Shared bicycle travel hotspot area positioning method and system based on travel vector field, medium and terminal

Abstract

The invention discloses a shared bicycle travel hot spot area positioning method and system based on a travel vector field, a medium and a terminal. The method comprises the following steps: obtaining geographic space information data of a to-be-identified area, and carrying out unit grid division; based on the travel data of the shared bicycle in the target research time period, the longitude and latitude information of the starting point and the ending point is matched to the corresponding grids; counting the travel volume of the shared bicycles in each grid to generate an accumulated travel vector of each grid; carrying out clustering analysis on all grids by taking the travel volume of the normalized grids and the modulus of the cumulative travel vector as features, and dividing unit grids into different categories; according to the accumulative travel vectors of the different types of unit grids, sub-travel vector fields are constructed respectively, and corresponding potential energy is calculated; and determining a corresponding potential energy weight according to the travel volume mean value of the grids of each category, and calculating the potential energy of the global travel vector field of the city. The problems that resident travel directivity features are not comprehensively considered, and the hot spot area of the shared bicycle is not accurately positioned are solved.

Description

Technical Field

[0001] This invention relates to the field of transportation technology, and in particular to a method, system, medium, and terminal for locating shared bicycle travel hotspots based on travel vector fields. Background Technology

[0002] Shared bicycles, as a new type of urban short-distance commuting tool, have been widely used in many cities. While the popularity of shared bicycles has provided great convenience for residents' travel, it has also brought new pressure to urban road traffic. Due to the complexity and spatiotemporal dependence of residents' travel behavior, the contradiction between the supply and demand of shared bicycles is becoming increasingly apparent: the deployment of shared bicycles in certain areas may lead to traffic disorder, making it crucial to optimize their spatial allocation and improve scheduling efficiency. Existing research on identifying shared bicycle travel hotspots is mostly based on cluster analysis or community division methods of travel origin and destination data. However, existing methods still have the following problems: methods for locating travel hotspots rarely take into account the directional characteristics of residents' travel (such as trajectory direction), making it difficult for the identified areas to fully reveal the true travel patterns; field analysis models based on travel vectors have not yet been systematically applied to the field of shared bicycle hotspot location, and how to combine the spatial heterogeneity of shared bicycle travel to construct an effective travel vector field remains a key problem that urgently needs to be solved. Summary of the Invention

[0003] This invention provides a method, system, medium, and terminal for locating shared bicycle hotspot areas based on travel vector fields. The method solves the technical problems of incomplete consideration of residents' travel directional characteristics and inaccurate positioning of shared bicycle hotspot areas.

[0004] In a first aspect, the present invention provides a method for locating shared bicycle travel hotspot areas based on travel vector fields, including:

[0005] S1: Obtain geospatial information data of the area to be identified and divide the area to be identified into unit grids;

[0006] S2: Obtain the travel data of shared bicycles during the target research period, match the latitude and longitude information of the origin and destination of the travel data with the corresponding cell grid, and obtain the travel data between cell grids;

[0007] S3: Based on the travel data between cell grids, the travel volume of shared bicycles in each cell grid is statistically analyzed, and the cumulative travel vector of each cell grid is generated;

[0008] S4: Using the normalized unit grid's trip volume and the magnitude of the cumulative trip vector as features, cluster analysis models are used to cluster all unit grids, dividing the unit grids into different categories.

[0009] S5: Construct sub-trip vector fields based on the cumulative trip vectors of each type of cell grid, and calculate the potential energy of each sub-trip vector field;

[0010] S6: Determine the potential energy weight of the corresponding sub-trip vector field by using the average trip volume of each type of cell grid, calculate the potential energy of the city's global trip vector field, and then locate the shared bicycle travel hotspot area in the area to be identified.

[0011] Furthermore, the travel data includes the trip end time, origin latitude and longitude, and destination latitude and longitude of the shared bicycle order.

[0012] Furthermore, in S3, the formula for calculating the cumulative travel vector of each cell grid is:

[0013]

[0014]

[0015] in, Let i be the cumulative travel vector of cell i; For all trips originating from cell i, the trip volume of cell i; For vectors The model; Let be the unit direction vector pointing from cell i to cell j; It is the cumulative vector of travel vectors that start from cell i and reach each destination cell. The trip volume from starting cell i to ending cell j; through the... The vector summation yields the composite vector. .

[0016] Furthermore, the cluster analysis employs a Gaussian mixture model. During the clustering process, the goal is to minimize the Bayesian information criterion value, and a grid search algorithm is used to obtain the number of clusters K and the covariance matrix. The optimal combination.

[0017] Furthermore, in S5, the categories Cell grid cumulative travel vector The constructed sub-trip vector field is Sub-travel vector field The formula for calculating potential energy is:

[0018]

[0019]

[0020] in, This indicates that the element mesh i is located in the two-dimensional plane. Line number List; For the first position located in a two-dimensional plane Line number Potential energy of column cell grid; assumption The zero potential energy point, i.e. Solve for the potential energy of the remaining element mesh. For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; and The cumulative anomaly vectors of cell i are respectively. The magnitude of the components in the x-axis and y-axis directions; and When the two values ​​are equal, they represent the side lengths of the cell grid on the x and y axes.

[0021] Furthermore, in S6, the potential energy weight of each sub-travel vector field is calculated using the following formula:

[0022]

[0023]

[0024] in, Indicate category The weights of the travel vector field potential energy; For category The mean of trip volume in the medium-sized grid unit; For category The number of cells in the grid; For all trips originating from cell i, the trip volume is calculated.

[0025] Furthermore, in S6, the calculation process of the potential energy of the city's global travel vector field is as follows:

[0026]

[0027] in, This indicates that the element mesh i is located in the two-dimensional plane. Line number List; Total number of categories; The potential energy of the city's overall travel vector field; Category located in a two-dimensional plane The Line number Potential energy of a column cell grid; Total number of categories; Indicate category The weights of the travel vector field potential energy.

[0028] Secondly, the present invention provides a shared bicycle travel hotspot area positioning system based on a travel vector field, the system being used to execute the method described above, including:

[0029] Cell grid division module: Used to acquire geospatial information data of the area to be identified and divide the area to be identified into cell grids;

[0030] Cell grid data matching module: used to obtain the travel data of shared bicycles within the target study period, and match the latitude and longitude information of the origin and destination of the travel data with the corresponding cell grid to obtain the travel data between cell grids;

[0031] Cell grid cumulative trip volume acquisition module: used to calculate the trip volume of shared bicycles in each cell grid based on the trip data between cell grids, and generate the cumulative trip vector of each cell grid;

[0032] Category acquisition module: It is used to use the normalized unit grid's trip volume and the magnitude of the cumulative trip vector as features, and to use a clustering analysis model to cluster all unit grids, dividing the unit grids into different categories;

[0033] The potential energy acquisition module for sub-trip vector fields is used to construct sub-trip vector fields based on the cumulative trip vectors of each type of cell grid and to calculate the potential energy of each sub-trip vector field.

[0034] Hotspot area positioning module: It is used to determine the potential energy weight of the corresponding sub-trip vector field based on the average trip volume of each type of unit grid, calculate the potential energy of the city's global trip vector field, and then locate the shared bicycle travel hotspot area in the area to be identified.

[0035] Thirdly, the present invention provides a readable storage medium storing a computer program that, when invoked by a processor, performs the steps of the method described above.

[0036] Fourthly, the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores a computer program, and the processor invokes the computer program to perform the steps of the method described above.

[0037] This invention proposes a method, system, medium, and terminal for locating shared bicycle travel hotspots based on travel vector fields. The method transforms and calculates urban geospatial data and shared bicycle travel data to obtain the travel volume of each unit grid and calculates the magnitude of the cumulative travel vector for each unit grid. A Gaussian mixture model is used to cluster all unit grids based on travel volume and the magnitude of the cumulative travel vector, constructing sub-travel vector fields for the cumulative travel vectors of different categories of unit grids and calculating their potential energy. The potential energy weights are determined based on the average travel volume of different categories of unit grids, and the potential energy of the global urban travel vector field is calculated to locate shared bicycle travel hotspots. This method can help city managers analyze the behavioral patterns of shared bicycle users, facilitate better development of shared bicycle operation and scheduling plans, improve user experience, and promote urban traffic management. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart of a method for locating shared bicycle travel hotspot areas based on travel vector fields, provided by an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of the cumulative travel vector distribution of each unit grid in a certain city, provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the potential energy distribution of the travel vector field of shared bicycles in a certain city, provided by an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0043] Example 1

[0044] like Figure 1 As shown, this invention provides a method for locating shared bicycle travel hotspot areas based on travel vector fields, including:

[0045] S1: Obtain geospatial information data of the area to be identified and divide the area into unit grids.

[0046] In this embodiment, a city is selected for study, and the area where the city is located is divided into unit grids. In specific implementation, the method of grid division is not limited and can be adjusted according to actual needs. In this embodiment, the area where the city is located is used as the circumscribed rectangle, and then square unit grids are divided into the circumscribed rectangle. The size of the unit grid is not limited and can be adjusted according to actual conditions. In this embodiment, the side length of the unit grid is 1 kilometer, thus dividing the city into 2204 unit grids.

[0047] S2: Obtain travel data for shared bicycles within the target research period. Match the origin and destination latitude and longitude information of the travel data with the corresponding cell grids to obtain travel data between cell grids. The travel data includes the trip end time, origin latitude and longitude, and destination latitude and longitude of shared bicycle orders.

[0048] In this embodiment, the period from 6 PM to 7 PM on August 18, 2021, was selected as the research period, and the travel data of 171,220 shared bicycles in a certain city during this time were used as a case study. Based on the origin and destination latitude and longitude information of each shared bicycle travel data, combined with the location of the unit grid in geospatial space, when the origin or destination of a shared bicycle travel falls within the range of the unit grid, the origin or destination data is considered to belong to that unit grid. Thus, the shared bicycle travel is transformed into travel between different unit grids, resulting in a total of 151,855 travel records between 14,107 OD pairs.

[0049] S3: Based on the travel data between cell grids, the travel volume of shared bicycles in each cell grid is statistically analyzed, and the cumulative travel vector of each cell grid is generated.

[0050] Specifically, the formula for calculating the number of trips made by shared bicycles in each grid cell is as follows:

[0051]

[0052] in, For all trips originating from cell i, the trip volume of cell i; Let be the travel volume from starting cell i to ending cell j.

[0053] The formula for calculating the cumulative travel vector for each cell grid is:

[0054]

[0055] in, Let i be the cumulative travel vector of cell i; For vectors The model; Let be the unit direction vector pointing from cell i to cell j; It is the cumulative vector of travel vectors that start from cell i and reach each destination cell. The trip volume from starting cell i to ending cell j; through the... The vector summation yields the composite vector. The cumulative travel vector distribution of the cell grid provided in this example is as follows: Figure 2 As shown.

[0056] S4: Using the normalized unit grid's trip volume and the magnitude of the cumulative trip vector as features (i.e., using these two features to group unit grids with the same characteristics into one category, ultimately resulting in four subsequent categories), a clustering analysis model is used to cluster all unit grids, dividing them into different categories. The clustering analysis employs a Gaussian mixture model, and during the clustering process, the goal is to minimize the Bayesian information criterion value. A grid search algorithm is used to obtain the number of clusters K and the covariance matrix. The optimal combination.

[0057] Specifically, the number of trips in each grid cell is counted. The data is normalized; the cumulative travel vector of each cell is calculated. The data is normalized. The normalized modulus of the unit grid trip volume and the modulus of the cumulative trip vector are used as features of the Gaussian mixture model to cluster all unit grids. In this specific implementation, the number of clusters K is continuously tested from 2 to 10, and the covariance matrix... Four types of covariance matrices are used for testing: complete covariance matrix, bound covariance matrix, diagonal covariance matrix, and spherical covariance matrix. A grid search algorithm is used to evaluate the number of clusters K and the covariance matrix. Combine and calculate the Bayesian information criterion value after clustering. When the number of clusters K is 4, the covariance matrix... When the covariance matrix is ​​diagonal, the Bayesian information criterion value is minimized, resulting in optimal clustering performance. In this embodiment, the number of cell grids per category is 375, 172, 240, and 325, respectively.

[0058] S5: Construct sub-trip vector fields based on the cumulative trip vectors of each category's cell grid, and calculate the potential energy of each sub-trip vector field; where, the potential energy is determined by the category... Corresponding cell grid cumulative travel vector The constructed sub-trip vector field is .

[0059] Specifically, sub-trip vector field The formula for calculating potential energy is:

[0060]

[0061]

[0062] in, For category; This indicates that the element mesh i is located in the two-dimensional plane. Line number List; For the first position located in a two-dimensional plane Line number Potential energy of column cell grid; assumption The zero potential energy point, i.e. Solve for the potential energy of the remaining element mesh. For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; and The cumulative anomaly vectors of cell i are respectively. The magnitude of the components in the x-axis and y-axis directions; and When the two values ​​are equal, they represent the side lengths of the cell grid on the x and y axes.

[0063] S6: Determine the potential energy weight of the corresponding sub-trip vector field based on the average trip volume of each type of unit grid, calculate the potential energy of the city's global trip vector field, and locate the hot spots for shared bicycle travel.

[0064] Specifically, the potential energy weight of each sub-travel vector field is calculated using the following formula:

[0065]

[0066]

[0067] in, Indicate category The weights of the travel vector field potential energy; For category The mean of trip volume in the medium-sized grid unit; For category The number of unit grid cells. In this specific implementation, the potential energy weights of the four sub-row vector fields were calculated to be 14.65%, 0.23%, 83.62%, and 1.50%, respectively.

[0068] The calculation process for the potential energy of the city's global travel vector field is as follows:

[0069]

[0070] The potential energy distribution of the travel vector field of shared bicycles in Shenzhen provided in this embodiment of the invention is as follows: Figure 3 As shown in the figure, the lower-middle area, central and western parts of the city have the lowest potential energy, indicating that travel to these areas was more concentrated and directional between 6 PM and 7 PM on August 18, 2021, representing the travel hotspots for shared bicycle users. The potential energy basins shown in the figure are all distributed in areas with a high concentration of urban points of interest, indicating a close relationship between the formation of travel hotspots and the location of these points of interest.

[0071] Example 2

[0072] This embodiment provides a shared bicycle travel hotspot area positioning system based on travel vector fields. The system is used to execute the method described above, including:

[0073] Cell grid division module: Used to acquire geospatial information data of the area to be identified and divide the area to be identified into cell grids;

[0074] Cell grid data matching module: used to obtain the travel data of shared bicycles within the target study period, and match the latitude and longitude information of the origin and destination of the travel data with the corresponding cell grid to obtain the travel data between cell grids;

[0075] Cell grid cumulative trip volume acquisition module: used to calculate the trip volume of shared bicycles in each cell grid based on the trip data between cell grids, and generate the cumulative trip vector of each cell grid;

[0076] Category acquisition module: Used to cluster all cell grids using the modulus of trip volume and the modulus of cumulative trip vector after normalization as features, and divide the cell grids into different categories using a clustering analysis model;

[0077] The potential energy acquisition module for sub-trip vector fields is used to construct sub-trip vector fields based on the cumulative trip vectors of each type of cell grid and to calculate the potential energy of each sub-trip vector field.

[0078] Hotspot area positioning module: It is used to determine the potential energy weight of the corresponding sub-trip vector field based on the average trip volume of each type of unit grid, calculate the potential energy of the city's global trip vector field, and then locate the shared bicycle travel hotspot area in the area to be identified.

[0079] Example 3

[0080] This embodiment provides a readable storage medium storing a computer program that, when invoked by a processor, performs the steps of the method described above.

[0081] Example 4

[0082] This embodiment provides an electronic terminal, including a processor and a memory, wherein the memory stores a computer program, and the processor calls the computer program to perform the steps of the method described above.

[0083] It should be understood that, in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0084] The readable storage medium is a computer-readable storage medium, which can be an internal storage unit of the controller described in any of the foregoing embodiments, such as the controller's hard drive or memory. The readable storage medium can also be an external storage device of the controller, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the controller. Further, the readable storage medium can include both the controller's internal storage unit and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0085] Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0086] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0087] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for locating shared bicycle travel hotspot areas based on travel vector fields, characterized in that, include: S1: Obtain geospatial information data of the area to be identified and divide the area to be identified into unit grids; S2: Obtain the travel data of shared bicycles during the target research period, match the latitude and longitude information of the origin and destination of the travel data with the corresponding cell grid, and obtain the travel data between cell grids; S3: Based on the travel data between cell grids, the travel volume of shared bicycles in each cell grid is statistically analyzed, and the cumulative travel vector of each cell grid is generated; S4: Using the normalized unit grid's trip volume and the magnitude of the cumulative trip vector as features, cluster analysis models are used to cluster all unit grids, dividing the unit grids into different categories. S5: Construct sub-trip vector fields based on the cumulative trip vectors of each type of cell grid, and calculate the potential energy of each sub-trip vector field; S6: Determine the potential energy weight of the corresponding sub-trip vector field based on the average trip volume of each type of unit grid, calculate the potential energy of the city's global trip vector field, and then locate the shared bicycle travel hotspot area in the area to be identified.

2. The method according to claim 1, characterized in that, The travel data includes the trip end time, origin latitude and longitude, and destination latitude and longitude of shared bicycle orders.

3. The method according to claim 1, characterized in that, In S3, the formula for calculating the cumulative travel vector of each cell grid is: ； ； in, Let i be the cumulative travel vector of cell i; For all trips originating from cell i, the trip volume of cell i; For vectors The model; Let be the unit direction vector pointing from cell i to cell j; It is the cumulative vector of travel vectors that start from cell i and reach each destination cell. The trip volume from starting cell i to ending cell j; through the... The vector summation yields the composite vector. .

4. The method according to claim 1, characterized in that, Cluster analysis employs a Gaussian mixture model. During the clustering process, the goal is to minimize the Bayesian information criterion value. A grid search algorithm is used to obtain the number of clusters K and the covariance matrix. The optimal combination.

5. The method according to claim 1, characterized in that, In S5, the categories are... Cell grid cumulative travel vector The constructed sub-trip vector field is Sub-travel vector field The formula for calculating potential energy is: ； ； in, For category; This indicates that the element mesh i is located in the two-dimensional plane. Line number List; For the first position located in a two-dimensional plane Line number Potential energy of column cell grid; assumption The zero potential energy point, i.e. Solve for the potential energy of the remaining mesh elements. For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; For the first position located in a two-dimensional plane Line number Potential energy of a column cell grid; and These are the cumulative anomaly vectors of cell i. The magnitude of the components in the x-axis and y-axis directions; and When the two values ​​are equal, they represent the side lengths of the cell grid on the x and y axes.

6. The method according to claim 1, characterized in that, In S6, the potential energy weight of each sub-travel vector field is calculated using the following formula: ； ； in, Indicate category The weights of the travel vector field potential energy; For category The mean of trip volume in the medium-sized grid unit; For category The number of cells in the grid; For all trips originating from cell i, the trip volume is calculated.

7. The method according to claim 1, characterized in that, In S6, the calculation process of the potential energy of the city's global travel vector field is as follows: ； in, This indicates that the element mesh i is located in the two-dimensional plane. Line number List; Total number of categories; The potential energy of the city's overall travel vector field; Category located in a two-dimensional plane The Line number Potential energy of a column cell grid; Total number of categories; Indicate category The weights of the travel vector field potential energy.

8. A shared bicycle travel hotspot area positioning system based on travel vector field, the system being used to execute the method according to any one of claims 1-7, characterized in that, include: Cell grid division module: Used to acquire geospatial information data of the area to be identified and divide the area to be identified into cell grids; Cell grid data matching module: used to obtain the travel data of shared bicycles within the target study period, and match the latitude and longitude information of the origin and destination of the travel data with the corresponding cell grid to obtain the travel data between cell grids; Cell grid cumulative trip volume acquisition module: used to count the trip volume of shared bicycles in each cell grid based on the trip data between cell grids, and generate the cumulative trip vector of each cell grid; Category acquisition module: It is used to use the normalized unit grid's trip volume and the magnitude of the cumulative trip vector as features, and to use a clustering analysis model to cluster all unit grids, dividing the unit grids into different categories; The potential energy acquisition module for sub-trip vector fields is used to construct sub-trip vector fields based on the cumulative trip vectors of each type of cell grid and to calculate the potential energy of each sub-trip vector field. Hotspot area positioning module: It is used to determine the potential energy weight of the corresponding sub-trip vector field based on the average trip volume of each type of unit grid, calculate the potential energy of the city's global trip vector field, and then locate the shared bicycle travel hotspot area in the area to be identified.

9. A readable storage medium, characterized in that: A computer program is stored, which, when invoked by a processor, performs the steps of the method according to any one of claims 1-7.

10. An electronic terminal, characterized in that: It includes a processor and a memory, the memory storing a computer program, the processor calling the computer program to perform the steps of the method according to any one of claims 1-7.

Images