Transportation mode prediction method considering parking lot charging and related equipment thereof

Abstract

The invention provides a traffic mode prediction method considering parking lot charging and related equipment thereof. The method comprises the following steps: acquiring a grid map of a target area, parking lot data and resident trip chain data; calculating the grid parking fee of each grid unit in the grid map based on the parking lot data and the resident trip chain data; based on the resident trip chain data and the grid parking fee, constructing a private car generalized trip cost expression; constructing a multivariate utility selection model according to the private car generalized travel cost expression and a plurality of preset other travel cost expressions; generating a travel distribution matrix among the grid units according to the grid map and the resident travel chain data; and carrying out traffic mode prediction on the travel distribution matrix according to a multivariate utility selection model to obtain a refined travel distribution matrix considering traffic mode selection. According to the invention, by considering the influence of the parking fees on resident travel mode selection, the accuracy of urban traffic travel prediction is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of urban planning, and particularly relate to a traffic mode prediction method considering parking lot charging and related devices. Background Art

[0002] The efficient operation of the urban traffic system has a decisive impact on urban development. Accurately predicting the choice of urban traffic travel modes can optimize the allocation of traffic resources and alleviate urban congestion. The urban traffic travel behavior is affected by multi-dimensional factors, including travel costs, time efficiency, urban spatial structure facilities, etc. How to comprehensively consider the influence of the above multiple factors on residents' travel modes is a difficult problem to solve at present.

[0003] In the related art, parking fees, as an important cost for private car travel, have a significant impact on the choice of travel modes, especially in areas such as the city center where parking spaces are in short supply and the fees are relatively high. However, existing models often simplify the calculation of the travel costs of private cars and do not take parking fees into consideration, which makes the prediction results difficult to accurately reflect the regulatory role of parking fee policies on residents' travel behavior, resulting in low prediction accuracy. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present application provides a traffic mode prediction method considering parking lot charging and related devices, which improves the accuracy of urban traffic travel prediction by considering the influence of parking fees on residents' travel mode choices.

[0005] To achieve the above object, a first aspect of the embodiments of the present application proposes a traffic mode prediction method considering parking lot charging, and the method includes: Obtain the grid map, parking lot data, and residents' travel chain data of the target area; Based on the parking lot data and the residents' travel chain data, calculate the grid parking fee of each grid unit in the grid map; Based on the residents' travel chain data and the grid parking fee, construct a general travel cost expression for private cars; According to the general travel cost expression for private cars and multiple pre-constructed other travel cost expressions, construct a multi-utility selection model; According to the grid map and the residents' travel chain data, generate an OD (Origin-Destination) matrix between the grid units; Perform traffic mode prediction on the OD matrix according to the multi-utility selection model to obtain a refined OD matrix considering traffic mode selection.

[0006] In some embodiments, the parking lot data includes the parking lot coordinates of multiple parking lots and the parking fee per unit time. Based on the parking lot data and the resident travel chain data, calculating the grid parking fee for each grid cell in the grid map includes: Determining the grid parking fee per unit time for each grid cell according to the parking lot coordinates of the multiple parking lots and the parking fee per unit time; Determining the average residence duration of each grid cell according to the resident travel chain data; Determining the corresponding grid parking fee according to the grid parking fee per unit time and the average residence duration of each grid cell.

[0007] In some embodiments, the determining the grid parking fee per unit time for each grid cell according to the parking lot coordinates of the multiple parking lots and the parking fee per unit time includes: Mapping the parking lot coordinates of the multiple parking lots onto the grid map to determine multiple parking lot grid cells; Calculating the grid parking fee per unit time for each parking lot grid cell according to the parking fee per unit time corresponding to each parking lot grid cell; For the blank grid cells without mapped parking lot coordinates, predicting and complementing based on the Kriging spatial interpolation method to obtain the grid parking fee per unit time for each blank grid.

[0008] In some embodiments, the resident travel chain data includes multiple travel chains, and each travel chain includes road segment length, free speed of private cars, fuel cost per unit mileage of private cars, average number of passengers in private cars, starting time of private cars, private car transfer factor, and private car additional time cost item. Based on the resident travel chain data and the grid parking fee, constructing a generalized travel cost expression for private cars includes: Constructing a driving time cost item for private cars according to the road segment length and the free speed of private cars; Constructing a fuel cost item for private cars according to the road segment length, the fuel cost per unit mileage of private cars, the average number of passengers in private cars, and a preset capital time value coefficient; Constructing a starting time cost item for private cars according to the private car transfer factor and the starting time of private cars; Constructing a parking fee cost item according to the grid parking fee and the average number of passengers in private cars; Constructing the generalized travel cost expression for private cars according to the driving time cost item, the fuel cost item, the starting time cost item, the private car additional time cost, and the parking fee cost item.

[0009] In some embodiments, predicting the transportation mode for the trip distribution matrix according to the multi-utility selection model to obtain a refined trip distribution matrix considering transportation mode selection includes: For each trip data in the trip distribution matrix, parsing the trip data to obtain the prediction element information of the trip data; Inputting the prediction element information into the multi-utility selection model, so that the multi-utility selection model calculates the utility value corresponding to each transportation mode, and determines the selection probability of each transportation mode according to multiple utility values; According to the selection probability of the transportation mode, determining the trip mode prediction result corresponding to each trip data; According to the trip mode prediction result corresponding to each trip data, obtaining the refined trip distribution matrix considering transportation mode selection.

[0010] In some embodiments, generating the trip distribution matrix between grid cells according to the grid map and the resident trip chain data includes: According to the grid map and the resident trip chain data, calculating the trip generation volume and trip attraction volume of each grid cell in the grid map; According to the trip generation volume and trip attraction volume of each grid cell, calculating the trip distribution of each grid cell to obtain the trip distribution matrix between the grid cells.

[0011] In some embodiments, after predicting the transportation mode for the trip distribution matrix according to the multi-utility selection model to obtain a refined trip distribution matrix considering transportation mode selection, it further includes: Based on the refined trip distribution matrix, redistributing the trip generation volume to specific sections in the transportation network to obtain the predicted traffic flow of each section.

[0012] In a second aspect, an embodiment of the present application provides a transportation mode prediction device considering parking lot charging, including: An acquisition module, configured to acquire a grid map, parking lot data, and resident trip chain data of a target area; A calculation module, configured to calculate the grid parking fee of each grid cell in the grid map based on the parking lot data and the resident trip chain data; A first construction module, configured to construct a private car generalized trip cost expression based on the resident trip chain data and the grid parking fee; A second construction module, configured to construct a multi-utility selection model according to the private car generalized trip cost expression and multiple pre-constructed other trip cost expressions; A generation module, configured to generate a travel distribution matrix between grid cells according to the grid map and the resident travel chain data; A prediction module, configured to perform traffic mode prediction on the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering traffic mode selection.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the traffic mode prediction method considering parking lot charging according to any one of the embodiments in the first aspect of the present application.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the storage medium stores a program, and when the program is executed by a processor, it implements the traffic mode prediction method considering parking lot charging according to any one of the embodiments in the first aspect of the present application.

[0015] The traffic mode prediction method considering parking lot charging proposed in the embodiment of the present application includes: in response to any node server obtaining a task request, the method includes: obtaining a grid map, parking lot data, and resident travel chain data of a target area; calculating the grid parking fee of each grid cell in the grid map based on the parking lot data and the resident travel chain data; constructing a private car generalized travel cost expression based on the resident travel chain data and the grid parking fee; constructing a multi-utility selection model according to the private car generalized travel cost expression and multiple pre-constructed other travel cost expressions; generating a travel distribution matrix between grid cells according to the grid map and the resident travel chain data; performing traffic mode prediction on the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering traffic mode selection.

[0016] The traffic mode prediction method considering parking lot charging proposed in this application first obtains the parking lot data and residents' travel chain data of the target area, and combines with the grid map to calculate the parking fees of each grid cell, obtaining the spatial distribution characteristics of the parking costs accurate to each grid cell. Different from the existing models that usually ignore the parking fees, this method fully considers the impact of parking fees on the travel costs of private cars and the differences in parking fees in different regions within the city, such as the differences in parking fees between commercial centers and suburbs. On this basis, this method constructs an expression of the generalized travel cost of private cars including parking fees, and combines with the cost expressions of other existing travel modes to construct a multi-utility choice model. The multi-utility choice model of this method can comprehensively consider various factors affecting travel choices, including travel costs, time efficiency, etc., thus more accurately reflecting the travel decision-making behavior of residents. Then, according to the grid map and residents' travel chain data, a travel distribution matrix between grid cells is generated, and the travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area; finally, the constructed multi-utility choice model is used to predict the traffic mode of the travel distribution matrix, obtaining a refined travel distribution matrix considering traffic mode selection, which enables the prediction of travel distribution to more accurately reflect the travel demands of different traffic modes in different regions. In summary, the method proposed in this application significantly improves the accuracy of urban traffic mode prediction through refined parking cost calculation, comprehensive consideration of travel costs, and refinement of the travel distribution matrix.

[0017] Other features and advantages of this application will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing this application. The objectives and other advantages of this application can be achieved and obtained through the structures specifically pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by an embodiment of this application; Figure 2 is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of this application; Figure 3 is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of this application; Figure 4 is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of this application; Figure 5 is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of this application; Figure 6It is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of the present application; Figure 7 It is a schematic flowchart of a traffic mode prediction method considering parking lot charging provided by another embodiment of the present application; Figure 8 It is a schematic overall flowchart of a traffic mode prediction method considering parking lot charging provided by an embodiment of the present application; Figure 9 It is a schematic diagram of a traffic mode prediction device considering parking lot charging provided by an embodiment of the present application; Figure 10 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0019] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] It should be noted that although functional module division is performed in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different module division in the device or a different order in the flowchart. Terms such as "first" and "second" in the specification, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0022] The efficient operation of the urban traffic system has a decisive impact on urban development. Among them, accurately predicting the travel mode selection of residents is crucial for optimizing traffic resource allocation, alleviating traffic congestion, and formulating reasonable traffic policies. However, urban traffic travel behavior is comprehensively affected by multiple factors, including but not limited to travel costs, time efficiency, urban spatial structure, traffic infrastructure, etc. How to comprehensively and fully consider the impact of these factors on residents' travel mode selection and build an accurate prediction model is a major challenge faced by the current traffic field.

[0023] Parking fees, as an important expense for private car travel, especially in areas such as the city center where parking space resources are scarce and the fees are relatively high, have a significant regulatory effect on residents' travel mode choices. However, in order to simplify calculations, many existing models often ignore this factor of parking fees or only use a rough average parking fee for estimation, which makes it difficult for the models to accurately reflect the actual impact of parking fee policies on residents' travel behaviors, thereby reducing the accuracy and reliability of the prediction results.

[0024] Based on this, the embodiments of the present application provide a traffic mode prediction method considering parking lot fees and its related devices, which improve the accuracy of urban traffic travel prediction by considering the impact of parking fees on residents' travel mode choices.

[0025] The traffic mode prediction method considering parking lot fees and its related devices provided by the embodiments of the present application will be specifically described through the following embodiments. First, the traffic mode prediction method considering parking lot fees in the embodiments of the present application will be described.

[0026] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. 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, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0027] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing that needs to be 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. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0028] Figure 1It is an optional flowchart of the traffic mode prediction method considering parking lot charging provided by an embodiment of the present application. Figure 1 The method in

[0029] Step 101: Obtain the grid map, parking lot data, and resident travel chain data of the target area.

[0030] Step 102: Calculate the grid parking fee for each grid cell in the grid map based on the parking lot data and the resident travel chain data.

[0031] Step 103: Construct a private car generalized travel cost expression based on the resident travel chain data and the grid parking fee.

[0032] Step 104: Construct a multi - utility selection model according to the private car generalized travel cost expression and multiple pre - constructed other travel cost expressions.

[0033] Step 105: Generate an origin - destination matrix of trips between grid cells according to the grid map and the resident travel chain data.

[0034] Step 106: Perform traffic mode prediction on the origin - destination matrix according to the multi - utility selection model to obtain a refined origin - destination matrix considering traffic mode selection.

[0035] Steps 101 to 106 illustrated in the embodiments of the present application first obtain the parking lot data and resident travel chain data of the target area, and calculate the parking fees of each grid cell in combination with the grid map, obtaining the spatial distribution characteristics of the parking costs accurate to each grid cell. Different from existing models that usually ignore parking fees, this method fully considers the impact of parking fees on the travel costs of private cars and the differences in parking fees in different areas within the city, such as the parking fee differences between commercial centers and suburbs. On this basis, this method constructs an expression for the generalized travel cost of private cars including parking fees, and combines it with the cost expressions of other existing travel modes to construct a multi-utility choice model. The multi-utility choice model of this method can comprehensively consider various factors affecting travel choices, including travel costs, time efficiency, etc., thus more accurately reflecting the travel decision-making behavior of residents. Then, according to the grid map and resident travel chain data, a travel distribution matrix between grid cells is generated, and the travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area; finally, the constructed multi-utility choice model is used to predict the traffic mode of the travel distribution matrix, obtaining a refined travel distribution matrix considering traffic mode selection, which enables the prediction of travel distribution to more accurately reflect the travel demands of different traffic modes in different areas. In summary, the method proposed in the present application significantly improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost consideration, and refinement of the travel distribution matrix.

[0036] In step 101 of some embodiments, three types of key data need to be obtained: the grid map of the target area, parking lot data, and resident travel chain data. First, obtain the grid map of the target area. This map divides the target area into several regular grid cells, and each grid cell has a unique identifier and geographical coordinate information. Second, obtain parking lot data, which can be extracted from POI (Point of Interest) data. POI data refers to all spatial geographical entities abstracted as point features, especially geographical features closely related to people's lives, such as restaurants, parking lots, stations, hospitals, etc. POI data usually includes information such as location coordinates (latitude and longitude), name, address, category, etc. In this embodiment, the parking lot POI data contains key information such as the geographical location, name, and parking fee per unit time of the parking lot. Finally, obtain resident travel chain data. 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, a series of control instructions will be generated, and the data fields of these instructions include various information such as time, location, and number. In the present invention, mobile phone signaling data is mainly used to obtain traffic travel chain data (starting point, staying point, ending point) of population flow within a city, and the specific fields include starting grid, staying point trajectory, ending grid, date, and population flow. Each travel chain records a resident's complete travel trajectory, including information such as travel starting point, ending point, passing locations, travel time, and transportation mode used. These data will be used for subsequent parking fee calculation, travel cost construction, and transportation mode prediction.

[0037] In step 102 of some embodiments, specifically, for the parking lots within each grid cell, first calculate the basic rate according to its charging standard (such as charging by the hour or by the time), and then calculate the expected parking fee in combination with the average staying duration of this grid extracted from the resident travel chain data. For grid cells without parking lot data, spatial interpolation methods can be used to complete the data based on adjacent grid data to ensure the continuity of parking fee data in space. This step converts the parking lot charging information of discrete grid cells into parking lot grid fees covering the whole city.

[0038] Please refer to Figure 2 , in some embodiments, step 102 may include, but is not limited to, steps 201 to 203.

[0039] Step 201, determine the grid unit time parking fee of each grid cell according to the parking lot coordinates and parking fee per unit time of multiple parking lots.

[0040] Step 202, determine the average staying duration of each grid cell according to the resident travel chain data.

[0041] Step 203: Determine the corresponding grid parking fee according to the grid unit time parking fee and the average residence duration of each grid unit.

[0042] In step 201 of some embodiments, each parking lot has its corresponding coordinate position and unit time parking fee. For the grid units containing parking lots, the unit time parking fee can be calculated based on the unit time parking fees of all parking lots within the grid unit, such as taking the average value or weighted average. For the grid units without parking lots, the corresponding unit time parking fee can be obtained through interpolation.

[0043] Please refer to Figure 3 , in some embodiments, step 201 may include, but is not limited to, steps 301 to 303.

[0044] Step 301: Map the coordinates of multiple parking lots onto the grid map to determine multiple parking lot grid units.

[0045] Step 302: Calculate the grid unit time parking fee of each parking lot grid unit according to the unit time parking fee corresponding to each parking lot grid unit.

[0046] Step 303: For the blank grid units without mapped parking lot coordinates, perform prediction and completion based on the Kriging spatial interpolation method to obtain the grid unit time parking fee of each blank grid.

[0047] In step 301 of some embodiments, each parking lot has its corresponding longitude and latitude 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.

[0048] In step 302 of some embodiments, a parking lot grid unit may contain multiple parking lots, and the unit time parking fees of each parking lot may be different. To determine the unit time parking fee of each parking lot grid unit, various methods can be adopted, such as taking the average value, weighted average or other statistical methods.

[0049] In step 303 of some embodiments, since not all grid units contain parking lots, there are some blank grid units not covered by parking lot data. To obtain the unit time parking fee of these blank grid units, the Kriging spatial interpolation method can be used for prediction. The Kriging interpolation method is a spatial interpolation method based on statistics. It uses the data of known observation points and estimates the values of unknown points through spatial correlation analysis.

[0050] Through steps 301 to 303, the parking fee per unit time of each grid cell in the target area can be determined, including grid cells containing parking lots and blank grid cells without parking lots. This method can effectively utilize the existing parking lot data and reasonably estimate the uncovered areas through spatial interpolation methods, so as to obtain more comprehensive and refined spatial distribution data of parking fees. At the same time, it solves the problem that the parking fees cannot be calculated in some areas due to the lack of parking lot POI data, making the calculation of parking fees more complete and accurate.

[0051] In step 202 of some embodiments, the average residence duration of each grid cell is determined according to the resident travel chain data. The resident travel chain data records the residence time of residents at different locations. By analyzing the residence time of residents in each grid cell in the travel chain data, the average residence duration of residents in each grid cell can be calculated. For grid cells without residence duration data, the Kriging interpolation method can also be used for prediction and supplementation.

[0052] In step 203 of some embodiments, according to the parking fee per unit time of each grid cell determined in step 201 and the average residence duration of each grid cell determined in step 202, the parking fee of each grid cell is calculated. Specifically, multiplying the parking fee per unit time of each grid cell by the average residence duration of the grid cell can obtain the parking fee of the grid cell.

[0053] Through steps 201 to 203, this embodiment combines the parking lot data and the resident travel chain data, so as to more finely depict the parking costs in different regions, thereby improving the accuracy of calculating the travel costs of private cars, and further improving the accuracy of the final travel mode prediction.

[0054] In step 103 of some embodiments, the constructed general travel cost expression of private cars needs to integrate multiple cost elements: such as the driving time cost, fuel cost, and parking fee cost calculated based on the road network, that is, the grid parking fee data obtained in step 102; these cost items need to be uniformly converted into currency equivalent or time equivalent to form a comparable comprehensive cost index.

[0055] Please refer to Figure 4 , in some embodiments, the resident travel chain data includes multiple private car travel chains, and each private car travel chain includes road segment length, private car free speed, private car fuel cost per unit mileage, average number of passengers in the private car, private car start time, private car transfer factor, and private car additional time cost item. Step 103 may include, but is not limited to, steps 401 to 405.

[0056] Step 401, construct a private car driving time cost item according to the road segment length and the private car free speed.

[0057] Step 402: Construct a private car fuel cost item based on the road section length, the fuel cost per unit mileage of the private car, the average number of passengers in the private car, and a preset capital time value coefficient.

[0058] Step 403: Construct a private car starting time cost item based on the private car transfer factor and the private car starting time.

[0059] Step 404: Construct a parking fee cost item based on the grid parking fee and the average number of passengers in the private car.

[0060] Step 405: Construct a private car generalized travel cost expression based on the private car travel 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.

[0061] In step 401 of some embodiments, the road section length refers to the actual length of a certain road section in the travel chain, with the unit of kilometer (km), denoted as . The free speed of the private car refers to the average driving speed that the private car can reach under ideal road conditions, with the unit of kilometer per hour (km / h), denoted as . The travel time cost item represents the time spent by residents on driving on this road section, which can be calculated by dividing the road section length by the free speed of the private car, with the unit of hour (h), and is expressed as follows:

[0062] In step 402 of some embodiments, the fuel cost per unit mileage of the private car refers to the fuel cost consumed by the private car per kilometer traveled, with the unit of yuan per kilometer (yuan / km), denoted as . The average number of passengers in the private car refers to the average number of passengers carried by the private car each time, denoted as . The capital time value coefficient refers to the coefficient for converting time cost into monetary cost, with the unit of yuan per hour (yuan / h), denoted as . The fuel cost item can be calculated by multiplying the road section length by the fuel cost per unit mileage and then dividing by the product of the average number of passengers and the capital time value coefficient, with the unit of yuan, and is expressed as follows:

[0063] In step 403 of some embodiments, the private car transfer factor is a binary variable. If a resident uses a private car in this travel chain, the value is 1; otherwise, it is 0, denoted as . The private car starting time refers to the time spent on starting the private car each time, with the unit of hour (h), denoted as The start-up time cost item can be calculated by multiplying the private car transfer factor by the private car start-up time, in hours (h), as follows: ×

[0064] In step 404 of some embodiments, the grid parking fee refers to the average parking fee of the destination grid unit of the travel 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 yuan as follows:

[0065] In step 405 of some embodiments, a generalized travel cost expression of 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, and the parking cost item. The private car extra time cost refers to the extra time consumption caused by factors such as traffic congestion, in hours (h), recorded as The generalized travel cost expression of private cars is the weighted sum of the above costs to obtain a comprehensive travel cost value in yuan. The formula is as follows: ×

[0066] Through step 401 to step 405, a generalized travel cost expression of a private car that comprehensively considers multiple factors can be constructed. This expression not only considers the traditional travel time cost and fuel cost, but also introduces factors such as parking fees, start-up time cost and additional time cost, making the calculation of the travel cost of a private car more comprehensive and accurate, thereby being able to more accurately reflect the actual cost of private car travel, providing more reliable input data for the subsequent multivariate utility selection model, and ultimately improving the accuracy of travel mode prediction.

[0067] 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 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:

[0068] in, is the random utility value for traveler i to choose transportation mode j, and k represents the number of all possible transportation modes. represents the probability that i chooses transportation mode j. The following are the generalized travel cost expressions for bicycles and walking respectively. For the sake of controlling the length, the generalized travel expressions for other transportation modes are omitted.

[0069] The calculation formula for the generalized travel cost of a bicycle is as follows: ×

[0070] In the formula, represents the length of the road section (km); represents the free speed of the bicycle (km / h); is the pick-up and start-up time of the bicycle (h); is the new bicycle travel factor. If the passenger chooses to travel by bicycle when starting from the origin or transfers to a bicycle from other transportation modes, the variable value is 1, otherwise it is 0. represents the cost per kilometer of the bicycle (yuan / km); represents the time value of money (yuan / h); The calculation formula for the generalized travel cost of walking is as follows:

[0071] In the formula, represents the length of the road section (km); represents the free speed of walking (km / h).

[0072] In step 105 of some embodiments, first, the research area is divided into several grid cells according to the grid map. Then, analyze the resident travel chain data, count the number of trips from each grid cell to other grid cells, and generate an initial travel distribution matrix. The rows of this matrix represent the origin grid cells of the trips, the columns represent the destination grid cells of the trips, and the values of the matrix elements represent the travel volume from the origin grid cell to the destination grid cell. This initial matrix reflects the travel demand between different grid cells.

[0073] Please refer to Figure 5 , in some embodiments, step 105 may include, but is not limited to, steps 501 to 502.

[0074] Step 501, calculate the trip generation volume and trip attraction volume of each grid cell in the grid map according to the grid map and the resident travel chain data.

[0075] Step 502: Calculate the trip distribution of each grid cell based on the trip generation volume and trip attraction volume of each grid cell, and obtain the trip distribution matrix between grid cells.

[0076] In step 501 of some embodiments, the trip generation volume refers to the total number of trips starting from a certain grid cell, and the trip attraction volume refers to the total number of trips with a certain grid cell as the destination. These indicators can reflect the traffic travel 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 volume and trip attraction volume of each grid cell can be counted.

[0077] In step 502 of some embodiments, based on the trip generation volume and trip attraction volume of each grid cell calculated in step 601, calculate the trip distribution between each grid cell, and obtain the trip distribution matrix between grid cells. The trip distribution matrix is a two-dimensional matrix, whose rows and columns respectively represent grid cells, and each element in the matrix represents the trip volume from a certain starting grid cell to a certain ending grid cell. The calculation method of trip distribution can adopt the gravity model. The gravity model is a commonly used spatial interaction model in traffic planning and geography, and is used to predict the trip volume, freight volume, population migration volume or other types of interaction volume between two locations.

[0078] Through step 501 and step 502, the trip generation volume, trip attraction volume of each grid cell and the trip distribution matrix between grid cells can be calculated. These information can more comprehensively reflect the traffic travel characteristics of the target area, and provide more detailed data support for subsequent traffic planning and management. For example, traffic demand hot spots can be identified based on the trip generation volume and trip attraction volume, and the traffic network structure and traffic resource allocation can be optimized based on the trip distribution matrix.

[0079] In step 106 of some embodiments, after obtaining the trip distribution matrix in step 105, step 106 further uses the multi-utility selection model constructed in step 104 to perform traffic mode division for each trip path (i.e., the trip from one grid cell to another grid cell). Specifically, for each element in the trip distribution matrix (representing a trip path), input the information such as the starting point, ending point, and distance of this path into the multi-utility selection model, and calculate the selection probabilities of different traffic modes. Then, based on these selection probabilities, allocate different traffic modes for this trip. Finally, a refined trip distribution matrix is obtained, which not only reflects the trip demand between different grid cells, but also reflects the proportion of different traffic modes on different trip paths.

[0080] Please refer to Figure 6, in some embodiments, the method provided by the embodiments of the present application may further include but are not limited to steps 601 to 604: Step 601, for each travel data in the travel distribution matrix, parse the travel data to obtain the prediction element information of the travel data.

[0081] Step 602, input the prediction element information into the multi-utility model, so that the multi-utility model calculates the utility value corresponding to each transportation mode, and determines the selection probability of each transportation mode according to multiple utility values.

[0082] Step 603, determine the travel mode prediction result corresponding to each travel data according to the selection probability of the transportation mode.

[0083] Step 604, obtain a refined travel distribution matrix considering the selection of transportation modes according to the travel mode prediction result corresponding to each travel data.

[0084] In step 601 of some embodiments, each travel data usually contains rich travel information, such as the travel origin, travel destination, travel distance, travel time, passing area, travel purpose, etc. In this step, it is necessary to extract the key feature information that affects the selection of transportation modes from the travel data, such as travel distance, travel time, average speed, whether to transfer, parking fees in the areas where the origin and destination are located, etc., so as to be used as the input of the multi-utility selection model.

[0085] In step 602 of some embodiments, input the prediction element information extracted in step 601 into the multi-utility selection model. The multi-utility selection model will calculate the random utility value corresponding to each transportation mode according to the generalized travel cost expression and model parameters of each transportation mode. The random utility value represents the preference degree of the traveler for each transportation mode. The higher the random utility value, the more inclined the traveler is to choose this transportation mode. Then, the model will calculate the selection probability of each transportation mode according to the random utility values of each transportation mode.

[0086] In step 603 of some embodiments, according to the selection probability of each transportation mode calculated in step 602, determine the travel mode prediction result corresponding to each travel data. Usually, the transportation mode with the highest selection probability will be considered the most likely travel mode for this trip.

[0087] In step 604 of some embodiments, based on the travel mode prediction results corresponding to each travel data determined in step 603, a refined travel distribution matrix considering traffic mode selection is obtained. The original travel distribution matrix only reflects the travel demand between different grid cells without distinguishing different traffic modes. In step 604, according to the traffic mode prediction results of each travel path, the travel volume in the original travel distribution matrix is proportionally allocated to different traffic modes, thereby obtaining a refined travel distribution matrix considering traffic mode selection. For example, the travel distribution matrix can be subdivided into a private car travel distribution matrix, a bus travel distribution matrix, etc., and each matrix reflects the travel distribution of the corresponding traffic mode between different grid cells.

[0088] Through steps 601 to 604, the refinement of the travel distribution matrix is achieved, and the travel demand is divided according to traffic modes, so that the travel demand and traffic flow distribution of different traffic modes can be predicted more accurately, providing more refined and effective data support for traffic planning and management.

[0089] Please refer to Figure 7 , in some embodiments, after step 106, it may further include, but is not limited to, step 701.

[0090] Step 701, based on the refined travel distribution matrix, reallocate the trip generation volume to specific sections in the traffic network to obtain the predicted traffic flow of each section.

[0091] In step 702 of some embodiments, based on the refined travel distribution matrix obtained in step 106, the trip generation volume is reallocated to specific sections in the traffic network to obtain the predicted traffic flow of each section. The refined travel distribution matrix reflects the travel demand between different grid cells and different traffic modes. By allocating these travel demands to specific traffic sections, the traffic flow of each section can be predicted. Among them, the traffic flow allocation can be based on the user-optimal allocation principle, that is, assuming that each traveler chooses the path with the lowest time or money cost, and finally outputs the traffic flow and traffic congestion conditions of each section in the traffic grid.

[0092] Please refer to Figure 8 , Figure 8This is the overall technical flow chart of the present invention provided by the embodiments of this application. This process is mainly based on the four-stage urban traffic model and combines the impact of parking fees for more refined travel mode prediction. First, parking lot data is extracted from POI data, and resident travel chain data is extracted from mobile phone signaling data. Parking fee data is used when calculating the travel cost of private cars in combination with the travel chain data. Then, travel cost expressions for various transportation modes are constructed respectively, including private cars, taxis, buses, rail transit, motorcycles, electric vehicles, bicycles, and walking. Among them, for the travel cost of private cars, parking lot data and resident travel chain data are combined to calculate a more accurate parking fee, which is incorporated into the generalized travel cost of private cars. Next, a multinomial Logit model is constructed based on the travel costs of all transportation modes to perform the transportation mode split step in the four-stage urban traffic model, predicting the probabilities of residents choosing various transportation modes. According to the process of the four-stage urban traffic model, traffic generation, traffic distribution, transportation mode split, and traffic volume allocation need to be carried out in sequence, and finally the predicted traffic flow of each road section is obtained. This process can more accurately predict residents' travel mode choices and finally predict the traffic flow of each road section through refined calculation of private car travel costs and transportation mode split based on the multinomial Logit model, providing more reliable prediction results for urban traffic planning and management.

[0093] The transportation mode prediction method considering parking lot charging proposed in this application first obtains the parking lot data and resident travel chain data of the target area, and combines the grid map to calculate the parking fee of each grid cell, obtaining the spatial distribution characteristics of the parking cost accurate to each grid cell. Different from existing models that usually ignore parking fees, this method fully considers the impact of parking fees on the travel cost of private cars and the differences in parking fees in different regions within the city, such as the parking fee differences between commercial centers and suburbs. On this basis, this method constructs a generalized travel cost expression for private cars including parking fees, and combines the existing cost expressions of other travel modes to construct a multinomial utility selection model. The multinomial utility selection model of this method can comprehensively consider various factors affecting travel choices, including travel cost, time efficiency, etc., thus more accurately reflecting residents' travel decision-making behaviors. Then, according to the grid map and resident travel chain data, a travel distribution matrix between grid cells is generated, and the travel distribution matrix can more comprehensively reflect the traffic travel characteristics of the target area; finally, the constructed multinomial utility selection model is used to predict the transportation mode of the travel distribution matrix, obtaining a refined travel distribution matrix considering transportation mode selection, which enables the prediction of travel distribution to more accurately reflect the travel demands of different transportation modes in different regions. In summary, the method proposed in this application significantly improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive consideration of travel costs, and refinement of the travel distribution matrix.

[0094] Please refer to Figure 9 , an embodiment of the present application further provides a traffic mode prediction device considering parking lot charging, which can implement the traffic mode prediction method considering parking lot charging as described above, including: An acquisition module, configured to acquire a grid map of a target area, parking lot data, and resident travel chain data; A calculation module, configured to calculate the grid parking fee of each grid unit in the grid map based on the parking lot data and the resident travel chain data; A first construction module, configured to construct a private car generalized travel cost expression based on the resident travel chain data and the grid parking fee; A second construction module, configured to construct a multi-utility selection model according to the private car generalized travel cost expression and multiple pre-constructed other travel cost expressions; A generation module, configured to generate a travel distribution matrix between grid units according to the grid map and the resident travel chain data; A prediction module, configured to perform traffic mode prediction on the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering traffic mode selection.

[0095] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the traffic mode prediction method considering parking lot charging according to any one of the embodiments in the first aspect of the present application.

[0096] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, the storage medium stores a program, and when the program is executed by a processor, it implements the traffic mode prediction method considering parking lot charging according to any one of the embodiments in the first aspect of the present application.

[0097] Please refer to Figure 10 , Figure 10 schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes: A processor 1001, which can be implemented in a general-purpose CPU (Central Processing Unit, central processor), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., and is configured to execute relevant programs to implement the technical solutions provided by the embodiments of the present application; 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), etc. The memory 1002 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1002 and are called by the processor 1001 to execute the traffic mode prediction method considering parking lot charging in the embodiments of this application; The input / output interface 1003 is used to implement information input and output; The communication interface 1004 is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); The bus 1005 transmits information between various components of the device (such as the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004); Among them, the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004 are communicatively connected to each other inside the device through the bus 1005.

[0098] The embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned traffic mode prediction method considering parking lot charging.

[0099] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] The embodiments described in the embodiments of this application are for more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0101] Those skilled in the art can 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 those shown, or combine certain steps, or different steps.

[0102] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0104] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0105] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (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 multiple.

[0106] In several embodiments provided by the present 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 illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0107] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0109] 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, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. And the aforementioned storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs.

[0110] The preferred embodiments of the embodiments of the present application have been described above with reference to the drawings, but this does not limit the scope of the rights of the embodiments of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the rights of the embodiments of the present application.

Claims

1. A traffic mode prediction method considering parking lot charging, characterized in that The method includes: Obtaining a grid map of the target area, parking lot data, and resident travel chain data; Calculating the grid parking fee for each grid cell in the grid map based on the parking lot data and the 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 multi-utility choice model according to the generalized travel cost expression for private cars and multiple pre-constructed other travel cost expressions; Generating a travel distribution matrix between the grid cells based on the grid map and the resident travel chain data; Performing traffic mode prediction on the travel distribution matrix according to the multi-utility choice model to obtain a refined travel distribution matrix considering traffic mode selection.

2. The traffic mode prediction method considering parking lot charging according to claim 1, wherein, The parking lot data includes the parking lot coordinates of multiple parking lots and the parking fee per unit time. The calculating the grid parking fee for each grid cell in the grid map based on the parking lot data and the resident travel chain data includes: Determining the grid parking fee per unit time for each grid cell according to the parking lot coordinates of the multiple parking lots and the parking fee per unit time; Determining the average residence duration of each grid cell according to the resident travel chain data; Determining the corresponding grid parking fee according to the grid parking fee per unit time and the average residence duration of each grid cell.

3. The traffic mode prediction method considering parking lot charging according to claim 2, wherein, The determining the grid parking fee per unit time for each grid cell according to the parking lot coordinates of the multiple parking lots and the parking fee per unit time includes: Mapping the parking lot coordinates of the multiple parking lots onto the grid map to determine multiple parking lot grid cells; Calculating the grid parking fee per unit time for each parking lot grid cell according to the parking fee per unit time corresponding to each parking lot grid cell; For the blank grid cells without mapped parking lot coordinates, predicting and complementing based on the Kriging spatial interpolation method to obtain the grid parking fee per unit time for each blank grid.

4. The traffic mode prediction method considering parking lot charging according to claim 1, wherein The resident travel chain data includes multiple private car travel chains. Each private car travel chain includes the road segment length, the free speed of the private car, the fuel cost per unit mileage of the private car, the average number of passengers in the private car, the starting time of the private car, the transfer factor of the private car, and the additional time cost item of the private car. The constructing a generalized travel cost expression for private cars based on the resident travel chain data and the grid parking fee includes: Constructing a driving time cost item according to the road segment length and the free speed of the private car; Constructing a fuel cost item for the private car according to the road segment length, the fuel cost per unit mileage of the private car, the average number of passengers in the private car, and a preset capital time value coefficient; Constructing a starting time cost item for the private car according to the transfer factor of the private car and the starting time of the private car; Constructing a parking fee cost item according to the grid parking fee and the average number of passengers in the private car; Construct the generalized travel cost expression of the private car according to the private car travel time cost item, the private car fuel cost item, the private car start-up time cost item, the private car extra time cost, and the parking fee cost item.

5. The traffic mode prediction method considering parking lot charging according to claim 1, characterized in that, Predict the travel mode of the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering travel mode selection, including: For each travel data in the travel distribution matrix, analyze the travel data to obtain the predicted element information of the travel data; Input the predicted element information into the multi-utility selection model, so that the multi-utility selection model calculates the utility value corresponding to each travel mode, and determines the selection probability of each travel mode according to multiple utility values; Determine the travel mode prediction result corresponding to each travel data according to the selection probability of the travel mode; Obtain the refined travel distribution matrix considering travel mode selection according to the travel mode prediction result corresponding to each travel data.

6. The traffic mode prediction method considering parking lot charging according to claim 1, characterized in that, Generate the travel distribution matrix between grid cells according to the grid map and the resident travel chain data, including: Calculate the travel generation volume and travel attraction volume of each grid cell in the grid map according to the grid map and the resident travel chain data; Calculate the travel distribution of each grid cell according to the travel generation volume and travel attraction volume of each grid cell, and obtain the travel distribution matrix between grid cells.

7. The traffic mode prediction method considering parking lot charging according to claim 6, wherein After predicting the travel mode of the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering travel mode selection, it further includes: Based on the refined travel distribution matrix, reallocate the travel generation volume to specific road sections in the traffic network to obtain the predicted traffic flow of each road section.

8. A traffic mode prediction device considering parking lot charging, characterized in that, Including: An acquisition module for acquiring the grid map, parking lot data, and resident travel chain data of the target area; A calculation module for calculating the grid parking fee of each grid cell in the grid map based on the parking lot data and the resident travel chain data; A first construction module for constructing the generalized travel cost expression of the private car based on the resident travel chain data and the grid parking fee; A second construction module for constructing a multi-utility selection model according to the generalized travel cost expression of the private car and multiple pre-constructed other travel cost expressions; A generation module for generating the travel distribution matrix between grid cells according to the grid map and the resident travel chain data; A prediction module for predicting the travel mode of the travel distribution matrix according to the multi-utility selection model to obtain a refined travel distribution matrix considering travel mode selection.

9. An electronic device, characterized in that, Including: A memory and a processor, the memory stores a computer program, and the processor implements the traffic mode prediction method considering parking lot charging according to any one of claims 1 to 7 when executing the computer program.

10. 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 charging as described in any one of claims 1 to 7.

Images