensional highway, and cannot achieve traffic diversion induction between highway layers. Summary of the invention

[0004] The embodiment of the present invention provides a diversion method based on a layered composite highway differentiated charging model, which implements diversion and induction of traffic volume between the upper and lower layers by formulating differentiated charging strategies for the upper and lower layers of a three-dimensional highway.

[0005] In a first aspect, an embodiment of the present invention provides a diversion method based on a hierarchical composite highway differentiated charging model, comprising:

[0006] Obtain the vehicle speeds on each level of the three-dimensional highway;

[0007] The vehicle speed and charging scheme of each layer of road are input into the differentiated charging model, and the differentiated charging model is used to predict the future traffic volume of each layer of road, and the charging scheme of each layer of road is adjusted according to the traffic volume to achieve traffic diversion induction between each layer of road.

[0008] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0009] one or more processors;

[0010] a memory for storing one or more programs,

[0011] When the one or more programs are executed by the one or more processors, the one or more processors implement the diversion method based on the hierarchical composite highway differentiated charging model as described in any embodiment.

[0012] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the diversion method based on the hierarchical composite highway differentiated charging model as described in any embodiment.

[0013] The embodiment of the present invention provides a diversion method based on a differentiated charging model for a layered composite highway. A differentiated charging model for each layer of roads is constructed according to the characteristics of a three-dimensional highway. A differentiated charging strategy is formulated by predicting the traffic flow of the upper and lower layers of roads to achieve diversion and induction of the upper and lower layer traffic volume and balance the upper and lower layer traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 is a schematic diagram of a three-dimensional expressway provided by an embodiment of the present invention;

[0016] Figure 2 It is a flow chart of a diversion method based on a hierarchical composite highway differentiated charging model provided by an embodiment of the present invention;

[0017] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0019] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0020] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] Figure 2 The flowchart of a diversion method based on a hierarchical composite highway differentiated charging model provided by an embodiment of the present invention is shown in FIG. The method is applicable to the case where each layer of a three-dimensional highway is charged separately and is executed by an electronic device. Figure 2 As shown, the method specifically includes:

[0022] S110: Obtain vehicle speeds on each level of the three-dimensional expressway.

[0023] For a layered three-dimensional highway, this step obtains the current vehicle speed of each layer of road respectively as the data source of the entire method.

[0024] Optionally, when the vehicle speed cannot be directly obtained, the current traffic volume of each road layer can be obtained first; and then the vehicle speed of each road layer can be determined according to the current traffic volume of each road layer.

[0025] Specifically, the "traffic volume-vehicle speed model" of the highway is as follows:

[0026]

[0027] Where s represents vehicle speed (km / h); V represents the hourly traffic volume of standard vehicles (vehicles / hour); C represents the hourly traffic capacity of standard vehicles (vehicles / lane / hour), which is a known fixed quantity; λ 1 , 2 , μ 1 and μ 2is the correlation coefficient, which can be obtained from Table 1. Substituting the current traffic volume V of each layer of road into the above model, the vehicle speed of each layer of road can be obtained. The specific conversion process is the existing technology and will not be repeated here.

[0028] Table 1 Coefficients of traffic volume and speed model

[0029] Model <![CDATA[λ 1 ]]> <![CDATA[λ 2 ]]> <![CDATA[μ 1 ]]> <![CDATA[μ 2 ]]> Small guest 96.55 -0.35 86.039 -0.648 VIP 87.81 -0.244 83.288 -0.616 Small goods 79.08 -0.154 78.71 -0.559 Chinese goods 73.67 -0.16 71.925 -0.469 Large goods 68.31 -0.06 70.956 -0.455 Trailer 65 -0.15 62.375 -0.327

[0030] S120, inputting the vehicle speed and charging scheme of each layer of road into a differentiated charging model, using the differentiated charging model to predict the future traffic volume of each layer of road, and adjusting the charging scheme of each layer of road according to the traffic volume to achieve traffic diversion induction between each layer of road.

[0031] This embodiment constructs a differentiated charging model for each layer of roads based on the characteristics of three-dimensional expressways. The model formulates charging plans for each layer of roads by predicting the future traffic volume of each layer of roads to balance the traffic flow (i.e., traffic volume) of each layer of roads.

[0032] In a specific implementation, the differentiated charging model includes a travel utility model, a path selection model, and a traffic volume prediction model. The differentiated charging model can adjust the charging scheme of each level of expressway through the following steps:

[0033] Step 1: Calculate the travel utility U of travelers choosing roads at each level according to the following travel utility model:

[0034]

[0035] Among them, w represents the current toll of each layer of road, l represents the travel distance of each layer of road, s represents the vehicle speed of each layer of road; j represents the uphill and downhill slope of each layer of road, with the uphill slope being positive; a 1 、a 2 、b 1 、b 2 、c 1 、c 2 and d 2 are the calibrated model parameters.

[0036] Optionally, the current toll w can be calculated based on the current weight-based toll rate, the actual toll mileage of each section, etc., l can be the distance between the starting point and the end point of the toll station on each level of road, and j can be pre-determined for a specific highway. The model can take into account the cost, time cost and vehicle operation cost of the traveler's choice of each level of road travel, and comprehensively measure the travel utility of each level of road. The construction of the model and the calibration process of each parameter will be described in detail in the subsequent embodiments.

[0037] Step 2: Calculate the probability of travelers choosing each layer of road based on the following path selection model:

[0038]

[0039] Among them, P(i) represents the probability of the traveler choosing the i-th layer road, and U(i) represents the travel utility of the traveler choosing the i-th layer road. According to the random utility theory, among different travel modes and paths, the traveler will choose the travel path with the highest utility to himself with the greatest probability. The above path selection model quantifies this probability based on the travel utility.

[0040] Step 3: Predict the future traffic volume of each road layer based on the following traffic volume prediction model:

[0041] T(i)=T 0 P(i) (4)

[0042] Among them, T(i) represents the future traffic volume of the i-th road, T 0 represents the total traffic volume of the three-dimensional highway in the future. Optionally, T can be determined by actual observation or traffic situation estimation. 0 , that is, how many vehicles will pass through the three-dimensional expressway in this embodiment in the future? 0 By multiplying it with the travel probability of each layer, we can get the future traffic volume of each layer of roads.

[0043] Step 4: Adjust the charging scheme for each layer of roads according to the future traffic volume of each layer of roads. Optionally, when the upper layer road is the main adjustment object, if the future traffic volume of the upper layer road is greater than the upper threshold, the toll of the upper layer road can be increased; if the future traffic volume of the upper layer road is less than the lower threshold, the toll of the upper layer road can be reduced, so as to balance the flow of the upper and lower layers and ensure efficient and safe operation. Furthermore, in order to improve the stability of the charging scheme and avoid traffic congestion caused by frequent adjustments, the toll of the upper layer road can be increased only when the future traffic volume of the upper layer road is greater than a set multiple of the upper threshold (for example, 1.2 times) and continues for a period of time; the toll of the upper layer road can be reduced only when the future traffic volume of the upper layer road is less than a set ratio of the lower threshold (for example, 0.8) and continues for a period of time.

[0044] Based on the above embodiment and the following embodiment, this embodiment describes the construction process of the travel utility model (2) and the calibration process of its parameters. In a specific implementation, first, according to the toll w, time cost t and vehicle operation cost k, the travel utility function of the traveler's choice of each layer of road is constructed, that is:

[0045] U=f(w,t,k) (5)

[0046] Among them, f is a function with w, t, k as independent variables and U as dependent variable, and the function form is to be determined.

[0047] Taking into account the influencing factors of the three-dimensional (double-layer) expressway in terms of entering and exiting the three-dimensional layer and the uphill and downhill slopes, a new influencing variable is added to the travel utility function, that is, the slope variable j is added. This variable will directly affect the vehicle operation cost k, that is, the vehicle will be affected by the slope when passing through the upper channel, resulting in a larger vehicle driving fuel consumption (that is, the total fuel consumption), resulting in an increase in vehicle operation costs.

[0048] Based on the above considerations, the travel utility function (5) can be modified into the following form:

[0049]

[0050] Among them, h is a function with s and j as independent variables and k as dependent variable, and the function form is to be determined; a 1 、b 1 and c 1 are the model parameters to be calibrated.

[0051] When the above driving fuel consumption is used as the vehicle running cost k, the relationship model between k and the vehicle speed and the road longitudinal slope (i.e., the slope in this embodiment) is as follows:

[0052]

[0053] Among them, a 2 、b 2 、c 2 and d 2 are the model parameters to be calibrated; It is used to characterize the inhibitory effect of vehicle speed on driving fuel consumption. The faster the vehicle speed, the shorter the time required to travel the same distance and the less total fuel consumed. 2 s 2 It is used to characterize the increasing effect of vehicle speed on driving fuel consumption. The faster the speed, the more fuel is consumed per unit distance.

[0054] Substituting model (7) into (6), the travel benefit model can be transformed into the following form:

[0055]

[0056] That is the form of model formula (2). The above is the construction process of travel utility model (2).

[0057] At the same time, before using the travel utility model (2) to calculate the travel utility U of the travelers choosing each layer of roads, it is necessary to calibrate each parameter in the model. According to the different calibration objects, this embodiment provides the following two optional calibration methods:

[0058] The first option is to use a 1 、a 2 , b 1 , b 2 、c 1 、c 2 and d 2 Specifically, first, the fuel consumption data and speed data of the vehicle on each layer of road are collected, and the fuel consumption data is used as the vehicle operation cost k. k, speed data s and slope k (known fixed quantity) are substituted into the fuel consumption model (7), and the parameter a is calibrated. 2 , b 2 、c 2 and d 2 Then, the calibrated a 2 , b 2 、c 2 and d 2 Substitute into the travel utility model (2), and collect the vehicle speed and traffic volume of each layer of road in actual operation, as well as the total traffic volume of the three-dimensional expressway; the vehicle speed, traffic volume of each layer of road in the same period, and the total traffic volume are used as s in the travel utility model (2), and T(i) and T in the traffic volume prediction model (5). 0 , the traffic volume prediction model (5), the route selection model (3) and the travel utility model (2) are jointly calibrated to determine the remaining model parameters a 1 , b 1 and c 1 Furthermore, if each set of traffic data of the same period is taken as a calibration sample, all calibration samples can be divided into n batches. 1 , b 1 and c 1 Performing n fittings will result in a series of a 1 , b 1 、c 1 value, and finally take its average value as the parameter value, that is:

[0059]

[0060] Among them, a 1i , b 1i and c 1i The table shows the parameter values ​​obtained by the i-th fitting. The method shown in formula (7) is also applicable to the calibration of other parameters, and will not be repeated elsewhere.

[0061] The second optional method is to calibrate the coefficients of each order term in model (2) as five independent parameters, where each order term in model (2) includes w, s2 , j and constant terms, and their corresponding coefficients are a 1 ,(b 1 l+b 2 c 1 ),c 1 c 2 、c 1 d 2 and c 1 a 2 Specifically, first, the vehicle speed and traffic volume of each layer of road in actual operation, as well as the total traffic volume of the three-dimensional highway, are collected; then the vehicle speed, traffic volume of each layer of road in the same period, and the total traffic volume are used as s in the travel utility model (2), and T(i) and T in the traffic volume prediction model (5). 0 , the traffic volume prediction model (5), the route selection model (3) and the travel utility model (2) are jointly calibrated to determine the values ​​of the above five parameters.

[0062] Furthermore, the charging scheme adjustment method of S110-S120 can also be executed repeatedly. In order to improve the rationality of the charging scheme, after each adjustment of the charging scheme, the diversion effect of the new charging scheme can be evaluated according to the future vehicle speed and current vehicle speed of each layer of road. If the new charging scheme can effectively achieve traffic diversion, the scheme will be put into actual operation at the toll station of the expressway; otherwise, it will not be put into operation and will be readjusted. In a specific embodiment, the above process may include the following steps:

[0063] First, the future vehicle speed of each road is predicted based on the future traffic volume of each road, and the future vehicle speed and the new charging scheme are input into the differentiated charging model, and the future traffic volume of each road is re-predicted by the differentiated charging model. Optionally, the future traffic volume of each road is substituted into the model (1) as V to obtain the future vehicle speed s of each road; s and the new charging scheme are input into the travel utility model, and the future traffic volume of each road is re-predicted after being processed by the travel utility model, the path selection model and the traffic volume prediction model. The re-prediction results may be in the following two situations:

[0064] Case 1: The re-predicted traffic volume of each layer of roads meets the set threshold range. At this time, the new charging scheme can be put into operation, and the operation of obtaining the vehicle speed of each layer of the three-dimensional highway is returned to enter the next cycle of adjusting the charging scheme. Specifically, since the new charging scheme is obtained when the first predicted future traffic volume does not meet the threshold range, the vehicle speed matching the traffic volume is also a traffic state that cannot meet both safety and operating efficiency, representing the worst state that will be reached if the current traffic state is not adjusted. If the new charging scheme can effectively adjust the traffic state and restore the traffic volume of each layer to the normal range, it means that the scheme is effective and can be put into operation.

[0065] Case 2: There is at least one layer of road whose re-predicted traffic volume does not meet the set threshold range. At this time, the current vehicle speed of each layer of road and the new charging scheme can be input into the differentiated charging model, and the differentiated charging model will predict the future traffic volume of each layer of road again, which is used to conduct a secondary evaluation of the diversion effect of the new scheme. Specifically, as described in Case 1, the vehicle speed that matches the first predicted future traffic volume represents the worst state that will be reached if the current traffic state is not adjusted. If the new charging scheme fails to effectively adjust the traffic state, it means that the diversion effect of the scheme is limited. The diversion effect of the new scheme can be further evaluated through the current vehicle speed of each layer of road. Since the current traffic volume of each layer of road has not exceeded the threshold range, the current vehicle speed that matches the traffic volume represents a relatively good traffic state, which is relatively loose compared to the inspection standard (worst state) of Case 1. The results of the re-prediction will also appear in the following two situations:

[0066] Case A: The traffic volume predicted again on each road level meets the set threshold range, indicating that the new charging scheme can maintain the relatively good traffic state and prevent the risk of future traffic volume exceeding the threshold range, that is, the new charging scheme still has a certain diversion effect and can be put into actual operation on expressways. However, the diversion effect is limited, and the traffic flow may still exceed the threshold range over time. Therefore, the time interval for the next round of adjustment of the charging scheme can be shortened, and S110 can be returned in advance to enter the next round of actual vehicle speed monitoring and charging scheme adjustment.

[0067] Case B: There is at least one layer of road whose predicted traffic volume does not meet the set threshold range, which means that the new charging scheme cannot maintain the relatively good traffic conditions, and the traffic volume of at least one layer will exceed the threshold range in a short period of time. At this time, the current round of charging scheme can be adjusted again by increasing the adjustment range (underadjustment) or changing the adjustment direction (overadjustment) until a charging scheme that meets Case 1 or Case A is obtained.

[0068] In summary, this embodiment provides a diversion method based on a differentiated charging model for a layered composite highway. A differentiated charging model for each layer of roads is constructed according to the characteristics of a three-dimensional highway. A differentiated charging strategy is formulated by predicting the traffic flow of the upper and lower layers of roads to achieve diversion and induction of the upper and lower traffic volumes and balance the upper and lower traffic flows. Specifically, the differentiated charging model includes a travel utility model, a path selection model, and a traffic volume prediction model. In the travel utility model, the influence of the slope on the travel utility is particularly considered, which more accurately reflects the travel characteristics of the three-dimensional highway. The probability of travelers choosing each layer of roads can be obtained through travel utility, thereby predicting the future traffic volume trend of each layer of roads, and formulating a new charging plan when the trend exceeds the set range. Each model paves the way for each other and is indispensable. Through the joint calibration of multiple models, the model parameters can be determined as a whole to provide support for the intelligent charging strategy of the three-dimensional highway.

[0069] In addition, before the new charging scheme is put into operation, this embodiment performs a two-level evaluation of the diversion effect of the new scheme through the future vehicle speed and the current vehicle speed of each layer of road. Among them, the future vehicle speed represents a worst traffic state, and the first evaluation through this state can verify the scheme with a stronger diversion effect; the current vehicle speed represents a better traffic state, and the second evaluation through this state can verify the scheme with the second strongest diversion effect; both schemes can achieve upper and lower layer diversion based on the current traffic state to prevent the traffic volume from exceeding the threshold.

[0070] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Figure 3 A processor 60 is taken as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0071] The memory 61, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the diversion method based on the hierarchical composite highway differentiated charging model in the embodiment of the present invention. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned diversion method based on the hierarchical composite highway differentiated charging model.

[0072] The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0073] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0074] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the diversion method based on a hierarchical composite highway differentiated charging model of any embodiment.

[0075] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0076] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0077] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0078] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A traffic diversion method based on a hierarchical composite highway differentiated charging model, characterized in that: include: Obtain the vehicle speeds on each level of the three-dimensional highway; Inputting the vehicle speed and charging scheme of each layer of road into a differentiated charging model, predicting the future traffic volume of each layer of road by the differentiated charging model, and adjusting the charging scheme of each layer of road according to the traffic volume to achieve traffic volume diversion and induction between the layers of road; Predicting the future vehicle speed of each road layer according to the future traffic volume of each road layer, inputting the future vehicle speed and the new charging scheme into the differentiated charging model, and re-predicting the future traffic volume of each road layer by the differentiated charging model; If the re-predicted traffic volume of each layer of road meets the set threshold range, the new charging scheme is put into operation, and the operation of obtaining the vehicle speed of each layer of the three-dimensional highway is returned to enter the next cycle of adjusting the charging scheme; Otherwise, the current vehicle speed of each layer of road and the new charging scheme are input into the differentiated charging model, and the differentiated charging model predicts the future traffic volume of each layer of road again; if the traffic volume predicted again on each layer of road meets the set threshold range, the new charging scheme is put into operation and the time interval for the next round of adjustment of the charging scheme is shortened; otherwise, the charging scheme of this round is adjusted again by increasing the adjustment range or changing the adjustment direction.

2. The method according to claim 1, characterized in that The differentiated charging model includes a travel utility model, a route selection model and a traffic volume prediction model; The method of predicting the future traffic volume of each layer of roads by the differentiated charging model and adjusting the charging scheme of each layer of roads according to the traffic volume to achieve traffic diversion induction between the layers of roads includes: According to the following travel utility model, the travel utility U of travelers choosing each level of road is calculated: Where w represents the current toll of each layer of road, l represents the travel distance of each layer of road, s represents the vehicle speed of each layer of road; j represents the uphill and downhill slopes of each layer of road, with the uphill slope being positive; a1, a2, b1, b2, c1, c2 and d2 are the calibrated model parameters; According to the following path selection model, the probability of travelers choosing each layer of road is calculated: Among them, P(i) represents the probability of the traveler choosing the i-th layer road, and U(i) represents the travel utility of the traveler choosing the i-th layer road; According to the following traffic volume prediction model, the future traffic volume of each layer of road is predicted: T(i)=T0P(i) Wherein, T(i) represents the future traffic volume of the i-th layer road, and T0 represents the total future traffic volume of the three-dimensional highway; Adjust the charging scheme for each level of roads based on the future traffic volume of each level of roads.

3. The method according to claim 2, characterized in that Before calculating the travel utility U of the travelers choosing the roads at each level according to the following travel utility model, the method further includes: Collecting the vehicle speed and traffic volume of each layer of roads in actual operation, as well as the total traffic volume of the three-dimensional expressway; The vehicle speed, traffic volume, and total traffic volume of each layer of road in the same period are respectively used as s in the travel utility model, and T(i) and T0 in the traffic volume prediction model. The traffic volume prediction model, path selection model, and travel utility model are jointly calibrated to determine the parameters of each model.

4. The method according to claim 3, characterized in that The vehicle speed, traffic volume, and total traffic volume of each layer of road at the same time are respectively used as s in the travel utility model, and T(i) and T0 in the traffic volume prediction model, and the traffic volume prediction model, the path selection model, and the travel utility model are jointly calibrated to determine the parameters of each model, including: The vehicle speed and fuel consumption data k of vehicles on each road layer are collected and substituted into the following fuel consumption model to calibrate the model parameters a2, b2, c2 and d2: Substituting the calibrated a2, b2, c2 and d2 into the travel utility model; The vehicle speed, traffic volume, and total traffic volume of each layer of road in the same period are respectively used as s in the travel utility model, and T(i) and T0 in the traffic volume prediction model. The traffic volume prediction model, path selection model and the travel utility model after substitution are jointly calibrated to determine the remaining model parameters a1, b1 and c1.

5. The method according to claim 3, characterized in that: The vehicle speed, traffic volume, and total traffic volume of each layer of road at the same time are respectively used as s in the travel utility model, and T(i) and T0 in the traffic volume prediction model, and the traffic volume prediction model, the path selection model, and the travel utility model are jointly calibrated to determine the parameters of each model, including: The coefficients a1, (b1l+b2c1), c1c2, c1d2 and c1a2 of each order term in the travel utility model are respectively used as 5 model parameters; The vehicle speed, traffic volume, and total traffic volume of each layer of roads in the same period are respectively used as s in the travel utility model, and T(i) and T0 in the traffic volume prediction model. The traffic volume prediction model, path selection model, and travel utility model are jointly calibrated to determine the values ​​of the five model parameters.

6. The method according to claim 2, characterized in that The charging scheme for each level of road is adjusted according to the future traffic volume of each level of road, including: If the future traffic volume of the upper road is greater than the upper threshold, increase the toll of the upper road; If the future traffic volume of the upper road is less than the lower threshold, the toll of the upper road is reduced.

7. The method according to claim 1, characterized in that The obtaining of the vehicle speeds of each layer of the three-dimensional expressway includes: Get the current traffic volume of each level of the three-dimensional highway; The vehicle speed on each level of road is determined based on the current traffic volume on each level of road.

8. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the diversion method based on the hierarchical composite highway differentiated charging model as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the diversion method based on a hierarchical composite highway differentiated charging model as described in any one of claims 1-7 is implemented.

Images