CN112784423A - Urban area feature analysis method based on complex network - Google Patents

Urban area feature analysis method based on complex network Download PDF

Info

Publication number
CN112784423A
CN112784423A CN202110115945.8A CN202110115945A CN112784423A CN 112784423 A CN112784423 A CN 112784423A CN 202110115945 A CN202110115945 A CN 202110115945A CN 112784423 A CN112784423 A CN 112784423A
Authority
CN
China
Prior art keywords
grid
getting
correlation
grids
network
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.)
Pending
Application number
CN202110115945.8A
Other languages
Chinese (zh)
Inventor
魏志成
于娜
路佳玲
田多
李美暄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hebei Normal University
Original Assignee
Hebei Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hebei Normal University filed Critical Hebei Normal University
Priority to CN202110115945.8A priority Critical patent/CN112784423A/en
Publication of CN112784423A publication Critical patent/CN112784423A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an urban area feature analysis method based on a complex network, which comprises the steps of urban grid division, grid network establishment and grid clustering. The method obtains a grid network by calculating the correlation among grids, and then utilizes the Louvain algorithm to perform clustering to obtain a new urban clustering area. The invention can discover the implicit complex relationship between the urban areas and simultaneously provides a new idea for planning the urban areas, knowing the active mode of the areas and knowing the functions of the urban areas.

Description

Urban area feature analysis method based on complex network
Technical Field
The invention relates to an urban area feature analysis method, in particular to an urban area feature analysis method based on a complex network, and belongs to the technical field of urban area clustering.
Background
Urban areas are closely related to human life, and urban areas are the carriers by which humans live. With the continuous acceleration of the industrialization process and the urbanization process, the relation between urban areas changes, and the situation of mutual coordination and mutual restriction is formed.
The city area relationship may be analyzed using relevant data for the city area. Dripping is the largest taxi service company in China and is also one of the largest taxi-on-demand service platforms in the world. With the increase of innovative transportation services, the drip taxi service is more competitive with the traditional taxi service, and the previous research finds that the trip proportion of the taxi service accounts for 5.5% of all trip modes in China and is 1.7% higher than the traditional trip mode. The drip vehicle service accounts for 85.7% of the total travel by bus, and other services account for the remaining 14.3%, so the drip vehicle can be used as a representative of actual travel, and drip outgoing data can be used for urban area classification research. This becomes a new data source for urban area analysis.
Therefore, a method for constructing a city area contact network by using the drip outgoing data and further analyzing the characteristics of the city area needs to be researched.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a city region feature analysis method based on a complex network.
In order to solve the technical problems, the invention adopts the technical scheme that: a city region feature analysis method based on a complex network comprises the following steps:
step 1: establishing a grid network: dividing the urban area into more than one grid according to the longitude and the latitude; taking grids as nodes, wherein edges are used for connecting different grids, and establishing an undirected graph as a grid network;
step 2: calculating the weight of the edges in the grid network: the weight of an edge is the correlation of the two grids it connects; the correlation calculation may be calculated from regional behavior, regional activity patterns, or regional functional indicators;
and step 3: grid clustering: clustering the grid network;
and 4, step 4: judging whether the next-stage division is needed, if so, turning to the step 5, and if not, ending;
and 5: selecting one type of the clustering results in the step 3 as a next-level division region, dividing the next-level division region into more than 1 grid, and establishing an undirected graph by taking the grid as a node; and turning to step 2.
And 3, further clustering the grid network by using a Louvain algorithm.
Furthermore, the method for calculating the correlation according to the regional behavior index in step 2 includes:
step 2-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2-2: and (3) calculating the grid attribute: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area behavior correlation ABI between the grid i and the grid j:
Figure BDA0002920456050000021
wherein, Cc(i, j) is the close correlation between grid i and grid j, Ct(i, j) is the pearson correlation between grid i and grid j;
the close correlation between grid i and grid j is calculated by:
Figure BDA0002920456050000031
wherein,
Figure BDA0002920456050000032
1≤k≤ni,fijthe frequency from grid i to grid j; max (f)ik) Take fikMaximum value of (d);
Figure BDA0002920456050000033
1≤k≤ni，tijthe time cost spent from the grid i to the grid j is the time consumed by the path from the center point of the grid i to the center point of the grid j crawled by the Baidu map; n isiThe total number of the grids started and reached by the grid i;
the calculation method of the Pearson correlation between the grid i and the grid j comprises the following steps:
Ct(i,j)＝Pearson(Oi *,Oj *) (3)
wherein, Oi *Is OiCorresponding one-dimensional matrix, OiThe output matrix of the grid i is (n-2) multiplied by 24, n is the number of grids of all alighting cars, and (n-2) is the number of grids after the grid i and the grid j are deleted; o isj *Is OjCorresponding one-dimensional matrix, OjThe output matrix of grid j is also (n-2) x 24 in size.
Further, the method for calculating the correlation according to the regional active mode index in step 2 includes:
step 2A-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2A-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the correlation AAPI of the area active mode between the grid i and the grid j:
AAPI＝Pearson(li,lj) (4)
wherein liIs a list describing the change in the sum of the number of getting-on and getting-off operations per hour from grid i, ljIs a list describing the change in the total number of getting-on and getting-off times per hour from grid j.
Further, the method for calculating the correlation according to the regional function index in step 2 includes:
step 2B-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2B-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area function correlation AFI between the grid i and the grid j:
AFI＝Pearson(l′i,l′j) (5)
wherein l'iIs a list describing the change per hour from grid i difference of number of alights, l'jIs a list describing the change in the difference between the number of getting-on and getting-off cars per hour from grid j.
Further, in step 3, the community size parameter is a default value when clustering is performed on the grid network by using the Louvain algorithm.
The technical effect obtained by adopting the technical scheme is as follows:
1. the method can be used for rasterizing the city, can calculate the correlation among grids by using any index under the framework, and then obtains the grid network with three different meanings of corresponding regional behaviors, regional active modes and regional functions;
2. when the method and the device are used for clustering the network by using the Louvain algorithm, parameter adjustment is not needed, human factors are reduced, and the accuracy of urban area clustering is improved.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is an administrative division of the Shijiazhuang;
fig. 3 is a clustering result of the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Example 1:
as shown in fig. 1, a method for analyzing urban regional characteristics based on a complex network includes the following steps:
step 1: establishing a grid network: dividing the urban area into more than one grid according to the longitude and the latitude; taking grids as nodes, wherein edges are used for connecting different grids, and establishing an undirected graph as a grid network;
step 2: calculating the weight of the edges in the grid network: the weight of an edge is the correlation of the two grids it connects; the correlation calculation may be calculated from regional behavior, regional activity patterns, or regional functional indicators;
and step 3: grid clustering: clustering the grid network;
and 4, step 4: judging whether the next-stage division is needed, if so, turning to the step 5, and if not, ending;
and 5: selecting one type of the clustering results in the step 3 as a next-level division region, dividing the next-level division region into more than 1 grid, and establishing an undirected graph by taking the grid as a node; and turning to step 2.
Each time the weights of the edges in the grid network are computed cyclically, the index on which the grid correlation is computed can be independently selected.
And 3, clustering the grid network by using a Louvain algorithm.
The calculation method for calculating the correlation according to the regional behavior index in the step 2 comprises the following steps:
step 2-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2-2: and (3) calculating the grid attribute: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area behavior correlation ABI between the grid i and the grid j:
Figure BDA0002920456050000051
wherein, Cc(i, j) is the close correlation between grid i and grid j, Ct(i, j) is the pearson correlation between grid i and grid j;
the close correlation between grid i and grid j is calculated by:
Figure BDA0002920456050000061
wherein,
Figure BDA0002920456050000062
1≤k≤ni,fijthe frequency from grid i to grid j; max (f)ik) Take fikMaximum value of (d);
Figure BDA0002920456050000063
1≤k≤ni，tijthe time cost spent from the grid i to the grid j is the time consumed by the path from the center point of the grid i to the center point of the grid j crawled by the Baidu map; n isiThe total number of the grids started and reached by the grid i;
pearson correlation coefficient is a linear correlation coefficient. It provides different processing steps for the value range of the variable, so that when different variables are compared, there is no influence of the value size, and the finally obtained correlation is measured by the comparison of the trend. The invention calculates the pearson correlation of two grids as the corresponding pearson packet in the called statistical function library scipy.
The calculation method of the Pearson correlation between the grid i and the grid j comprises the following steps:
Ct(i,j)＝Pearson(Oi *,Oj *) (3)
wherein, Oi *Is OiCorresponding one-dimensional matrix, OiThe output matrix of the grid i is (n-2) multiplied by 24, n is the number of grids of all alighting cars, and (n-2) is the number of grids after the grid i and the grid j are deleted; o isj *Is OjCorresponding one-dimensional matrix, OjThe output matrix of grid j is also (n-2) x 24 in size.
The calculation method for calculating the correlation according to the regional active mode index in the step 2 comprises the following steps:
step 2A-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2A-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the correlation AAPI of the area active mode between the grid i and the grid j:
AAPI＝Pearson(li,lj) (4)
wherein liIs a list describing the change in the sum of the number of getting-on and getting-off operations per hour from grid i, ljIs a list describing the change in the total number of getting-on and getting-off times per hour from grid j.
The calculation method for calculating the correlation according to the regional function index in the step 2 comprises the following steps:
step 2B-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2B-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area function correlation AFI between the grid i and the grid j:
AFI＝Pearson(l′i,l′j) (5)
wherein l'iIs a list describing the change per hour from grid i difference of number of alights, l'jIs a list describing the change in the difference between the number of getting-on and getting-off cars per hour from grid j.
And 3, using a Louvain algorithm to cluster the grid network, wherein the community size parameter resolution is a default value.
According to the geography latitude and longitude, the city is divided into a plurality of grids, and the size of each grid is 1000 multiplied by 1000. The divided data comprises an getting-on latitude, a getting-on longitude, a getting-on place block, a getting-off latitude, a getting-off longitude, a getting-off place block, a place of departure set by the order, order ending information, order initiation time and order ending time.
The specific data are as follows:
s1: 37.597749114.595091268637.609610114.6154562872S 393. Gaoyi county, public road station, Gaoyi county, leaping billiard fun 2018-03-0319: 01: 122018-03-0319: 17:00
S2: 37.583335114.609188250337.605864114.5985782870 Gaoyi county |, doctor village Gaoyi county |, Gaoyi bus stop 2018-03-0313: 04: 432018-03-0313: 23:32
S3, 37.642844114.384020358537.660159114.3787983952 Chijiazhuang city, Hebei province, Jindu Huafu (232 province, Daoxi 140 m), Zanhuang county, Chinese medicine Homeph-Dongmen 2018-03-0307: 59: 472018-03-0308: 08:13
After the grids are divided, a grid network is established; and taking the grids as nodes, connecting edges with different grids, and establishing an undirected graph as a grid network.
Calculating the weight of the edges in the grid network: the weight of an edge is the correlation of the two grids it connects. The correlation between the grids is calculated in this example using the area behavior index ABI.
And clustering the obtained grid network by using a Louvain algorithm to obtain a new urban area clustering result. The Louvain algorithm is an algorithm based on multi-level optimization modulation, has the advantages of rapidness and accuracy, and is considered to be one of the community discovery algorithms with the best performance. When clustering is performed on the obtained grid network by using a Louvain packet carried by python, no adjustment is made on the parameter resolution for changing the size of the community, and the default value is 1. The clustering results are shown in FIG. 1.
TABLE 1
Figure BDA0002920456050000081

Claims (6)

1. A city region feature analysis method based on a complex network is characterized in that: the method comprises the following steps:
step 1: establishing a grid network: dividing the urban area into more than one grid according to the longitude and the latitude; taking grids as nodes, wherein edges are used for connecting different grids, and establishing an undirected graph as a grid network;
step 2: calculating the weight of the edges in the grid network: the weight of an edge is the correlation of the two grids it connects; the correlation calculation may be calculated from regional behavior, regional activity patterns, or regional functional indicators;
and step 3: grid clustering: clustering the grid network;
and 4, step 4: judging whether the next-stage division is needed, if so, turning to the step 5, and if not, ending;
and 5: selecting one type of the clustering results in the step 3 as a next-level division region, dividing the next-level division region into more than 1 grid, and establishing an undirected graph by taking the grid as a node; and turning to step 2.
2. The urban area feature analysis method based on the complex network as claimed in claim 1, wherein: and 3, clustering the grid network by using a Louvain algorithm.
3. The urban area feature analysis method based on the complex network as claimed in claim 1, wherein: the calculation method for calculating the correlation according to the regional behavior indexes comprises the following steps:
step 2-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2-2: and (3) calculating the grid attribute: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area behavior correlation ABI between the grid i and the grid j:
Figure FDA0002920456040000021
wherein, Cc(i, j) is the close correlation between grid i and grid j, Ct(i, j) is the pearson correlation between grid i and grid j;
the close correlation between grid i and grid j is calculated by:
Figure FDA0002920456040000022
wherein,
Figure FDA0002920456040000023
fijthe frequency from grid i to grid j; max (f)ik) Take fikMaximum value of (d);
Figure FDA0002920456040000024
tijthe time cost spent from the grid i to the grid j is the time consumed by the path from the center point of the grid i to the center point of the grid j crawled by the Baidu map; n isiThe total number of the grids started and reached by the grid i;
the calculation method of the Pearson correlation between the grid i and the grid j comprises the following steps:
Ct(i，j)＝Pearson(Oi *，Oj *) (3)
wherein, Oi *Is OiCorresponding one-dimensional matrix, OiThe output matrix of the grid i is (n-2) multiplied by 24, n is the number of grids of all alighting cars, and (n-2) is the number of grids after the grid i and the grid j are deleted; o isj *Is OjCorresponding one-dimensional matrix, OjThe output matrix of grid j is also (n-2) x 24 in size.
4. The urban area feature analysis method based on the complex network as claimed in claim 1, wherein: the calculation method for calculating the correlation according to the regional active mode index in the step 2 comprises the following steps:
step 2A-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2A-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the correlation AAPI of the area active mode between the grid i and the grid j:
AAPI＝Pearson(li，lj) (4)
wherein liIs a list describing the change in the sum of the number of getting-on and getting-off operations per hour from grid i, ljIs a list describing the change in the total number of getting-on and getting-off times per hour from grid j.
5. The urban area feature analysis method based on the complex network as claimed in claim 1, wherein: the calculation method for calculating the correlation according to the regional function index in the step 2 comprises the following steps:
step 2B-1: collecting data: the data comprises anonymous ID, getting-on longitude, getting-on latitude, getting-off longitude, getting-off latitude, order initiation time and order ending time;
step 2B-2: determining a starting grid and a terminating grid of each piece of data according to the data and the grids divided in the step 1, and calculating the area function correlation AFI between the grid i and the grid j:
AFI＝Pearson(l′i，l′j) (5)
wherein l'iIs a list describing the change per hour from grid i difference of number of alights, l'jIs a list describing the change in the difference between the number of getting-on and getting-off cars per hour from grid j.
6. The urban area feature analysis method based on the complex network as claimed in claim 2, wherein: and the community size parameter is a fixed value when clustering is carried out on the grid network by using the Louvain algorithm.
CN202110115945.8A 2021-01-28 2021-01-28 Urban area feature analysis method based on complex network Pending CN112784423A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110115945.8A CN112784423A (en) 2021-01-28 2021-01-28 Urban area feature analysis method based on complex network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110115945.8A CN112784423A (en) 2021-01-28 2021-01-28 Urban area feature analysis method based on complex network

Publications (1)

Publication Number Publication Date
CN112784423A true CN112784423A (en) 2021-05-11

Family

ID=75759239

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110115945.8A Pending CN112784423A (en) 2021-01-28 2021-01-28 Urban area feature analysis method based on complex network

Country Status (1)

Country Link
CN (1) CN112784423A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117079148A (en) * 2023-10-17 2023-11-17 腾讯科技（深圳）有限公司 Urban functional area identification method, device, equipment and medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2897088A1 (en) * 2014-01-16 2015-07-22 Fundació Privada Barcelona Digital Centre Tecnologic Method and apparatus for optimum spatial clustering
CN106503714A (en) * 2016-10-11 2017-03-15 湖州师范学院 A kind of method that urban function region is recognized based on interest point data
CN108280550A (en) * 2018-01-30 2018-07-13 杭州电子科技大学 A kind of visual analysis method that relatively public bicycles website community divides
CN109614458A (en) * 2018-12-20 2019-04-12 中国人民解放军战略支援部队信息工程大学 Community in urban areas structure method for digging and device based on navigation data
CN109740957A (en) * 2019-01-11 2019-05-10 江苏省城市规划设计研究院 A kind of urban traffic network node-classification method
CN109949574A (en) * 2018-05-18 2019-06-28 中山大学 A kind of urban road network traffic zone GradeNDivision method of data-driven
US20200336400A1 (en) * 2019-04-22 2020-10-22 Oath Inc. Efficient Density Based Geo Clustering

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2897088A1 (en) * 2014-01-16 2015-07-22 Fundació Privada Barcelona Digital Centre Tecnologic Method and apparatus for optimum spatial clustering
CN106503714A (en) * 2016-10-11 2017-03-15 湖州师范学院 A kind of method that urban function region is recognized based on interest point data
CN108280550A (en) * 2018-01-30 2018-07-13 杭州电子科技大学 A kind of visual analysis method that relatively public bicycles website community divides
CN109949574A (en) * 2018-05-18 2019-06-28 中山大学 A kind of urban road network traffic zone GradeNDivision method of data-driven
CN109614458A (en) * 2018-12-20 2019-04-12 中国人民解放军战略支援部队信息工程大学 Community in urban areas structure method for digging and device based on navigation data
CN109740957A (en) * 2019-01-11 2019-05-10 江苏省城市规划设计研究院 A kind of urban traffic network node-classification method
US20200336400A1 (en) * 2019-04-22 2020-10-22 Oath Inc. Efficient Density Based Geo Clustering

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117079148A (en) * 2023-10-17 2023-11-17 腾讯科技（深圳）有限公司 Urban functional area identification method, device, equipment and medium
CN117079148B (en) * 2023-10-17 2024-01-05 腾讯科技（深圳）有限公司 Urban functional area identification method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN109743683B (en) Method for determining position of mobile phone user by adopting deep learning fusion network model
CN108181607B (en) Positioning method and device based on fingerprint database and computer readable storage medium
CN107103754A (en) A kind of road traffic condition Forecasting Methodology and system
CN108282860A (en) Data processing method and device
US20120220274A1 (en) Position information analysis device and position information analysis method
CN104320795A (en) Evaluation method for health degree of multidimensional wireless network
CN112506972B (en) User resident area positioning method and device, electronic equipment and storage medium
US20230215272A1 (en) Information processing method and apparatus, computer device and storage medium
CN114926098B (en) Urban and rural life circle rapid demarcation method and system based on mobile positioning data
CN115082250B (en) Method, device and terminal for analyzing network relation between individual movement and ecological space
CN110134865A (en) A kind of commuting passenger's social recommendation method and platform based on urban public transport trip big data
CN104066058A (en) Wireless local area network (WLAN) indoor positioning method based on overlapping of two sets of fingerprints
CN111881243A (en) Taxi track hotspot area analysis method and system
CN112101132A (en) Traffic condition prediction method based on graph embedding model and metric learning
CN113256405B (en) Method, device, equipment and storage medium for predicting cheating user concentrated area
CN112784423A (en) Urban area feature analysis method based on complex network
CN109064750B (en) Urban road network traffic estimation method and system
CN110750730A (en) Group detection method and system based on space-time constraint
Qiu et al. RPSBPT: A route planning scheme with best profit for taxi
CN116680586A (en) Urban resident activity space access mode analysis method based on access probability
CN111008730B (en) Crowd concentration prediction model construction method and device based on urban space structure
Ferreira et al. Dynamic Identification of Stop Locations from GPS Trajectories Based on Their Temporal and Spatial Characteristics
CN113947123B (en) Personnel trajectory identification method, system, storage medium and equipment
KR102241221B1 (en) Apparatus and method subdividing regional spaces of interest
CN112529311B (en) Road flow prediction method and device based on graph convolution analysis

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210511