CN113240265B - Urban space division method based on multi-mode traffic data - Google Patents
Urban space division method based on multi-mode traffic data Download PDFInfo
- Publication number
- CN113240265B CN113240265B CN202110508261.4A CN202110508261A CN113240265B CN 113240265 B CN113240265 B CN 113240265B CN 202110508261 A CN202110508261 A CN 202110508261A CN 113240265 B CN113240265 B CN 113240265B
- Authority
- CN
- China
- Prior art keywords
- data
- loc
- bicycle
- cluster
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005070 sampling Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000000638 solvent extraction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 235000019580 granularity Nutrition 0.000 description 6
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G06Q50/40—
Abstract
The invention discloses a city space dividing method based on multi-mode traffic data, which comprises the steps of firstly acquiring order data of a multi-mode traffic system, and counting start and stop point coordinates and start and stop time of each order; then, considering that the spatial distribution mode of the network taxi data and the shared bicycle data in the city is obviously different from that of subway data, hierarchical clustering is carried out on the first two traffic data, so that the number of the sampable points of the three traffic data is guaranteed to be similar, and the complexity of subsequent operation is reduced; then, uniformly sampling start and stop points of three order data, performing KD-Tree division on the urban geographic space by using the sampling points, and counting actual order quantity contained in each area; and finally, for each divided area, taking each subway station in the area as a center, and matching shared bicycle and network taxi data in an reachable range so as to realize multi-granularity urban space division. The method can effectively realize the uniform urban space division of the multi-mode traffic data and provide data support for multi-mode urban traffic situation identification.
Description
Technical Field
The invention belongs to the technical field of big data processing, and particularly relates to a city space division method.
Background
Traffic situation is a description of the state and trend of operation of vehicles in a traffic network system. I.e. the instant status and development trend of the vehicle operating environment in a certain time or period of time and in a certain range of traffic network systems. And the urban traffic situation is accurately, objectively analyzed in real time, so that the urban traffic layout is optimized, the traffic jam condition is found in time, and the travel mode of residents is mined. The primary work of traffic situation analysis is to reasonably divide urban areas so as to realize dynamic analysis of urban traffic situations with different granularities based on division results. The space division method can be specifically described as: knowing that the presence set P in the urban space contains n data points, for a given partitioning requirement, the urban space is partitioned into a subspace set Q of capacity m, such that for data point P i E P, all have unique subregion q i E Q, where Q i Comprises p i . Conventional geographic information systems typically express attributes of data using an equal-scale approach to describe information such as spatial features, temporal features, etc. of the data. However, in urban traffic environment, traffic running situation is affected by geographical location, functional area, time and other factors, and the difference between different areas is significant. For example, in Beijing city, traffic flow in four rings is densely distributed; outside the four rings, traffic flows are mainly distributed radially along the main road, and the traffic flows are obviously lower than those in the central urban area. In this case, simply dividing the grid area is not suitable for an urban traffic environment in which the data distribution situation is complicated, and the spatial characteristics of the urban functional area are not considered. Meanwhile, due to the continuous development of urban traffic, the traffic travel mode of residents is gradually changed from a single mode to a diversified and compounded multi-mode travel mode. Under the multi-mode traffic environment, space-time correlation and difference exist among the multi-mode traffic systems, and the different traffic systems jointly reflect the complete traffic situation of the city. In addition, as the urban geographic space is wide in range and the traffic situation operation modes of different functional areas are obviously different, a multi-granularity traffic situation modeling method is needed in a modern environment: on one hand, coarse-grained traffic situation and migration relationship exist among all divided areas of the city, and on the other hand, traffic is carried outThere are traffic situations with fine granularity inside the area, such as transfer relations of different traffic systems in the reachable range.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a city space division method based on multi-mode traffic data, which comprises the steps of firstly acquiring order data of a multi-mode traffic system, and counting start and stop point coordinates and start and stop time of each order; then, considering that the spatial distribution mode of the network taxi data and the shared bicycle data in the city is obviously different from that of subway data, hierarchical clustering is carried out on the first two traffic data, so that the number of the sampable points of the three traffic data is guaranteed to be similar, and the complexity of subsequent operation is reduced; then, uniformly sampling start and stop points of three order data, performing KD-Tree division on the urban geographic space by using the sampling points, and counting actual order quantity contained in each area; and finally, for each divided area, taking each subway station in the area as a center, and matching shared bicycle and network taxi data in an reachable range so as to realize multi-granularity urban space division. The method can effectively realize the uniform urban space division of the multi-mode traffic data and provide data support for multi-mode urban traffic situation identification.
The technical scheme adopted by the invention for solving the technical problems comprises the following steps:
step 1: acquiring order data of a multi-mode traffic system of a designated city, wherein the order data comprise three types of traffic system order data, namely shared bicycle order data, network about bicycle order data and subway order data;
the three order data comprise start-stop point coordinates and start-stop time information;
the three order data have different spatial distribution modes, the network about vehicle order data and the shared bicycle order data are distributed in a city space in a discrete mode, and subway orders are distributed in a centralized mode at a fixed site;
uniformly converting start-stop coordinates of each order data into a WGS8 coding format;
step 2: the order check-in data sets of three traffic systems are defined, as follows: check-in data sets respectively representing order data of shared bicycles, subways and network buses; wherein n is b 、n s And n w The number of sign-on points of the shared bicycle, the subway and the network about bicycle is respectively;
check-in data for the i-th check-in point: loc *,i ＝[Loc *,i,lng ，Loc *,i,lat， Loc *,i,time ，Loc *,i,type ，Loc *，i,weight ]The data in the matrix respectively represent longitude, latitude, order time, sign-in point type and weight of sign-in data, wherein the sign-in point type comprises a starting point and an ending point, and subscript is bicycle, subway, wyc;
setting Loc bicycle,i,weight ＝1，Loc wyc,i，weight ＝1；
Step 3: hierarchical clustering processing of shared bicycle and network about bicycle order sign-in data;
step 3-1: respectively constructing a distance matrix X between sign-to-point of net appointment vehicle and shared single vehicle w And X b ：
The elements in the two matrixes are the distances between sign-in points;
step 3-2: inputting a distance matrix and an order signing data set into a hierarchical clustering algorithm, dividing all signing points into K clusters by taking the minimum distance between each signing point and the cluster center to which the signing point belongs as an objective function, wherein each signing point belongs to one cluster;
step 3-3: adopting a bottom-up method, taking each sign-on point as an independent class cluster to form a class cluster C, wherein the distance between two class clusters is expressed as the average value of the distances between all sign-on points in one class cluster and all sign-on points in the other class cluster;
step 3-4: selecting two class clusters with the smallest distance, and merging the two class clusters into a new class cluster; recalculating the distance between the class clusters in the class cluster C;
step 3-5: continuously repeating the steps 3-4 until the number of the class clusters in the set C is equal to K; obtaining a network about vehicle clustering set C wyc ＝{C wyc，1 ，C wyc，2 ，...，C wyc,K Cluster set C of } and shared bicycle bicycle ＝{C bicycle,1 ，C bicycle,2 ，...，C bicycle,K -a }; for the j-th cluster: c (C) +，j ＝[C +，i，lng ，C +，i，lat ，C +,i,weight ]The data in the matrix respectively represent longitude of a clustering center, latitude of the clustering center and weight, and subscript+ is wyc or one of the bicycles;
step 4: uniformly sampling the multi-mode traffic data;
clustering set C for network-bound vehicles wyc Cluster set C of shared bicycle bicycle And subway order check-in dataset Loc subway Uniformly sampling, wherein the sampling proportion is p; obtaining a sampling data set Loc ' = { Loc ' for KD-Tree partitioning ' 1 ，Loc′ 2 ，...，Loc′ M M=p (2k+n) s ) Sample data Loc' i ＝[Loc′ i，lng ，Loc ′i，lat ，Loc′ i，weight ，Loc′ i，type ]The data in the matrix are respectively sampling point longitude, latitude, weight and type, and the type is one of a network bus, a sharing bus and a subway;
step 5: a spatial KD-Tree dividing method based on a sampling data set;
step 5-1: setting the initial set of KD-Tree dividing regions as Region 0 ＝{Loc′}；
Step 5-2: for divided region setk=0, 1,2,3, space division based on latitude;
for the followingFor all the sampled data, the median is calculated according to ascending order of latitude>All latitude coordinates are less than +.>Is divided into left subtree, i.eWherein->All latitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-3: for divided region setk=1, 2,3, space division based on longitude;
for the followingFor all the sampled data in the above order, calculate the median +.>All longitude coordinates are less than +.>Is divided into left subtree, i.eWherein->1≤j≤M 2k,i The method comprises the steps of carrying out a first treatment on the surface of the All longitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-4: repeating the step 5-2 and the step 5-3 until the number of the divided areas is the designated number N; the KD-Tree partitioning result is Region depth ＝{region depth,1 ，...，region depth,N Depth is the depth of the tree;
step 5-5 order check-in dataset Loc of multimode transportation system bicycle 、Loc subway 、Loc wyc And dividing the result Region depth Matching is carried out; obtaining the division result of three traffic mode traffic data by using a space KD-Tree method: cluster subway 、Cluster wyc 、Cluster bicycle Respectively representing subway check-in data sets and network contracts contained in each divided areaA vehicle check-in data set, a shared bicycle check-in data set; wherein Cluster * ＝{Cluster *，1 ，Cluster *，2 ，...，Cluster *,N }，* Bicycle, subway, wyc is one of them;
step 6: fine granularity matching of the multi-mode traffic data;
then for each divided region depth,i Matching all the sharing bicycles and the network bus sign-on points in the area with subway stations in the distance to obtain multimode traffic system sign-on point matching sets in each divided area: match= { Match 1 ，Match 2 ，...，Match N -a }; matching case for the i-th divided regionmatch i,j And the shared bicycle and network about bicycle order data set which can be transferred around each subway station is contained in the divided area.
Preferably, k=300, p=35%, depth=7, n=128, distance=500 m.
The beneficial effects of the invention are as follows:
the invention relates to a city space division method based on multi-mode traffic data, which is used for carrying out multi-granularity division on a city area under a multi-mode traffic environment, so that the uniform division of the city space of the multi-mode traffic data can be effectively realized, the variance and the information entropy of a division result are reduced, and data support is provided for multi-mode city traffic situation identification.
Drawings
FIG. 1 is a diagram of the system architecture of the method of the present invention.
FIG. 2 is a flow chart of a hierarchical clustering method for point-of-arrival data.
Fig. 3 is a schematic diagram of a spatial KD-Tree partitioning method according to the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
As shown in fig. 1, a method for dividing urban space based on multi-mode traffic data includes the following steps:
step 1: acquiring order data of a multi-mode traffic system of a designated city, wherein the order data comprise three types of traffic system order data, namely shared bicycle order data, network about bicycle order data and subway order data;
the three order data comprise start-stop point coordinates and start-stop time information;
the three order data have different spatial distribution modes, the network about vehicle order data and the shared bicycle order data are distributed in a city space in a discrete mode, and subway orders are distributed in a centralized mode at a fixed site;
in order to facilitate the processing of the multi-mode traffic data, the start and stop coordinates of each order data are uniformly converted into a WGS8 coding format;
step 2: the order check-in data sets of three traffic systems are defined, as follows: check-in data sets respectively representing order data of shared bicycles, subways and network buses; wherein n is b 、n s And n w The number of sign-on points of the shared bicycle, the subway and the network about bicycle is respectively;
check-in data for the i-th check-in point: loc *,i ＝[Loc *，i，lng ，Loc *,i,lat ，Loc *,i,time ，Loc *,i,type ，Loc *,i,weight ]The data in the matrix respectively represent longitude, latitude, order time, sign-in point type and weight of sign-in data, the sign-in point type comprises a starting point and an ending point, the weight indicates the occurrence frequency, and the subscript is bicycle, subway, wyc;
setting Loc bicycle,i,weight ＝1，Loc wyc,i,weight ＝1；
Step 3: as shown in fig. 2, hierarchical clustering of shared bicycle and network about bicycle order check-in data;
the spatial distribution mode of the check-in data of the network bus and the sharing bus is obviously different from that of the subway. In this case, direct spatial KD-Tree partitioning results in an excessive difference in the number and average weights of the three check-in data. Therefore, hierarchical clustering is firstly carried out on the first two kinds of traffic data, so that the number of the three kinds of traffic data sampling points is guaranteed to be similar, and the complexity of subsequent operation is reduced.
Step 3-1: respectively constructing a distance matrix X between sign-to-point of net appointment vehicle and shared single vehicle w And X b ：
The elements in the two matrixes are the distances between sign-in points;
step 3-2: inputting a distance matrix and an order signing data set into a hierarchical clustering algorithm, dividing all signing points into K=300 clusters by taking the minimum distance between each signing point and the cluster center to which the signing point belongs as an objective function, wherein each signing point belongs to one cluster;
step 3-3: adopting a bottom-up method, taking each sign-on point as an independent class cluster to form a class cluster C, wherein the distance between two class clusters is expressed as the average value of the distances between all sign-on points in one class cluster and all sign-on points in the other class cluster;
step 3-4: selecting two class clusters with the smallest distance, and merging the two class clusters into a new class cluster; recalculating the distance between the class clusters in the class cluster C;
step 3-5: continuously repeating the steps 3-4 until the number of the class clusters in the set C is equal to K; obtaining a netCar reduction clustering set C wyc ＝{C wyc，1 ，C wyc，2 ，...，C wyc,K Cluster set C of } and shared bicycle bicycle ＝{C bicycle,1 ，C bicycle,2 ，...，C bicycle,K -a }; for the j-th cluster: c (C) +，j ＝[C +，i，lng ，C +，i，lat ，C +,i,weight ]The data in the matrix respectively represent longitude of a clustering center, latitude of the clustering center and weight, the weight refers to data quantity contained in the clusters, and subscript+ wyc or dicyclohexyl;
step 4: uniformly sampling the multi-mode traffic data;
clustering set C for network-bound vehicles wyc Cluster set C of shared bicycle bicycle And subway order check-in dataset Loc subway Uniformly sampling, wherein the sampling proportion is p=35%; obtaining a sampling data set Loc ' = { Loc ' for KD-Tree partitioning ' 1 ，Loc′ 2 ，...，Loc′ M M=p (2k+n) s ) Sample data Loc' i ＝[Loc′ i，lng ，Loc′ i，lat ，Loc′ i，weight ，Loc′ i，type ]The data in the matrix are respectively sampling point longitude, latitude, weight and type, and the type is one of a network bus, a sharing bus and a subway;
step 5: as shown in fig. 3, the spatial KD-Tree partitioning method based on the sampled data set;
dividing a sampling data set Loc' based on a spatial KD-Tree algorithm to realize a city region dividing method based on multi-mode traffic data, and dividing order data Loc of a multi-mode traffic system bicycle 、Loc subway 、Loc wyc Matching with KD-Tree division result set Region. KD-Tree (k-dimensional Tree) is a data structure that divides a set of points in a data space, i.e., a complete binary Tree with a division amount of N=2 depth Depth=7 is the depth of the tree; when KD-Tree is constructed based on the sampling data set, the data points are uniformly divided into rectangular areas represented by leaf nodes, so that urban space division is performed;
step 5-1: setting the initial set of KD-Tree dividing regions as Region 0 ＝{Loc′}；
Step 5-2: for divided region setk=0, 1,2,3, space division based on latitude;
for the followingFor all the sampled data, the median is calculated according to ascending order of latitude>All latitude coordinates are less than +.>Is divided into left subtree, i.eWherein->All latitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-3: for divided region setk=1, 2,3, space based on longitudeDividing;
for the followingFor all the sampled data in the above order, calculate the median +.>All longitude coordinates are less than +.>Is divided into left subtree, i.eWherein->1≤j≤M 2k,i The method comprises the steps of carrying out a first treatment on the surface of the All longitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-4: repeating steps 5-2 and 5-3 until the number of divided areas is a specified number n=128; the KD-Tree partitioning result is Region depth ＝{region depth,1 ，...，region depth,N }；
Step 5-5: signing orders of a multimodal transportation system into a dataset Loc bicycle 、Loc subway 、Loc wyc And dividing the result Region depth Matching is carried out; for each check-in data loc i There must be a unique region depth,j So that loc i ∈region depth,j The method comprises the steps of carrying out a first treatment on the surface of the Obtaining the division result of three traffic mode traffic data by using a space KD-Tree method: cluster subway 、Cluster wyc 、Cluster bicycle The subway sign-in data set, the network appointment vehicle sign-in data set and the sharing bicycle sign-in data set contained in each divided area are respectively represented; wherein Cluster * ＝{Cluster *，1 ，Cluster *,2 ，...，Cluster *,N }，* Bicycle, subway, wyc is one of them;
step 6: fine granularity matching of the multi-mode traffic data;
in consideration of the fact that in a real urban traffic environment, coarse-granularity traffic situations such as traffic migration quantity of an interval exist, and meanwhile, fine-granularity transfer and competition relations among different traffic systems in a divided area exist. In order to represent multiple granularity traffic situations in the traffic system at the same time, matching is performed on the order data in each divided area, which is close to the space. According to the method, subway order data are intensively distributed in subway stations, and the correlation between a subway system and other traffic systems is high, so that the shared bicycle and network bus data in each divided area are matched with the subway stations in the distance range; then for each divided region depth,i Matching all the sharing single vehicles and network contract vehicle sign-on points in the region with subway stations in the distance=500m respectively to obtain multimode traffic system sign-on point matching sets in each divided region respectively: match= { Match 1 ，Match 2 ，...，Match N -a }; matching case for the i-th divided region match i,j Sharing of the surrounding of each subway station included in the divided areaSingle car, net car order data sets.
The multi-mode traffic system sign-in data are matched, so that the traffic situation of fine granularity such as relevance among traffic systems can be found.
Claims (2)
1. A city space division method based on multi-mode traffic data is characterized by comprising the following steps:
step 1: acquiring order data of a multi-mode traffic system of a designated city, wherein the order data comprise three types of traffic system order data, namely shared bicycle order data, network about bicycle order data and subway order data;
the three order data comprise start-stop point coordinates and start-stop time information;
the three order data have different spatial distribution modes, the network about vehicle order data and the shared bicycle order data are distributed in a city space in a discrete mode, and subway orders are distributed in a centralized mode at a fixed site;
uniformly converting start-stop coordinates of each order data into a WGS8 coding format;
step 2: the order check-in data sets of three traffic systems are defined, as follows: check-in data sets respectively representing order data of shared bicycles, subways and network buses; wherein n is b 、n s And n w The number of sign-on points of the shared bicycle, the subway and the network about bicycle is respectively;
check-in data for the f-th check-in point: loc *,i ＝[Loc *,i,lng ，Loc *,i,lat ，Loc *,i,time ，Loc *,i,type ，Loc *,i,weight ]The data in the matrix respectively represent the number of check-insAccording to longitude, latitude, order time, type of check-in point and weight, the type of the check-in point comprises a starting point and an end point, and subscript is bicycle, subway, wyc;
setting Loc bicycle,i,weight ＝1，Loc wyc,i,weight ＝1；
Step 3: hierarchical clustering processing of shared bicycle and network about bicycle order sign-in data;
step 3-1: respectively constructing a distance matrix X between sign-to-point of net appointment vehicle and shared single vehicle w And X b ：
The elements in the two matrixes are the distances between sign-in points;
step 3-2: inputting a distance matrix and an order signing data set into a hierarchical clustering algorithm, dividing all signing points into K clusters by taking the minimum distance between each signing point and the cluster center to which the signing point belongs as an objective function, wherein each signing point belongs to one cluster;
step 3-3: adopting a bottom-up method, taking each sign-on point as an independent class cluster to form a class cluster C, wherein the distance between two class clusters is expressed as the average value of the distances between all sign-on points in one class cluster and all sign-on points in the other class cluster;
step 3-4: selecting two class clusters with the smallest distance, and merging the two class clusters into a new class cluster; recalculating the distance between the class clusters in the class cluster C;
step 3-5: continuously repeating the steps 3-4 until the number of the class clusters in the set C is equal to K; obtaining a network about vehicle clustering set C wyc ＝{C wyc，1 ，C wyc，2 ，...，C wyc,K Cluster set C of } and shared bicycle bicycle ＝{C bicycle,1 ，C bicycle,2 ，...，C bicycle,K -a }; for the j-th cluster: c (C) +，j ＝[C +，i，lng ，C +，i，lat ，C +,i,weight ]The data in the matrix respectively represent longitude of a clustering center, latitude of the clustering center and weight, and subscript+ is wyc or one of the bicycles;
step 4: uniformly sampling the multi-mode traffic data;
clustering set C for network-bound vehicles wyc Cluster set C of shared bicycle bicycle And subway order check-in dataset Loc subway Uniformly sampling, wherein the sampling proportion is p; obtaining a sampling data set Loc ' = { Loc ' for KD-Tree partitioning ' 1 ，Loc′ 2 ，...，Loc′ M M=p (2k+n) s ) Sample data Loc' i ＝[Loc′ i，lng ，Loc′ i，lat ，Loc′ i，weight ，Loc′ i，type ]The data in the matrix are respectively sampling point longitude, latitude, weight and type, and the type is one of a network bus, a sharing bus and a subway;
step 5: a spatial KD-Tree dividing method based on a sampling data set;
step 5-1: setting the initial set of KD-Tree dividing regions as Region 0 ＝{Loc′}；
Step 5-2: for divided region set Space division is performed based on latitude;
for the followingFor all the sampled data, the median is calculated according to ascending order of latitude>All latitude coordinates are less than +.>Is divided into left subtree, i.eWherein->All latitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-3: for divided region setk=1, 2,3, space division based on longitude;
for the followingFor all the sampled data in the above order, calculate the median +.>All longitude coordinates are less than +.>Is divided into left subtree, i.eWherein->All longitude coordinates are equal to or greater than +.>Is divided into the right subtree, i.e +.> Wherein->
Step 5-4: repeating the step 5-2 and the step 5-3 until the number of the divided areas is the designated number N; the KD-Tree partitioning result is Region depth ＝{region depth,1 ，...，region depth,N Depth is the depth of the tree;
step 5-5 order check-in dataset Loc of multimode transportation system bicycle 、Loc subway 、Loc wyc And dividing the result Region depth Matching is carried out; obtaining the division result of three traffic mode traffic data by using a space KD-Tree method: cluster subway 、Cluster wyc 、Cluster bicycle The subway sign-in data set, the network appointment vehicle sign-in data set and the sharing bicycle sign-in data set contained in each divided area are respectively represented; wherein Cluster * ＝{Cluster *，1 ，Cluster *，2 ，...，Cluster *，N }， * Bicycle, subway, wyc is one of them;
step 6: fine granularity matching of the multi-mode traffic data;
then for each divided region depth,i Matching all the sharing bicycles and the network bus sign-on points in the area with subway stations in the distance to obtain multimode traffic system sign-on point matching sets in each divided area: match= { Match 1 ，Match 2 ，...，Match N -a }; matching case for the f-th divided regionmatch i,j And the shared bicycle and network about bicycle order data set which can be transferred around each subway station is contained in the divided area.
2. The urban space division method based on multi-mode traffic data according to claim 1, wherein k=300, p=35%, depth=7, n=128, distance=500 m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110508261.4A CN113240265B (en) | 2021-05-11 | 2021-05-11 | Urban space division method based on multi-mode traffic data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110508261.4A CN113240265B (en) | 2021-05-11 | 2021-05-11 | Urban space division method based on multi-mode traffic data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113240265A CN113240265A (en) | 2021-08-10 |
| CN113240265B true CN113240265B (en) | 2023-10-27 |
Family
ID=77133127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110508261.4A Active CN113240265B (en) | 2021-05-11 | 2021-05-11 | Urban space division method based on multi-mode traffic data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240265B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114238491B (en) * | 2021-12-02 | 2024-02-13 | 西北工业大学 | Heterogeneous graph-based multi-mode traffic operation situation association rule mining method |
| CN114418328A (en) * | 2021-12-27 | 2022-04-29 | 宁波诺丁汉大学 | City functional area planning method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| WO2019242520A1 (en) * | 2018-06-20 | 2019-12-26 | 菜鸟智能物流控股有限公司 | Logistics distribution station planning method, and server |
| CN112597402A (en) * | 2020-12-17 | 2021-04-02 | 东南大学 | Rail transit transfer shared single-vehicle influence area defining method based on multi-source data |
| CN112734532A (en) * | 2021-01-15 | 2021-04-30 | 东南大学 | Commuting behavior identification method based on shared electric bicycle borrowing and returning point data |
-
2021
- 2021-05-11 CN CN202110508261.4A patent/CN113240265B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| WO2019242520A1 (en) * | 2018-06-20 | 2019-12-26 | 菜鸟智能物流控股有限公司 | Logistics distribution station planning method, and server |
| CN112597402A (en) * | 2020-12-17 | 2021-04-02 | 东南大学 | Rail transit transfer shared single-vehicle influence area defining method based on multi-source data |
| CN112734532A (en) * | 2021-01-15 | 2021-04-30 | 东南大学 | Commuting behavior identification method based on shared electric bicycle borrowing and returning point data |
Non-Patent Citations (2)
| Title |
|---|
| Urbanization patterns and their impacts on social restructuring of urban space in Chilean mid-cities: The case of Los Angeles, Central Chile;Gerardo;EI;全文 * |
| 基于站点兴趣点的城市轨道交通站点分类方法;王焕栋;马红伟;;交通与运输(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113240265A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359162B (en) | GIS-based school site selection method | |
| CN113240265B (en) | Urban space division method based on multi-mode traffic data | |
| CN110555544B (en) | Traffic demand estimation method based on GPS navigation data | |
| CN108388970B (en) | Bus station site selection method based on GIS | |
| CN107656987B (en) | Subway station function mining method based on L DA model | |
| CN113763700B (en) | Information processing method, information processing device, computer equipment and storage medium | |
| CN110990661B (en) | Region of interest access extraction method based on road network constraint and density clustering | |
| CN115062873B (en) | Traffic travel mode prediction method and device, storage medium and electronic device | |
| CN111881939B (en) | Shared single-vehicle parking area layout method based on clustering algorithm | |
| Yang et al. | Multiagent reinforcement learning-based taxi predispatching model to balance taxi supply and demand | |
| Chen et al. | An analysis of movement patterns between zones using taxi GPS data | |
| CN111581325A (en) | K-means station area division method based on space-time influence distance | |
| CN114723596A (en) | Urban functional area identification method based on multi-source traffic travel data and theme model | |
| CN113573238B (en) | Method for identifying trip passenger trip chain based on mobile phone signaling | |
| CN109684604B (en) | City dynamic analysis method based on context-aware nonnegative tensor decomposition | |
| CN109740957A (en) | A kind of urban traffic network node-classification method | |
| CN114238491B (en) | Heterogeneous graph-based multi-mode traffic operation situation association rule mining method | |
| Schoier et al. | Individual movements and geographical data mining. Clustering algorithms for highlighting hotspots in personal navigation routes | |
| CN108960684B (en) | Public transport passenger closed travel chain mining method based on incomplete track segment | |
| CN108764518B (en) | Traffic resource dynamic optimization method based on big data of Internet of things | |
| Tan et al. | Statistical analysis and prediction of regional bus passenger flows | |
| CN116132998A (en) | Urban edge server deployment method based on intersection centrality | |
| Zhao et al. | Analysis of Spatial Distribution of China's station-free bike-sharing by Clustering Algorithms | |
| CN114579748A (en) | Method for constructing autonomous traffic system functional architecture | |
| CN114999162A (en) | Road traffic flow obtaining method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |