Traffic mode prediction method considering parking lot charges and related equipment

Abstract

This application proposes a method for predicting traffic modes that takes parking fees into account, and related equipment. The method includes: obtaining a grid map, parking data, and resident travel chain data for a target area; calculating the grid parking fee for each grid cell in the grid map based on the parking data and resident travel chain data; constructing a generalized travel cost expression for private cars based on the resident travel chain data and the grid parking fee; constructing a multivariate utility choice model based on the generalized travel cost expression for private cars and multiple other preset travel cost expressions; generating a travel distribution matrix between grid cells based on the grid map and resident travel chain data; and performing traffic mode prediction on the travel distribution matrix based on the multivariate utility choice model to obtain a refined travel distribution matrix that takes traffic mode selection into account. This application improves the accuracy of urban traffic travel prediction by considering the impact of parking fees on resident travel mode choices.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of urban planning, and in particular to a method for predicting traffic modes taking parking fees into consideration and related equipment. Background Art

[0002] The efficient operation of urban transportation systems has a decisive impact on urban development. Accurately predicting urban transportation travel mode choices can optimize transportation resource allocation and alleviate urban congestion. Urban transportation travel behavior is affected by multi-dimensional factors, including travel costs, time efficiency, urban spatial structure facilities, etc. How to comprehensively consider the impact of the above-mentioned multiple factors on residents' travel modes is a relatively unresolved problem at present.

[0003] Parking fees, as a significant cost for private car travel, significantly influence travel mode choices, especially in areas like city centers where parking spaces are scarce and fees are high. However, existing models often simplify the calculation of private car travel costs and fail to factor in parking fees. This makes it difficult to accurately reflect the regulatory impact of parking fee policies on residents' travel behavior, resulting in low prediction accuracy. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application provides a method and related equipment for predicting traffic modes that takes parking fees into account. By considering the impact of parking fees on residents' travel mode choices, the accuracy of urban traffic travel prediction is improved.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application provides a method for predicting traffic modes taking parking fees into consideration, the method comprising:

[0006] Obtain grid maps, parking lot data, and resident travel chain data for the target area;

[0007] Calculating a grid parking fee for each grid cell in the grid map based on the parking lot data and the resident trip chain data;

[0008] Constructing a generalized travel cost expression for private cars based on the resident travel chain data and the grid parking fee;

[0009] Constructing a multivariate utility choice model based on the generalized travel cost expression of private cars and a plurality of pre-constructed other travel cost expressions;

[0010] generating a travel distribution matrix between the grid units according to the grid map and the resident travel chain data;

[0011] The travel distribution matrix is ​​subjected to traffic mode prediction according to the multivariate utility selection model to obtain a refined travel distribution matrix that takes traffic mode selection into consideration.

[0012] In some embodiments, the parking lot data includes parking lot coordinates and parking fees per unit time of a plurality of parking lots, and calculating the grid parking fee for each grid unit in the grid map based on the parking lot data and the resident trip chain data includes:

[0013] determining a grid unit time parking fee for each of the grid units according to the parking lot coordinates of the plurality of parking lots and the unit time parking fee;

[0014] Determine the average dwell time of each grid cell according to the resident travel chain data;

[0015] The corresponding grid parking fee is determined according to the grid unit time parking fee and the average residence time of each grid unit.

[0016] In some embodiments, determining the grid unit time parking fee of each grid unit based on the parking lot coordinates of the plurality of parking lots and the unit time parking fee includes:

[0017] Mapping the plurality of parking lot coordinates onto the grid map to determine a plurality of parking lot grid units;

[0018] Calculating the parking fee per unit time for each parking lot grid unit according to the parking fee per unit time corresponding to each parking lot grid unit;

[0019] For blank grid cells that are not mapped with the parking lot coordinates, prediction and completion are performed based on the Kriging spatial interpolation method to obtain the grid unit time parking fee of each blank grid.

[0020] In some embodiments, the resident travel chain data includes multiple travel chains, each of which includes a road segment length, a private car's free speed, a private car's fuel cost per mile, an average number of private car passengers, a private car's start-up time, a private car transfer factor, and a private car's additional time cost item. Constructing a generalized private car travel cost expression based on the resident travel chain data and the grid parking fee includes:

[0021] Constructing a private car travel time cost item according to the road section length and the free speed of the private car;

[0022] Constructing a private car fuel cost item based on the road section length, the private car unit mileage fuel cost, the average number of passengers carried by the private car, and a preset time value of money coefficient;

[0023] Constructing a private car startup time cost item according to the private car transfer factor and the private car startup time;

[0024] Constructing a parking fee cost item based on the grid parking fee and the average number of passengers carried by the private car;

[0025] The generalized travel cost expression of the private car is constructed according to the private car driving time cost item, the private car fuel cost item, the private car starting time cost item, the private car additional time cost and the parking fee cost item.

[0026] In some embodiments, performing transportation mode prediction on the travel distribution matrix according to the multivariate utility choice model to obtain a refined travel distribution matrix considering transportation mode selection includes:

[0027] For each trip data in the trip distribution matrix, the trip data is analyzed to obtain prediction element information of the trip data;

[0028] Inputting the prediction factor information into the multivariate utility selection model so that the multivariate utility selection model calculates the utility value corresponding to each mode of transportation, and determines the selection probability of each mode of transportation based on the plurality of utility values;

[0029] Determining a travel mode prediction result corresponding to each of the travel data according to the selection probability of the transportation mode;

[0030] According to the travel mode prediction result corresponding to each travel data, the refined travel distribution matrix considering the choice of transportation mode is obtained.

[0031] In some embodiments, generating a travel distribution matrix between the grid units based on the grid map and the resident travel chain data includes:

[0032] Calculating the trip generation and trip attraction of each grid unit in the grid map according to the grid map and the resident trip chain data;

[0033] The travel distribution of each grid unit is calculated according to the travel generation volume and the travel attraction volume of each grid unit to obtain the travel distribution matrix between the grid units.

[0034] In some embodiments, after performing a transportation mode prediction on the travel distribution matrix according to the multivariate utility choice model to obtain a refined travel distribution matrix that takes transportation mode selection into consideration, the method further includes:

[0035] Based on the refined travel distribution matrix, the travel volume is redistributed to specific road sections in the traffic network to obtain the predicted traffic flow of each road section.

[0036] In a second aspect, an embodiment of the present application provides a traffic mode prediction device that takes parking fees into consideration, including:

[0037] The acquisition module is used to obtain the grid map, parking lot data and residents' travel chain data of the target area;

[0038] a calculation module, configured to calculate a grid parking fee for each grid unit in the grid map based on the parking lot data and the resident travel chain data;

[0039] A first construction module is configured to construct a generalized travel cost expression for a private car based on the resident travel chain data and the grid parking fee;

[0040] A second construction module is used to construct a multivariate utility choice model based on the generalized travel cost expression of private cars and a plurality of pre-constructed other travel cost expressions;

[0041] A generation module, configured to generate a travel distribution matrix between the grid cells based on the grid map and the resident travel chain data;

[0042] A prediction module is used to perform traffic mode prediction on the travel distribution matrix according to the multivariate utility selection model to obtain a refined travel distribution matrix that takes traffic mode selection into consideration.

[0043] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a traffic mode prediction method taking into account parking lot charges as described in any one of the embodiments of the first aspect of the present application.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement a traffic mode prediction method taking into account parking lot charges as described in any one of the embodiments of the first aspect of the present application.

[0045] The embodiment of the present application proposes a method for predicting a traffic mode that takes parking fees into consideration, the method comprising: in response to any node server obtaining a task request, the method comprising: obtaining a grid map, parking data, and resident travel chain data of a target area; calculating the grid parking fee for each grid unit in the grid map based on the parking data and the resident travel chain data; constructing a generalized travel cost expression for a private car based on the resident travel chain data and the grid parking fee; constructing a multivariate utility selection model based on the generalized travel cost expression for a private car and a plurality of pre-constructed other travel cost expressions; generating a travel distribution matrix between grid units based on the grid map and the resident travel chain data; and performing traffic mode prediction on the travel distribution matrix based on the multivariate utility selection model to obtain a refined travel distribution matrix that takes traffic mode selection into consideration.

[0046] The transportation mode prediction method proposed in this application, which takes parking fees into consideration, first obtains parking data and resident travel chain data in the target area, and calculates the parking fee for each grid unit in combination with the grid map, thereby obtaining the spatial distribution characteristics of parking costs accurate to each grid unit. Unlike existing models that generally ignore parking fees, this method fully considers the impact of parking fees on private car travel costs, as well as the differences in parking fees in different areas within the city, such as the difference in parking fees between commercial centers and suburbs. On this basis, this method constructs a generalized travel cost expression for private cars that includes parking fees, and combines it with the existing cost expressions of other travel modes to construct a multivariate utility choice model. The multivariate utility choice model of this method can comprehensively consider various factors that affect travel choices, including travel costs, time efficiency, etc., thereby more accurately reflecting residents' travel decision-making behavior. Then, based on the grid map and residents' travel chain data, a travel distribution matrix between grid cells is generated. The travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area. Finally, the constructed multivariate utility choice model is used to predict the travel mode of the travel distribution matrix, and a refined travel distribution matrix that takes into account the choice of transportation mode is obtained. This allows the prediction of travel distribution to more accurately reflect the travel demand of different transportation modes in different areas. In summary, the method proposed in this application significantly improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost considerations, and refinement of the travel distribution matrix.

[0047] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. The purposes and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by an embodiment of the present application;

[0049] Figure 2 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0050] Figure 3 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0051] Figure 4 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0052] Figure 5 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0053] Figure 6 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0054] Figure 7 This is a flow chart of a method for predicting traffic modes taking parking fees into consideration, provided by another embodiment of the present application;

[0055] Figure 8 This is a schematic diagram of the overall flow of a method for predicting traffic modes taking parking fees into consideration, provided by an embodiment of the present application;

[0056] Figure 9 This is a schematic diagram of a traffic mode prediction device taking parking fees into consideration provided by an embodiment of the present application;

[0057] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0061] The efficient operation of urban transportation systems has a crucial impact on urban development. Accurately predicting residents' travel mode choices is crucial for optimizing transportation resource allocation, alleviating traffic congestion, and formulating sound transportation policies. However, urban travel behavior is influenced by a variety of factors, including but not limited to travel costs, time efficiency, urban spatial structure, and transportation infrastructure. Comprehensively and comprehensively considering the impact of these factors on residents' travel mode choices and building accurate prediction models is a major challenge facing the current transportation sector.

[0062] Parking fees are a significant expense for private car travel, particularly in areas like city centers where parking spaces are scarce and fees are high. They significantly influence residents' travel choices. However, many existing models often ignore parking fees to simplify calculations, or use only rough average parking fee estimates. This makes it difficult for the models to accurately reflect the actual impact of parking fee policies on residents' travel behavior, thereby reducing the accuracy and reliability of the prediction results.

[0063] Based on this, the embodiment of the present application provides a traffic mode prediction method and related equipment that takes parking fees into consideration, which improves the accuracy of urban traffic travel prediction by considering the impact of parking fees on residents' travel mode choices.

[0064] The traffic mode prediction method considering parking lot charges and related equipment provided in the embodiment of the present application are specifically illustrated through the following embodiments. First, the traffic mode prediction method considering parking lot charges in the embodiment of the present application is described.

[0065] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0066] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0067] Figure 1 This is an optional flow chart of a method for predicting traffic modes taking parking fees into consideration provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps 101 to 106.

[0068] Step 101: Obtain a grid map, parking lot data, and resident travel chain data of a target area.

[0069] Step 102 : Calculate the grid parking fee for each grid unit in the grid map based on the parking lot data and the resident travel chain data.

[0070] Step 103: construct a generalized travel cost expression for private cars based on the residents' travel chain data and grid parking fees.

[0071] Step 104 : construct a multivariate utility choice model based on the generalized travel cost expression for private cars and a plurality of pre-constructed other travel cost expressions.

[0072] Step 105: Generate a travel distribution matrix between grid cells based on the grid map and the resident travel chain data.

[0073] Step 106 , performing a transportation mode prediction on the travel distribution matrix according to the multivariate utility choice model to obtain a refined travel distribution matrix that takes transportation mode selection into consideration.

[0074] In steps 101 to 106 shown in the embodiment of the present application, first, by obtaining parking lot data and resident travel chain data of the target area, and combining the grid map to calculate the parking fee of each grid unit, the spatial distribution characteristics of the parking cost of each grid unit are obtained. Unlike existing models that usually ignore parking fees, this method fully considers the impact of parking fees on the travel cost of private cars, as well as the differences in parking fees in different areas within the city, such as the difference in parking fees between commercial centers and suburbs. On this basis, this method constructs a generalized travel cost expression for private cars that includes parking fees, and combines it with the existing cost expressions of other travel modes to construct a multivariate utility selection model. The multivariate utility selection model of this method can comprehensively consider various factors that affect travel choices, including travel costs, time efficiency, etc., thereby more accurately reflecting residents' travel decision-making behavior. Then, based on the grid map and residents' travel chain data, a travel distribution matrix between grid cells is generated. The travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area. Finally, the constructed multivariate utility choice model is used to predict the travel mode of the travel distribution matrix, and a refined travel distribution matrix that takes into account the choice of transportation mode is obtained. This allows the prediction of travel distribution to more accurately reflect the travel demand of different transportation modes in different areas. In summary, the method proposed in this application significantly improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost considerations, and refinement of the travel distribution matrix.

[0075] In some embodiments, step 101 requires acquiring three types of key data: a grid map of the target area, parking lot data, and resident travel chain data. First, a grid map of the target area is acquired. This map divides the target area into a number of regular grid cells, each with a unique identifier and geographic coordinate information. Second, parking lot data is acquired. This data can be extracted from POI (Point of Interest) data. POI data refers to all spatial geographic entities abstracted as point elements, particularly those closely related to people's lives, such as restaurants, parking lots, train stations, and hospitals. POI data typically includes location coordinates (latitude and longitude), name, address, and category. In this embodiment, parking lot POI data includes key information such as the parking lot's geographic location, name, and parking fee per unit time. Finally, resident travel chain data is acquired. Mobile phone signaling is the communication record data between a mobile phone and a communication base station. When a mobile phone connects to a mobile communication network, it generates a series of control commands. The data fields of these commands include various information such as time, location, and number. In this invention, mobile phone signaling data is primarily used to capture trip chain data (origin, dwelling point, and destination) for urban population movement. Specific fields include the origin grid, dwelling point trajectory, destination grid, date, and population flow. Each trip chain records a complete resident's travel trajectory, including information such as the origin, destination, transit points, travel time, and transportation mode used. This data is subsequently used for parking fee calculations, travel cost calculations, and transportation mode predictions.

[0076] In some embodiments, step 102 specifically calculates a base rate for each parking lot within each grid cell based on its charging standard (e.g., hourly or per-use). This rate is then combined with the average dwell time for that grid cell, extracted from the resident travel chain data, to calculate the expected parking fee. For grid cells without parking lot data, spatial interpolation methods can be used to supplement the data based on adjacent grid cells to ensure spatial continuity of parking fee data. This step converts parking fee information for discrete grid cells into a city-wide grid parking fee.

[0077] See also Figure 2 In some embodiments, step 102 may include, but is not limited to, steps 201 to 203 .

[0078] Step 201 : determining the parking fee per unit time of each grid unit according to the parking lot coordinates and the parking fees per unit time of a plurality of parking lots.

[0079] Step 202: Determine the average dwell time of each grid unit based on the residents' travel chain data.

[0080] Step 203 : determining the corresponding grid parking fee according to the grid unit time parking fee and the average dwelling time of each grid unit.

[0081] In step 201 of some embodiments, each parking lot has its corresponding coordinate location and parking fee per unit time. For a grid cell containing a parking lot, its parking fee per unit time can be calculated based on the parking fees per unit time of all parking lots within the grid cell, for example, by taking an average or weighted average. For grid cells that do not contain a parking lot, the corresponding parking fee per unit time can be calculated using interpolation.

[0082] See also Figure 3 In some embodiments, step 201 may include, but is not limited to, steps 301 to 303 .

[0083] Step 301 : Mapping multiple parking lot coordinates onto a grid map to determine multiple parking lot grid units.

[0084] Step 302 : Calculate the parking fee per unit time of each parking lot grid unit according to the parking fee per unit time corresponding to each parking lot grid unit.

[0085] Step 303 : For blank grid cells that are not mapped with parking lot coordinates, prediction and completion are performed based on the Kriging spatial interpolation method to obtain the grid unit time parking fee for each blank grid.

[0086] In step 301 of some embodiments, each parking lot has its corresponding latitude and longitude coordinates. By matching these coordinates with the grid map, the grid unit to which each parking lot belongs can be determined. These grid units containing parking lots are called parking lot grid units.

[0087] In step 302 of some embodiments, a parking lot grid unit may include multiple parking lots, and each parking lot may have a different parking fee per unit time. To determine the parking fee per unit time for each parking lot grid unit, various methods may be used, such as taking an average, a weighted average, or other statistical methods.

[0088] In step 303 of some embodiments, since not all grid cells contain parking lots, some blank grid cells may be left without parking lot data. To obtain the unit-time parking fee for these blank grid cells, a kriging spatial interpolation method can be used for prediction. Kriging is a statistically based spatial interpolation method that uses data from known observation points and spatial correlation analysis to estimate the value of unknown points.

[0089] Through steps 301 to 303, the parking fee per unit time for each grid cell within the target area can be determined, including grid cells containing parking lots and blank grid cells that do not. This method effectively utilizes existing parking lot data and uses spatial interpolation to reasonably estimate uncovered areas, thereby obtaining more comprehensive and detailed spatial distribution data on parking fees. It also solves the problem of being unable to calculate parking fees in some areas due to a lack of parking point of interest (POI) data, making parking fee calculation more complete and accurate.

[0090] In step 202 of some embodiments, the average dwell time of each grid cell is determined based on the resident trip chain data. The resident trip chain data records the length of time residents spend at different locations. By analyzing the dwell time of residents in each grid cell as shown in the trip chain data, the average dwell time of residents in each grid cell can be calculated. For grid cells where dwell time data is not available, kriging interpolation can also be used to provide supplementary predictions.

[0091] In step 203 of some embodiments, the parking fee for each grid unit is calculated based on the unit time parking fee for each grid unit determined in step 201 and the average dwelling time for each grid unit determined in step 202. Specifically, the parking fee for each grid unit is calculated by multiplying the unit time parking fee for each grid unit by the average dwelling time for the grid unit.

[0092] Through steps 201 to 203, this embodiment combines parking lot data and resident travel chain data, so that the parking costs in different areas can be more finely characterized, thereby improving the accuracy of private car travel cost calculation, and further improving the accuracy of the final travel mode prediction.

[0093] In step 103 of some embodiments, the constructed generalized travel cost expression for private cars needs to integrate multiple cost elements: for example, the driving time cost and fuel cost calculated based on the road network, as well as the parking fee cost, i.e., the grid parking fee data obtained in step 102; these cost items need to be uniformly converted into monetary equivalents or time equivalents to form a comparable comprehensive cost indicator.

[0094] See also Figure 4 In some embodiments, the resident travel chain data includes multiple private car travel chains, each of which includes the road section length, the private car free speed, the private car unit mileage fuel cost, the average number of private car passengers, the private car start-up time, the private car transfer factor and the private car additional time cost item. Step 103 may include, but is not limited to, steps 401 to 405.

[0095] Step 401: construct a private car travel time cost item based on the road section length and the free speed of the private car.

[0096] Step 402 : constructing a private car fuel cost item based on the road section length, the private car fuel cost per mileage, the average number of private car passengers, and a preset time value of money coefficient.

[0097] Step 403: construct a private car startup time cost item based on the private car transfer factor and the private car startup time.

[0098] Step 404 : Construct a parking fee cost item based on the grid parking fee and the average number of passengers carried by private cars.

[0099] Step 405 : construct a generalized travel cost expression for a private car based on the private car driving time cost item, the private car fuel cost item, the private car starting time cost item, the private car extra time cost, and the parking fee cost item.

[0100] In step 401 of some embodiments, the segment length refers to the actual length of a segment in the trip chain, in kilometers (km), denoted as The free speed of a private car refers to the average speed that a private car can reach under ideal road conditions, in kilometers per hour (km / h), recorded as The travel time cost item represents the time residents spend traveling on the road section. It can be calculated by dividing the length of the road section by the free speed of private cars. The unit is hour (h), which is expressed as follows:

[0101]

[0102] In step 402 of some embodiments, the fuel cost per mileage of a private car refers to the fuel cost consumed per kilometer traveled by the private car, in units of yuan / kilometer (yuan / km), recorded as The average number of passengers carried by private cars per trip is the average number of passengers carried by private cars per trip, recorded as The time value of money coefficient refers to the coefficient that converts time cost into monetary cost, and its unit is yuan / hour (yuan / h), which is recorded as The fuel cost item can be calculated by multiplying the length of the road section by the fuel cost per unit mileage and then dividing it by the product of the average number of passengers and the time value of money coefficient. The unit is RMB and is expressed as follows:

[0103]

[0104] In step 403 of some embodiments, the private car transfer factor is a binary variable. If the resident uses a private car in the travel chain, the value is 1; otherwise, it is 0, which is recorded as The starting time of a private car refers to the time it takes to start the private car each time, in hours (h), recorded as The startup time cost term can be calculated by multiplying the private car transfer factor by the private car startup time, expressed in hours (h), as follows:

[0105] ×

[0106] In step 404 of some embodiments, the grid parking fee refers to the average parking fee of the destination grid unit of the trip chain, in RMB, recorded as The parking cost item can be calculated by dividing the average parking fee by the average number of private car passengers, expressed in RMB as follows:

[0107]

[0108] In step 405 of some embodiments, a generalized travel cost expression for a private car is constructed based on the private car driving time cost item, the private car fuel cost item, the private car startup time cost item, the private car extra time cost item, and the parking cost item. The private car extra time cost refers to the extra time consumed due to factors such as traffic congestion, and is expressed in hours (h), which is recorded as The generalized travel cost expression for private cars is a weighted summation of the above costs to obtain a comprehensive travel cost value in yuan. The formula is as follows:

[0109] ×

[0110] Through steps 401 to 405, a comprehensive expression for the cost of private car travel can be constructed that considers multiple factors. This expression not only considers traditional travel time and fuel costs, but also incorporates factors such as parking fees, startup time costs, and additional time costs. This makes the calculation of private car travel costs more comprehensive and accurate, and thus more accurately reflects the actual cost of private car travel. This provides more reliable input data for subsequent multivariate utility choice models, ultimately improving the accuracy of travel mode predictions.

[0111] In step 104 of some embodiments, in order to construct a multivariate utility choice model, in addition to the generalized travel cost expression for private cars constructed in step 103, cost expressions for other modes of transportation are also required. These modes of travel include but are not limited to taxis, buses, rail transit, motorcycles, electric vehicles, bicycles, and walking. The generalized travel cost calculation method for each mode of transportation is already relatively mature in the prior art. This solution will not go into too much detail about the specific calculation process. It is only necessary to integrate these cost expressions into the multivariate utility choice model. The cost expressions of each mode can be integrated through a nested multivariate Logit model architecture. The form of the multivariate Logit model is as follows:

[0112]

[0113] in, is the random utility value of traveler i choosing transportation mode j, k represents the number of all possible transportation modes, represents the probability that person i chooses mode j. Below are the generalized travel cost expressions for cycling and walking, respectively. To limit the length of this article, the generalized travel cost expressions for other modes of transportation are omitted.

[0114] The generalized travel cost calculation formula for bicycles is as follows:

[0115] ×

[0116] Where, Indicates the length of the road section (km); Indicates the free speed of the bicycle (km / h); is the bicycle pickup start time (h); is the new bicycle travel factor. If the passenger chooses to travel by bicycle when starting from the starting point or switches to a bicycle from other modes of transportation, the variable value is 1, otherwise it is 0. Indicates the cost per mile of bicycle (yuan / km); represents the time value of money (yuan / h);

[0117] The generalized travel cost calculation formula for walking is as follows:

[0118]

[0119] Where, Indicates the length of the road section (km); Indicates the free walking speed (km / h).

[0120] In step 105 of some embodiments, the study area is first divided into several grid cells according to a grid map. Resident trip chain data is then analyzed, and the number of trips from each grid cell to each other is counted to generate an initial trip distribution matrix. The rows of this matrix represent the grid cells where a trip originates, and the columns represent the grid cells where a row ends. The values ​​of the matrix elements represent the number of trips from the starting grid cell to the ending grid cell. This initial matrix reflects the travel demand between different grid cells.

[0121] See also Figure 5 In some embodiments, step 105 may include, but is not limited to, steps 501 to 502.

[0122] Step 501 : Calculate the trip generation and trip attraction of each grid unit in the grid map based on the grid map and the residents' trip chain data.

[0123] Step 502 : Calculate the travel distribution of each grid unit based on the travel generation volume and travel attraction volume of each grid unit to obtain a travel distribution matrix between the grid units.

[0124] In step 501 of some embodiments, trip generation refers to the total number of trips originating from a particular grid cell, and trip attraction refers to the total number of trips destined for a particular grid cell. These indicators can reflect the transportation demand and supply situation of each grid cell. By analyzing the starting and ending grid cells of each trip chain in the resident trip chain data, the trip generation and trip attraction of each grid cell can be calculated.

[0125] In step 502 of some embodiments, the travel distribution between each grid unit is calculated based on the trip generation and trip attraction of each grid unit calculated in step 601, thereby obtaining a travel distribution matrix between the grid units. The travel distribution matrix is ​​a two-dimensional matrix whose rows and columns represent grid units, respectively, and each element in the matrix represents the travel volume from a starting grid unit to a destination grid unit. The travel distribution can be calculated using a gravity model, which is a spatial interaction model commonly used in transportation planning and geography to predict travel volume, freight volume, population migration, or other types of interaction between two locations.

[0126] Through steps 501 and 502, the trip generation and attraction volume for each grid cell, as well as the trip distribution matrix between grid cells, can be calculated. This information can more comprehensively reflect the traffic and travel characteristics of the target area, providing more detailed data support for subsequent traffic planning and management. For example, traffic demand hotspots can be identified based on trip generation and attraction volume, and the traffic network structure and traffic resource allocation can be optimized based on the trip distribution matrix.

[0127] In step 106 of some embodiments, after obtaining the travel distribution matrix in step 105, step 106 further utilizes the multivariate utility choice model constructed in step 104 to classify each travel path (i.e., travel from one grid cell to another) by transportation mode. Specifically, for each element in the travel distribution matrix (representing a travel path), information such as the path's starting point, end point, and distance is input into the multivariate utility choice model to calculate the probability of selecting different transportation modes. Then, based on these selection probabilities, different transportation modes are assigned to the trip. Ultimately, a refined travel distribution matrix is ​​obtained that not only reflects travel demand across different grid cells but also reflects the proportion of different transportation modes on different travel paths.

[0128] See also Figure 6 In some embodiments, the method provided in the embodiments of the present application may also include but is not limited to steps 601 to 604:

[0129] Step 601 : For each trip data in the trip distribution matrix, the trip data is analyzed to obtain prediction element information of the trip data.

[0130] In step 602 , the prediction factor information is input into the multivariate utility model so that the multivariate utility model calculates the utility value corresponding to each transportation mode and determines the selection probability of each transportation mode according to the multiple utility values.

[0131] Step 603: Determine the travel mode prediction result corresponding to each travel data according to the selection probability of the transportation mode.

[0132] Step 604: Based on the travel mode prediction results corresponding to each travel data, a refined travel distribution matrix considering the choice of transportation mode is obtained.

[0133] In step 601 of some embodiments, each trip data typically contains rich trip information, such as trip origin, trip destination, trip distance, trip time, transit areas, and trip purpose. In this step, key feature information that influences transportation mode selection needs to be extracted from the trip data, such as trip distance, trip time, average speed, whether to transfer, and parking fees in the starting and ending areas, so as to serve as input for the multivariate utility choice model.

[0134] In step 602 of some embodiments, the prediction factor information extracted in step 601 is input into a multivariate utility choice model. The multivariate utility choice model calculates the random utility value corresponding to each mode of transportation based on the generalized travel cost expression for each mode of transportation and the model parameters. The random utility value represents the traveler's preference for each mode of transportation; a higher random utility value indicates a greater tendency for the traveler to choose that mode of transportation. The model then calculates the probability of choosing each mode of transportation based on the random utility value of each mode of transportation.

[0135] In step 603 of some embodiments, the travel mode prediction result corresponding to each travel data is determined based on the selection probability of each transportation mode calculated in step 602. Generally, the transportation mode with the highest selection probability will be considered to be the most likely travel mode for the trip.

[0136] In step 604 of some embodiments, a refined travel distribution matrix that takes into account the choice of transportation mode is obtained based on the travel mode prediction results corresponding to each trip data determined in step 603. The original travel distribution matrix only reflects the travel demand between different grid cells, without distinguishing between different transportation modes. In step 604, based on the transportation mode prediction results of each travel path, the travel volume in the original travel distribution matrix is ​​proportionally distributed to different transportation modes, thereby obtaining a refined travel distribution matrix that takes into account the choice of transportation mode. For example, the travel distribution matrix can be subdivided into a private car travel distribution matrix, a bus travel distribution matrix, etc., each matrix reflecting the travel distribution of the corresponding transportation mode between different grid cells.

[0137] Through steps 601 to 604, the travel distribution matrix is ​​refined and travel demand is divided according to transportation modes, so that the travel demand and flow distribution of different transportation modes can be predicted more accurately, providing more refined and effective data support for transportation planning and management.

[0138] See also Figure 7 In some embodiments, after step 106 , the process may further include, but not be limited to, step 701 .

[0139] Step 701 : Based on the refined travel distribution matrix, the travel volume is redistributed to specific road sections in the traffic network to obtain the predicted traffic flow of each road section.

[0140] In some embodiments, in step 702, based on the refined travel distribution matrix obtained in step 106, the generated travel volume is redistributed to specific road segments in the transportation network to obtain predicted traffic flows for each road segment. The refined travel distribution matrix reflects travel demand between different grid cells and for different transportation modes. By allocating this travel demand to specific transportation road segments, the traffic flow for each road segment can be predicted. Traffic flow allocation can be based on the user optimal allocation principle, assuming that each traveler chooses the route with the lowest time or financial cost. Finally, the traffic flow and traffic congestion status for each road segment in the transportation grid are output.

[0141] See also Figure 8 , Figure 8 The overall technical flow chart of the present invention provided in the embodiment of this application is mainly based on the four-stage model of urban traffic and combines the impact of parking fees to make more refined travel mode predictions. First, parking lot data is extracted from POI data, and resident travel chain data is extracted from mobile phone signaling data. Parking fee data will be used when calculating the travel cost of private cars in combination with travel chain data. Then, travel cost expressions for various modes of transportation are constructed separately, including private cars, taxis, buses, rail transit, motorcycles, electric vehicles, bicycles and walking. Among them, the travel cost of private cars needs to be combined with parking lot data and resident travel chain data to calculate a more accurate parking fee and include it in the generalized travel cost of private cars. Next, a multivariate Logit model is constructed based on the travel costs of all modes of transportation, and the mode division step in the four-stage model of urban traffic is carried out to predict the probability of residents choosing various modes of transportation. According to the process of the four-stage model of urban traffic, traffic generation, traffic distribution, mode division and traffic volume distribution need to be carried out in sequence to finally obtain the predicted traffic flow of each section. This process, through refined calculation of private car travel costs and a classification of transportation modes based on a multivariate logit model, can more accurately predict residents' travel mode choices and ultimately predict traffic flow on each road section, providing more reliable prediction results for urban transportation planning and management.

[0142] The transportation mode prediction method proposed in this application, which takes parking fees into consideration, first obtains parking data and resident travel chain data in the target area, and calculates the parking fee for each grid unit in combination with the grid map, thereby obtaining the spatial distribution characteristics of parking costs accurate to each grid unit. Unlike existing models that generally ignore parking fees, this method fully considers the impact of parking fees on private car travel costs, as well as the differences in parking fees in different areas within the city, such as the difference in parking fees between commercial centers and suburbs. On this basis, this method constructs a generalized travel cost expression for private cars that includes parking fees, and combines it with the existing cost expressions of other travel modes to construct a multivariate utility choice model. The multivariate utility choice model of this method can comprehensively consider various factors that affect travel choices, including travel costs, time efficiency, etc., thereby more accurately reflecting residents' travel decision-making behavior. Then, based on the grid map and residents' travel chain data, a travel distribution matrix between grid cells is generated. The travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area. Finally, the constructed multivariate utility choice model is used to predict the travel mode of the travel distribution matrix, and a refined travel distribution matrix that takes into account the choice of transportation mode is obtained. This allows the prediction of travel distribution to more accurately reflect the travel demand of different transportation modes in different areas. In summary, the method proposed in this application significantly improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost considerations, and refinement of the travel distribution matrix.

[0143] See also Figure 9 The embodiment of the present application further provides a traffic mode prediction device that takes parking fees into consideration, which can implement the above-mentioned traffic mode prediction method that takes parking fees into consideration, including:

[0144] The acquisition module is used to obtain the grid map, parking lot data and residents' travel chain data of the target area;

[0145] A calculation module, for calculating the grid parking fee for each grid cell in the grid map based on parking lot data and resident travel chain data;

[0146] The first building block is used to construct a generalized travel cost expression for private cars based on residents’ travel chain data and grid parking fees;

[0147] The second building module is used to build a multivariate utility choice model based on the generalized travel cost expression of private cars and multiple pre-built other travel cost expressions;

[0148] A generation module is used to generate a travel distribution matrix between grid cells based on the grid map and residents' travel chain data;

[0149] The prediction module is used to predict the transportation mode of the travel distribution matrix based on the multivariate utility choice model, and obtain a refined travel distribution matrix that takes transportation mode selection into consideration.

[0150] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a traffic mode prediction method taking into account parking lot charges as described in any one of the embodiments of the first aspect of the present application.

[0151] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement a traffic mode prediction method taking into account parking lot charges as described in any one of the embodiments of the first aspect of the present application.

[0152] See also Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0153] The processor 1001 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0154] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called by the processor 1001 to execute the traffic mode prediction method considering parking fee in the embodiments of this application.

[0155] Input / output interface 1003, used to implement information input and output;

[0156] Communication interface 1004, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0157] Bus 1005 , which transmits information between various components of the device (e.g., processor 1001 , memory 1002 , input / output interface 1003 , and communication interface 1004 );

[0158] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0159] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned traffic mode prediction method considering parking lot charges.

[0160] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor 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.

[0161] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0162] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0163] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0164] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0165] The terms "first," "second," "third," "fourth," and the like (if any) in the specification of the present application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in orders other than those illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0166] It should be understood that in this application, "at least one (item)" means one or more, and "more" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or plural.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0168] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store programs.

[0171] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A traffic mode prediction method considering parking fees, characterized in that: The method comprises: Obtaining a grid map, parking lot data, and resident travel chain data for a target area; wherein the parking lot data includes parking lot coordinates and parking fees per unit time for multiple parking lots; Calculating a grid parking fee for each grid unit in the grid map based on the parking lot data and the resident travel chain data, including: determining a grid unit time parking fee for each of the grid units according to the parking lot coordinates of the plurality of parking lots and the unit time parking fee; Determine the average dwell time of each grid cell according to the resident travel chain data; Determining the corresponding grid parking fee according to the grid unit time parking fee and the average residence time of each grid unit; Calculating a grid parking fee for each grid cell in the grid map based on the parking lot data and the resident trip chain data; Constructing a generalized travel cost expression for private cars based on the resident travel chain data and the grid parking fee; Constructing a multivariate utility choice model based on the generalized travel cost expression of private cars and a plurality of pre-constructed other travel cost expressions; generating a travel distribution matrix between the grid units according to the grid map and the resident travel chain data; The travel distribution matrix is ​​subjected to a traffic mode prediction based on the multivariate utility choice model to obtain a refined travel distribution matrix that takes traffic mode selection into consideration, including: For each trip data in the trip distribution matrix, the trip data is analyzed to obtain prediction element information of the trip data; Inputting the prediction factor information into the multivariate utility selection model so that the multivariate utility selection model calculates the utility value corresponding to each mode of transportation, and determines the selection probability of each mode of transportation based on the plurality of utility values; Determining a travel mode prediction result corresponding to each of the travel data according to the selection probability of the transportation mode; According to the travel mode prediction result corresponding to each travel data, the refined travel distribution matrix considering the choice of transportation mode is obtained.

2. The method for predicting traffic mode considering parking fees according to claim 1, characterized in that: The determining, based on the parking lot coordinates of the plurality of parking lots and the parking fees per unit time, a grid unit time parking fee of each grid unit includes: Mapping the plurality of parking lot coordinates onto the grid map to determine a plurality of parking lot grid units; Calculating the parking fee per unit time for each parking lot grid unit according to the parking fee per unit time corresponding to each parking lot grid unit; For blank grid cells that are not mapped with the parking lot coordinates, prediction and completion are performed based on the Kriging spatial interpolation method to obtain the grid unit time parking fee of each blank grid.

3. The method for predicting traffic mode considering parking fees according to claim 1, characterized in that: The resident travel chain data includes multiple private car travel chains, each of which includes road segment length, private car free speed, private car unit mileage fuel cost, average number of private car passengers, private car start time, private car transfer factor, and private car additional time cost item. Based on the resident travel chain data and the grid parking fee, a generalized private car travel cost expression is constructed, including: Constructing a private car travel time cost item according to the road section length and the free speed of the private car; Constructing a private car fuel cost item based on the road section length, the private car unit mileage fuel cost, the average number of passengers carried by the private car, and a preset time value of money coefficient; Constructing a private car startup time cost item according to the private car transfer factor and the private car startup time; Constructing a parking fee cost item based on the grid parking fee and the average number of passengers carried by the private car; The generalized travel cost expression of the private car is constructed according to the private car driving time cost item, the private car fuel cost item, the private car starting time cost item, the private car additional time cost and the parking fee cost item.

4. The method for predicting traffic mode considering parking fees according to claim 1, characterized in that: Generating a travel distribution matrix between the grid units according to the grid map and the resident travel chain data includes: Calculating the trip generation and trip attraction of each grid unit in the grid map according to the grid map and the resident trip chain data; The travel distribution of each grid unit is calculated according to the travel generation volume and the travel attraction volume of each grid unit to obtain the travel distribution matrix between the grid units.

5. The method for predicting traffic mode considering parking fees according to claim 4, characterized in that: After performing a transportation mode prediction on the travel distribution matrix according to the multivariate utility choice model to obtain a refined travel distribution matrix that takes transportation mode selection into consideration, the method further includes: Based on the refined travel distribution matrix, the travel volume is redistributed to specific road sections in the traffic network to obtain the predicted traffic flow of each road section.

6. A traffic mode prediction device taking parking fees into consideration, characterized in that: include: An acquisition module, configured to acquire a grid map of a target area, parking lot data, and resident travel chain data; wherein the parking lot data includes parking lot coordinates and parking fees per unit time of multiple parking lots; a calculation module, configured to calculate a grid parking fee for each grid unit in the grid map based on the parking lot data and the resident trip chain data, comprising: determining a grid unit time parking fee for each grid unit based on the parking lot coordinates of the plurality of parking lots and the unit time parking fee; determining an average dwell time for each grid unit based on the resident trip chain data; and determining a corresponding grid parking fee based on the grid unit time parking fee and the average dwell time for each grid unit; A first construction module is configured to construct a generalized travel cost expression for a private car based on the resident travel chain data and the grid parking fee; A second construction module is used to construct a multivariate utility choice model based on the generalized travel cost expression of private cars and a plurality of pre-constructed other travel cost expressions; A generation module, configured to generate a travel distribution matrix between the grid cells based on the grid map and the resident travel chain data; A prediction module is used to perform transportation mode prediction on the travel distribution matrix according to the multivariate utility selection model to obtain a refined travel distribution matrix that takes transportation mode selection into consideration, including: parsing the travel data for each trip in the travel distribution matrix to obtain prediction element information of the travel data; inputting the prediction element information into the multivariate utility selection model so that the multivariate utility selection model calculates the utility value corresponding to each transportation mode and determines the selection probability of each transportation mode based on multiple utility values; determining the travel mode prediction result corresponding to each trip data according to the selection probability of the transportation mode; and obtaining the refined travel distribution matrix that takes transportation mode selection into consideration based on the travel mode prediction result corresponding to each trip data.

7. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for predicting traffic mode taking parking lot charges into consideration as claimed in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that The storage medium stores a program, and the program is executed by a processor to implement the traffic mode prediction method considering parking lot charges as described in any one of claims 1 to 5.

Images