Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides the traffic mode prediction method considering the parking charge and the related equipment thereof, and the accuracy of urban traffic travel prediction is improved by considering the influence of the parking charge on the resident travel mode selection.
To achieve the above object, a first aspect of an embodiment of the present application provides a traffic pattern prediction method considering charging of a parking lot, the method including:
acquiring a grid map of a target area, parking lot data and resident trip chain data;
Calculating grid parking fees of each grid unit in the grid map based on the parking lot data and resident trip 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-effect selection model according to the private car generalized travel cost expression and a plurality of other pre-constructed travel cost expressions;
Generating a travel distribution matrix among the grid cells according to the grid map and the resident travel chain data;
and predicting the travel distribution matrix in a traffic mode according to the multi-element utility selection model to obtain a refined travel distribution matrix selected by considering the traffic mode.
In some embodiments, the parking lot data includes parking lot coordinates of a plurality of parking lots and parking fees per unit time, and the calculating the grid parking fee of each grid cell in the grid map based on the parking lot data and resident trip chain data includes:
Determining grid unit time parking fees of each grid unit according to parking lot coordinates of the plurality of parking lots and the unit time parking fees;
determining the average residence time of each grid unit according to the resident trip chain data;
And determining the corresponding grid parking fee according to the grid unit time parking fee and the average residence time length of each grid unit.
In some embodiments, the determining the grid time-per-unit parking fee for each of the grid cells according to the parking lot coordinates of the plurality of parking lots and the time-per-unit parking fee includes:
mapping a plurality of parking lot coordinates onto the grid map, and determining a plurality of parking lot grid units;
Calculating 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;
and for the blank grid units which are not mapped with the parking lot coordinates, carrying out prediction completion based on a kriging space interpolation method to obtain the grid unit time parking fee of each blank grid.
In some embodiments, the resident travel chain data includes a plurality of travel chains, each including a road segment length, private car free speed per hour, private car unit mileage fuel charge, private car average passenger capacity, private car start time, private car transfer factor, and private car extra time cost term, the constructing a private car generalized travel cost expression based on the resident travel chain data and the grid parking charge includes:
constructing a private car running time cost item according to the road section length and the private car free speed per hour;
constructing a private car fuel cost item according to the road section length, the private car unit mileage fuel cost, the private car average passenger carrying number and a preset fund time value coefficient;
constructing a private car starting time cost item according to the private car transfer factor and the private car starting time;
constructing a parking fee cost item according to the grid parking fee and the average passenger carrying number of the private car;
and constructing the private car generalized travel cost expression according to the private car travel 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.
In some embodiments, the predicting the travel distribution matrix according to the multiple utility selection model to obtain a refined travel distribution matrix considering the traffic mode selection includes:
Analyzing the travel data aiming at each travel data in the travel distribution matrix to obtain prediction element information of the travel data;
inputting the prediction element information into the multi-element utility selection model so that the multi-element utility selection model calculates utility values corresponding to each traffic mode, and determining the selection probability of each traffic mode according to a plurality of utility values;
determining travel mode prediction results corresponding to the travel data each time according to the selection probability of the traffic modes;
and obtaining the refined travel distribution matrix selected by considering the traffic mode according to the travel mode prediction result corresponding to the travel data each time.
In some embodiments, the generating a travel distribution matrix between the grid cells from the grid map and the resident travel chain data includes:
calculating travel generation amount and travel attraction amount of each grid unit in the grid map according to the grid map and the resident travel chain data;
and calculating the travel distribution of each grid cell according to the travel generation amount and the travel attraction amount of each grid cell to obtain the travel distribution matrix among the grid cells.
In some embodiments, after predicting the travel distribution matrix according to the multiple utility selection model to obtain a refined travel distribution matrix selected in consideration of the traffic mode, the method further includes:
and redistributing the travel generation quantity to specific road sections in a traffic network based on the refined travel distribution matrix to obtain predicted traffic flow of each road section.
In a second aspect, an embodiment of the present application provides a traffic pattern prediction apparatus considering charging of a parking lot, including:
the acquisition module is used for acquiring the grid map of the target area, the parking lot data and resident trip chain data;
the calculation module is used for calculating the grid parking fee of each grid unit in the grid map based on the parking lot data and resident trip chain data;
the first construction module is used for constructing a private car generalized travel cost expression based on the resident travel chain data and the grid parking fee;
The second construction module is used for constructing a multi-effect selection model according to the private car generalized travel cost expression and a plurality of other pre-constructed travel cost expressions;
the generation module is used for generating a travel distribution matrix among the grid cells according to the grid map and the resident travel chain data;
and the prediction module is used for predicting the traffic mode of the travel distribution matrix according to the multi-element utility selection model to obtain a refined travel distribution matrix which is selected by considering the traffic mode.
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 the processor implements the traffic pattern prediction method according to any one of the embodiments of the first aspect of the present application, where the traffic pattern prediction method considers charging of a parking lot when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program that is executed by a processor to implement the traffic pattern prediction method according to any one of the embodiments of the first aspect of the present application, in consideration of charging in a parking lot.
The traffic mode prediction method considering parking lot charging comprises the steps of responding to a task request, obtaining a grid map of a target area, parking lot data and resident travel chain data, calculating grid parking fees of each grid unit 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 fees, constructing a multiple utility selection model according to the private car generalized travel cost expression and a plurality of other pre-constructed travel cost expressions, generating a travel distribution matrix among the grid units according to the grid map and the resident travel chain data, and predicting the traffic mode according to the multiple utility selection model to obtain a refined travel distribution matrix considering traffic mode selection.
According to the traffic mode prediction method considering the parking lot charge, firstly, parking lot data and resident trip chain data of a target area are obtained, and parking fees of each grid cell are calculated by combining a grid map, so that spatial distribution characteristics accurate to parking cost of each grid cell are obtained. Unlike the existing model, which usually ignores the parking fee, the method fully considers the influence of the parking fee on the travel cost of private cars and the difference of the parking fee in different areas inside the city, such as the difference of the parking fee in a business center and a suburban area. On the basis, the method constructs a private car generalized travel cost expression containing parking fees, and combines cost expressions of other existing travel modes to construct a multi-effect selection model, and the multi-effect selection model of the method can comprehensively consider various factors influencing travel selection, including travel cost, time efficiency and the like, so that travel decision behaviors of residents are reflected more accurately. And finally, predicting the travel distribution matrix by using the constructed multi-element utility selection model to obtain a refined travel distribution matrix considering the traffic mode selection, so that the prediction of the obtained travel distribution can reflect the travel demands of different traffic modes in different areas more accurately. In summary, the method provided by the application remarkably improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost consideration and refinement of travel distribution matrix.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
The efficient operation of the urban traffic system has a decisive influence on urban development, wherein the accurate prediction of travel mode selection of residents is important for optimizing traffic resource allocation, relieving traffic jams and making reasonable traffic policies. However, urban traffic travel behavior is affected by a combination of factors including, but not limited to, travel cost, time efficiency, urban space structure, traffic infrastructure, and the like. How to comprehensively and comprehensively consider the influence of the factors on the selection of the resident trip mode and construct an accurate prediction model is a great challenge facing the current traffic field.
The parking fee is an important expense for private car travel, and particularly has a remarkable regulating effect on resident travel mode selection in areas with scarce parking space resources and high charge, such as city centers. However, many existing models often ignore the factor of parking fee for simplifying calculation, or only adopt rough average parking fee for estimation, which makes it difficult for the models to accurately reflect the actual influence of parking charging policy on the traveling behavior of residents, and further reduces the accuracy and reliability of the prediction result.
Based on the above, the embodiment of the application provides a traffic mode prediction method considering parking charge and related equipment thereof, and the accuracy of urban traffic travel prediction is improved by considering the influence of parking charge on resident travel mode selection.
The traffic mode prediction method considering the parking lot charge and the related equipment provided by the embodiment of the application are specifically described through the following embodiment, and the traffic mode prediction method considering the parking lot charge in the embodiment of the application is firstly described.
The application is operational with numerous general purpose or special purpose computer system environments or configurations. Such as a personal computer, a server computer, a hand-held or portable device, a tablet device, a multiprocessor system, a microprocessor-based system, a set top box, a programmable consumer electronics, a network PC, a minicomputer, a mainframe computer, a distributed computing environment that includes any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It should be noted that, in each specific embodiment of the present application, when related processing is required according to user information, user behavior data, user history data, user location information, and other data related to user identity or characteristics, permission or consent of the user is obtained first, and the collection, use, processing, and the like of the data comply with related laws and regulations and standards. In addition, when the embodiment of the application needs to acquire the sensitive personal information of the user, the independent permission or independent consent of the user is acquired through popup or jump to a confirmation page and the like, and after the independent permission or independent consent of the user is definitely acquired, the necessary relevant data of the user for enabling the embodiment of the application to normally operate is acquired.
Fig. 1 is an optional flowchart of a traffic pattern prediction method considering parking lot charging according to an embodiment of the present application, and the method in fig. 1 may include, but is not limited to, steps 101 to 106.
Step 101, acquiring a grid map of a target area, parking lot data and resident trip chain data.
Step 102, calculating the grid parking fee of each grid cell in the grid map based on the parking lot data and the resident trip chain data.
And step 103, constructing a private car generalized travel cost expression based on resident travel chain data and grid parking fees.
And 104, constructing a multi-effect selection model according to the private car generalized travel cost expression and a plurality of other pre-constructed travel cost expressions.
And 105, generating a travel distribution matrix among the grid cells according to the grid map and resident travel chain data.
And 106, predicting the travel distribution matrix in a traffic mode according to the multi-element utility selection model to obtain a refined travel distribution matrix selected by considering the traffic mode.
In steps 101 to 106 shown in the embodiment of the present application, parking fee of each grid cell is calculated by acquiring parking lot data and resident trip chain data of a target area and combining a grid map, so as to obtain a spatial distribution feature of parking cost accurate to each grid cell. Unlike the existing model, which usually ignores the parking fee, the method fully considers the influence of the parking fee on the travel cost of private cars and the difference of the parking fee in different areas inside the city, such as the difference of the parking fee in a business center and a suburban area. On the basis, the method constructs a private car generalized travel cost expression containing parking fees, and combines cost expressions of other existing travel modes to construct a multi-effect selection model, and the multi-effect selection model of the method can comprehensively consider various factors influencing travel selection, including travel cost, time efficiency and the like, so that travel decision behaviors of residents are reflected more accurately. And finally, predicting the travel distribution matrix by using the constructed multi-element utility selection model to obtain a refined travel distribution matrix considering the traffic mode selection, so that the prediction of the obtained travel distribution can reflect the travel demands of different traffic modes in different areas more accurately. In summary, the method provided by the application remarkably improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost consideration and refinement of travel distribution matrix.
In step 101 of some embodiments, three types of key data, namely, a grid map of a target area, parking lot data, and resident trip chain data, need to be acquired. First, a grid map of a target area is obtained, the map dividing the target area into a number of regular grid cells, each grid cell having a unique identifier and geographical coordinate information. Next, parking lot data is acquired, which can be extracted from POI (point of interest) data. POI data refers to all spatial geographical entities abstracted as point elements, especially geographical elements closely related to people's life, such as restaurants, parking lots, stations, hospitals, etc. POI data typically contains information of location coordinates (latitude and longitude), name, address, category, and the like. In this embodiment, the parking lot POI data includes key information such as geographic location, name, and parking fee per unit time of the parking lot. And finally, acquiring resident trip chain data, wherein the mobile phone signaling is communication record data between the mobile phone and the communication base station. When the mobile phone is connected to the mobile communication network, a series of control instructions are generated, and the data fields of the instructions comprise various information such as time, position, number and the like. In the invention, the mobile phone signaling data is mainly used for acquiring traffic chain data (a starting point, a resident point and a terminal point) flowing in a manway in a city, and specific fields comprise a starting point grid, a resident point track, a terminal point grid, a date and population flow. Each travel chain records a complete travel track of residents at one time, and comprises travel starting points, travel ending points, route points, travel time, traffic modes used and the like. These data will be used for subsequent parking fee calculation, trip cost construction and traffic pattern prediction.
In step 102 of some embodiments, specifically, for a parking lot within each grid cell, a base rate is first calculated based on its charging criteria (e.g., hourly or pay-per-view), and then an expected parking fee is calculated in combination with the average residence time of the grid extracted from the resident link data. For the grid unit without parking lot data, the space interpolation method can be adopted to complement the adjacent grid data, so that the continuity of parking fee data in space is ensured. This step converts the parking lot charging information of the discrete grid cells into a parking lot grid charge covering the whole city.
Referring to fig. 2, in some embodiments, step 102 may include, but is not limited to, steps 201 through 203.
Step 201, determining the grid unit time parking fee of each grid unit according to the parking lot coordinates of a plurality of parking lots and the unit time parking fee.
Step 202, determining the average residence time of each grid cell according to resident trip chain data.
Step 203, determining the corresponding grid parking fee according to the grid unit time parking fee and the average residence time duration of each grid unit.
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, the parking cost per unit time can be calculated according to the parking cost per unit time of all parking lots in the grid cell, for example, an average value or a weighted average value is taken, and for a grid cell not containing a parking lot, the corresponding parking cost per unit time can be calculated by interpolation.
Referring to fig. 3, in some embodiments, step 201 may include, but is not limited to, steps 301 through 303.
Step 301, mapping a plurality of parking lot coordinates onto a grid map, and determining a plurality of parking lot grid units.
Step 302, calculating 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.
And 303, for the blank grid cells which are not mapped with the parking lot coordinates, carrying out prediction completion based on a kriging space interpolation method to obtain the grid unit time parking fee of each blank grid.
In step 301 of some embodiments, each parking lot has its corresponding longitude and latitude coordinates, and by matching these coordinates with the grid map, the grid cell to which each parking lot belongs can be determined. These parking lot containing grid cells are referred to as parking lot grid cells.
In step 302 of some embodiments, one parking lot grid cell may contain multiple parking lots, each of which may have a different parking fee per unit time. To determine the parking fee per unit time for each parking lot grid cell, various methods may be employed, such as averaging, weighted averaging, or other statistical methods.
In step 303 of some embodiments, since not all grid cells contain a parking lot, there are some empty grid cells that are not covered by the parking lot data. To obtain the parking fees per unit time for these blank grid cells, predictions may be made using kriging spatial interpolation. The kriging interpolation method is a statistical-based spatial interpolation method, which uses data of known observation points to estimate values of unknown points through spatial correlation analysis.
Through steps 301 to 303, the parking fee per unit time of each grid cell in the target area may be determined, including grid cells including a parking lot and blank grid cells not including a parking lot. The method can effectively utilize the existing parking lot data, reasonably estimate the uncovered area through a spatial interpolation method, thereby obtaining more comprehensive and finer parking fee spatial distribution data, and simultaneously solving the problem that the parking fee cannot be calculated due to the lack of parking lot POI data in a part of areas, so that the calculation of the parking fee is more complete and accurate.
In step 202 of some embodiments, an average residence time length for each grid cell is determined from the resident trip chain data. Resident trip chain data records residence time of residents at different sites. By analyzing the residence time of residents in each grid cell in the travel chain data, the average residence time of the residents in each grid cell can be calculated, and for the grid cells without residence time data, the prediction supplement can be performed by adopting a Kriging interpolation method.
In step 203 of some embodiments, a parking fee per grid cell is calculated based on the parking fee per unit time determined in step 201 and the average residence time per grid cell determined in step 202. Specifically, the parking cost per unit time of each grid cell is multiplied by the average residence time of the grid cell to obtain the parking cost of the grid cell.
Through steps 201 to 203, the parking lot data and resident trip chain data are combined, so that parking costs of different areas can be more finely represented, accuracy of private car trip cost calculation is improved, and accuracy of final trip mode prediction is further improved.
In step 103 of some embodiments, the constructed private car generalized travel cost expression needs to integrate multiple cost elements, such as travel time cost and fuel cost calculated based on road network and parking fee cost, that is, grid parking fee data obtained in step 102, and these cost elements need to be uniformly converted into currency equivalent or time equivalent to form a comparable comprehensive cost index.
Referring to fig. 4, in some embodiments, the resident travel chain data includes a plurality of private car travel chains, each of which includes a road segment length, a private car free speed per hour, a private car unit mileage fuel fee, a private car average passenger count, a private car start time, a private car transfer factor, and a private car additional time cost item, and step 103 may include, but is not limited to, steps 401 to 405.
And step 401, constructing a private car running time cost item according to the road section length and the private car free speed per hour.
And step 402, constructing a private car fuel cost item according to the road section length, the private car unit mileage fuel cost, the average passenger carrying capacity of the private car and the preset fund time value coefficient.
Step 403, constructing a private car starting time cost item according to the private car transfer factor and the private car starting time.
Step 404, constructing a parking fee cost item according to the grid parking fee and the average passenger carrying number of the private car.
And step 405, constructing a private car generalized travel cost expression 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 extra time cost and the parking fee cost item.
In step 401 of some embodiments, the link length is an actual length, in kilometers (km), of a link in the link, noted as. The free speed of the private car refers to the average running speed which the private car can reach under ideal road conditions, and the unit is kilometers per hour (km/h), and is recorded as. The travel time cost term represents the time it takes for a resident to travel on that road segment, which can be calculated by dividing the road segment length by the private car free hour speed in hours (h), expressed as follows:
In step 402 of some embodiments, the private car mileage fuel cost refers to the fuel cost per kilometer traveled by the private car, expressed in units of yuan/kilometer (yuan/km), recorded as. The average passenger carrying number of private cars refers to the average number of passengers carried by the private cars during each trip, and is recorded as. The capital time value coefficient is a coefficient for converting time cost into currency cost, and is expressed as yuan per hour (yuan per hour), and is expressed as. The fuel cost term can be calculated by multiplying the road length by the fuel cost per unit mileage and dividing by the product of the average passenger carrying number and the fund time value coefficient, and the unit is represented as follows:
In step 403 of some embodiments, the private car transfer factor is a binary variable, which is a value of 1 if the resident uses the private car in the travel chain, otherwise 0, noted as. The private car start time is the time taken to start the private car each time, and is expressed as hours (h). The start time cost term can be calculated by multiplying the private car transfer factor by the private car start time in hours (h) as follows:
×
in step 404 of some embodiments, the grid parking fee refers to the average parking fee in units of cells, denoted as elements, at the destination grid cell of the travel chain. The cost term of parking fees can be calculated by dividing the average parking fee by the average passenger number of private cars, and is expressed as follows:
in step 405 of some embodiments, a private car generalized travel cost expression is constructed from the private car travel time cost term, the private car fuel cost term, the private car start time cost term, the private car additional time cost, and the parking fee cost term. The extra time cost of the private car refers to extra time consumption caused by factors such as traffic jam, and the unit is hour (h) and is recorded as. The general trip cost expression of the private car carries out weighted summation on the cost to obtain a comprehensive trip cost value, wherein the unit is a unit, and the formula is as follows:
×
Through steps 401 to 405, a private car generalized travel cost expression comprehensively considering various factors can be constructed. The expression not only considers the traditional driving time cost and fuel cost, but also introduces the factors such as parking cost, starting time cost, additional time cost and the like, so that the calculation of the traveling cost of the private car is more comprehensive and accurate, the actual traveling cost of the private car can be reflected more accurately, more reliable input data is provided for a subsequent multi-element utility selection model, and the traveling mode prediction accuracy is finally improved.
In step 104 of some embodiments, in order to construct the multiple utility selection model, cost expressions of other transportation means are required in addition to the private car generalized travel cost expression constructed in step 103. These travel modes include, but are not limited to, taxis, buses, rail transit, motorcycles, battery cars, bicycles, and walking. The generalized travel cost calculation method of each traffic mode is mature in the prior art, the specific calculation process is not repeated, and only the cost expressions are integrated into the multi-effect selection model. The cost expressions of the modes can be integrated through a nested multi-Logit model architecture, and the multi-Logit model is in the following form:
wherein, theA random utility value for traffic pattern j is selected for traveler i, k representing the number of all possible traffic patterns,The probability of occurrence at i of the selected traffic pattern j is represented. The generalized travel cost expressions of the bicycle and the walking are respectively shown below, and the generalized travel expressions of other traffic modes are omitted for control of the space.
The generalized travel cost calculation formula of the bicycle is as follows:
×
In the formula,Representing the length (km) of the road segment; Indicating the free speed per hour (km/h) of the bicycle; the starting time (h) for taking the bicycle; for the new bicycle trip factor, if the passenger selects a bicycle to trip or changes the bicycle from other traffic modes when starting from the starting point, the variable value is 1, otherwise, the variable value is 0.Representing bicycle unit mileage expense (yuan/km); representing the value of funding time (yuan/h);
The generalized travel cost calculation formula for walking is as follows:
In the formula,Representing the length (km) of the road segment; The free speed of walking (km/h) is indicated.
In step 105 of some embodiments, first, a study area is divided into a number of grid cells according to a grid map. And then, analyzing resident travel chain data, counting travel times from each grid cell to other grid cells, and generating an initial travel distribution matrix. The rows of the matrix represent travel starting grid cells, the columns represent travel ending grid cells, the values of the matrix elements represent the travel amounts from the starting grid cells to the ending grid cells, and this initial matrix reflects travel demands between different grid cells.
Referring to fig. 5, in some embodiments, step 105 may include, but is not limited to, steps 501-502.
Step 501, calculating travel generation amount and travel attraction amount of each grid unit in the grid map according to the grid map and resident travel chain data.
Step 502, calculating travel distribution of each grid cell according to the travel generation amount and the travel attraction amount of each grid cell, and obtaining a travel distribution matrix among the grid cells.
In step 501 of some embodiments, the travel generation amount refers to the total number of travel from a certain grid cell, and the travel attraction amount refers to the total number of travel with a certain grid cell as a destination. These metrics may reflect the travel demand and supply of each grid cell. By analyzing the starting point and the ending point grid cells of each travel chain in resident travel chain data, the travel generation amount and the travel attraction amount of each grid cell can be counted.
In step 502 of some embodiments, according to the travel generation amount and the travel attraction amount of each grid cell calculated in step 601, travel distribution between each grid cell is calculated, and a travel distribution matrix between grid cells is obtained. The travel distribution matrix is a two-dimensional matrix whose rows and columns respectively represent grid cells, each element in the matrix representing the amount of travel from a certain starting grid cell to a certain ending grid cell. The travel distribution calculation method can adopt an attraction Model, wherein the attraction Model (Gravity Model) is a space interaction Model commonly used in traffic planning and geography and is used for predicting travel volume, freight volume, population migration volume or other types of interaction volume between two places.
Through step 501 and step 502, the travel generation amount, travel attraction amount, and travel distribution matrix between grid cells can be calculated for each grid cell. The information can reflect the traffic travel characteristics of the target area more comprehensively, and more detailed data support is provided for subsequent traffic planning and management. For example, traffic demand hot spot areas can be identified according to travel production and travel attraction, and traffic network structures and traffic resource allocation can be optimized according to travel distribution matrixes.
In step 106 of some embodiments, after the travel distribution matrix is obtained in step 105, step 106 further uses the multi-component utility selection model constructed in step 104 to traffic-mode divide each travel path (i.e., travel from one grid cell to another grid cell). Specifically, for each element (representing one travel path) in the travel distribution matrix, information such as the start point, the end point, the distance and the like of the path is input into the multi-effect selection model, and the selection probability of different traffic modes is calculated. And then, according to the selection probabilities, different traffic modes are allocated for the trip. Finally, a refined travel distribution matrix is obtained, and the matrix not only reflects travel demands among different grid units, but also reflects the proportion of different traffic modes on different travel paths.
Referring to fig. 6, in some embodiments, the method provided by the embodiments of the present application may further include, but is not limited to, steps 601 to 604:
And step 601, analyzing the travel data aiming at each travel data in the travel distribution matrix to obtain prediction element information of the travel data.
Step 602, inputting the prediction element information into the multiple utility model, so that the multiple utility model calculates utility values corresponding to each traffic mode, and determining the selection probability of each traffic mode according to the multiple utility values.
And step 603, determining travel mode prediction results corresponding to the travel data of each time according to the selection probability of the traffic modes.
And step 604, obtaining a refined travel distribution matrix selected by considering the traffic mode according to the travel mode prediction result corresponding to each travel data.
In step 601 of some embodiments, each trip data typically contains rich trip information, such as trip start point, trip end point, trip distance, trip time, via area, trip purpose, and the like. In this step, key feature information that affects the traffic mode selection, such as travel distance, travel time, average speed, whether transfer, parking costs of the area where the start point and the end point are located, and the like, need to be extracted from the travel data to be input as a multi-effect selection model.
In step 602 of some embodiments, the predicted element information extracted in step 601 is input into a multi-element utility selection model. The multi-effect selection model calculates a random effect value corresponding to each traffic mode according to the generalized travel cost expression and model parameters of each traffic mode. The random utility value represents the traveler's preference for each mode of transportation, with higher random utility values indicating that the traveler is more inclined to select that mode of transportation. The model then calculates the probability of selection for each mode of transportation based on the random utility value for each mode of transportation.
In step 603 of some embodiments, according to the selection probability of each traffic mode calculated in step 602, a travel mode prediction result corresponding to each travel data is determined, where in general, the traffic mode with the highest selection probability is considered as the most probable travel mode of the trip.
In step 604 of some embodiments, a refined travel distribution matrix selected in consideration of the traffic mode is obtained according to the travel mode prediction result corresponding to each travel data determined in step 603. The original travel distribution matrix only reflects travel demand among different grid cells, and different traffic modes are not distinguished. In step 604, according to the traffic mode prediction result of each travel path, the travel amounts in the original travel distribution matrix are proportionally distributed to different traffic modes, so as to obtain a refined travel distribution matrix selected in consideration of the traffic modes. For example, the travel distribution matrix may be subdivided into a private car travel distribution matrix, a bus travel distribution matrix, and the like, each of which reflects the travel distribution of the corresponding traffic pattern among different grid cells.
Through steps 601 to 604, the refinement of the travel distribution matrix is realized, and travel demands are divided according to traffic modes, so that travel demands and flow distribution of different traffic modes can be predicted more accurately, and finer and more effective data support is provided for traffic planning and management.
Referring to FIG. 7, in some embodiments, after step 106, step 701 may also be included, but is not limited to.
And 701, redistributing the travel generation quantity to specific road sections in the traffic network based on the refined travel distribution matrix to obtain the predicted traffic flow of each road section.
In step 702 of some embodiments, the travel generation amount is redistributed to specific road segments in the traffic network based on the refined travel distribution matrix obtained in step 106, to obtain predicted traffic flow of each road segment. The refined travel distribution matrix reflects travel demands of different traffic modes among different grid units. By assigning these travel demands to specific traffic segments, the traffic flow per segment can be predicted. The traffic flow distribution can be based on the optimal distribution principle of users, namely, each traveler is assumed to select a path with the lowest time or money cost, and finally, the traffic flow and traffic jam condition of each road section in the traffic grid are output.
Referring to fig. 8, fig. 8 is a flowchart of the overall technology of the present application provided by the embodiment of the present application, and the process is mainly based on the urban traffic four-stage model and combines with the parking fee effect to perform finer travel mode prediction. Firstly, parking lot data are extracted from POI data, resident trip chain data are extracted from mobile phone signaling data, and parking fee data are used when private car trip cost is calculated by combining the trip chain data. And then, respectively constructing travel cost expressions of various traffic modes, including private cars, taxis, buses, rail transit, motorcycles, battery cars, bicycles and walking, wherein the travel cost of the private cars is required to be combined with parking lot data and resident travel chain data, so that more accurate parking cost is calculated, and the parking cost is brought into the generalized travel cost of the private cars. And constructing a multi-element Logit model according to the travel cost of all traffic modes, carrying out a traffic mode dividing step in the urban traffic four-stage model, and predicting the probability of residents selecting various traffic modes. According to the flow of the urban traffic four-stage model, traffic generation, traffic distribution, traffic mode division and traffic distribution are needed to be sequentially carried out, and finally the predicted traffic flow of each road section is obtained. The method can more accurately predict travel mode selection of residents through refined private car travel cost calculation and traffic mode division based on a multivariate Logit model, and finally predict traffic flow of each road section, thereby providing more reliable prediction results for urban traffic planning and management.
According to the traffic mode prediction method considering the parking lot charge, firstly, parking lot data and resident trip chain data of a target area are obtained, and parking fees of each grid cell are calculated by combining a grid map, so that spatial distribution characteristics accurate to parking cost of each grid cell are obtained. Unlike the existing model, which usually ignores the parking fee, the method fully considers the influence of the parking fee on the travel cost of private cars and the difference of the parking fee in different areas inside the city, such as the difference of the parking fee in a business center and a suburban area. On the basis, the method constructs a private car generalized travel cost expression containing parking fees, and combines cost expressions of other existing travel modes to construct a multi-effect selection model, and the multi-effect selection model of the method can comprehensively consider various factors influencing travel selection, including travel cost, time efficiency and the like, so that travel decision behaviors of residents are reflected more accurately. And finally, predicting the travel distribution matrix by using the constructed multi-element utility selection model to obtain a refined travel distribution matrix considering the traffic mode selection, so that the prediction of the obtained travel distribution can reflect the travel demands of different traffic modes in different areas more accurately. In summary, the method provided by the application remarkably improves the accuracy of urban traffic travel mode prediction through refined parking cost calculation, comprehensive travel cost consideration and refinement of travel distribution matrix.
Referring to fig. 9, the embodiment of the present application further provides a traffic mode prediction device considering parking lot charges, which can implement the traffic mode prediction method considering parking lot charges, including:
the acquisition module is used for acquiring the grid map of the target area, the parking lot data and resident trip chain data;
the calculation module is used for 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;
The first construction module is used for constructing a private car generalized travel cost expression based on resident travel chain data and grid parking fees;
The second construction module is used for constructing a multi-effect selection model according to the generalized travel cost expression of the private car and a plurality of other travel cost expressions which are pre-constructed;
the generation module is used for generating a travel distribution matrix among the grid cells according to the grid map and resident travel chain data;
And the prediction module is used for predicting the travel distribution matrix in a traffic mode according to the multi-element utility selection model to obtain a refined travel distribution matrix selected by considering the traffic mode.
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 the processor implements the traffic pattern prediction method according to any one of the embodiments of the first aspect of the present application, where the traffic pattern prediction method considers charging of a parking lot when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program that is executed by a processor to implement the traffic pattern prediction method according to any one of the embodiments of the first aspect of the present application, in consideration of charging in a parking lot.
Referring to fig. 10, fig. 10 illustrates a hardware structure of an electronic device according to another embodiment, the electronic device includes:
The processor 1001 may be implemented by using a general-purpose CPU (central processing unit), a microprocessor, an application-specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. to execute related programs to implement the technical solution provided by the embodiments of the present application;
Memory 1002 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). The memory 1002 may store an operating system and other application programs, and when the technical solution provided in the embodiments of the present disclosure is implemented by software or firmware, relevant program codes are stored in the memory 1002, and the processor 1001 invokes a traffic pattern prediction method that performs the embodiment of the present disclosure, considering parking lot charging;
An input/output interface 1003 for implementing information input and output;
the communication interface 1004 is configured to implement communication interaction between the present device and other devices, and may implement communication in a wired manner (e.g. USB, network cable, etc.), or may implement communication in a wireless manner (e.g. mobile network, WIFI, bluetooth, etc.);
A bus 1005 for transferring information between the various components of the device (e.g., the processor 1001, memory 1002, input/output interface 1003, and communication interface 1004);
Wherein the processor 1001, the memory 1002, the input/output interface 1003, and the communication interface 1004 realize communication connection between each other inside the device through the bus 1005.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program which is executed by a processor to realize the traffic mode prediction method considering the charge of the parking lot.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.
It will be appreciated by persons skilled in the art that the embodiments of the application are not limited by the illustrations, and that more or fewer steps than those shown may be included, or certain steps may be combined, or different steps may be included.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the application and in the above figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
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 an association relationship of an associated object, and indicates that three relationships may exist, for example, "a and/or B" may indicate that only a exists, only B exists, and three cases of a and B exist simultaneously, where a and B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one of a, b or c may represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is merely a logical function division, and there may be another division manner in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present application. The storage medium includes various media capable of storing programs, such as a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a magnetic disk, or an optical disk.
The preferred embodiments of the present application have been described above with reference to the accompanying drawings, and are not thereby limiting the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.