CN106503714A - A kind of method that urban function region is recognized based on interest point data - Google Patents
A kind of method that urban function region is recognized based on interest point data Download PDFInfo
- Publication number
- CN106503714A CN106503714A CN201610887062.8A CN201610887062A CN106503714A CN 106503714 A CN106503714 A CN 106503714A CN 201610887062 A CN201610887062 A CN 201610887062A CN 106503714 A CN106503714 A CN 106503714A
- Authority
- CN
- China
- Prior art keywords
- interest
- point
- base station
- cluster
- grid
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
Abstract
The invention provides a kind of method for recognizing urban function region based on interest point data, is realized by following steps：Step one, map segmentation：By map rasterizing；Base station belonging to step 2, searching point of interest：Find the base station nearest apart from the point of interest；Step 3, each base station point of interest distribution characteristicss of calculating；Step 4, cluster：Matrix in step 3 carries out fuzzy cluster analysis, obtains different cluster results；Step 5, identification urban function region：Distribution Duplication of the different cluster results that point of interest and step 4 of the calculating with category feature are obtained on map, is identified to each base station after cluster.The method that the present invention recognizes urban function region according to interest point data, either tourist district, working area residential block can be to these urban area identification of function, and result is matched substantially with actual, effect whether can more summing-up perfect under.
Description
Technical field
A kind of the present invention relates to big data analysis field, more particularly to side for recognizing urban function region based on interest point data
Method.
Background technology
As economic develops rapidly, a series of urban issueses come one after another, especially for some provincial capitals or big
For city, urban issues is particularly acute.Development of the "urban disease" as Urbanization In Developing Countries, shows as traffic and gathers around
Stifled, acute housing shortage, insufficient water, energy scarcity, ecological deterioration, employment difficulties etc., this just cause burden, or even system to city
The about development in city, is also easy to cause civic somatopsychic illness etc..
In recent years, some experts and scholars carry out " city calculating " using various isomery big datas, solve urbanization with this
The problem that brings.City calculate be a cross discipline, be with city as background in computer science, with urban planning, traffic,
The emerging field of the energy, environment, sociology and economic dispatch subject convergence.More specifically, city calculate by constantly obtaining, whole
Close and analysis city in multiple isomery big datas come solve city institute facing challenges (as ecological deterioration, traffic congestion, energy consumption increase
Plus, planning fall behind etc.).Wherein, urban planning is one of application that city calculating is related generally to.Carry out the premise bar of urban planning
Part is to understand city, and understands the distribution situation of each functional area in city.Urban function region refers to land use function, use
Intensity, Land_use change direction, benchmark land price region unanimous on the whole, their intensive use level and using potentiality also basic phase
With, such as cultural district, shopping centre and residential quarter etc..
At present, Chinese scholars are for the research of urban function region is mainly using data in mobile phone, floating car data and POI
Data etc..Wherein, POI data is widely used in the discovery of urban function region.POI data, full name are Point of
Interest, i.e. interest point data.In generalized information system, a POI data can be a cell, a shop, a public transport
Station etc..One POI data includes the parameters such as title, longitude and latitude, better address, POI classifications and telephone number.It was related in recent years
Find that to POI data the research of urban function region mainly has：Yuan Jing etc. proposes one under study for action using taxi GPS track
The DPoF frameworks (i.e. Discovers Regions of Different Functions) that data and region POI data are constituted；
Du Run waits by force the theme class that used POI numbers most when the mobile phone park point of irregular switching is solved as the theme of cell
Neighbor cell is merged；Bus IC card brushing card data and POI data has been used to construct city work(under study for action in Xiang
Can area's identification model (Discovering Zones of different Functions, DZoF).
And the positional information of cellular base station often combined with Voronoi Thiessen polygons be used for split city substantially single
Unit.The research for being related to cellular base station segmentation survey region mainly has：Jameson L.Toole etc. are being produced using cellphone subscriber
Dynamic data identification land use and make use of the positional information of base station to carry out region to map when dynamic population's relation
Divide；The information that V í cto Soto and EnriueFr í as-Mart í nez propose to produce using cellular base station network carrys out automatic identification
Also region division is carried out to map using the positional information of base station during the technology for dividing land use situation.
In addition, the type that POI data includes, is related to every aspect comprehensively, and crawl is very convenient, and some other data
Often compare difficult acquisition.Currently, the cellular base station of three big operators substantially covers whole China.And, it is more preferable
The service masses, the base station of operator are set up according to the closeness of population and urban planning.That is, densely populated,
The region of tall buildings exit, the setting of base station also can be relatively dense, and in more spacious region, the quantity of base station will be corresponding
Reduce.
Content of the invention
The technical problem to be solved is to provide the method for recognizing urban function region based on interest point data, can make
The function of city regional is identified with interest point data.For this purpose, the present invention provides technical scheme below：
A kind of method for recognizing urban function region based on interest point data, comprises the following steps：
Step one, map segmentation：By map rasterizing, and all grids are numbered；According to cellular base station position point
Cede territory figure, calculate the distance of each grid and base station, and regulation grid belongs to the base station nearest from it, obtain apart from each base station away from
From nearest grid list, and grid matrix number G shared by each base station；
Base station belonging to step 2, searching point of interest：The base station nearest apart from the point of interest is found, and judges this point of interest
Belong to the base station, obtain all interest point lists for belonging to each base station；
Step 3, each base station point of interest distribution characteristicss of calculating：According to " point of interest in the data of each base station interest point list
Classification " this parameter carries out classified statistic to the point of interest of each base station, i.e., count the different classes of point of interest in each base station respectively
Number, obtains the point of interest category distribution matrix D of each base station；And point of interest category distribution matrix D is combined shared grid number square
Battle array G is processed to which using normalized method, obtains the matrix eventually for analysis, and the matrix is named as Y；
Step 4, cluster：Matrix Y in step 3 carries out fuzzy cluster analysis, obtains different cluster results；
Step 5, identification urban function region：Calculate the different clusters that the point of interest with category feature and step 4 are obtained
As a result the distribution Duplication on map, is identified to each base station after cluster.
On the basis of using above-mentioned technical proposal, the present invention can also adopt technical scheme further below：
In the step 3, normalization processing method is as follows：
Respectively point of interest category distribution matrix D and shared grid matrix number G are normalized using formula (1), will
Two matrix normalizations are in the interval of [0,1], and are combined both normalization results by formula (2),
Y=A e-X(2)
In formula (1), { xiBe sample set, xiFor all sample components of sample set, xmaxFor each component of all samples of sample set
Maximum, xminMinima for each component of all samples of sample set；
In formula (2), Y is the matrix eventually for analysis, and dimension is n × m；A be point of interest category distribution matrix D according to formula
(1) matrix after normalization, dimension are n × m；X be shared grid matrix number G according to the matrix after formula (1) normalization, dimension is
1×n；N is base station number, and m is point of interest category number.
In step 4, institute's directed quantity is divided into C cluster using C means clustering algorithms by the fuzzy cluster analysis, and is tried to achieve
The cluster centre of each cluster so that cluster internal variance and reach minimum；
Clustered by C averages fuzzy clustering algorithm again, the result for drawing is the probability list that base station i belongs to different clusters,
Then, the class belonging to maximums of the base station i in all kinds of probabilities is extracted, such classification belonging to the i of base station is defined, is obtained each
The list of base station generic, the list are cluster result.
In step 5, calculating point of interest category is the base station of " n " dividing on map for the point of interest of " s " with cluster classification
The Duplication of cloth, by input：" according to the grid list that the point of interest that point of interest category is " s " is located；Cluster classification is " n "
The grid list that covered of base station ", obtain Duplication.
In step 5, calculate " point of interest category " be " s " point of interest with cluster classification be " n " base station on map
The concrete grammar of the Duplication of distribution is as follows：
Step1:According to each point of interest longitude and latitude that " point of interest category " is " s ", their place grids number are found out；
Step2:Area is amplified according to the feature of " s ", i.e., southeastward northwest four centered on the grid number that Step1 is obtained
Area is amplified to a square area by direction, obtains all grids number in this amplification area；
Step3:The all unduplicated grid number that statistics Step2 is obtained, this set are designated as S；
Step4:According to the grid list that cluster classification is covered by the base station number and each base station of " n ", cluster class is found
The grid number not covered by " n ", this set are designated as N；
Step5:According to formula (3) computation grid Duplication (OverlapRatio):The grid Duplication is " point of interest class
Not " by grid number set S and the Duplication that cluster classification is the grid number set N that " n " is covered of " s "；
In step one, cellular base station position segmentation map is utilized using the method that finds from the nearest base station of grid.
Due to adopting technical scheme, beneficial effects of the present invention to be：Invention recognizes city according to interest point data
The method of city functional areas, either tourist district, working area residential block, can to these urban area identification of function, and result with
Actual match substantially, whether effect can be under the improving of more summing-up.
Description of the drawings (figure is following instance, and whether position will change)
Fig. 1 is Hangzhou survey region provided by the present invention.
Base station division results of the Fig. 2 for Fig. 1.
Fig. 3 is the cluster result of clustering parameter C=4 provided by the present invention.
Computer-aided mappings of the Fig. 4 for Hangzhou 2001-2020
Fig. 5 is projection of the cluster result to " residential block " on the master plan of Hangzhou.
Fig. 6 is projection of " tourist district " cluster result in Baidu map.
Fig. 7 is the point of interest distribution thermodynamic chart that " point of interest category " is " work ".
Specific embodiment
As illustrated, a kind of method for recognizing urban function region based on interest point data, comprises the following steps：
Step one, map segmentation：By map rasterizing, and all grids are numbered；According to cellular base station position point
Cede territory figure, calculate the distance of each grid and base station, and regulation grid belongs to the base station nearest from it, obtain apart from each base station away from
From nearest grid list, and grid matrix number G shared by each base station；Using the method profit that finds from the nearest base station of grid
With cellular base station position segmentation map.
Base station belonging to step 2, searching point of interest：The base station nearest apart from the point of interest is found, and judges this point of interest
Belong to the base station, obtain all interest point lists for belonging to each base station；
Step 3, each base station point of interest distribution characteristicss of calculating：According to " point of interest in the data of each base station interest point list
Classification " this parameter carries out classified statistic to the point of interest of each base station, i.e., count the different classes of point of interest in each base station respectively
Number, obtains the point of interest category distribution matrix D of each base station；And point of interest category distribution matrix D is combined shared grid number square
Battle array G is processed to which using normalized method, obtains the matrix eventually for analysis, and the matrix is named as Y；
Normalization processing method is as follows：
Respectively point of interest category distribution matrix D and shared grid matrix number G are normalized using formula (1), will
Two matrix normalizations are in the interval of [0,1], and are combined both normalization results by formula (2),
Y=A e-X(2)
In formula (1), { xiBe sample set, xiFor all sample components of sample set, xmaxFor each component of all samples of sample set
Maximum, xminMinima for each component of all samples of sample set；
In formula (2), Y is the matrix eventually for analysis, and dimension is n × m；A be point of interest category distribution matrix D according to formula
(1) matrix after normalization, dimension are n × m；X be shared grid matrix number G according to the matrix after formula (1) normalization, dimension is
1×n；N is base station number, and m is point of interest category number.
Step 4, cluster：Matrix Y in step 3 carries out fuzzy cluster analysis, obtains different cluster results；Described
Institute's directed quantity is divided into C cluster using C means clustering algorithms by fuzzy cluster analysis, and tries to achieve the cluster centre of each cluster so that
Cluster internal variance and reach minimum；
Clustered by C averages fuzzy clustering algorithm again, the result for drawing is the probability list that base station i belongs to different clusters,
Then, the class belonging to maximums of the base station i in all kinds of probabilities is extracted, such classification belonging to the i of base station is defined, is obtained each
The list of base station generic, the list are cluster result.
Step 5, identification urban function region：Calculate the different clusters that the point of interest with category feature and step 4 are obtained
As a result the distribution Duplication on map, is identified to each base station after cluster.
In step 5, calculating point of interest category is the base station of " n " dividing on map for the point of interest of " s " with cluster classification
The Duplication of cloth, by input：" according to the grid list that the point of interest that point of interest category is " s " is located；Cluster classification is " n "
The grid list that covered of base station ", obtain Duplication.
The point of interest that " point of interest category " is " s " is calculated with the weight that cluster classification is distribution of the base station of " n " on map
The concrete grammar of folded rate is as follows：
Step1:According to each point of interest longitude and latitude that " point of interest category " is " s ", their place grids number are found out；
Step2:Area is amplified according to the feature of " s ", i.e., southeastward northwest four centered on the grid number that Step1 is obtained
Area is amplified to a square area by direction, obtains all grids number in this amplification area；
Step3:The all unduplicated grid number that statistics Step2 is obtained, this set are designated as S；
Step4:According to the grid list that cluster classification is covered by the base station number and each base station of " n ", cluster class is found
The grid number not covered by " n ", this set are designated as N；
Step5:According to formula (3) computation grid Duplication (OverlapRatio):The grid Duplication is " point of interest class
Not " by grid number set S and the Duplication that cluster classification is the grid number set N that " n " is covered of " s "；
For example, " live ", " work " etc.；Cluster classification is represented for the base station of " N "
The station list of " N " class is shown as in cluster result, the feature of itself is determined the amplification in Step2 by " S ", such as " occupy
Firmly " the point of interest of classification, generally one house, and the area coverage in a house is generally 30m × 30m=900m2If,
Calculate according to the area that 9.6m × 11.1m is a grid, then classification should be with the grid at point of interest place for the point of interest of " inhabitation "
Amplify nine times centered on lattice, i.e., the square area of 3 × 3 centered on the grid being located by the point of interest.
With single cellular base station scope as unit region, the present invention is carried using the interest point data of Hangzhou certain area
The functional areas recognition methodss for going out are verified.
Step one：Map separates
Choose 120.040 °～120.410 ° of Hangzhou, Zhejiang province city longitude as shown in Figure 1,30.090 °～30.400 ° of latitude
In the range of rectangular area as object of study, be 0.0001 ° × 0.0001 ° (about 9.6m × 11.1m) by this region division
Grid, and the cellular base station longitude and latitude degrees of data according to Hangzhou operator divides city using grid ownership computational methods
Unit area, division result are as shown in Figure 2.
As described above, after one of ordinary skill in the art reads file of the present invention, technology according to the present invention scheme with
Technology design makes other various corresponding conversion schemes without the need for creative mental work, belongs to the model protected by the present invention
Enclose.
Step 2：Find the base station belonging to point of interest
Baidu's interest point data is commonly used at home, and its city space distribution and practical situation kiss substantially
Close, it is ensured that the accuracy of data and reliability, therefore extract interest point data of the Baidu in research range and studied.The number
According to the interest point information included in research range more than 110,000, title, longitude and latitude comprising point of interest, better address, interest
The point parameter such as classification and telephone number.Interest point data is processed according to " point of interest category " parameter in research, by interest
Point data is divided into shopping, work, inhabitation, tourism, colleges and universities' culture and education, primary school's kindergarten, middle school, medical treatment, entertainment, life clothes
Business, financial service, automobile services, station, parking lot, 16 big class of cuisines and hotel.
Step 3：Calculate each base station point of interest distribution characteristicss
Represent base station number with i, j represents the classification of point of interest, wherein i=1,2,3 ..., j=1,2,3 ..., 16.Gained is tied
Distributed number of the fruit for the affiliated point of interest category j of base station i, such as distributed number list of the table 1 for the affiliated point of interest category j of base station i.
Finally, grid number according to shared by combining is processed to the result of table 1 using normalized method, obtain for post analysis
Matrix Y.
Table 1
Step 4：Cluster：Base station cluster analyses are carried out to matrix of consequence Y according to clustering method proposed by the present invention.Take ginseng
Number C=4, will survey region be divided into the different functional area of 4 classes, finally analysis result is visualized, as a result as shown in Figure 3.
Step 5：Identification urban function region
" inhabitation ", " work " and " tourism " the three big eigenvalue that chooses in " point of interest category " parameter carries out base station functions knowledge
Not.According to the Duplication computational methods of the present invention, Duplication calculating is carried out to cluster result, result of calculation such as table 2 is step 5
Duplication result of calculation.When point of interest area is amplified, in conjunction with practical situation, it is the emerging of " inhabitation " and " work " to classification
The area that interest point amplifies is 30m × 30m, i.e., centered on the affiliated grid of each point of interest, 3 × 3 square area；And to class
The area that the point of interest that " Wei do not traveled " amplifies is 90m × 90m, i.e., centered on the affiliated grid of each point of interest, 9 × 9 just
Square region.
| Duplication (%) | Color 4 | Color 3 | Color 1 | Color 2 |
| Work | 1.37 | 1.69 | 1.86 | 0.49 |
| Live | 0.30 | 0.93 | 4.65 | 0.08 |
| Tourism | 0.14 | 0.17 | 0.36 | 0.88 |
Table 2
According to the Duplication result of calculation of table 2, can be determined that the function in 1 region of color in Fig. 3 should be " to live first
Area ", the function in 2 region of color should be " tourist district ", because their Duplication is more a lot of than being higher by for other colors.Secondly,
It is also in 1 region of color, but due to " inhabitation " and face that " point of interest category " is the maximum of the Duplication result of calculation of " work "
The Duplication in 1 region of color is far higher by its Duplication with other color regions, it is clear that 1 region of color should be " residential area ", rather than
" working area ".In addition " work " relative also not low with the Duplication in 3 region of 4 region of color and color, therefore 4 region of color and color
The function that must have one in the middle of 3 regions is " work ".And in a practical situation, " residential area " is often close with " working area " can not
Point, both are often adjacent on geographical position, adjacent with 1 region of color most for 3 region of color, 4th area of color in Fig. 3
Domain is mostly adjacent with color 3 and 2 region of color, and therefore, 3 region of color should be " working area ".Finally, in Fig. 3, region A is Hangzhou
Famous West Lake scenic spot, hidden etc. including the West Lake, Dragon Well tea, spirit, this region landform mostly is mountain area, so, the region is except interest
Point classification is outside the point of interest of " tourism " seldom, or even there be not in some base station ranges substantially the point of interest distribution of remaining classification
Point of interest is distributed.In Fig. 3, except color 2,4 part accounting of color is slightly more than remaining color for a-quadrant, and the function in 2 region of color
" tourist district " is judged as, then the function in 4 region of color is less " the uninhabited area " of point of interest distribution.
Understand that the recognition result in each region in city is as described below in Fig. 3 through above analysis：1 region of color is " residential area "；
2 region of color is " tourist district "；3 region of color is " working area "；4 region of color is " uninhabited area ".
With the inventive method, in embodiment, the goodness of fit of each functional area is as follows：
(1) " residential block " goodness of fit
The Computer-aided mapping of Fig. 4 Hangzhous 2001-2020, Fig. 5 be identical longitude and latitude under the conditions of according to the present invention
Projection of " residential block " scattergram of method identification on the Computer-aided mapping of Hangzhou 2001-2020, black in figure
Part is identified as distribution of the region of " residential block " on map according to the inventive method, during it is with Hangzhou master plan
Residential land coincide substantially.It follows that being consistent with actual substantially to the recognition result of " residential block " herein.
(2) " tourist district " goodness of fit
According to Fig. 6, projection of the present invention to the recognition result of " tourist district " in Baidu map is also basic with actual
It is consistent.Base station work(of the experimental result to scenic spots such as coverings " Liangzhu Culture village ", " western small stream wetland ", " Westlake Scenic Spot " and " Xiang Hu "
Accurately identification can be made that.
(3) " working area " goodness of fit
" working area " of the method according to the invention identification and Computer-aided mapping of Fig. 4 Hangzhous 2001-2020
In may be defined as " working area " " public administration with public service facility land used ", " commerce services industry facilities land " and " industry
Land used " distribution coincide substantially.3 region of color in conjunction with " work " point of interest distribution thermodynamic chart and Fig. 3 of Fig. 7 is understood according to this
" working area " of bright method identification is consistent substantially with actual.
Comprehensive (1), (2), the goodness of fit analysis of (3) understand, proposed by the present invention according to interest point data identification city work(
The method in energy area is matched with actual substantially to the recognition result of urban area function.
Claims (6)
1. a kind of based on interest point data recognize urban function region method, it is characterised in that comprise the following steps：
Step one, map segmentation：By map rasterizing, and all grids are numbered；According to cellular base station position dividedly
Figure, calculates the distance of each grid and base station, and regulation grid belongs to the base station nearest from it, obtain apart from each base station distance most
Near grid list, and grid matrix number G shared by each base station；
Base station belonging to step 2, searching point of interest：The base station nearest apart from the point of interest is found, and judges that this point of interest belongs to
The base station, obtains all interest point lists for belonging to each base station；
Step 3, each base station point of interest distribution characteristicss of calculating：According to " point of interest class in the data of each base station interest point list
" this parameter does not carry out classified statistic to the point of interest of each base station, obtains the point of interest category distribution matrix D of each base station；And
Point of interest category distribution matrix D is processed to which using normalized method with reference to shared grid matrix number G, is obtained final
For the matrix that analyzes, the matrix is named as Y；
Step 4, cluster：Matrix Y in step 3 carries out fuzzy cluster analysis, obtains different cluster results；
Step 5, identification urban function region：Calculate the different cluster results that the point of interest with category feature and step 4 are obtained
Distribution Duplication on map, is identified to each base station after cluster.
2. as claimed in claim 1 a kind of based on interest point data recognize urban function region method, it is characterised in that described
In step 3, normalization processing method is as follows：
Respectively point of interest category distribution matrix D and shared grid matrix number G are normalized using formula (1), by two
Matrix normalization is in the interval of [0,1], and is combined both normalization results by formula (2),
Y=A e-X(2)
In formula (1), { xiBe sample set, xiFor all sample components of sample set, xmaxFor each component of all samples of sample set most
Big value, xminMinima for each component of all samples of sample set；
In formula (2), Y is the matrix eventually for analysis, and dimension is n × m；A be point of interest category distribution matrix D according to formula (1)
Matrix after normalization, dimension are n × m；X be shared grid matrix number G according to the matrix after formula (1) normalization, dimension is 1 ×
n；N is base station number, and m is point of interest category number.
3. as claimed in claim 1 a kind of based on interest point data recognize urban function region method, it is characterised in that step
In four, institute's directed quantity is divided into C cluster using C means clustering algorithms by the fuzzy cluster analysis, and tries to achieve the cluster of each cluster
Center so that cluster internal variance and reach minimum；
Clustered by C averages fuzzy clustering algorithm again, the result for drawing is the probability list that base station i belongs to different clusters, then,
The class belonging to maximums of the base station i in all kinds of probabilities is extracted, such classification belonging to the i of base station is defined, is obtained each base station
The list of generic, the list are cluster result.
4. as claimed in claim 1 a kind of based on interest point data recognize urban function region method, it is characterised in that step
In five, point of interest and Duplication that cluster classification be the base station of " n " distribution on map of the point of interest category for " s " is calculated,
By input：" according to the grid list that the point of interest that point of interest category is " s " is located；Cluster classification is covered by the base station of " n "
Grid list ", obtain Duplication.
5. as claimed in claim 4 a kind of based on interest point data recognize urban function region method, it is characterised in that step
In five, the point of interest that " point of interest category " is " s " is calculated with the Duplication that cluster classification is distribution of the base station of " n " on map
Concrete grammar as follows：
Step1:According to each point of interest longitude and latitude that " point of interest category " is " s ", their place grids number are found out；
Step2:Area is amplified according to the feature of " s ", i.e., southeastward northwest four direction centered on the grid number that Step1 is obtained
Area is amplified to a square area, all grids number in this amplification area are obtained；
Step3:The all unduplicated grid number that statistics Step2 is obtained, this set are designated as S；
Step4:According to the grid list that cluster classification is covered by the base station number and each base station of " n ", finding cluster classification is
The grid number covered by " n ", this set are designated as N；
Step5:According to formula (3) computation grid Duplication (OverlapRatio):The grid Duplication is " point of interest category "
Grid number set S and the Duplication that cluster classification is the grid number set N that " n " is covered by " s "；
6. as claimed in claim 1 a kind of based on interest point data recognize urban function region method, it is characterised in that step
In one, cellular base station position segmentation map is utilized using the method that finds from the nearest base station of grid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610887062.8A CN106503714B (en) | 2016-10-11 | 2016-10-11 | Method for identifying city functional area based on point of interest data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610887062.8A CN106503714B (en) | 2016-10-11 | 2016-10-11 | Method for identifying city functional area based on point of interest data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106503714A true CN106503714A (en) | 2017-03-15 |
| CN106503714B CN106503714B (en) | 2020-01-03 |
Family
ID=58294741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610887062.8A Active CN106503714B (en) | 2016-10-11 | 2016-10-11 | Method for identifying city functional area based on point of interest data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503714B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991142A (en) * | 2017-03-22 | 2017-07-28 | 湖州师范学院 | A kind of method that urban function region is recognized based on wechat data and interest point data |
| CN107220308A (en) * | 2017-05-11 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | POI rational detection method and device, equipment and computer-readable recording medium |
| CN108182253A (en) * | 2017-12-29 | 2018-06-19 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN108334624A (en) * | 2018-02-09 | 2018-07-27 | 城市生活（北京）资讯有限公司 | A kind of POI identification processing methods and device |
| CN108876475A (en) * | 2018-07-12 | 2018-11-23 | 青岛理工大学 | A kind of urban function region recognition methods, server and storage medium based on point of interest acquisition |
| CN109523186A (en) * | 2018-11-28 | 2019-03-26 | 杭州中奥科技有限公司 | Urban area partitioning method and device |
| CN109688532A (en) * | 2017-10-16 | 2019-04-26 | 中移(苏州)软件技术有限公司 | A kind of method and device dividing city function region |
| 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 |
| CN110766589A (en) * | 2019-10-28 | 2020-02-07 | 电子科技大学 | Method for deducing city function based on communication data and interest point data |
| CN110866156A (en) * | 2019-11-26 | 2020-03-06 | 北京明略软件系统有限公司 | Method, device, equipment and medium for identifying functional park based on social data |
| CN111985514A (en) * | 2019-05-23 | 2020-11-24 | 顺丰科技有限公司 | Business circle identification method and device, electronic equipment and storage medium |
| CN112257970A (en) * | 2019-07-22 | 2021-01-22 | 山东科技大学 | Automatic city functional area dividing method based on interest point big data |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
| CN114937215A (en) * | 2022-06-10 | 2022-08-23 | 中国科学院地理科学与资源研究所 | Method and device for identifying urban functional area |
| CN116756262A (en) * | 2023-08-15 | 2023-09-15 | 北京博道焦点科技有限公司 | Electronic fence generation method and system based on map interest point auditing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456233A (en) * | 2012-05-28 | 2013-12-18 | 腾讯科技（深圳）有限公司 | Method and system for searching interest points based on electronic map |
| CN104457743A (en) * | 2014-12-17 | 2015-03-25 | 深圳市亲觅科技有限公司 | Footmark processing method of intelligent wearing device |
| CN104834666A (en) * | 2015-03-06 | 2015-08-12 | 中山大学 | Acoustic environment functional area partitioning method based on road network and interest points |
| CN105657725A (en) * | 2016-02-01 | 2016-06-08 | 重庆邮电大学 | Method for defining radiating area of urban function area based on mobile phone signaling data |
| CN105740401A (en) * | 2016-01-28 | 2016-07-06 | 北京理工大学 | Individual behavior and group interest-based interest place recommendation method and device |
-
2016
- 2016-10-11 CN CN201610887062.8A patent/CN106503714B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456233A (en) * | 2012-05-28 | 2013-12-18 | 腾讯科技（深圳）有限公司 | Method and system for searching interest points based on electronic map |
| CN104457743A (en) * | 2014-12-17 | 2015-03-25 | 深圳市亲觅科技有限公司 | Footmark processing method of intelligent wearing device |
| CN104834666A (en) * | 2015-03-06 | 2015-08-12 | 中山大学 | Acoustic environment functional area partitioning method based on road network and interest points |
| CN105740401A (en) * | 2016-01-28 | 2016-07-06 | 北京理工大学 | Individual behavior and group interest-based interest place recommendation method and device |
| CN105657725A (en) * | 2016-02-01 | 2016-06-08 | 重庆邮电大学 | Method for defining radiating area of urban function area based on mobile phone signaling data |
Non-Patent Citations (6)
| Title |
|---|
| JING YUAN 等: "Discovering Regions of Different Functions in a City Using Human Mobility and POIs", 《PROCEEDINGS OF THE 18TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING》 * |
| VÍCTOR SOTO 等: "Automated Land Use Identification using Cell-Phone", 《HOTPLANET 11 PROCEEDINGS OF THE 3RD ACM INTERNATIONAL WORKSHOP ON MOBIARCH》 * |
| 吴健生 等: "基于手机基站数据的城市交通流量模拟", 《地理学报》 * |
| 江贵林 等: "基于呼叫详细记录数据的城市功能区识别", 《计算机应用》 * |
| 池娇 等: "基于POI数据的城市功能区定量识别及其可视化", 《测绘地理信息》 * |
| 辜寄蓉 等: "城市功能区划分空间聚类算法研究", 《测绘科学》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991142A (en) * | 2017-03-22 | 2017-07-28 | 湖州师范学院 | A kind of method that urban function region is recognized based on wechat data and interest point data |
| CN107220308A (en) * | 2017-05-11 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | POI rational detection method and device, equipment and computer-readable recording medium |
| CN109688532B (en) * | 2017-10-16 | 2020-11-24 | 中移(苏州)软件技术有限公司 | Method and device for dividing city functional area |
| CN109688532A (en) * | 2017-10-16 | 2019-04-26 | 中移(苏州)软件技术有限公司 | A kind of method and device dividing city function region |
| CN108182253A (en) * | 2017-12-29 | 2018-06-19 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN108182253B (en) * | 2017-12-29 | 2021-12-28 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN108334624A (en) * | 2018-02-09 | 2018-07-27 | 城市生活（北京）资讯有限公司 | A kind of POI identification processing methods and device |
| CN108876475A (en) * | 2018-07-12 | 2018-11-23 | 青岛理工大学 | A kind of urban function region recognition methods, server and storage medium based on point of interest acquisition |
| CN108876475B (en) * | 2018-07-12 | 2022-02-01 | 青岛理工大学 | City functional area identification method based on interest point acquisition, server and storage medium |
| CN109523186A (en) * | 2018-11-28 | 2019-03-26 | 杭州中奥科技有限公司 | Urban area partitioning method and device |
| CN109523186B (en) * | 2018-11-28 | 2021-02-09 | 杭州中奥科技有限公司 | Urban area division method and device |
| CN111985514A (en) * | 2019-05-23 | 2020-11-24 | 顺丰科技有限公司 | Business circle identification method and device, electronic equipment and storage medium |
| 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 |
| CN112257970A (en) * | 2019-07-22 | 2021-01-22 | 山东科技大学 | Automatic city functional area dividing method based on interest point big data |
| CN110766589A (en) * | 2019-10-28 | 2020-02-07 | 电子科技大学 | Method for deducing city function based on communication data and interest point data |
| CN110866156A (en) * | 2019-11-26 | 2020-03-06 | 北京明略软件系统有限公司 | Method, device, equipment and medium for identifying functional park based on social data |
| CN110866156B (en) * | 2019-11-26 | 2022-05-17 | 北京明略软件系统有限公司 | Method, device, equipment and medium for identifying functional park based on social data |
| CN112784423A (en) * | 2021-01-28 | 2021-05-11 | 河北师范大学 | Urban area feature analysis method based on complex network |
| CN114937215A (en) * | 2022-06-10 | 2022-08-23 | 中国科学院地理科学与资源研究所 | Method and device for identifying urban functional area |
| CN116756262A (en) * | 2023-08-15 | 2023-09-15 | 北京博道焦点科技有限公司 | Electronic fence generation method and system based on map interest point auditing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106503714B (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503714A (en) | A kind of method that urban function region is recognized based on interest point data | |
| CN106991142A (en) | A kind of method that urban function region is recognized based on wechat data and interest point data | |
| CN109325085B (en) | A kind of urban land identification of function and change detecting method | |
| CN110348506B (en) | Land use classification method based on remote sensing image, storage medium and computing device | |
| CN108920481B (en) | Road network reconstruction method and system based on mobile phone positioning data | |
| Shi et al. | Reconsideration of the methodology for estimation of land population carrying capacity in Shanghai metropolis | |
| CN102332210B (en) | Method for extracting real-time urban road traffic flow data based on mobile phone positioning data | |
| CN105138668A (en) | Urban business center and retailing format concentrated area identification method based on POI data | |
| CN109508585A (en) | A method of urban function region is extracted based on POI and high-resolution remote sensing image | |
| CN108052876B (en) | Regional development assessment method and device based on image recognition | |
| CN109189917A (en) | A kind of city function limited region dividing method and system merging landscape and social characteristic | |
| CN109359162A (en) | A kind of school's site selecting method based on GIS | |
| CN107872808A (en) | A kind of WLAN sites prediction analysis method and device | |
| WO2018045529A1 (en) | Network station site planning method and device | |
| CN111563666B (en) | Urban public service facility space configuration evaluation method based on network heat | |
| CN112633774A (en) | Intelligent homeland space planning auxiliary compilation method and system | |
| Jiao et al. | Understanding the land use function of station areas based on spatiotemporal similarity in rail transit ridership: A case study in Shanghai, China | |
| CN106547862A (en) | Traffic big data dimension-reduction treatment method based on manifold learning | |
| CN111708859B (en) | Business circle boundary identification method based on spatial data | |
| Zhou et al. | Village-town system in suburban areas based on cellphone signaling mining and network hierarchy structure analysis | |
| Tian et al. | Suburban sprawl measurement and landscape analysis of cropland and ecological land: A case study of Jiangsu Province, China | |
| CN106529560B (en) | A kind of recognition methods of the urban function region of the comprehensive density of population and landscape structure | |
| Cui et al. | Spatial Pattern and Mechanism of the Life Service Industry in Polycentric Cities: Experience from Wuhan, China | |
| Wu et al. | Urban functional area recognition based on unbalanced clustering | |
| Zhao et al. | Urban spatial structure analysis: quantitative identification of urban social functions using building footprints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |