Method for determining service range of modern tramcar station based on POI data

Abstract

The invention discloses a method for determining the service range of a modern tramcar station based on POI data, and the method comprises the steps: obtaining the environmental factors of a residential area in the vicinity of a tramcar through a POI database, improving a breaking point model, building a related influence factor model for each influence factor, and carrying out the calculation of the related influence factor model. And finally, optimizing and correcting the service range through the service range correction model. And acquiring and processing the acquired POI data, performing rasterization processing on the POI data and site data by applying a GeoHash algorithm, inputting the processed POI data and site data into the series model, acquiring radius data of the breaking point of the tramcar site, and performing visual analysis by means of ArcGIS. Through the POI database, the environmental factors of residents in the vicinity of the tramcar can be obtained more accurately and detailedly, and then the improved breaking point model is used to establish the related model for each influence factor, so that the service range of the tramcar station can be comprehensively determined.

Description

Technical Field

[0001] The invention relates to the field of urban rail transit planning, and in particular to a method for determining the service range of a modern tram station based on POI data. Background Art

[0002] In the planning and design of modern trams, determining the service range of stations is an important step. The traditional method is mainly based on historical data such as distance or time. Because there are deviations in the assessment of service range, it may also cause waste of resources and urban planning in the subsequent construction of public facilities.

[0003] POI (Point of Interest) refers to landmarks and geographic entity point data that are closely related to people's lives, such as schools, hospitals, etc. POI data usually contains information such as name, category, longitude and latitude, and address, reflecting urban activities, and is easy to obtain and process, making it possible to participate in the site service range assessment using POI data. However, in the existing technology, there is a lack of combined consideration of the time or space factors of the site itself while analyzing POI data, which leads to greater room for improvement in the accuracy of the site service range that can be determined. Summary of the invention

[0004] Purpose of the invention: To solve the problems mentioned in the background technology, the present invention provides a method for determining the service range of a modern tram station based on POI data. By collecting and preprocessing the POI data of tram stations, an improved breakpoint model is used in combination with a service range influencing factor model and an attraction scale model, so as to more accurately obtain the service range of a visualized station, which is beneficial for residents' navigation and travel and subsequent urban planning around the station, and reduces the waste of public facility resources.

[0005] Technical solution:

[0006] The present invention discloses a method for determining the service range of a modern tram station based on POI data, the method comprising the following steps:

[0007] S1 obtains POI data about the site location and its surrounding environment, preprocesses and constructs a data set;

[0008] S2 constructs an improved breakpoint model applied to the site;

[0009] S2.1 Establish a site service scope influencing factor model and obtain the influencing factor scores;

[0010] S2.2 Using the scores of each influencing factor, establish an attraction scale model and obtain the attraction scale parameters of the improved breakpoint model;

[0011] S2.3 Calculate the service range interval corresponding to the data set by improving the breakpoint model;

[0012] S3 establishes a service range correction model, corrects the service range of the site to be corrected, obtains the corrected service range interval and visualizes it.

[0013] Furthermore, the steps of S1 preprocessing and constructing the data set are as follows:

[0014] Use GeoHash algorithm to rasterize the site and nearby POI data;

[0015] Count the POI data in each grid;

[0016] Compare the distance between each grid and the site, and select the grid data within the range as the site POI data;

[0017] Raster processing was performed with a grid interval of 1.2km*0.6km. After GeoHash encoding of each POI data, a total of 89 grid areas were obtained. After counting the POI data contained in each grid, the sum of the grid where each station is located and the number of adjacent grids was taken as the number of POIs at each station.

[0018] Furthermore, the steps of constructing the S2 improved breakpoint model include:

[0019] The breakpoint of the attraction range between the two cities is expressed as:

[0020]

[0021] Among them, it represents D x The distance from the breakpoint to city x, d xy represents the straight-line distance between two cities, P x and P y represents the population of cities x and y;

[0022] The original breakpoint model uses the city population to indirectly represent the city's attractiveness and size. Based on the study of factors affecting the service scope of a site, an improved breakpoint model applied to sites is proposed using an analogy method:

[0023]

[0024] Among them, R i represents the distance from the breakpoint to site i, r i,i+1 represents the straight-line distance between two stations. It represents the attraction scale of site i, which is derived from the scores of various influencing factors.

[0025] Furthermore, the target influencing factors obtained by the site service range influencing factor model in S3 are divided into time factors and space factors:

[0026] Time factors include: arrival and departure time, waiting time and riding time;

[0027] Spatial factors include: land use and building density around the station, supporting service facilities, residents’ travel types, and transportation connections;

[0028] Based on the objective assessment of the changes in the factors affecting the service scope reflected by data availability and quantitative analysis, the influencing factors are screened again, including: land use building density, resident travel type, station type, station layout and transportation connection. The station service scope influencing factor model is established based on each influencing factor as follows:

[0029] Land use building density

[0030] As for the building density of land use, since the building density is closely related to the number of POIs in the local area, it is converted into POI research, and a mathematical model for the factors affecting the building density of land use is obtained, as shown in the formula:

[0031]

[0032] HD i =D i ×100

[0033] Among them, D i Indicates the building density of the area where site i is located, POI j Represents the j-th type of POI data, POI sum Indicates the total POI data near the site, HD i represents the land use density score of the ith site;

[0034] Residents' travel types

[0035] In terms of the types of residents' travel, they can be divided into different types of residents according to their travel needs, as shown in the formula:

[0036] PEO t =TD i ·P t

[0037] Among them, PEO t represents the number of residents of type t traveling, TD i represents the passenger flow of the ith station, P t It indicates the proportion of residents whose travel purpose is type t to the total population;

[0038] Site Type

[0039] In terms of site types, the importance of each site is analyzed based on the relationship between the POI data of each site and the POI data of different types and each site, and each site is divided into first-level sites, second-level sites, and third-level sites, as shown in the formula:

[0040]

[0041] Among them, ST i Represents the weight of the i-th site type, POI j represents the POI data of the i-th station of the j-th POI type, represents the number of all POIs of the jth type, PF j represents the travel demand of the jth type, TD i represents the passenger flow of the ith station, represents the total passenger flow of all stations;

[0042] PF j The travel demand calculation formula is as follows:

[0043]

[0044] Among them, PPF j represents the number of travelers at the i-th station of the j-th type, represents the number of travelers of all POI types at the i-th station, and AC represents the amplification coefficient, which is used to increase the comparability and improve the calculation accuracy;

[0045] Site Layout

[0046] Compare the distances from each station to the center of each major business district, select the shortest distance, and then use the ratio of the sum of the shortest distances from all stations to the center of each major business district and the shortest distance of each station as the station layout weight. The formula is as follows:

[0047]

[0048]

[0049] Among them, la i Indicates the site layout weight, DIS i represents the shortest distance from site i to the center of each business circle, Hl represents the sum of the shortest distances from all sites to the centers of each business circle. i represents the site layout score of the i-th site, la sum The weight number representing the total site layout;

[0050] Transportation

[0051] The POI data converted into transportation facilities in terms of transportation connection is studied, and a mathematical model for the influencing factors of transportation connection is obtained. The formula is as follows:

[0052]

[0053]

[0054] Among them, T i Indicates the transportation connection in the area where station i is located. represents the POI data of transportation facilities at station i, Indicates the total POI data of transportation facilities near all stations, HT i represents the traffic connection score of the i-th station, T sum Indicates the weight of total traffic connections.

[0055] Furthermore, by establishing the models of various influencing factors and obtaining the scores of influencing factors, the attraction scale of tram stations is calculated. The calculation formula of attraction scale is as follows:

[0056] S i =Hl i ·ST i ·HT i ·∫(PEO t ×HD i ×AC)

[0057] Among them, S i represents the attraction scale of site i, Hl i represents the site layout score of the i-th site, ST i Indicates the weight of the site type, HT i represents the traffic connection score of the i-th station, PEO t represents the number of residents of type t traveling, HD i It represents the land use density score of the ith site, and AC is the amplification coefficient, which is used to increase the contrast and improve the calculation accuracy.

[0058] Furthermore, the detailed steps of S3 are:

[0059] In order to correct the service range of the station to be corrected, the correction coefficient can be obtained from the correction model. A correction model based on the POI data of each station and the adjacent distance information is established. The formula is as follows:

[0060]

[0061] In the formula, R_c i represents the revised service scope, r i,i+1 Represents the straight-line distance between two sites.

[0062] Furthermore, S3 visualized the revised service range intervals through ArcGIS and drew a visualization map of the tram station service range for subsequent scheduling research.

[0063] Beneficial effects:

[0064] 1. Based on the study of factors affecting the service range of stations, the present invention uses an analogy method to propose an improved breakpoint model applied to stations, which is suitable for the accurate determination of the service range of trams and ensures generalization and convergence speed.

[0065] 2. The present invention analyzes the influencing factors based on POI data, conducts secondary selection of factors affecting modern tram stations, selects five influencing factors for analysis and establishes an influencing factor model, and further determines the attraction scale parameters to improve the accuracy of the service scope.

[0066] 3. The present invention performs model calculation on the service range of the station to be corrected, establishes a correction model based on the POI data of each station and the adjacent distance information, improves the calculation upper limit of the service range and corrects it, eliminates and filters the service range that does not meet the authenticity, maintains the authenticity and practicality of the service range results, and can be applied to actual scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a specific flow chart of the present invention;

[0068] Figure 2 This is the POI distribution map within 1km of each site under ArcGIS of the present invention;

[0069] Figure 3 This is a schematic diagram of the rasterization of the site and nearby POI data of the present invention;

[0070] Figure 4 This is a schematic diagram of the site location and surrounding GeoHash locations of the present invention;

[0071] Figure 5 This is a population ratio diagram of each type of passenger flow at the site of the present invention;

[0072] Figure 6 A passenger flow line chart of Huai'an City on April 24, 2023 was collected for the present invention survey;

[0073] Figure 7 A schematic diagram summarizing the factors affecting the service range of modern tram stations for the present invention;

[0074] Figure 8 Obtaining a weight map of each site for the site type model of the present invention;

[0075] Fig. 9 Obtaining a service range map of each site for the present invention;

[0076] Fig.10 A comparison chart of the revised service scope and the original service scope of the present invention;

[0077] Fig.11 The final service scope visualization result diagram is obtained for the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0079] like Figure 1 As shown, the method steps used in the present invention are as follows:

[0080] S1 obtains POI data about the site location and its surrounding environment, preprocesses and constructs a data set;

[0081] S2 constructs an improved breakpoint model applied to the site;

[0082] S2.1 Establish a site service scope influencing factor model and obtain the influencing factor scores;

[0083] S2.2 Using the scores of each influencing factor, establish an attraction scale model and obtain the attraction scale parameters of the improved breakpoint model;

[0084] S2.3 Calculate the service range interval corresponding to the data set by improving the breakpoint model;

[0085] S3 establishes a service range correction model, corrects the service range of the site to be corrected, obtains the corrected service range interval and visualizes it.

[0086] Based on the above method, this embodiment takes Huai'an Modern Tram Line 1 as the research object, and further explains the process of obtaining the service range of the tram station in the present invention:

[0087] Step 1: Data collection and processing:

[0088] In order to determine the service scope of modern tram stations in Huai'an, it is necessary to obtain data about the station location and its surrounding environment. The location information of Huai'an tram stations and the surrounding POI data are retrieved through the AutoNavi open platform to determine the specific location of each station and the traffic, business, and residential characteristics of the surrounding environment, so as to classify the stations and further study their service scope.

[0089] First, the names of tram stations in Huai'an City were obtained from Amap. The specific contents are shown in Table 1:

[0090] Table 1

[0091]

[0092]

[0093] Secondly, the coordinate picking function is used in the AutoNavi open platform to obtain the geographical location of each station in the AutoNavi coordinate system (gcj02). ArcGIS is used for visual analysis. ArcGIS is a comprehensive system that users can use to collect, organize, manage, analyze, communicate and publish geographic information. ArcGIS can be used to visualize the tram. Because the coordinates in ArcGIS need to use the WGS84 coordinate system, the coordinates are converted according to the obtained coordinates. After conversion, the coordinates in WGS84 are as shown in Table 2.

[0094] Table 2

[0095]

[0096] Based on the acquired geographic location information, ArcGIS is used for visualization analysis. First, the location information is imported into ArcGIS to obtain the relevant coordinate points, and then the point integration line function is used to connect the tram network map, such as Figure 2 shown.

[0097] The service range of the breakpoint radius of the modern tram in Huai'an City was initially determined to be 800 meters. In order to reduce errors, the original 800-meter service radius was expanded to 1 kilometer, and the POI data type within a one-kilometer radius around the tram in Huai'an City was retrieved through the AutoNavi open platform.

[0098] According to the above POI types, the demand of each POI type was counted, and five POI types with main research characteristics, namely, companies and enterprises, transportation facilities and services, science and education, entertainment, culture and sports, business and residential, and medical care, were selected for research. The site characteristics were studied by acquiring POI data and performing ArcGIS visualization.

[0099] In this example, a total of 31,811 POI data were obtained. To improve research efficiency, Python was used to rasterize the POI data and site data. The results are as follows: Figure 3 The research process is as follows:

[0100] (1) Use the GeoHash algorithm to rasterize the site and nearby POI data;

[0101] (2) Count the POI data in each grid;

[0102] (3) Compare the distance between each grid and the site, and select the grid data within the range as the site POI data.

[0103] Raster processing was performed with a grid interval of 1.2km*0.6km. After GeoHash encoding of each POI data, a total of 89 grid areas were obtained. After counting the POI data contained in each grid, the sum of the grid where each station is located and the number of adjacent grids was taken as the number of POIs at each station.

[0104] Among them, GeoHash algorithm is a way of spatial indexing, which understands the earth as a two-dimensional plane. By encoding the two-dimensional spatial longitude and latitude data into a string, the plane can be decomposed into sub-blocks, and each sub-block has the same code within a certain longitude and latitude range. The GeoHash encoding rule is similar to the binary method. First, the accuracy meets the requirements, and then the longitude and latitude codes are combined. The odd-numbered digits are placed in the latitude, and the even-numbered digits are placed in the longitude to form a new string of binary codes, which are encoded according to Base32. Using GeoHash to establish a spatial index can improve the efficiency of longitude and latitude retrieval of spatial POI data.

[0105] like Figure 4 As shown in the figure, if wtuxhs (region code) is the location of the station, the statistical POI data near the station is the sum of the data in the nine grids of wtuxhm, wtuxht, wtuxhv, wtuxhk, wtuxhs, wtuxhu, wtuxh7, wtuxhe, and wtuxhg. By counting the POI data near the station and obtaining the results, the results are shown in Table 3:

[0106] Table 3

[0107]

[0108]

[0109] As can be seen from the table, the number of POIs at Laobakou Station, Yunhe Square Station, and Huaihai East Road Station account for the top 15%, while the number of POIs at Banzha Station, Sanya Road Station, and Grand Theater Station account for the bottom 15%.

[0110] Demand data collection around the site

[0111] Through the questionnaire survey, the demand for each POI type was counted, and the five most important POI types were selected as influencing factors. They are companies and enterprises, transportation facilities and services, science and education, entertainment, culture and sports, business and residential, and medical care. A total of 221 questionnaires were distributed, and 203 questionnaires were valid. The results are shown in Table 4.

[0112] Table 4

[0113]

[0114] Land use building density classification

[0115] As shown in Table 5, based on the POI data and the total POI data of each site, the POI data of five types of companies and enterprises, transportation facilities and services, science, education, entertainment, culture and sports, commercial and residential, and medical care at each site and the total number of POI data near the site are calculated respectively.

[0116] Table 5

[0117]

[0118]

[0119] There are more POIs in the science, education, entertainment, culture and sports categories around each station, and fewer POIs in the business and residential categories. The total number of POIs within one kilometer of Laobakou Station, Yunhe Square Station, and Huaihai East Road Station is the largest, at 5,998.

[0120] like Figure 5 As shown in the figure, people are divided into five categories according to the five types of POI, namely, commuting, transportation transfer, entertainment and learning, visiting relatives and going home, and medical care. A relevant questionnaire was designed based on the five categories of people, and a total of 367 questionnaires were obtained, of which 358 were valid. According to the questionnaire, among the travel purposes of various types of people, commuting to work accounts for 46%, transportation transfer accounts for 8%, entertainment and learning accounts for 33%, going home and visiting relatives and friends accounts for 10%, and medical care accounts for 3%.

[0121] At the same time Figure 6 As shown in Figure 2, based on the field survey and the time distribution of commuter traffic in Huai'an City, the morning peak period of 7:00-8:00 and the off-peak period of 10:00-13:00 on April 24, 2023 were selected as the survey time periods, and the passenger flow of modern trams in Huai'an City on that day was counted, as shown in Figure 2. Fig. 9 Through analysis, it is found that among the 23 stations of Huai'an Tram, the Stadium Station has the largest passenger flow, while the passenger flow of other stations is relatively small.

[0122] Site Layout

[0123] According to the development characteristics of Huai'an, three commercial circles are set up along the line, namely Huaihai Commercial Circle Center, Shuidukou Wanda Commercial Circle Center, and Chuzhou Wanda Commercial Circle Center. The shortest distance (meters) from each station to the nearby commercial circle is studied through Euclidean distance, as shown in Table 6.

[0124] Table 6

[0125]

[0126] Traffic facilities data around the station

[0127] Since the POI data of Huai'an transportation facilities are mainly based on bus route data, the number of bus route POIs near each station and the number of bus route POIs near all stations are calculated, as shown in Table 7.

[0128] Table 7

[0129]

[0130]

[0131] Distance between adjacent sites

[0132] According to the latitude and longitude distances of each station, they are converted into a meter coordinate system to obtain the distances between adjacent stations, as shown in Table 8.

[0133] Table 8

[0134]

[0135]

[0136] Step 2: Construct an improved breakpoint model to be applied to the site

[0137] Step 2.1: Establish a site service scope influencing factor model and obtain the influencing factor scores:

[0138] like Figure 7 As shown in the figure, the service scope of modern tram stations is affected by many factors. According to the evaluation index system of large passenger transport hubs, the factors affecting the service scope of stations are selected based on the basic principles of authenticity and comprehensiveness of index selection. The influencing factors are divided into two major factors: time and space.

[0139] Time is an important factor affecting the service scope of modern tram stations. Residents' travel time mainly includes arrival and departure time, waiting time and riding time. Different travel times will affect residents' travel needs. When the average travel time is relatively low, residents will give priority to shared bicycles and other means of transportation. Therefore, the travel time of passengers can be analyzed based on residents' travel needs. The interval operation time of modern trams is mainly affected by the distance between stations and the location of stations. At present, the development of modern trams is in its early stages, and the impact of interval operation time is relatively small.

[0140] Spatial factors refer to the impact of the geographical environment around the tram station and the factors of the station itself on the station service range. The surrounding geographical environment includes the land use and building density around the station, supporting service facilities, residents' travel types, transportation connections, etc. Residents' travel types are classified according to the purpose of residents' travel and are an important factor in judging the service range of the station. The connection between trams and other transportation facilities will also affect the service range of tram stations. Station characteristics include factors such as station capacity, station layout, and station type.

[0141] According to actual data and research needs, further selection is made on the factors affecting the service range of the above modern tram stations. The specific selection basis is as follows:

[0142] (1) Data availability. Data availability is related to the source of data, difficulty of obtaining data, and data quality. The assignment of influencing factors needs to be based on various types of data. If data is not available, it can be indirectly reflected through the transformation between influencing factors. Influencing factors with lower importance can be deleted.

[0143] (2) It can reflect the changes of factors affecting the service scope through quantitative analysis. It can define the service scope of trams through objective evaluation rather than subjective judgment.

[0144] In view of the selected basis, this embodiment analyzes the influencing factors based on POI data. A secondary selection is made on the factors affecting modern tram stations, five influencing factors are selected for analysis, and influencing factor models are established respectively:

[0145] Establishment of building density model for land use around the site

[0146] This example is calculated using a land building density model:

[0147]

[0148] HD i =D i ×100

[0149] Among them, D i Indicates the building density of the area where site i is located, POI j Represents the j-th type of POI data, POI sum Indicates the total POI data near the site, HD i represents the land use density score of the ith site; the calculation results are shown in Table 9:

[0150] Table 9

[0151]

[0152]

[0153] Establishment of resident travel type model

[0154] In terms of the types of residents' travel, they can be divided into different types of residents according to their travel needs, as shown in the formula:

[0155] PEO t =TD i ·P t

[0156] Among them, PEO t represents the number of residents of type t traveling, TD i represents the passenger flow of the ith station, P t It indicates the proportion of residents with travel purpose of type t to the total population. According to the passenger flow of each station and the number of residents with each type of travel purpose, the number of residents of each type can be known. According to the resident travel type model, the values ​​of each population type are calculated, as shown in Table 10.

[0157] Table 10

[0158]

[0159]

[0160] Site type model establishment

[0161] In terms of site types, the importance of each site is analyzed based on the relationship between the POI data of each site and the POI data of different types and each site, and each site is divided into first-level sites, second-level sites, and third-level sites, as shown in the formula:

[0162]

[0163] Among them, ST i Represents the weight of the i-th site type, POI j represents the POI data of the i-th station of the j-th POI type, represents the number of all POIs of the jth type, PF j represents the travel demand of the jth type, TD i represents the passenger flow of the ith station, represents the total passenger flow of all stations;

[0164] PF j The travel demand calculation formula is as follows:

[0165]

[0166] Among them, PPF j represents the number of travelers at the i-th station of the j-th type, represents the number of travelers of all POI types at the i-th station, and AC represents the amplification coefficient, which is used to increase the comparability and improve the calculation accuracy;

[0167] Based on the relationship between the POI data of each station and the data of different types of POIs and each station, as well as the travel demand of residents at each station, a station type model is established. The travel demand of each station is calculated according to the travel demand model, as shown in Table 11:

[0168] Table 11

[0169]

[0170] Next, according to the site type model, combined with Table 13, the weight of each site type is calculated, and the relevant data is divided into three sections, with 15% and 85% as the boundaries.

[0171] Depend on Figure 8 As shown in Table 12, the weights of Stadium Station, Huaihai East Road Station, and Shuidukou Station account for the first 15%, and the weights of Shantou Road Station, Nanmen Station, Grand Theater Station, Forest Park Station, and Sanya Road Station account for the last 15%. According to the weights of each station type, the importance of each station is analyzed. Each station is divided into first-level stations, second-level stations, and third-level stations, as shown in Table 12.

[0172] Table 12

[0173]

[0174] Site layout model establishment

[0175] Compare the distances from each station to the center of each major business district, select the shortest distance, and then use the ratio of the sum of the shortest distances from all stations to the center of each major business district and the shortest distance of each station as the station layout weight. The formula is as follows:

[0176]

[0177] Among them, la i Indicates the site layout weight, DIS i represents the shortest distance from site i to the center of each business circle, Hl represents the sum of the shortest distances from all sites to the centers of each business circle. i represents the site layout score of the i-th site, la sum Indicates the weight number of the total site layout; the scores of each site layout are shown in Table 13. As can be seen from the table, Gumokou Station has the highest site layout score, followed by Shuidukou Station, and Banzha Station has the lowest site layout score.

[0178] Table 13

[0179]

[0180] Traffic connection model establishment

[0181] The POI data converted into transportation facilities in terms of transportation connection is studied, and a mathematical model for the influencing factors of transportation connection is obtained. The formula is as follows:

[0182]

[0183] Among them, T i Indicates the transportation connection in the area where station i is located. represents the POI data of transportation facilities at station i, Indicates the total POI data of transportation facilities near all stations, HT i represents the traffic connection score of the i-th station, T sum Indicates the weight of total traffic connections.

[0184] The traffic connection in the area is calculated according to the traffic connection model, and then the traffic connection score is converted. The traffic connection score of each station is shown in Table 14:

[0185] Table 14

[0186]

[0187]

[0188] Steps 2.2-2.3 Establishment and calculation of the breakpoint model and acquisition of attraction scale parameters

[0189] According to the establishment of each influencing factor model and the breaking point model theory, the improved breaking point model of this embodiment is shown in the formula. This model can better complete the calculation of the service range of the tram station.

[0190]

[0191] Among them, R i represents the distance from the breakpoint to site i, r i,i+1 represents the straight-line distance between two stations. It represents the attraction scale of site i, which is derived from various influencing factors.

[0192] According to the establishment of the model of each influencing factor, the attraction scale of the tram station is obtained, and the formula is as follows:

[0193] S i =Hl i ·ST i ·HT i ·∫(PEO t ×HD i ×AC)

[0194] Among them, S i represents the attraction scale of site i, Hl i represents the site layout score of the i-th site, ST i Indicates the weight of the site type, HT i represents the traffic connection score of the ith station. t represents the number of residents of type t traveling, HD i Indicates the land use density score of the ith site. AC is the amplification coefficient, which is used to increase the contrast and improve the calculation accuracy.

[0195] For the integral part, this embodiment normalizes it and assigns points, performs calculations, and obtains the score of the integral part, as shown in Table 17. The scores of the influencing factors of each site are shown in Table 15:

[0196] Table 15

[0197]

[0198] The attraction scale of each site calculated by the influencing factor scores is shown in Table 16:

[0199] Table 16

[0200]

[0201] The obtained attraction scale parameters are input into the improved breakpoint model, and the obtained breakpoint radius is the service range radius data of the site, as shown in Table 17:

[0202] Table 17

[0203]

[0204] Step 3: Service scope revision

[0205] Service scope results analysis

[0206] In order to verify the authenticity and reliability of the results, this embodiment studies and corrects the data obtained from each site. The service range of each site is sorted and segmented from high to low, and a visualization diagram is established, such as Fig. 9 As shown in the figure, the service ranges of Banzha Station, Wushahe Station, and Gumokou Station are all over 800 meters, accounting for the first 15%. However, the service ranges of Grand Theater Station, Huaxi Road Station, Yunhe Square Station, and Administrative Service Center Station are less than 100 meters, accounting for the last 15%. Therefore, it is necessary to revise the service ranges of these stations.

[0207] Service scope correction model establishment

[0208] In order to correct the service range of the station to be corrected, the correction coefficient can be obtained from the correction model. Therefore, this embodiment establishes a correction model based on the POI data of each station and the adjacent distance information. The formula is as follows:

[0209]

[0210] In the formula, R_c i Indicates the revised service scope, R_end i The service range is finally optimized. According to the field statistics, the service range of Huai'an tram is about 800 meters. Therefore, the upper limit of the service range is set to 1000 meters in this embodiment.

[0211] According to the revised model, the revised service ranges of Banzha Station, Wushahe Station and Gumokou Station are shown in Table 18:

[0212] Table 18

[0213]

[0214] The revised service scopes of Grand Theater Station, Huaxi Road Station, Yunhe Square Station, and Government Affairs Center Station are shown in Table 19:

[0215] Table 19

[0216]

[0217] After correction, all stations are within the service range. The service range of Banzha Station is 775.32 meters, Wushahe Station is 703.16 meters, Gumokou Station is 498.59 meters, Grand Theater Station is 279.14 meters, Huaxi Road Station is 494.07 meters, Canal Square Station is 147.71 meters, and the service range of Government Affairs Center Station is 321.29 meters.

[0218] Revised Conclusions and Visualizations

[0219] The revised service scope is shown in Table 20:

[0220] Table 20

[0221]

[0222] According to the results in Table 22, the service range of tram stations was visualized using ArcGIS. The results are as follows: Fig.10 As shown in the figure, the revised site service range is more reasonable, and the over-large and under-small service ranges are adjusted. Based on the revised data, the final result of this embodiment is as follows: Fig.11 shown.

Claims

1. A method for determining the service range of a modern tram station based on POI data, characterized in that: The method comprises the following steps: S1 obtains POI data about the site location and its surrounding environment, preprocesses and constructs a data set; S2 constructs an improved breakpoint model applied to the site; S2.1 Establish a site service scope influencing factor model and obtain the influencing factor scores; S2.2 Using the scores of each influencing factor, establish an attraction scale model and obtain the attraction scale parameters of the improved breakpoint model; S2.3 Calculate the service range interval corresponding to the data set by improving the breakpoint model; S3 establishes a service range correction model, corrects the service range of the site to be corrected, obtains the corrected service range interval and visualizes it.

2. The method for determining the service range of a modern tram station based on POI data according to claim 1, characterized in that: The steps for S1 preprocessing and constructing the dataset are as follows: Use GeoHash algorithm to rasterize the site and nearby POI data; Count the POI data in each grid; Compare the distance between each grid and the site, and select the grid data within the range as the site POI data; Raster processing was performed with a grid interval of 1.2km*0.6km. After GeoHash encoding of each POI data, a total of 89 grid areas were obtained. After counting the POI data contained in each grid, the sum of the grid where each station is located and the number of adjacent grids was taken as the number of POIs at each station.

3. The method for determining the service range of a modern tram station based on POI data according to claim 1, characterized in that: The steps of constructing the S2 improved breakpoint model include: The breakpoint of the attraction range between the two cities is expressed as: Among them, it means D x The distance from the breakpoint to city x, d xy represents the straight-line distance between two cities, P x and P y represents the population of cities x and y; The original breakpoint model uses the city population to indirectly represent the city's attractiveness and size. Based on the study of factors affecting the service scope of a site, an improved breakpoint model applied to sites is proposed using an analogy method: Among them, R i represents the distance from the breakpoint to site i, r i,i+1 represents the straight-line distance between two stations. It represents the attraction scale of site i, which is derived from the scores of various influencing factors.

4. The method for determining the service range of a modern tram station based on POI data according to claim 1 or 3, characterized in that: The target influencing factors obtained by the site service scope influencing factor model in S3 are divided into time factors and space factors: Time factors include: arrival and departure time, waiting time and riding time; Spatial factors include: land use and building density around the station, supporting service facilities, residents’ travel types, and transportation connections; Based on the objective assessment of the changes in the factors affecting the service scope reflected by data availability and quantitative analysis, the influencing factors are screened again, including: land use building density, resident travel type, station type, station layout and transportation connection. The station service scope influencing factor model is established based on each influencing factor as follows: Land use building density As for the building density of land use, since the building density is closely related to the number of POIs in the local area, it is converted into POI research, and a mathematical model for the factors affecting the building density of land use is obtained, as shown in the formula: HD i =D i ×100 Among them, D i Indicates the building density of the area where site i is located, POI j Represents the j-th type of POI data, POI sum Indicates the total POI data near the site, HD i represents the land use density score of the ith site; Residents' travel types In terms of the types of residents' travel, they can be divided into different types of residents according to their travel needs, as shown in the formula: PEO t =TD i ·P t Among them, PEO t represents the number of residents of type t traveling, TD i represents the passenger flow of the ith station, P t It indicates the proportion of residents whose travel purpose is type t to the total population; Site Type In terms of site types, the importance of each site is analyzed based on the relationship between the POI data of each site and the POI data of different types and each site, and each site is divided into first-level sites, second-level sites, and third-level sites, as shown in the formula: Among them, ST i Represents the weight of the i-th site type, POI j represents the POI data of the i-th station of the j-th POI type, represents the number of all POIs of the jth type, PF j represents the travel demand of the jth type, TD i represents the passenger flow of the ith station, represents the total passenger flow of all stations; PF j The travel demand calculation formula is as follows: Among them, PPF j represents the number of travelers at the i-th station of the j-th type, represents the number of travelers of all POI types at the i-th station, and AC represents the amplification coefficient, which is used to increase the comparability and improve the calculation accuracy; Site Layout Compare the distances from each site to the center of each major business district, select the shortest distance, and then use the ratio of the sum of the shortest distances from all sites to the center of each major business district and the shortest distance of each site as the site layout weight. The formula is as follows: Among them, la i Indicates the site layout weight, DIS i represents the shortest distance from site i to the center of each business circle, Hl represents the sum of the shortest distances from all sites to the centers of each business circle. i represents the site layout score of the i-th site, la sum The weight number representing the total site layout; Transportation The POI data converted into transportation facilities in terms of transportation connection is studied, and a mathematical model for the influencing factors of transportation connection is obtained. The formula is as follows: Among them, T i Indicates the transportation connection in the area where station i is located. represents the POI data of transportation facilities at station i, Indicates the total POI data of transportation facilities near all stations, HT i represents the traffic connection score of the i-th station, T sum Indicates the weight of total traffic connections.

5. The method for determining the service range of a modern tram station based on POI data according to claim 4, characterized in that: By establishing the models of various influencing factors and obtaining the scores of influencing factors, the attraction scale of tram stations is calculated. The calculation formula of attraction scale is as follows: S i =Hl i ·ST i ·HT i ·∫(PEO t ×HD i ×AC) Among them, S i represents the attraction scale of site i, Hl i represents the site layout score of the i-th site, ST i Indicates the weight of the site type, HT i represents the traffic connection score of the i-th station, PEO t represents the number of residents of type t traveling, HD i It represents the land use density score of the ith site, and AC is the amplification coefficient, which is used to increase the contrast and improve the calculation accuracy.

6. The method for determining the service range of a modern tram station based on POI data according to claim 1, characterized in that: The detailed steps of S3 are: In order to correct the service range of the station to be corrected, the correction coefficient can be obtained from the correction model. A correction model based on the POI data of each station and the adjacent distance information is established. The formula is as follows: In the formula, R_c i represents the revised service scope, r i,i+1 Represents the straight-line distance between two sites.

7. The method for determining the service range of a modern tram station based on POI data according to claim 1, characterized in that: S3 visualizes the revised service range interval through ArcGIS and draws a visualization map of the tram station service range for subsequent scheduling research.

Images