CN109614458A - Community in urban areas structure method for digging and device based on navigation data - Google Patents
Community in urban areas structure method for digging and device based on navigation data Download PDFInfo
- Publication number
- CN109614458A CN109614458A CN201811564764.8A CN201811564764A CN109614458A CN 109614458 A CN109614458 A CN 109614458A CN 201811564764 A CN201811564764 A CN 201811564764A CN 109614458 A CN109614458 A CN 109614458A
- Authority
- CN
- China
- Prior art keywords
- community
- region
- division
- point
- urban
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims 1
- 238000010168 coupling process Methods 0.000 claims 1
- 238000005859 coupling reaction Methods 0.000 claims 1
- 101100100125 Mus musculus Traip gene Proteins 0.000 abstract description 7
- 238000010276 construction Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 7
- 230000003542 behavioural effect Effects 0.000 abstract description 4
- 238000013439 planning Methods 0.000 abstract description 4
- 244000144992 flock Species 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 13
- 230000006870 function Effects 0.000 description 8
- 230000003595 spectral effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001601331 Sphingomonas taxi Species 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to community in urban areas structure method for digging and device based on navigation data, belong to technical field of data processing, it is clustered according to upper and lower visitor's point that taxi navigation data provides, and determine the central point of each cluster, Thiessen polygon division is carried out to hot spot region using central point as reference point, realize urban area division so that all sample points in polygon with a distance from the reference point in the polygon ratio to other any one of reference points apart from shorter；Hot spot region after will be discrete is abstracted into figure, will contact stronger division region by clustering algorithm and flocks together to form community.The present invention makes full use of taxi operation behavior to resident trip activity and the good perceptibility of city behavioral characteristics, it can be under the premise of no expertise, community in urban areas structure feature is obtained automatically in unsupervised mode, effective decision making approach and reference information can be provided for the planning of reasonable city function region and the construction of land resources utilization and road traffic.
Description
Technical field
The invention belongs to technical field of data processing, and in particular to the community in urban areas structure method for digging based on navigation data
With device.
Background technique
Community refers to the subregion in the complex networks system that one is made of node and side, between the node inside community
With close connection, and belong between the nodes of different communities contact it is then weaker.Community discovery is to pass through special algorithm
To excavate the subregion for having the above property in complex network structures, such as social networks, city traffic network and food web etc..
Community in city refers to that resident frequently carries out daily routines, carries the space region of a large amount of resident trip round trips
Domain.This class formation in city is excavated, the distribution with the community being closely connected is obtained, will be optimization road traffic construction, and subtract
Few congestion, and more reasonably city function region planning, the offers help such as smart city construction.
Currently, the regional structure for city is excavated if the method for community structure and function zoning is mainly using relevant
Geography information and expertise.As publication No. provides for the Chinese patent application of CN106503714A, " one kind is based on point of interest
The method of data identification urban function region ", the process of this method are as follows: after city is carried out rasterizing, calculate each region interest
Point distribution characteristics, and fuzzy clustering is carried out to it, point of interest and different clusters knot with category feature are calculated on this basis
Distribution Duplication of the fruit on map, identifies urban function region.But this method only obtains urban infrastructure rule
The static structure drawn, has ignored the movable influence of city dweller, can not excavate resident's activity i.e. city present in community structure
Behavioral characteristics.
With the rise of the applications such as navigation equipment and social networks, a large amount of navigation data and location information are in city
It is generated in city's construction and resident's activity.Therefore there is the method that community in urban areas structure is excavated using track of vehicle information.It is public
Cloth number is that the Chinese patent application of CN106886607A proposes a kind of " urban area division methods, device and terminal device ",
The each cell divided in city is labeled, the markup information of each cell includes the vehicle by each cell
Information；By clustering method, the similar cell of adjacent similar and vehicle movement rule is flocked together, with complete
At the division of urban area.This method still depends on artificial markup information although it is contemplated that resident movable influence, needs
A large amount of premise knowledge is wanted, and only accounts for the similitude of the characteristics of motion, has ignored and is closely closed between community structure interior joint
Connection property.Therefore, the community that existing community structure method for digging is marked off is not accurate enough.
Summary of the invention
The object of the present invention is to provide community in urban areas structure method for digging and device based on navigation data, for solving mesh
Not accurate enough, the reasonable problem in preceding marked off community.
In order to solve the above technical problems, the present invention proposes a kind of community in urban areas structure method for digging based on navigation data,
The following steps are included:
1) to the city of taxi navigation data offer, objective point data is clustered above and below, and is determined in each cluster
Heart point；
2) using central point as reference point, Thiessen polygon division is carried out to urban area, the division of urban area is realized, makes
All sample points in polygon with a distance from the reference point in the polygon ratio to other any one reference points apart from more
It is short；
3) urban area after division is abstracted into figure, the node of figure is each division region of urban area, connecting node
Side by travel to and fro between it is each division region between stroke indicate, according to it is each division region between number of strokes pass through clustering algorithm pair
Each region that divides is clustered, and cluster result is determining community in urban areas.
In order to solve the above technical problems, the present invention also proposes that a kind of community in urban areas structure based on navigation data excavates dress
Set, including memory and processor, and the computer program that runs on a memory and on a processor of storage, processor with
Memory is coupled, and processor realizes above step 1 when executing computer program), step 2) and step 3).
The present invention is clustered according to upper and lower visitor's point that taxi navigation data provides, and determines the center of each cluster
Point carries out Thiessen polygon division to hot spot region, the division of urban area is realized, so that polygon using central point as reference point
All sample points in shape with a distance from the reference point in the polygon ratio to other any one reference points apart from shorter；Then
Hot spot region after will be discrete is abstracted into figure, will contact stronger division region by clustering algorithm and flocks together to form society
Area will contact weaker region division to different communities.The present invention takes full advantage of taxi operation behavior to resident trip
Activity and the good perceptibility of city behavioral characteristics, can be under the premise of no expertise, in unsupervised mode from original
Community in urban areas structure feature is excavated in data, can for reasonable city function region planning and land resources utilization, and
The construction of road traffic provides effective decision making approach and reference information.
The upper and lower objective point data clustered in step 1) is the data in the hot spot region of city, before step 1), first to out
The upper and lower objective point data hired a car is clustered, and determines the city hot spot region of resident trip access, which is
It include the most region of upper and lower objective point data in cluster result.The division that community in urban areas is only carried out to hot spot region, without examining
Consider remote area, improve the division efficiency of community in urban areas, alleviates the work load of community's division.
City hot spot region is using DBSCAN clustering algorithm or OPTICS clustering algorithm to taxi objective point data above and below
Space clustering is carried out to obtain.The clustering algorithm is advantageous in that, without knowing that cluster number just can be carried out cluster in advance.
For the above-mentioned cluster centre of determination, clustered in turn using upper and lower objective point data of the K-means algorithm to taxi
Determine city hot spot region.
Detailed description of the invention
Fig. 1 is community in urban areas structure method for digging flow chart of the invention；
Fig. 2 is Thiessen polygon region division schematic diagram of the invention；
Fig. 3 is a kind of community structure schematic diagram of the invention；
Fig. 4 is community in urban areas structure method for digging effect diagram of the invention.
Specific embodiment
A specific embodiment of the invention is further described with reference to the accompanying drawing.
Embodiment of the method one:
The community in urban areas structure method for digging of the present embodiment is led based on what the round-the-clock taxi throughout urban global generated
Boat data excavate city hot spot region by space clustering first, and carry out grid dividing to city according to cluster feature, herein
On the basis of using spectral clustering excavate the region with close association, so that it is constituted the community structure in city.Such as Fig. 1
It is shown, the specific steps are as follows:
Step 1: according to the passenger carrying status in taxi navigation data, upper and lower visitor is extracted from taxi navigation data
Point, it is poly- using DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
Class algorithm carries out space clustering to upper and lower visitor's point, the hot spot region frequently accessed when excavating resident trip, DBSCAN clustering algorithm
Do not have to be determined in advance cluster number in the case where can preferably handle whole city be unevenly distributed, on irregular taxi,
The coordinate data of drop-off point.Above-mentioned DBSCAN clustering algorithm can also use density-based algorithms such as OPTICS
(Ordering Points To Identify the Clustering Structure) clustering algorithm is replaced.
Step 2: carrying out discretization to city hot spot region on the basis of excavating hot spot region, using based on distance
K-means algorithm in hot spot region it is upper and lower visitor point cluster again, determine the central point of each cluster.With each
Central point is reference point, carries out Thiessen polygon (also referred to as Voronoi polygon) to central city and divides, obtains division
All sample points in each polygon with a distance from the reference point in the polygon ratio to other any one reference points distances more
It is short.This urban area discretization method compares other methods, can accurately identify the upper and lower visitor of taxi and put intensive hot zone
Domain, while the partition strategy based on distance between upper and lower visitor's point hires out wheel paths minute but also each region remains well
The characteristic of cloth, as shown in Figure 2.
Step 3: being abstracted into figure for the urban area after discretization, community 1 as shown in Figure 3, community 2 and community 3,
The node of figure indicates that the side of connecting node is indicated by travelling to and fro between the taxi stroke between region in figure by the region divided.
The taxi number of strokes between different zones will be travelled to and fro between as the weight on side, stroke is more, and the weight on side is bigger, two end segment of side
Connection between point is closer.According to mentioned above principle, there will be the region clustering being closely connected one using spectral clustering
It rises and forms community, and contact weaker region and be then divided into different communities.
Above step three excavates the specific side of community structure on the basis of the discretization of urban area using spectral clustering
Method is as follows:
Urban area after discretization can be abstracted as the figure G (v, e) being made of the side of node and Weight, and v indicates section
Point, i.e. taxi upper and lower visitor's point region, e indicate the side of Weight, taxi number of strokes conduct between two regions
The weight on side.Number of strokes N between definition region i and region jij:
Nij=N { O ∈ i ∩ D ∈ j }+N { O ∈ j ∩ D ∈ i } (1)
Wherein, objective point, D indicate drop-off point, N in O expressionijIndicate region i, the number of strokes between j schemes the power of side e in G
Weight.If the number of regions divided in total is m, then one can be constructed by Nij(between m × m area that i, j=1,2 ... m) are constituted mutually
Mutually access frequency matrix V:
Wherein, i, j=1,2 ... m indicate each zone number, the N known to definitionij=Nji, matrix V is symmetrical matrix, should
Representation of the matrix as figure G (v, e), also referred to as adjacency matrix, describe the frequent degree accessed mutually between region, Nij
Bigger, the relevance between corresponding region is stronger.
Matrix V is standardized to obtain by N ' by range transformationij(the adjacency matrix V ' that i, j=1,2 ... m) are constituted:
Wherein, min expression is minimized, and max expression is maximized.
Above-mentioned adjacency matrix V ' is studied using spectral graph theory, is completed using objective function Ncut as the division of criterion, even if
Objective function Ncut is obtained to minimize:
Wherein, A1,A2,…,AkFor all nodes in figure, AiTo belong to the node inside particular community,For specific society
Node except area,For the weight between community's interior nodes and community's exterior node,For vol (Ai) it is same
Weight between community's internal node.
The Laplacian matrix of figure G (v, e) is expressed as:
L=D-V ' (5)
Wherein, L is Laplacian matrix, and D is diagonal matrix, diagonal element dii=∑jN′ij.By Laplacian matrix into
After row standardization:
L (norm)=D-1LD-1 (6)
The characteristic value and character pair vector for seeking matrix L (norm), choose the corresponding feature of the smallest k characteristic value to
Amount constitutes the space of m × k dimension, and carries out traditional k-means cluster to m Area Node in this space, can obtain by
The k different community that the region of tight association is constituted.
The magnanimity navigation data that the present invention is generated using taxi in city, has excavated city Zhong Ju by space clustering
It is good to resident trip activity and city behavioral characteristics to take full advantage of taxi operation behavior for the frequent hot spot region of people's trip
Perceptibility, community in urban areas structure feature can be obtained automatically in unsupervised mode under the premise of no expertise, can
For the planning of reasonable city function region and the construction of land resources utilization and road traffic provide effective decision making approach and
Reference information, as shown in Figure 4.
Embodiment of the method two:
Above method embodiment from entire urban area first is that first find hot spot region (central city), just for heat
Point region carries out community's division.Central city, suburb are generally comprised in city, the data in suburb are more dispersed, without to it
Community's division is carried out, therefore, embodiment one is just for hot spot region, that is, central city.
Different from embodiment of the method one, the community in urban areas structure method for digging of the present embodiment does not have to divide hot spot region, right
There are carry out community's division of upper and lower objective point data in city, the division to entire community in urban areas is realized.Including following step
It is rapid:
1) to the city of taxi navigation data offer, objective point data is clustered above and below, and is determined in each cluster
Heart point；
2) using central point as reference point, Thiessen polygon division is carried out to urban area, the division of urban area is realized, makes
All sample points in polygon with a distance from the reference point in the polygon ratio to other any one reference points apart from more
It is short；
3) urban area after division is abstracted into figure, the node of figure is each division region of urban area, connecting node
Side by travel to and fro between it is each division region between stroke indicate, according to it is each division region between number of strokes pass through clustering algorithm pair
Each region that divides is clustered, and cluster result is determining community in urban areas.
The community in urban areas structure method for digging mentioned in above method embodiment one and embodiment of the method two, is excavated
The characteristics of community structure, more intuitively the rule of reflection resident's daily routines and urban infrastructure are planned, by city
Multidate information and static information it is comprehensive, be more reasonable urban construction, land resources utilization and accurate resident's activity prison
It surveys and support is provided.
Corresponding above-mentioned community in urban areas structure method for digging, it is also proposed that the community in urban areas structure based on navigation data excavates dress
Set, including memory and processor, and the computer program that runs on a memory and on a processor of storage, processor with
Memory is coupled, and processor realizes the step in above method embodiment one or embodiment of the method two when executing computer program
Suddenly.
Due to the community in urban areas structure excavating gear based on navigation data, it is actually based on the method for the present invention process
A kind of computer solution, i.e., a kind of software architecture, can be applied in computer, and above-mentioned apparatus is and method flow phase
Corresponding treatment progress.Since sufficiently clear is complete for the introduction to the above method, therefore no longer it is described in detail.
Claims (8)
1. a kind of community in urban areas structure method for digging based on navigation data, which comprises the following steps:
1) to the city of taxi navigation data offer, objective point data is clustered above and below, and determines the central point of each cluster；
2) using central point as reference point, Thiessen polygon division is carried out to urban area, the division of urban area is realized, so that more
All sample points in the shape of side with a distance from the reference point in the polygon ratio to other any one reference points apart from shorter；
3) urban area after division is abstracted into figure, the node of figure is each division region of urban area, the side of connecting node
It is indicated by travelling to and fro between the stroke between each division region, according to the number of strokes between each division region by clustering algorithm to each stroke
Subregion is clustered, and cluster result is determining community in urban areas.
2. the community in urban areas structure method for digging according to claim 1 based on navigation data, which is characterized in that step 1)
The upper and lower objective point data of middle cluster is the data in the hot spot region of city, before step 1), first to the upper and lower visitor of taxi
Point data is clustered, and determines that the city hot spot region of resident trip access, the city hot spot region are to wrap in cluster result
Containing the most region of upper and lower objective point data.
3. the community in urban areas structure method for digging according to claim 2 based on navigation data, which is characterized in that Urban Thermal
Point region is that taxi, objective point data progress space clustering is obtained above and below using DBSCAN clustering algorithm or OPTICS clustering algorithm
It arrives.
4. the community in urban areas structure method for digging according to claim 1 or 2 based on navigation data, which is characterized in that really
The clustering method used when cluster centre is determined for K-means algorithm.
5. a kind of community in urban areas structure excavating gear based on navigation data, which is characterized in that including memory and processor, with
And it is stored in the computer program run on the memory and on the processor, the processor and the memory phase
Coupling, the processor perform the steps of when executing the computer program
1) to the city of taxi navigation data offer, objective point data is clustered above and below, and determines the central point of each cluster；
2) using central point as reference point, Thiessen polygon division is carried out to urban area, the division of urban area is realized, so that more
All sample points in the shape of side with a distance from the reference point in the polygon ratio to other any one reference points apart from shorter；
3) urban area after division is abstracted into figure, the node of figure is each division region of urban area, the side of connecting node
It is indicated by travelling to and fro between the stroke between each division region, according to the number of strokes between each division region by clustering algorithm to each stroke
Subregion is clustered, and cluster result is determining community in urban areas.
6. the community in urban areas structure excavating gear according to claim 5 based on navigation data, which is characterized in that step 1)
The upper and lower objective point data of middle cluster is the data in the hot spot region of city, before step 1), first to the upper and lower visitor of taxi
Point data is clustered, and determines that the city hot spot region of resident trip access, the city hot spot region are to wrap in cluster result
Containing the most region of upper and lower objective point data.
7. the community in urban areas structure excavating gear according to claim 6 based on navigation data, which is characterized in that Urban Thermal
Point region is that taxi, objective point data progress space clustering is obtained above and below using DBSCAN clustering algorithm or OPTICS clustering algorithm
It arrives.
8. the community in urban areas structure excavating gear according to claim 5 or 6 based on navigation data, which is characterized in that really
The clustering method used when cluster centre is determined for K-means algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811564764.8A CN109614458B (en) | 2018-12-20 | 2018-12-20 | Urban community structure mining method and device based on navigation data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811564764.8A CN109614458B (en) | 2018-12-20 | 2018-12-20 | Urban community structure mining method and device based on navigation data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109614458A true CN109614458A (en) | 2019-04-12 |
| CN109614458B CN109614458B (en) | 2021-07-16 |
Family
ID=66008947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811564764.8A Expired - Fee Related CN109614458B (en) | 2018-12-20 | 2018-12-20 | Urban community structure mining method and device based on navigation data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109614458B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334321A (en) * | 2019-06-24 | 2019-10-15 | 天津城建大学 | A kind of city area Gui Jiaozhan identification of function method based on interest point data |
| CN110443736A (en) * | 2019-06-26 | 2019-11-12 | 深圳市和讯华谷信息技术有限公司 | A kind of analysis method of community in urban areas, device and system |
| CN110774974A (en) * | 2019-09-27 | 2020-02-11 | 沈阳美行科技有限公司 | Vehicle headlamp control method and device and related equipment |
| CN111428764A (en) * | 2020-03-17 | 2020-07-17 | 电子科技大学 | Image clustering method for image category identification |
| CN112131330A (en) * | 2020-09-16 | 2020-12-25 | 上海交通大学 | Site selection layout method for shared automobile operation area in free flow mode |
| CN112214567A (en) * | 2020-10-28 | 2021-01-12 | 兰州交通大学 | Urban space structure discovery design scheme under support of complex graph theory |
| CN112241685A (en) * | 2020-09-16 | 2021-01-19 | 四川天翼网络服务有限公司 | Community activity track-based personnel clustering method and system |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
| CN113225260A (en) * | 2021-04-25 | 2021-08-06 | 湖南大学 | Mixed clustering opportunistic routing implementation method based on machine learning |
| CN113487465A (en) * | 2021-06-22 | 2021-10-08 | 中国地质大学（武汉） | City overlapping structure characteristic detection method and system based on label propagation algorithm |
| CN115100394A (en) * | 2022-06-24 | 2022-09-23 | 南京大学 | City block function identification method based on interest point Voronoi graph |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203681A (en) * | 2016-06-29 | 2016-12-07 | 大连理工大学 | The constant due-date type urban area of a kind of data-driven divides and method for digging |
| CN108417023A (en) * | 2018-05-02 | 2018-08-17 | 长安大学 | Traffic zone central point choosing method based on taxi on-board and off-board space of points cluster |
-
2018
- 2018-12-20 CN CN201811564764.8A patent/CN109614458B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203681A (en) * | 2016-06-29 | 2016-12-07 | 大连理工大学 | The constant due-date type urban area of a kind of data-driven divides and method for digging |
| CN108417023A (en) * | 2018-05-02 | 2018-08-17 | 长安大学 | Traffic zone central point choosing method based on taxi on-board and off-board space of points cluster |
Non-Patent Citations (4)
| Title |
|---|
| DAQIANG ZHANG: "Identifying Region-Wide Functions Using Urban Taxicab Trajectories", 《ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS》 * |
| XI LIU: "Revealing travel patterns and city structure with taxi trip data", 《JOURNAL OF TRANSPORT GEOGRAPHY》 * |
| 信睿: "顾及出租车OD点分布密度的空间Voronoi 剖分", 《地理信息科学》 * |
| 陈斌: "基于轨迹数据和图模型的城市区域重要程度可视分析", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334321A (en) * | 2019-06-24 | 2019-10-15 | 天津城建大学 | A kind of city area Gui Jiaozhan identification of function method based on interest point data |
| CN110334321B (en) * | 2019-06-24 | 2023-03-31 | 天津城建大学 | City rail transit station area function identification method based on interest point data |
| CN110443736A (en) * | 2019-06-26 | 2019-11-12 | 深圳市和讯华谷信息技术有限公司 | A kind of analysis method of community in urban areas, device and system |
| CN110774974B (en) * | 2019-09-27 | 2023-01-24 | 沈阳美行科技股份有限公司 | Vehicle headlamp control method and device and related equipment |
| CN110774974A (en) * | 2019-09-27 | 2020-02-11 | 沈阳美行科技有限公司 | Vehicle headlamp control method and device and related equipment |
| CN111428764A (en) * | 2020-03-17 | 2020-07-17 | 电子科技大学 | Image clustering method for image category identification |
| CN111428764B (en) * | 2020-03-17 | 2022-06-03 | 电子科技大学 | Image clustering method for image category identification |
| CN112131330A (en) * | 2020-09-16 | 2020-12-25 | 上海交通大学 | Site selection layout method for shared automobile operation area in free flow mode |
| CN112241685A (en) * | 2020-09-16 | 2021-01-19 | 四川天翼网络服务有限公司 | Community activity track-based personnel clustering method and system |
| CN112131330B (en) * | 2020-09-16 | 2024-01-26 | 上海交通大学 | Method for selecting and laying out operation area of shared automobile in free flow mode |
| CN112214567A (en) * | 2020-10-28 | 2021-01-12 | 兰州交通大学 | Urban space structure discovery design scheme under support of complex graph theory |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
| CN113225260A (en) * | 2021-04-25 | 2021-08-06 | 湖南大学 | Mixed clustering opportunistic routing implementation method based on machine learning |
| CN113225260B (en) * | 2021-04-25 | 2022-11-18 | 湖南大学 | Mixed clustering opportunistic routing implementation method based on machine learning |
| CN113487465A (en) * | 2021-06-22 | 2021-10-08 | 中国地质大学（武汉） | City overlapping structure characteristic detection method and system based on label propagation algorithm |
| CN115100394A (en) * | 2022-06-24 | 2022-09-23 | 南京大学 | City block function identification method based on interest point Voronoi graph |
| CN115100394B (en) * | 2022-06-24 | 2023-11-03 | 南京大学 | Urban block function identification method based on Voronoi diagram of interest point |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109614458B (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614458A (en) | Community in urban areas structure method for digging and device based on navigation data | |
| CN110263111B (en) | Priori knowledge-based space-time monitoring method for land utilization/coverage information | |
| CN109272170B (en) | A kind of traffic zone dividing system based on Louvain algorithm | |
| CN109493119B (en) | POI data-based urban business center identification method and system | |
| CN109167805A (en) | Analysis and processing method based on car networking space-time data in City scenarios | |
| CN113806419B (en) | Urban area function recognition model and recognition method based on space-time big data | |
| Yan et al. | Dynamic partitioning of urban traffic network sub-regions with spatiotemporal evolution of traffic flow | |
| Perez et al. | Identifying building typologies and their spatial patterns in the metropolitan areas of Marseille and Osaka | |
| Hu et al. | A framework to detect and understand thematic places of a city using geospatial data | |
| Zhang et al. | Unveiling transit mobility structure towards sustainable cities: An integrated graph embedding approach | |
| Yang et al. | Inferring passengers’ interactive choices on public transits via ma-al: Multi-agent apprenticeship learning | |
| Cai et al. | Spatial attention based grid representation learning for predicting origin–destination flow | |
| CN118195341A (en) | Regional carbon emission prediction method and device based on road network and travel demand data | |
| Qiu et al. | RPSBPT: A route planning scheme with best profit for taxi | |
| Liao | [Retracted] Hot Spot Analysis of Tourist Attractions Based on Stay Point Spatial Clustering | |
| Schoier et al. | Individual movements and geographical data mining. Clustering algorithms for highlighting hotspots in personal navigation routes | |
| Perchinunno et al. | Identification of “Hot Spots” of inner areas in Italy: Scan statistic for urban planning policies | |
| Hao et al. | A novel shortest path algorithm with topology transformation for urban rail transit network | |
| CN115794977A (en) | Method for establishing discrete track of moving target | |
| Yu et al. | RePiDeM: A refined POI demand modeling based on multi-source data | |
| Nagappan et al. | Machine learning predictors for sustainable urban planning | |
| Han et al. | A novel handover detection model via frequent trajectory patterns mining | |
| CN113343565A (en) | Neighborhood effect mode construction and CA simulation method and system considering spatial heterogeneity | |
| Zhou et al. | MVMAFOL: A Multi-Access Three-Layer Federated Online Learning Algorithm for Internet of Vehicles | |
| Wu et al. | Massive-scale visual information retrieval towards city residential environment surveillance |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210716 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |