A method for predicting highway transfer traffic volume based on discrete choice model

Abstract

The present invention discloses a method for predicting highway transfer traffic based on a discrete selection model, comprising: obtaining environmental data of a target highway, collecting environmental data and traffic data of a traffic network, and establishing a traffic network model; performing dynamic time window division on the traffic data to obtain window data, and predicting the window data to obtain predicted window data; performing an impact analysis on the window data based on the environmental data to obtain an environmental selection probability, and obtaining predicted highway transfer traffic based on the predicted window data and the environmental selection probability based on a discrete selection model; constructing a highway transfer traffic prediction model based on the predicted highway transfer traffic, inputting the highway data to be analyzed into the highway transfer traffic prediction model, and outputting a prediction result. The method can not only improve the accuracy of highway transfer traffic prediction, but also has good interpretability, and can be directly applied to a highway transfer traffic prediction system.

Description

Technical Field

[0001] The invention relates to the field of traffic flow prediction, and in particular to a method for predicting highway transfer traffic volume based on a discrete selection model. Background Art

[0002] With the acceleration of urbanization and the increasing complexity of transportation networks, accurate prediction of traffic flow is of great significance for traffic management and planning. Traditional traffic flow prediction methods include time series analysis, regression analysis, etc., but these methods often have difficulty in dealing with the nonlinearity and complexity of traffic data. In recent years, with the development of big data and machine learning technology, traffic flow prediction methods based on deep learning have gradually become a research hotspot. These methods can better capture the spatiotemporal characteristics and complex relationships of traffic data, but they often require a large amount of data support and the interpretability of the model is poor.

[0003] The highway transfer traffic volume prediction method based on discrete choice model involved in the present invention aims to provide a new traffic flow prediction method by combining the interpretability of traditional traffic models and the predictive ability of machine learning models. The method establishes a traffic network model by analyzing the environmental data and traffic data of the traffic network, and uses technical means such as dynamic time window division, environmental impact analysis and discrete choice model to achieve accurate prediction of highway transfer traffic volume. This method not only improves the prediction accuracy, but also has good interpretability. It can be directly applied to the highway transfer traffic volume prediction system, providing a scientific basis for traffic management and planning. Summary of the invention

[0004] The purpose of the present invention is to provide a method for predicting highway transfer traffic volume based on a discrete selection model.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Obtain environmental data of the target highway, collect environmental data and traffic data of the transportation network, and establish a transportation network model;

[0008] Performing dynamic time window division on the traffic data to obtain window data, and predicting the window data to obtain predicted window data;

[0009] Performing an impact analysis on the window data based on the environmental data to obtain an environmental selection probability, and obtaining a predicted highway transfer traffic volume based on the discrete selection model and the traffic network model according to the predicted window data and the environmental selection probability;

[0010] A highway transfer traffic volume prediction model is constructed according to the predicted highway transfer traffic volume, the highway data to be analyzed is input into the highway transfer traffic volume prediction model, and a prediction result is output.

[0011] Furthermore, the method of obtaining environmental data of the target highway, collecting environmental data and traffic data of the traffic network, and establishing a traffic network model includes:

[0012] The target roads include rebuilt roads and newly built roads. The traffic data include traffic flow, average vehicle speed and vehicle type distribution. The environmental data include weather data, road humidity, air quality index and light intensity.

[0013] The traffic network model is an undirected graph consisting of nodes and edges. Intersections and road connection points are nodes of the traffic network model, and roads are edges.

[0014] Furthermore, the method of dynamically dividing the traffic data into time windows to obtain window data includes:

[0015] The traffic flow and average speed of each node in the traffic data are normalized to establish data points. The hierarchical clustering algorithm is used to cluster the data points of each node. The inter-cluster spacing of the clusters is:

[0016]

[0017] in, for and The inter-cluster spacing, For data points and The Euclidean distance of and are the d-th and b-th data points, and For different clusters, and for and The number of data points included, is the time attenuation coefficient, For data points and time interval;

[0018] Get a dynamic window length based on the density of clusters:

[0019]

[0020] in, is the window length, for The weight of is the density of the e-th cluster, is the number of clusters, and is the preset adjustment parameter, is the basic window length,

[0021] The traffic data is divided into time windows according to the window length of the cluster to obtain window data.

[0022] Furthermore, a method for predicting the window data to obtain predicted window data includes:

[0023] Perform a stationary test on the window data:

[0024]

[0025] in is the window data at time point t, yes The first-order difference of is a constant term, is the coefficient of the time trend term, is the coefficient of the autoregressive term, is the coefficient of the i-th order lag term, is the order of the autoregressive term, is the coefficient of the j-th order difference term, is the order of the difference term, is the error term, is the heteroskedasticity adjustment term,

[0026] When , the window data is stable, When , the window data is non-stationary, and the non-stationary window data is differentiated to obtain the stationary window data.

[0027] Using VAR model for forecasting:

[0028]

[0029] in is the target window data of the t-th prediction window data, , is the number of window data, is the k-dimensional intercept column vector, X is the d-dimensional exogenous variable column vector, and is the window data other than the target window data. yes The estimated matrix of dimension B is dimensional matrix to be estimated, p is the lag order of the VAR model, is the k-dimensional error vector, is the coefficient matrix to be estimated,

[0030] The Bayesian Information Criterion is used to select the optimal lag order and to perform back-difference on the forecast data of the non-stationary window data.

[0031] Furthermore, the method of performing an impact analysis on the window data based on the environment data to obtain the environment selection probability includes:

[0032] The environmental data and window data of the traffic network are used to establish a data set. The traffic flow in the window data is used as the dependent variable, and the environmental data and the average traffic flow in the cluster are used as independent variables. The data set is used to train a regression model based on the random forest algorithm:

[0033] The decision tree performs feature selection and splitting based on the information gain rate. The formula for the information gain rate is:

[0034]

[0035] In the formula, is the information gain rate of feature f, It is The sample ratio of each category in the dataset R, is the number of categories in the dataset R, E express The conditional entropy of is a subset of feature f whose value is w, yes The number of samples in is the number of samples in the dataset R, is the feature importance The variance of For control The regularization term of

[0036] The objective function of a single decision tree is:

[0037]

[0038] in and are the number of samples in the left child node and the right child node after the decision tree splits. Left and Right represent the sample index sets in the left child node and the right child node respectively. For the dependent variable, It is a sample The weight of and are the average target values ​​of samples in the left and right child nodes, respectively. is the regularization weight, The decision tree The splitting coefficient, is the number of split coefficients of the decision tree,

[0039] According to the proportion of the predicted value of the dependent variable of different environmental data of the road in the total predicted value of the road, the environmental data is divided into quartile intervals to obtain the classification index and the environmental selection probability of the environmental data of the road under different classifications.

[0040] Furthermore, a method for predicting highway transfer traffic volume based on the prediction window data and the environmental selection probability based on a discrete selection model and the traffic network model includes:

[0041] The input data of the discrete choice model include the length of the road, the prediction window data and the probability of environmental selection. The utility function is:

[0042]

[0043] in, For the road middle The utility function of the vehicle model, is the random error utility, which follows the Gumbel distribution, , , and are the length of the road, the average speed, the probability of environment selection and The weight of the traffic volume of the vehicle type, , , and Road The length of the node, the predicted average speed of the adjacent nodes, and the environmental data category are The environmental selection probability and the prediction of the adjacent nodes The flow of vehicle models, For categories in environmental data The proportion of A classification index for environmental data. The number of classification indexes for environmental data,

[0044] The path selection probability of the target road in the connected nodes of the target road is:

[0045]

[0046] in, Target highway Predicted highway transfer traffic volume by vehicle type, and Road and target highway The utility function of the vehicle model, is the number of vehicle models, is the number of connected roads of the connected nodes of the target highway,

[0047] The predicted highway transfer traffic volume of the target highway is the sum of the products of the predicted traffic flows of all its connected nodes and the corresponding path selection probabilities.

[0048] Furthermore, a method for constructing a highway transfer traffic volume prediction model according to the predicted highway transfer traffic volume includes:

[0049] Taking traffic data and environmental selection probability as input features, and the predicted highway transfer traffic volume as the target variable, the graph neural network algorithm is used to learn the topological structure of the traffic network model and the mapping relationship between the input features and the target variables, and then a highway transfer traffic volume prediction model is established.

[0050] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0051] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0052] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0053] The beneficial effects of the present invention are:

[0054] The present invention is a method for predicting highway transfer traffic volume based on a discrete selection model. Compared with the prior art, the present invention has the following technical effects:

[0055] The present invention improves the accuracy of highway transfer traffic forecasting by comprehensively considering the environmental data and traffic data of the target highway and traffic network, and using a variety of advanced algorithms for data processing and model construction. The application of discrete selection models and traffic network models makes the forecast results more consistent with actual traffic conditions. It provides strong support for highway traffic planning and management, helps to improve the efficiency of traffic resource utilization, and optimizes traffic operation conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of the steps of a method for predicting highway transfer traffic volume based on a discrete selection model of the present invention;

[0057] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0058] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0059] The present invention provides a method for predicting highway transfer traffic volume based on a discrete selection model, comprising the following steps:

[0060] like Figure 1 As shown, in this embodiment, the following steps are included:

[0061] Obtain environmental data of the target highway, collect environmental data and traffic data of the transportation network, and establish a transportation network model;

[0062] In the actual evaluation, the traffic network consists of roads and intersections around the target highway;

[0063] Performing dynamic time window division on the traffic data to obtain window data, and predicting the window data to obtain predicted window data;

[0064] In the actual evaluation, the unit of window length is minutes, and the minimum unit is 5 minutes;

[0065] Performing an impact analysis on the window data based on the environmental data to obtain an environmental selection probability, and obtaining a predicted highway transfer traffic volume based on the discrete selection model and the traffic network model according to the predicted window data and the environmental selection probability;

[0066] A highway transfer traffic volume prediction model is constructed according to the predicted highway transfer traffic volume, the highway data to be analyzed is input into the highway transfer traffic volume prediction model, and a prediction result is output.

[0067] In this example, the method of obtaining the environmental data of the target highway, collecting the environmental data and traffic data of the traffic network, and establishing the traffic network model includes:

[0068] The target roads include rebuilt roads and newly built roads. The traffic data include traffic flow, average vehicle speed and vehicle type distribution. The environmental data include weather data, road humidity, air quality index and light intensity.

[0069] The traffic network model is an undirected graph consisting of nodes and edges. Intersections and road connection points are nodes of the traffic network model, and roads are edges.

[0070] In this example, the method of dynamically dividing the traffic data into time windows to obtain window data includes:

[0071] The traffic flow and average speed of each node in the traffic data are normalized to establish data points. The hierarchical clustering algorithm is used to cluster the data points of each node. The inter-cluster spacing of the clusters is:

[0072]

[0073] in, for and The inter-cluster spacing, For data points and The Euclidean distance of and are the d-th and b-th data points, and For different clusters, and for and The number of data points included, is the time attenuation coefficient, For data points and time interval;

[0074] Get a dynamic window length based on the density of clusters:

[0075]

[0076] in, is the window length, for The weight of is the density of the e-th cluster, is the number of clusters, and is the preset adjustment parameter, is the basic window length,

[0077] The traffic data is divided into time windows according to the window length of the cluster to obtain window data.

[0078] In this example, the method of predicting the window data to obtain predicted window data includes:

[0079] Perform a stationary test on the window data:

[0080]

[0081] in is the window data at time point t, yes The first-order difference of is a constant term, is the coefficient of the time trend term, is the coefficient of the autoregressive term, is the coefficient of the i-th order lag term, is the order of the autoregressive term, is the coefficient of the j-th order difference term, is the order of the difference term, is the error term, is the heteroskedasticity adjustment term,

[0082] When , the window data is stable, When , the window data is non-stationary, and the non-stationary window data is differentiated to obtain the stationary window data.

[0083] Using VAR model for forecasting:

[0084]

[0085] in is the target window data of the t-th prediction window data, , is the number of window data, is the k-dimensional intercept column vector, X is the d-dimensional exogenous variable column vector, and is the window data other than the target window data. yes The estimated matrix of dimension B is dimensional matrix to be estimated, p is the lag order of the VAR model, is the k-dimensional error vector, is the coefficient matrix to be estimated,

[0086] The Bayesian Information Criterion is used to select the optimal lag order and to perform back-difference on the forecast data of the non-stationary window data.

[0087] In this example, the method of performing an impact analysis on the window data based on the environment data to obtain the environment selection probability includes:

[0088] The environmental data and window data of the traffic network are used to establish a data set. The traffic flow in the window data is used as the dependent variable, and the environmental data and the average traffic flow in the cluster are used as independent variables. The data set is used to train a regression model based on the random forest algorithm:

[0089] The decision tree performs feature selection and splitting based on the information gain rate. The formula for the information gain rate is:

[0090]

[0091] In the formula, is the information gain rate of feature f, It is The sample ratio of each category in the dataset R, is the number of categories in the dataset R, E express The conditional entropy of is a subset of feature f whose value is w, yes The number of samples in is the number of samples in the dataset R, is the feature importance The variance of For control The regularization term of

[0092] The objective function of a single decision tree is:

[0093]

[0094] in and are the number of samples in the left child node and the right child node after the decision tree splits. Left and Right represent the sample index sets in the left child node and the right child node respectively. For the dependent variable, It is a sample The weight of and are the average target values ​​of samples in the left and right child nodes, respectively. is the regularization weight, The decision tree The splitting coefficient, is the number of split coefficients of the decision tree,

[0095] According to the proportion of the predicted value of the dependent variable of different environmental data of the road in the total predicted value of the road, the environmental data is divided into quartiles to obtain the classification index, and the environmental selection probability of the environmental data of the road under different classifications is obtained. The environmental selection probability of the environmental data under different classifications is the average value of the environmental selection probability of the environmental data of the current category.

[0096] In this example, the method for predicting highway transfer traffic volume based on the discrete selection model and the traffic network model according to the prediction window data and the environmental selection probability includes:

[0097] The input data of the discrete choice model include the length of the road, the prediction window data and the probability of environmental selection. The utility function is:

[0098]

[0099] in, For the road middle The utility function of the vehicle model, is the random error utility, which follows the Gumbel distribution, , , and are the length of the road, the average speed, the probability of environment selection and The weight of the traffic volume of the vehicle type, , , and Road The length of the node, the predicted average speed of the adjacent nodes, and the environmental data category are The environmental selection probability and the prediction of the adjacent nodes The flow of vehicle models, For categories in environmental data The proportion of A classification index for environmental data. The number of classification indexes for environmental data,

[0100] The path selection probability of the target road in the connected nodes of the target road is:

[0101]

[0102] in, Target highway Predicted highway transfer traffic volume by vehicle type, and Road and target highway The utility function of the vehicle model, is the number of vehicle models, is the number of connected roads of the connected nodes of the target highway,

[0103] The predicted highway transfer traffic volume of the target highway is the sum of the products of the predicted traffic flows of all its connected nodes and the corresponding path selection probabilities.

[0104] In this example, the method for constructing a highway transfer traffic volume prediction model according to the predicted highway transfer traffic volume includes:

[0105] Taking traffic data and environmental selection probability as input features, and the predicted highway transfer traffic volume as the target variable, the graph neural network algorithm is used to learn the topological structure of the traffic network model and the mapping relationship between the input features and the target variables, and then a highway transfer traffic volume prediction model is established.

[0106] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0107] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0108] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0109] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a highway transfer traffic volume prediction device based on a discrete selection model at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the above-mentioned highway transfer traffic volume prediction methods based on a discrete selection model.

[0110] The above application Figure 1The highway transfer traffic volume prediction method based on a discrete selection model disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0111] The electronic device may also perform Figure 1 A highway transfer traffic volume prediction method based on discrete choice model is proposed and implemented Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0112] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, any one of the aforementioned highway transfer traffic volume prediction methods based on discrete choice models is executed.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0118] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0120] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0121] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0122] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A highway transfer traffic volume prediction method based on discrete choice model, characterized in that: The following steps are involved: Obtain environmental data of the target highway, collect environmental data and traffic data of the transportation network, and establish a transportation network model; Performing dynamic time window division on the traffic data to obtain window data, and predicting the window data to obtain predicted window data; Performing an impact analysis on the window data based on the environmental data to obtain an environmental selection probability, and obtaining a predicted highway transfer traffic volume based on the discrete selection model and the traffic network model according to the predicted window data and the environmental selection probability; Constructing a highway transfer traffic volume prediction model according to the predicted highway transfer traffic volume, inputting the highway data to be analyzed into the highway transfer traffic volume prediction model, and outputting the prediction result; The method of dynamically dividing the traffic data into time windows to obtain window data includes: The traffic flow and average speed of each node in the traffic data are normalized to establish data points. The hierarchical clustering algorithm is used to cluster the data points of each node. The inter-cluster spacing of the clusters is: in, for and The inter-cluster spacing, For data points and The Euclidean distance of and are the d-th and b-th data points, and For different clusters, and for and The number of data points included, is the time attenuation coefficient, For data points and time interval; Get a dynamic window length based on the density of clusters: in, is the window length, for The weight of is the density of the e-th cluster, is the number of clusters, and is the preset adjustment parameter, is the basic window length, The traffic data is divided into time windows according to the window length of the cluster to obtain window data.

2. The highway transfer traffic volume prediction method based on discrete choice model according to claim 1 is characterized in that: The method of obtaining environmental data of a target highway, collecting environmental data and traffic data of a traffic network, and establishing a traffic network model includes: The target roads include rebuilt roads and newly built roads. The traffic data include traffic flow, average vehicle speed and vehicle type distribution. The environmental data include weather data, road humidity, air quality index and light intensity. The traffic network model is an undirected graph consisting of nodes and edges. Intersections and road connection points are nodes of the traffic network model, and roads are edges.

3. The highway transfer traffic volume prediction method based on discrete choice model according to claim 1 is characterized in that: The method of predicting the window data to obtain predicted window data includes: Perform a stationary test on the window data: in is the window data at time point t, yes The first-order difference of is a constant term, is the coefficient of the time trend term, is the coefficient of the autoregressive term, is the coefficient of the i-th order lag term, is the order of the autoregressive term, is the coefficient of the j-th order difference term, is the order of the difference term, is the error term, is the heteroskedasticity adjustment term, When , the window data is stable, When , the window data is non-stationary, and the non-stationary window data is differentiated to obtain the stationary window data. Using VAR model for forecasting: in is the target window data of the t-th prediction window data, , is the number of window data, is the k-dimensional intercept column vector, X is the d-dimensional exogenous variable column vector, and is the window data other than the target window data. yes The estimated matrix of dimension B is dimensional matrix to be estimated, p is the lag order of the VAR model, is the k-dimensional error vector, is the coefficient matrix to be estimated, The Bayesian Information Criterion is used to select the optimal lag order and to perform back-difference on the forecast data of the non-stationary window data.

4. The highway transfer traffic volume prediction method based on discrete choice model according to claim 1 is characterized in that: The method for obtaining the probability of environmental selection by performing an impact analysis on the window data based on the environmental data includes: The environmental data and window data of the traffic network are used to establish a data set. The traffic flow in the window data is used as the dependent variable, and the environmental data and the average traffic flow in the cluster are used as independent variables. The data set is used to train a regression model based on the random forest algorithm: The decision tree performs feature selection and splitting based on the information gain rate. The formula for the information gain rate is: In the formula, is the information gain rate of feature f, It is The sample ratio of each category in the dataset R, is the number of categories in the dataset R, E express The conditional entropy of is a subset of feature f with value w, yes The number of samples in is the number of samples in the dataset R, is the feature importance The variance of For control The regularization term of The objective function of a single decision tree is: in and are the number of samples in the left and right child nodes after the decision tree splits, Left and Right represent the sample index sets in the left and right child nodes, respectively. For the dependent variable, It is a sample The weight of and are the average target values ​​of samples in the left and right child nodes, respectively. is the regularization weight, The decision tree The splitting coefficient, is the number of split coefficients of the decision tree, According to the proportion of the predicted value of the dependent variable of different environmental data of the road in the total predicted value of the road, the environmental data is divided into quartile intervals to obtain the classification index and the environmental selection probability of the environmental data of the road under different classifications.

5. The highway transfer traffic volume prediction method based on discrete choice model according to claim 1 is characterized in that: The method for predicting highway transfer traffic volume based on the prediction window data and the environmental selection probability based on a discrete selection model and the traffic network model comprises: The input data of the discrete choice model include the length of the road, the prediction window data and the probability of environmental selection. The utility function is: in, For the road middle The utility function of the vehicle model, is the random error utility, which follows the Gumbel distribution, , , and are the length of the road, the average speed, the probability of environment selection and The weight of the traffic volume of the vehicle type, , , and Road The length of the node, the predicted average speed of the adjacent nodes, and the environmental data category are The environmental selection probability and the prediction of the adjacent nodes The flow of vehicle models, For categories in environmental data The proportion of A classification index for environmental data. The number of classification indexes for environmental data, The path selection probability of the target road in the connected nodes of the target road is: in, Target highway Predicted highway transfer traffic volume by vehicle type, and Road and target highway The utility function of the vehicle model, is the number of vehicle models, is the number of connected roads of the connected nodes of the target highway, The predicted highway transfer traffic volume of the target highway is the sum of the products of the predicted traffic flows of all its connected nodes and the corresponding path selection probabilities.

6. The highway transfer traffic volume prediction method based on discrete choice model according to claim 1 is characterized in that: The method for constructing a highway transfer traffic volume prediction model according to the predicted highway transfer traffic volume comprises: Taking traffic data and environmental selection probability as input features, and the predicted highway transfer traffic volume as the target variable, the graph neural network algorithm is used to learn the topological structure of the traffic network model and the mapping relationship between the input features and the target variables, and then a highway transfer traffic volume prediction model is established.

7. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 6.

8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 6.

Images