Multi-stage method and device for temporary parking site of municipal vehicles and storage medium

Abstract

The application relates to a multi-stage site selection method, device and storage medium for temporary parking points of urban distribution vehicles, wherein the method comprises the following steps: S1, acquiring a planar map of a target area and gridizing; S2, generating the weight of each grid according to the number of potential temporary parking points in each grid, clustering all the grids to obtain a plurality of grid clusters, and taking each grid cluster as a research area; S3, in a single research area, pre-siting all the potential temporary parking points to select part of the potential temporary parking points as core points; S4, in the research area, extracting all the interest points related to the potential temporary parking points, combining the weight of each interest point, respectively calculating the weighted distance sum of each core point and all the interest points, and selecting the core point with the largest weighted distance sum as the final temporary parking point. Compared with the prior art, the application meets the actual parking demand of urban distribution vehicles and can reduce the influence on the normal life of the city.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of traffic information, and particularly to a multi-stage method and device for temporary parking site selection of urban distribution vehicles and a storage medium. BACKGROUND

[0002] Identifying and classifying the stopping points of freight vehicles is a fundamental task in freight data analysis, which aims to segment continuous vehicle trajectory data into a series of meaningful trip segments and activity areas by identifying the locations and purposes of vehicle stops. This process is crucial for further freight characteristic analysis and travel mode research. The types of stopping points are usually divided based on the related activities of vehicle stops, which include the start and end points of freight loading and unloading, stops due to rest, dining, refueling, accidents or severe traffic congestion, and short stops due to traffic light control, minor congestion or tolls. In the process of identifying stopping points, researchers usually first determine a low-speed threshold to identify potential stopping points by comparing the instantaneous speed or average speed within a certain time window of the freight vehicle, and then use appropriate techniques to determine the specific type of stopping point.

[0003] In existing literature, the methods for identifying the types of freight vehicle stopping points can be mainly divided into the following three categories:

[0004] (1) Auxiliary information method

[0005] This method mainly relies on auxiliary information, such as driver survey data and land use information, to identify stopping points. Alho et al. successfully identified the types of freight vehicle stopping points by combining freight vehicle trajectory data and feedback from driver surveys. Although this method performs well in handling small sample data, its application is limited by the availability of auxiliary information and the size of the data, and its generalization ability is low.

[0006] (2) Rule-based discrimination method

[0007] This method mainly uses the residence time as the judgment standard, and identifies the type of parking point by setting a specific residence time threshold. According to different research backgrounds, the residence time threshold will be different. For example, Richardson and Sharman set the threshold of 3 minutes and 5 minutes respectively in the study of urban freight, while Gingerich set the threshold between 15 to 45 minutes in the study of cross-border freight. In addition, Li Jiangtao identified the parking point by setting the parking speed threshold of freight trucks, and further processed and analyzed the data through map matching and SCAN clustering method. This method is simple to operate, but its classification result is rough, and it is usually used for preliminary screening. Yang et al. combined rule-based discrimination and auxiliary information method, defined the speed threshold and multi-level time threshold required to identify truck parking points, and considered the complexity of urban freight environment, combined with urban road network and POI data to improve the identification accuracy, effectively reflecting the spatial distribution and operation mode of heavy truck freight in the city.

[0008] (3) Machine learning algorithm

[0009] Including spatial density-based algorithms such as K-means and DBSCAN, as well as support vector machines (SVM), random forests (RF), and maximum entropy models. These methods usually use features such as residence time and distance from a specific location for classification, and can achieve high identification accuracy. SUMMARY

[0010] The purpose of the present application is to provide a multi-stage site selection method, device and storage medium for temporary parking points of city distribution vehicles.

[0011] The purpose of the present application can be achieved by the following technical solutions:

[0012] A multi-stage site selection method for temporary parking points of city distribution vehicles, comprising:

[0013] Step S1: Obtain the planar map of the target area and grid it;

[0014] Step S2: Generate the weight of each grid with the number of potential temporary parking points in each grid, cluster all grids to obtain multiple grid clusters, and take each grid cluster as a research area;

[0015] Step S3: In a single research area, pre-site all potential temporary parking points to select part of the potential temporary parking points as core points;

[0016] Step S4: In the research area, extract all interest points related to the potential temporary parking points, combine the weights of each interest point, calculate the weighted distance sum of each core point and all interest points respectively, and select the core point with the largest weighted distance sum as the final temporary parking point.

[0017] The grid is a square grid.

[0018] The step S2 comprises:

[0019] Step S2-1: generating the weight of each grid with the number of potential temporary stopping points in each grid, clustering the grids by K-Means weighted clustering method to obtain a preliminary clustering result, wherein the weight of the grid is positively correlated with the number of potential temporary stopping points;

[0020] Step S2-2: correcting the preliminary clustering result to obtain a plurality of grid clusters, and taking each grid cluster as a research area.

[0021] The correction process in step S2-2 comprises:

[0022] (1) Density center principle: each grid cluster contains at least one super-high-density grid or high-density grid as the core of division, wherein the super-high-density grid contains a number of potential temporary stopping points greater than a first set threshold, and the high-density grid contains a number of potential temporary stopping points greater than a second set threshold;

[0023] (2) Exclusivity principle: each grid can only be assigned to one grid cluster;

[0024] (3) Expansion principle: taking the high-density grid or super-high-density grid as the center, expanding to the surrounding, if there are medium-density and above grids in the adjacent four grids, the medium-density and above grids will be added to the grid cluster where the high-density grid or super-high-density grid is located;

[0025] (4) Edge expansion principle: if the high-density grid or super-high-density grid has a cluster of potential temporary stopping points extending to adjacent grids, and the adjacent grids are medium-density and above grids, the medium-density and above grids will be added to the grid cluster where the high-density grid or super-high-density grid is located.

[0026] The step S3 divides the potential temporary stopping points in the research area into core points, edge points and noise points,

[0027] The core point is: the number of potential temporary stopping points within the set radius range around the core point is greater than the minimum neighbor number;

[0028] The edge point is: the distance from any core point is less than the set radius, and the number of potential temporary stopping points within the set radius range around the edge point is less than the minimum neighbor number;

[0029] The noise point is the potential temporary stopping point other than the core point and the edge point.

[0030] The step S4 comprises:

[0031] Step S4-1: Extract all the interest points related to the potential temporary stopover points in the study area;

[0032] Step S4-2: Screen the interest points obtained in step S4-1;

[0033] Step S4-3: Obtain the weight of all the interest points after screening;

[0034] Step S4-4: Calculate the weighted distance sum of each core point and all the interest points respectively, and select the core point with the largest weighted distance sum as the final temporary stopover point.

[0035] The screening method in the step S4-2 comprises:

[0036] Exclude service industry interest points with low relevance to freight delivery;

[0037] Exclude medical and health interest points;

[0038] Exclude shopping and consumption interest points.

[0039] The weighted distance sum D is:

[0040]

[0041] Wherein: n is the number of interest points, w i is the weight of the ith interest point, d i is the distance between the core point and the ith interest point.

[0042] A city distribution vehicle temporary stopover point multi-stage site selection device comprises a memory, a processor, and a program stored in the memory, and the processor implements the method as described above when executing the program.

[0043] A storage medium having a program stored thereon, the program being executed to implement the method as described above.

[0044] Compared with the prior art, the present application has the following beneficial effects:

[0045] 1. By creating grid cells, the potential temporary parking points are gridded, and the grid is preliminarily divided by the weighted clustering method, and on this basis, the research area is further divided based on the experience rule; then the potential temporary parking points are pre-sited; then combined with the interest points in the research area which are significantly related to city distribution, the temporary parking points are optimized to ensure that the selected location meets the demand of city freight as much as possible; through this method, on the basis of the data information of city distribution vehicle temporary parking points, scientific basis can be provided for the site selection of city distribution vehicle temporary parking points, technical support can be provided for improving the efficiency of city distribution vehicle freight distribution and relieving traffic congestion, which will help to promote the sustainable development of urban traffic.

[0046] 2. The weighted clustering method is adopted, so that the data points are divided into K clusters, and each cluster is composed of the data points closest to its center of gravity (center point). Unlike the traditional K-Means method, weighted K-Means assigns a weight value to each data point during the clustering process, so that different data points have different influence in determining the cluster center. In the context of city freight, the number of stops in each grid can be regarded as the weight value, which means that the grid with more stops has a higher priority in the clustering process.

[0047] 3. The DBSCAN clustering method is adopted to divide the potential temporary parking points in the research area into core points, edge points and noise points, so that irregular or disorganized data sets can be effectively processed, and the true clustering structure can be identified, while ignoring isolated data points or outliers.

[0048] 4. The actual parking needs of city distribution vehicles are met, and the impact on normal urban life is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 The main step flowchart of the method of the present application is shown in the figure;

[0050] Figure 2 The POI correlation coefficient diagram of the city distribution vehicle of the present application is shown in the figure. DETAILED DESCRIPTION

[0051] The present application will be described in detail below in combination with the drawings and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present application, and detailed implementation and specific operation process are given, but the protection scope of the present application is not limited to the following embodiments.

[0052] A multi-stage site selection method for city distribution vehicle temporary parking points, as shown in Figure 1 , includes:

[0053] Step S1: Obtain the planar map of the target area and grid it;

[0054] Generally, the grid is a square grid, and in the embodiment, a square grid with a side length of 1 kilometer is adopted.

[0055] Step S2: generating the weight of each grid according to the number of potential temporary stopping points in each grid, clustering all the grids to obtain a plurality of grid clusters, and taking each grid cluster as a research area, including:

[0056] Step S2-1: generating the weight of each grid according to the number of potential temporary stopping points in each grid, and clustering the grids by using a K-Means weighted clustering method to obtain a preliminary clustering result, wherein the weight of the grid is positively correlated with the number of potential temporary stopping points;

[0057] Since the weighted clustering method is adopted, each grid is assigned a weight, so that different grids have different influences when determining the cluster center. The K-Means weighted clustering is a clustering method based on partition, which aims to divide the grids into k sets, and each set is composed of the grids closest to its center (center point).

[0058] The value of K is determined by the elbow method or the silhouette coefficient method:

[0059] (1) The elbow method is to determine the best value of k by observing the change of clustering cost under different values of k. As the value of k increases, the clustering cost decreases, and the clustering cost calculation formula is:

[0060]

[0061] Wherein: n1 is the number of grids, Distortion is the clustering cost, μ j is the center of set j, x i is the i-th grid,

[0062] (2) The silhouette coefficient method is to calculate the average distance a of the grid to other grids in the set and the average distance b of the nearest set to all grids in the set, and the silhouette coefficient s calculation formula is:

[0063]

[0064] Wherein: s is between -1 and 1, and the higher the value of s indicates the better the clustering effect.

[0065] Step S2-2: correcting the preliminary clustering result to obtain a plurality of grid clusters, and taking each grid cluster as a research area, wherein the correction process includes:

[0066] (1) Density center principle: each grid cluster contains at least one super-high-density grid or high-density grid as the core of the division, wherein the super-high-density grid is a grid containing a number of potential temporary stopping points greater than a first set threshold, and the high-density grid is a grid containing a number of potential temporary stopping points greater than a second set threshold;

[0067] (2) Exclusivity principle: each grid can only be assigned to one grid cluster;

[0068] (3) Expansion principle: taking the high-density grid or super-high-density grid as the center, expanding to the surrounding, if there are medium-density and above grids in the adjacent four grids, the medium-density and above grids are added to the grid cluster where the high-density grid or super-high-density grid is located;

[0069] (4) Edge expansion principle: if the high-density grid or super-high-density grid has a cluster of potential temporary stopping points extending to adjacent grids, and the adjacent grids are medium-density and above grids, the medium-density and above grids are added to the grid cluster where the high-density grid or super-high-density grid is located.

[0070] In addition, in the embodiment, the embodiment also includes:

[0071] (5) Morphology optimization principle: when forming a grid cluster, if a rectangular area can be formed by completing the medium-density grid, it can be considered to be included in the grid cluster that may become a rectangular area, but this is not a mandatory requirement.

[0072] (6) Special case handling principle: for areas containing large commercial centers and other special landmarks, they should be completely divided into the same grid cluster according to the actual situation.

[0073] (7) Partition area principle: low-density areas are generally considered as partition areas and used as an important reference for grid cluster division.

[0074] (8) Cutting large area principle: for large grid clusters that may be formed due to the concentration of stopping points, further cutting and subdivision should be performed according to features such as street groups to obtain smaller and more practical grid clusters.

[0075] Step S3: In a single study area, pre-site selection is performed on all potential temporary stopping points, and part of the potential temporary stopping points are selected as core points;

[0076] Step S3 divides the potential temporary stopping points in the study area into core points, edge points and noise points,

[0077] Among them, the core point is: the number of potential temporary stopping points within the radius range set around the core point is greater than the minimum neighbor number;

[0078] Edge points are: the distance from any core point is less than the set radius, and the number of potential temporary parking points within the set radius around the edge point is less than the minimum number of neighbors;

[0079] Noise points are potential temporary parking points other than core points and edge points.

[0080] In this embodiment, the DBSCAN density clustering method is used to pre-site the potential temporary parking points; the DBSCAN density clustering method is a density-based clustering algorithm.

[0081] Step S4: In the study area, extract all interest points related to potential temporary parking points, combine the weights of each interest point, and calculate the weighted distance sum of each core point and all interest points, select the core point with the largest weighted distance sum as the final temporary parking point, including:

[0082] Step S4-1: In the study area, extract all interest points related to potential temporary parking points;

[0083] The introduction of POI data related to city distribution, i.e. POI data, can make up for the limitations of site selection based only on the number of temporary parking points and regional density. Considering the differences in freight volume, cargo type and the importance of freight service involved in different stopping points, a simple site selection method based on the absolute number of stopping points may not accurately reflect these subtle differences. In addition, the actual stopping point location may not always correspond to the specific destination of freight demand, for example, vehicles may choose to stop in residential areas, near schools, and other non-target locations around demand points, which not only may affect the normal travel of local residents and students, but also may interfere with the accuracy of site selection.

[0084] Therefore, the present application will use the distribution and weight of POI points with high relevance to urban freight distribution in the study area to make site selection decisions. Through this method, it can be ensured that the finally selected temporary parking points not only meet the actual parking needs of city distribution vehicles, but also reduce the impact on urban normal life.

[0085] Step S4-2: Screen the interest points obtained in step S4-1;

[0086] As Figure 2 shown, it is a city distribution vehicle POI correlation coefficient diagram. In order to screen out POI categories closely related to urban freight distribution, the following three types of POIs are excluded in Figure 2

[0087] (1) Exclude service industry POIs with low relevance to freight distribution;

[0088] (2) Exclude medical and health POIs;

[0089] ​(3) exclude shopping consumption POIs that can cause repeated counting;

[0090] Step S4-3: Obtain the weight of all POIs after screening;

[0091] The POI types related to the temporary parking needs of city distribution vehicles obtained after screening are shown in Table 1. Since the similarity between the sub-category POIs in the food and beverage and hotel accommodation categories is high, they are combined. The combination result in this embodiment is shown in Table 1:

[0092] Table 1

[0093]

[0094] Step S4-4: Calculate the weighted distance sum of each core point and all POIs, and select the core point with the largest weighted distance sum as the final temporary parking point.

[0095] After screening the POI types related to city distribution, the expert evaluation method is used to weight each type of POI. After weighting each type of POI related to city distribution, the POI weighted distance model is constructed. In the POI weighted distance model, each geographic location is assigned a weight, and the distance is adjusted by adjusting the weight. The weighted proximity uses the reciprocal of the distance as the weight. The total weighted distance calculation formula of all city distribution vehicle related POIs to the preselected temporary parking point is:

[0096]

[0097] Wherein: n is the number of POIs, w i is the weight of the i-th POI, d i is the distance between the core point and the i-th POI.

[0098] Finally, in this embodiment, the site selection result is evaluated and analyzed by Voronoi diagram. The analysis process is as follows:

[0099] Step S5-1: Determine the seed points. A series of seed points are determined, which can be geographic location points;

[0100] Step S5-2: Construct the Voronoi boundary. For each pair of seed points in the seed point set, find the set of all points that are equidistant from the two seed points. This set of points forms a line, called the Voronoi edge,

[0101] Step S5-3: Generate the Voronoi unit. Repeat step S5-2 until the Voronoi edge between each pair of seed points is determined. These boundaries collectively define the Voronoi unit around each seed point, forming a complete Voronoi diagram.

[0102] Step S5-4: Analysis and application: By evaluating the size and shape of these Voronoi cells, the spatial coverage of the temporary stopping points can be evaluated, thus optimizing their location and distribution.

[0103] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of 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 described in various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A multi-stage site selection method for temporary parking spots for urban distribution vehicles, characterized in that, include: Step S1: Obtain a planar map of the target area and grid it; Step S2: Generate the weight of each grid based on the number of potential temporary docking points in each grid, cluster all grids to obtain multiple grid clusters, and treat each grid cluster as a study area; Step S3: In a single study area, pre-select all potential temporary stops and screen out a portion of potential temporary stops as core points; Step S4: Within the study area, extract all points of interest related to potential temporary stops. Combine the weights of each point of interest to calculate the weighted sum of distances between each core point and all points of interest. Select the core point with the largest weighted sum of distances as the final temporary stop. Step S2 includes: Step S2-1: Generate the weight of each grid based on the number of potential temporary docking points in each grid, and cluster the grids using the K-Means weighted clustering method to obtain preliminary clustering results. The weight of the grid is positively correlated with the number of potential temporary docking points. Step S2-2: Correct the preliminary clustering results to obtain multiple grid clusters, and treat each grid cluster as a study area; Step S3 classifies potential temporary stopping points within the study area into core points, edge points, and noise points. The core point is defined as follows: the number of potential temporary docking points within a radius around the core point is greater than the minimum number of neighbors. The edge point is defined as follows: the distance from any core point is less than the set radius, and the number of potential temporary docking points within the set radius around the edge point is less than the minimum number of neighbors; The noise points are potential temporary stopping points other than core points and edge points; Step S4 includes: Step S4-1: Within the study area, extract all points of interest related to potential temporary rest stops; Step S4-2: Filter the points of interest obtained in step S4-1; Step S4-3: Obtain the weights of all interest points after filtering; Step S4-4: Calculate the weighted sum of distances between each core point and all points of interest, and select the core point with the largest weighted sum of distances as the final temporary resting point; The weighted distance and D for: in: n For the number of points of interest, w i For the first i The weight of each point of interest d i As the core point and the first i The distance between points of interest.

2. The multi-stage site selection method for temporary parking points for urban distribution vehicles according to claim 1, characterized in that, The grid is a square grid.

3. The multi-stage site selection method for temporary parking spots for urban distribution vehicles according to claim 1, characterized in that, The correction process in step S2-2 includes: (1) Density center principle: Each grid cluster contains at least one ultra-high density grid or high density grid as the core of the division, wherein the ultra-high density grid is a grid with a number of potential temporary docking points greater than a first set threshold, and the high density grid is a grid with a number of potential temporary docking points greater than a second set threshold. (2) Exclusivity principle: Each grid can only be assigned to one grid cluster; (3) Expansion principle: Expand outward from the high-density grid or ultra-high-density grid as the center. If there are medium-density or higher grids in the four adjacent grids, the medium-density or higher grids are added to the grid cluster where the high-density grid or ultra-high-density grid is located. (4) Edge expansion principle: If there are potential temporary docking points of high-density grids or ultra-high-density grids that extend to neighboring grids, and the neighboring grids are medium-density or higher, then the medium-density or higher grids are added to the grid cluster where the high-density grid or ultra-high-density grid is located.

4. The multi-stage site selection method for temporary parking spots for urban distribution vehicles according to claim 1, characterized in that, The filtering methods in step S4-2 include: Exclude service sector interests that are low in relevance to freight delivery; Exclude points of interest related to healthcare; Exclude points of interest related to shopping and consumption.

5. A multi-stage location selection device for temporary parking spots for urban distribution vehicles, comprising a memory, a processor, and a program stored in the memory, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-4.

6. A storage medium having a program stored thereon, characterized in that, When the program is executed, it implements the method as described in any one of claims 1-4.

Images