CN110297875B - Method and device for evaluating contact demand compactness among functional areas of city - Google Patents
Method and device for evaluating contact demand compactness among functional areas of city Download PDFInfo
- Publication number
- CN110297875B CN110297875B CN201910400753.4A CN201910400753A CN110297875B CN 110297875 B CN110297875 B CN 110297875B CN 201910400753 A CN201910400753 A CN 201910400753A CN 110297875 B CN110297875 B CN 110297875B
- Authority
- CN
- China
- Prior art keywords
- base station
- area
- functional
- data set
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013508 migration Methods 0.000 claims abstract description 32
- 230000005012 migration Effects 0.000 claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 230000000694 effects Effects 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims 1
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000005295 random walk Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G06Q50/40—
Abstract
The invention discloses a method and a device for evaluating the contact demand compactness among functional areas of a city, wherein the method comprises the following steps: determining a data set for urban area division; determining a functional area where the base station is located through a clustering algorithm according to the characteristics of the flow time sequence of the base station; clustering the base stations through the functional area data set where the base stations are located and the geographical position data set of the base stations to obtain the classification result of each functional area of the city; and evaluating the link demand closeness index among the functional areas based on the Newton gravitation model of population activity aiming at the population migration volume and the population migration volume of each divided functional area and the distance among the areas.
Description
Technical Field
The invention relates to the field of city planning, in particular to a method and a device for evaluating the contact demand compactness among functional areas of a city.
Background
Urban regional division is the most important link in urban planning, and reasonable regional division is of great importance to urban development. Toole J L et al use new dynamic data generated by cell phones to measure spatiotemporal changes of population, use machine learning algorithms to identify regions with the same function, measure land use non-uniformity[1]. Tao P et al restore the user's activities from the mobile phone data, mine the social functional features, combine the physical features of the urban land itself, and obtain the functional types of the urban land by fuzzy clustering method[2]. Wang M et al established a linear regression model to predict the traffic flow in Beijing City, and explored the relationship between regional functions and human activities[3]. Zhong G et al use mobile phone data to characterize passenger flow of traffic hubs, study travel characteristics of urban passengers at different time intervals, and provide a passenger active area identification method based on space-time clustering[4]. Xuhui M et al propose a partitioning method based on road network reachability, establish a reachability matrix to analyze the network reachability, select an optimal reachability node as a core node, and select a node cluster of the core node as a result of sub-regions[5]. The research methods measure the functions of the urban area and measure the urban areaHowever, the area after the division is not controlled within a reasonable range, and there is a possibility that an excessively large or excessively small area may occur.
With the acceleration of the economic integration process, the connection and division of labor among urban areas are more definite. Dong L et al studied the intensity of the interrelationship of the tourist areas and the membership degree of the tourist economy among the areas by means of a model of the tourist economy, and studied and analyzed the internal relation of the tourist economy by calculating the strength and direction of the relation among the areas[6]. Trasarti R et al propose a sequential pattern of extraction of temporal and spatial constraints for real scenes of two different spatial scales, the paris zone and the whole france, which enables to capture the correlation between geographic regions according to a significant common variation of the estimation[7]. Xuejun D et al studied the spatial structure of the tourist attraction system in Nanjing city by using the correlation dimension method based on the geographical features and tourist attraction systems of Nanjing, and determined the fractal dimension values between the tourist areas of Nanjing[8]. The Timberlay M takes the functional areas of cities as research units, strengthens the research on the dense areas of cities and towns, and finds out the fit relation among the areas[9]. Zhan J et al consider that the construction of regional infrastructure is a prerequisite for regional urbanization, and explore the interdependence and interaction relationship between city and countryside by researching the complete condition of public infrastructure[10]. Pingde Z et al applied the software Eviews of the metrology economics to study the quantitative relationship between the economic growth of the logistics industry, cities and regions and to measure the economic coordination relationship of the relevant regions[11]. The research starts from a single aspect, the consideration of the influence factors of the regional connection is not comprehensive, the used data is traditional static data, and the description of the regional connection is one-sidedly.
Disclosure of Invention
The embodiment of the invention provides a method and a device for evaluating the compactness of contact requirements among functional areas of a city, the method comprises processing the user network traffic log to generate base station traffic time sequence, extracting characteristics of the base station traffic time sequence from statistics, time domain and frequency domain, obtaining functional characteristics of the base station by using clustering algorithm, converting longitude and latitude coordinates of the base station into mercator coordinates as geographical position characteristics of the base station, then the functional characteristics and the geographical position characteristics of the base station are used as input, a clustering algorithm is used for obtaining the result of urban area division, finally the population migration volume, the migration volume and the distance between areas of the areas are calculated, the proposed Newton gravitation model based on population activity is used for obtaining the contact compactness between the areas, the method has important significance for understanding the inter-regional connection, improving the living standard of residents and developing urban economy.
The embodiment of the invention discloses a method for evaluating the contact demand compactness among functional areas of a city, which comprises the following steps: determining a data set for urban area division; determining a functional area where the base station is located through a clustering algorithm according to the characteristics of the flow time sequence of the base station; clustering the base stations through the functional area data set where the base stations are located and the geographical position data set of the base stations to obtain the classification result of each functional area of the city; and evaluating the link demand closeness index among the functional areas based on the Newton gravitation model of population activity aiming at the population migration volume and the population migration volume of each divided functional area and the distance among the areas.
The embodiment of the invention also discloses a device for evaluating the contact demand compactness among all the functional areas of a city, which comprises the following steps: the parameter set setting module is used for setting a parameter set corresponding to the clustering algorithm; the data set acquisition and preprocessing module is used for acquiring a base station flow time sequence and preprocessing the base station flow time sequence into a base station characteristic data set; the division model module is used for taking the processed characteristic data set as input and applying a clustering algorithm to obtain a region division result; and the contact closeness calculation module is used for calculating the contact closeness among the divided regions.
As can be seen from the above embodiments of the present invention, the embodiments of the present invention comprehensively consider the functions and the geographic locations of the base stations according to the actual situations, and determine the input features in the clustering algorithm. Meanwhile, the clustering algorithm in the embodiment of the invention adopts a k-means + + algorithm instead of the traditional k-means algorithm. The initial k clustering centers in k-means need to be given manually or generated randomly, and the final clustering results may be different due to different initial centers. Only 1 class center is initialized by k-means + +, the remaining k-1 class centers are selected in the algorithm operation process, and the selection of the center point is more reasonable compared with the selection of the k-means. When the inter-area contact tightness is measured, factors such as population migration-in and migration-out of areas, distance between areas and the like are comprehensively considered, the considered factors are diversified, and certain rationality is achieved. The method solves the limitations of unreasonable area, unreasonable number and unreasonable shape of the areas in the area division, meets the basic requirements of the area division in the urban planning, and has positive effects on understanding the relation among the areas and promoting the economic development of the areas.
Drawings
FIG. 1 is a flowchart illustrating a method for evaluating closeness of contact requirements between functional areas of a city according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating another embodiment of the method for evaluating the closeness of contact requirements between functional areas of a city according to the present invention;
FIG. 3 is a flow chart of a method of obtaining a functional characteristic data set of a base station in accordance with the present invention;
FIG. 4 is a flow chart of a method of obtaining a geographic location feature data set for a base station in accordance with the present invention;
FIG. 5 is a flowchart of a method for obtaining inter-domain connections according to the present invention;
FIG. 6 is a block diagram of an embodiment of an apparatus for evaluating the closeness of contact requirements between functional areas in a city according to the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Example one
The embodiment of the present invention provides a method for evaluating the closeness of connection requirements between functional areas in a city, please refer to fig. 1, which includes the following steps:
step 101: determining a data set for urban area division;
step 102: determining a functional area where the base station is located through a clustering algorithm according to the characteristics of the flow time sequence of the base station;
step 103: clustering the base stations through the functional area data set where the base stations are located and the geographical position data set of the base stations to obtain the classification result of each functional area of the city;
step 104: and evaluating the link demand closeness index among the functional areas based on the Newton gravitation model of population activity aiming at the population migration volume and the population migration volume of each divided functional area and the distance among the areas.
Referring to fig. 2, a flowchart of another embodiment of the method for evaluating the closeness of connection requirements between functional areas of a city according to the present invention includes the following steps:
step 201: determining a corresponding parameter set in a clustering algorithm, wherein the main parameters comprise the number of the types of clustering, the maximum iteration times, the times of running the algorithm at different initial centers, the minimum threshold value for achieving convergence and the like;
step 202: determining a functional characteristic data set of a base station when an urban area is divided;
referring to fig. 3, a specific implementation of the method for constructing a functional feature data set of a base station includes the following steps:
step 301: constructing a base station flow time sequence;
step 302: the method comprises the steps of extracting the characteristics of the base station flow time sequence from statistics, and selecting four indexes of mean value, variance, skewness and kurtosis.
The mean is a measure of the trend in the data set and is calculated as follows:
where μ is the mean value, xiIs the ith numerical value, and n is the data number.
The variance is a statistic reflecting the degree of dispersion of data, and the calculation formula is as follows:
wherein σ2Is the variance, μ is the mean, xiIs the ith numerical value, and n is the data number. The larger the variance, the greater the degree of data dispersion, and the more dispersed the data distribution.
Skewness is the number of data representing the symmetric situation of data distribution, and the calculation formula is as follows:
wherein S represents skewness, μ is mean, xiIs the ith numerical value, and n is the data number. If the skewness is 0, perfect symmetry is achieved, and data are represented as normal distribution; the skewness is larger than 0, the data is in a positive skew state and is represented as a long tail on the right side; the skewness is less than 0, and the data is negatively biased and appears as a long left tail.
The kurtosis is a measurement value reflecting the degree of steepness of data distribution, and the calculation formula is as follows:
wherein K represents kurtosis, mu is mean value, xiIs the ith numerical value, and n is the data number. The kurtosis of the data is usually determined by using the kurtosis of the normal distribution as a reference standard. The kurtosis of the normal distribution is 3, and if the kurtosis is greater than 3, the data distribution curve is sharper than the normal distribution, and if the kurtosis is less than 3, the data distribution curve is more gentle.
Step 303: the characteristics of the base station flow are extracted from the time domain, and the index of the Hurst index is selected.
The Hurst index is an index for determining whether time-series data is random walk or biased random walk. The calculation process of the Hurst index comprises seven steps, which are as follows:
(1) time series X ═ X1，...，xi，...，xTGet the logarithm sequence Y ═ Y }1，...，yi，...，yT-1In which yiIs calculated by the formula
Dividing the sequence Y into n subintervals, each subinterval having a length L, each subinterval being defined as Aj＝{a1j，...，aij，...，aLj}，1＜j＜n
(2) Calculating the mean value mu of each subintervalj
(3) Calculate each subinterval AjCumulative intercept to mean Ek，j
(4) Calculating the range Rj
Rj＝max(Ek，j)-min(Ek，i)，1≤k≤n
(5) Calculate each subinterval AjStandard deviation of (S)j
(6) Each RjAre all formed by corresponding SjNormalized, redefined as R/S:
(7) and (3) continuously increasing the interval length L, and repeating the steps from 1 to 6 until the L is equal to (T-1)/2. Log (n) is the independent variable, log ((R/S)n) As dependent variable, log ((R/S)n) Linear regression was performed on H · log (n) + c, where c is a constant and the slope H is the estimated Hurst value.
Step 304: and extracting the characteristics of the base station flow from the frequency domain, and selecting a coefficient after DWT conversion.
DWT represents the original time series with a few wavelet parameters. The time series is treated as discrete signals x n which are passed through a low-pass filter g with impulse response, the signals being simultaneously decomposed by a high-pass filter h. The signal output from the low-pass filter is then down-sampled and passed through a new low-pass filter and a new high-pass filter again, and is repeated in succession.
The ith layer in the structure outputs:
step 305: the characteristic of the base station flow is used as input, a clustering algorithm is applied, and the output is the functional characteristic of the base station, namely the base station serves a certain functional area in a working area, a residential area and a mixed area.
After the functional feature data set of the base station is obtained, the flow returns to the urban area division method, and step 203 is executed.
Step 203: determining a geographical position characteristic data set of a base station when a city area is divided;
referring to fig. 4, a specific implementation of the method for constructing a geographical location feature data set of a base station includes the following steps:
step 401: the Location Area Code (LAC) of a base station is combined with the Cell identity (Cell Id, CI), which uniquely identifies a base station.
Step 402: and comparing the LAC of the base station with the CI to form a conversion table, converting the conversion table into corresponding longitude and latitude, and determining the specific physical position coordinate of the base station.
Step 403: and converting the longitude and latitude coordinates of the base station into the mercator coordinates. The longitude and latitude of one point on the earth surface is (alpha, beta), and the corresponding calculation formula of the mercator coordinates (x, y) is as follows:
x＝R·(α-α0)
y＝ln(tan(α)+sec(α))
wherein R is the equatorial radius, alpha0The longitude of the central meridian.
After the geographical location feature data set of the base station is obtained, the flow of the urban area division method is returned to, and step 204 is executed.
Step 204: and taking the functional characteristics and the geographical position characteristics of the base station as input, setting parameters according to the input parameter set by using a clustering algorithm, and outputting the result as a city region division result.
Step 205: and calculating the connection compactness among the regions aiming at the divided regions.
Referring to fig. 5, a specific implementation of the method for calculating the closeness of connection between regions includes the following steps: step 501: and determining the population migration volume and the population migration volume of the area. Extracting fields related to the user and the base station from the original data, replacing the base station with an area where the base station is located, and sequencing according to time to obtain a preliminary movement behavior record of the user; the user may have a continuous record showing that the user is in the same area, and at this time, the continuous records are merged into one record, and the final movement behavior data of the user is obtained through processing, and the form is as follows:
wherein Q ismRepresents the line of movement of the mth userFor data, M represents the number of users,
and
represents the m-th user at the moment
In a region
Within, z represents a data dimension. After the mobile data of the user between the areas is obtained, the population immigration number I of the area I can be calculatediAnd the emigration amount OiThe calculation formula is as follows:
Ii＝Ci-Gi
Oi＝Ci-Hi
wherein, CiIs the number of times zone i appears in all user movement behavior data, GiIs the number of times that the region i appears as the starting point of the user's movement in all the user movement behavior data, HiThe number of times the area i appears as the end point of the user's movement in all the user movement behavior data.
Step 502: the center of each region is determined. Let the longitude and latitude coordinates of the base stations in area i be
The central calculation formula of the area i is as follows:
wherein, lon(i)And lat(i)Is the longitude of the center of area iAnd the latitude, the number of times of the flight,
and
is the longitude and latitude of the p-th base station in area i, and n is the number of base stations in area i.
Step 503: for the distance D between the centers of the region i and the region ji，jAnd (6) solving. At this time, the region i and the region j are far away from each other and cannot be directly solved by the Euclidean distance of the plane, so that the haversine formula capable of directly calculating the spherical distance is adopted to solve the Di，jThe concrete formula is as follows:
Di，f＝2R·arcsin(h)
wherein R is the equatorial radius,
wherein, lon(i)And lat(i)Is the longitude and latitude, lon, of the center of the area i(j)And lat(j)Is the longitude and latitude of the center of region j.
Step 504: the region relation is calculated by using a Newton gravitation model based on population activities, and the formula is as follows:
wherein, Fi，jIs a connection of area I and area j, IiAnd OiIs the population migration in and out number of area I, IjAnd OjIs the population migration in and out number, D, of the region ji，jIs the distance between the centers of the regions. Since the association between different regions is studied here, the association of a region with itself is ignored and its value is set to 0.
Therefore, all implementation steps of the method for evaluating the closeness of the connection requirements among the functional areas of the city are completed.
Example two
An embodiment of the present invention provides a device for evaluating the closeness of connection requirements between functional areas in a city, please refer to fig. 6. The apparatus includes a parameter set setting module 601, a data set acquisition and preprocessing module 602, a partitioning model module 603, and a contact affinity calculation module 604. The internal structure and connection relationship of the device will be further described below in conjunction with the working principle of the device.
A parameter set setting module 601, configured to set a parameter set of a clustering algorithm;
a data set obtaining and preprocessing module 602, configured to obtain a base station traffic time sequence and preprocess the base station traffic time sequence into a base station characteristic data set;
and the partitioning model module 603 is configured to obtain a final partitioning result by using a clustering algorithm with the processed feature data set as an input.
The contact affinity calculation module 604 calculates contact affinity between the regions by using a newton gravity model based on population activities for the divided regions.
The data set obtaining and preprocessing module 602 includes:
a base station traffic time sequence constructing module 605, configured to process internet traffic log data of a user into a base station traffic time sequence;
a base station functional characteristic constructing module 606, configured to extract characteristics of a base station traffic time sequence, and obtain functional characteristics of a base station by applying a clustering algorithm, that is, the base station serves a certain functional area;
the base station geographic location feature construction module 607 is configured to convert the longitude and latitude coordinates of the base station into mercator coordinates, so as to obtain the geographic location feature of the base station.
The contact closeness calculation module 604 includes:
the regional population migration volume and migration volume calculation module 608 is configured to process internet traffic log data of the user into user regional transfer data, so as to obtain a regional population migration volume and a regional population migration volume;
an inter-region distance calculating module 609, configured to calculate a center position of the obtained region, and then calculate a distance between the regions by using a haversine formula;
and the Newton gravitation model module 610 based on population activities is used for taking the migration volume of the regional population, the migration volume and the distance between the regions as input and outputting the input as the connection compactness between the regions.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Reference to the literature
[1]Toole J L,Ulm M,González M C,et al.Inferring land use from mobile phone activity[A].//Proceedings of the Acm Sigkdd International Workshop on Urban Computing[C],New York:ACM,2012:1-8.
[2]Tao P,Sobolevsky S,Ratti C,et al.A new insight into land use classification based on aggregated mobile phone data[J].International Journal of Geographical Information Science,2014,28(9):1988-2007.
[3]Wang M,Yang S,Sun Y,et al.Human mobility prediction from region functions with taxi trajectories[J].Plos One,2017,12(11):e0188735.
[4]Zhong G,Wan X,Zhang J,et al.Characterizing Passenger Flow for a Transportation Hub Based on Mobile Phone Data[J].IEEE Transactions on Intelligent Transportation Systems,2017,18(6):1507-1518.
[5]Xuhui M A,Yafei H,Zhonghe H E.Traffic control subzone division approach based on reachability of road net-work[J].Computer Engineering and Applications,2017,53(17):224-228.
[6]Dong L,Zhao-Ping Y,Hui S,et al.The relationship between regional tourism interrelation and fractal structure of scenic spots in Xinjiang[A].//International Conference on Management Science&Engineering[C],Harbin:IEEE,2013:218-223.
[7]Trasarti R,Olteanu-Raimond A M,Nanni M,et al.Discovering urban and country dynamics from mobile phone data with spatial correlation patterns[J].Telecommunications Policy,2015,39(3-4):347-362.
[8]Xuejun D,Dengshan D.Correlation Fractal Dimension of Spatial Structure of Tourist Spots Systems——A Case Study in Nanjing City[J].Resources Science,2006,28(1):180-185.
[9]Timberlake M.The Polycentric Metropolis:Learning from Mega-City Regions in Europe[J].Journal of the American Planning Association,2008,74(3):384-385.
[10]Zhan J,Qi L U.Assessment and Empirical Study on the Relationship between Infrastructure Construction and Urban-Rural Development[J].2003,4:133-141.
[11]Pingde Z,Jianqian Z.Logistics Industry in Guangzhou,Shenzhen and Hong Kong and Its Relationship to Economic Growth in the PRD City Groups[J].Tropical Geography,2009,29(1):37-42.
Claims (8)
1. A method for evaluating the closeness of connection requirements among functional areas of a city is characterized by comprising the following steps:
determining a data set for urban area division;
according to the base station flow time sequence, respectively extracting base station flow characteristics from statistics, a time domain and a frequency domain, specifically: selecting a mean value, a variance, a skewness and a kurtosis to extract statistical characteristics; selecting a Hurst index to extract time domain characteristics; selecting a coefficient of DWT transformation to extract frequency domain characteristics;
determining a functional area in which a base station is positioned through a K-means + + clustering algorithm;
clustering the base stations through a K-means + + clustering algorithm according to a functional area data set where the base stations are located and a geographical position data set of the base stations to obtain a partitioning result of each functional area of the city;
the base station flow time sequence is as follows: recording the encrypted user mobile phone number, Location Area Code (LAC) of the base station, Cell identification Code (Cell Id, CI), time of the user connecting to the base station, the traffic generated by the connection and other user internet traffic log data in a constant period to obtain a sequence;
the functional area data set in which the base station is located refers to: clustering the characteristics of the base station flow to obtain the base station flow;
the geographical location data set of the base station refers to: base station latitude and longitude coordinates;
evaluating a contact demand compactness index between each functional area based on a Newton gravitation model of population activity aiming at the population migration volume and the population migration volume of each divided functional area and the distance between the areas;
the population immigration is as follows: number of persons within a functional area leaving the functional area
The emigration amount is: the number of people outside the functional area entering the functional area
The distance between the regions means: distance between the centers of the two functional regions
Calculating the migration volume of the population in the region, the migration volume and the distance between the regions, wherein the calculation comprises the following steps:
acquiring transfer data of a user between areas: extracting fields related to the user and the base station from the original data, replacing the base station with an area where the base station is located, and sequencing according to time to obtain a preliminary movement behavior record of the user; the user may have a section of continuous records showing that the user is in the same area, and at this time, the continuous records are combined into one record, so that the final movement behavior data of the user is obtained through processing;
determining the center of each region: the area of each area is small for the whole earth surface, so each area can be approximately considered as a plane, and the base stations in each area are distributed uniformly, so the center of each area can be represented by the geometric center of the base stations in the area;
calculating the tight degree index of the connection requirement among the functional areas according to the Newton gravitation model, wherein the tight degree index comprises the following steps:
wherein, Fi，jIs a connection of area I and area j, IiAnd oiIs the population migration in and out number of area I, IjAnd OjIs the population migration in and out number, D, of the region ji，jIs the distance between the centers of the regions; since the association between different regions is studied here, the association of a region with itself is ignored and its value is set to 0.
2. The method of claim 1, wherein:
the data set for determining the urban area division consists of a functional characteristic data set of a base station in an city and a geographic position characteristic data set of the base station, and both the two data sets take a base station flow time sequence as a data source;
the functional characteristic data set of the base stations in the city comprises: the functional area type of the base station comprises: a working area, a residential area, a mixed area;
the geographical location characteristic data set of the base station comprises: and converting the longitude and latitude coordinates of the base station into mercator coordinates.
3. The method of claim 1, wherein:
and adopting a clustering algorithm K-means + + according to the characteristics of the flow time sequence of the base station, wherein the corresponding parameter sets of the algorithm comprise a clustering number, a maximum iteration number, a number of operating the algorithm and a minimum threshold value for reaching convergence.
4. The method of claim 1, wherein:
the functional area division of the city determines the number of the finally divided areas according to the city area and the area size of each area.
5. The method of claim 2, wherein constructing a base station traffic time series comprises:
and counting a value in each hour in selected days, wherein the value represents the sum of the flow generated by the base station in the hour, and the time sequence is constructed.
6. The method of claim 2, wherein determining the geographic location characteristic of the base station comprises:
converting longitude and latitude coordinates which cannot be subjected to Euclidean distance calculation into ink card holder coordinates which can be used for the Euclidean distance calculation, thereby obtaining the geographic position characteristics of the base station;
the longitude and latitude of one point on the earth surface is (alpha, beta), and the corresponding calculation formula of the mercator coordinates (x, y) is as follows:
x＝R·(α-α0)
y＝ln(tan(α)+sec(α))
wherein R is the equatorial radius, alpha0The longitude of the central meridian.
7. The method of claim 3, wherein determining the characteristics of the time series of base station traffic comprises:
constructing a base station flow time sequence, and respectively extracting characteristics from statistics, a time domain and a frequency domain; the method specifically comprises the following steps: extracting mean, variance, skewness and kurtosis from statistics; extracting a Hurst index from a time domain; the parameters of the DWT transform are extracted from the frequency domain.
8. An apparatus for evaluating closeness of contact demand between functional areas in a city, comprising:
the parameter set setting module is used for setting a parameter set corresponding to the clustering algorithm;
the data set acquisition and preprocessing module is used for acquiring a base station flow time sequence and preprocessing the base station flow time sequence into a base station characteristic data set;
the division model module is used for taking the processed characteristic data set as input and applying a clustering algorithm to obtain a region division result;
the contact closeness calculation module is used for calculating the contact closeness among the divided regions;
the dataset acquisition and preprocessing module comprises:
the base station traffic time sequence construction module is used for processing the internet traffic log data of the user into a base station traffic time sequence;
the base station functional characteristic construction module is used for extracting the characteristics of the base station flow time sequence, and specifically comprises the following steps: the method comprises the steps of obtaining functional characteristics of a base station by using a clustering algorithm, namely the base station serves a certain functional area, wherein the average value, the variance, the skewness, the kurtosis, a time domain characteristic Hurst index and a coefficient after frequency domain characteristic DWT are transformed;
the base station geographic position characteristic construction module is used for converting the longitude and latitude coordinates of the base station into the mercator coordinates to obtain the geographic position characteristics of the base station;
the contact closeness calculation module includes:
the regional population migration volume and migration volume calculation module is used for processing the internet traffic log data of the user into user regional transfer data to obtain the population migration volume and migration volume of the region;
the inter-region distance calculation module is used for calculating the center position of the obtained regions and calculating the distance between the regions by using a haversine formula;
the Newton gravitation model module based on population activities is used for taking the migration volume of regional population, the migration volume and the distance between regions as input and outputting the input as the connection compactness between the regions;
the population immigration is as follows: number of persons within a functional area leaving the functional area
The emigration amount is: the number of people outside the functional area entering the functional area
The internet traffic log data of the user means: the encrypted mobile phone number of the user, the Location Area Code (LAC) of the base station, the Cell identification Code (Cell Id, CI), the time when the user connects to the base station, the traffic generated by the connection, and the like
The distance between the regions means: distance between the centers of the two functional regions
The calculation formula of the Newton gravitation model module is as follows:
wherein, Fi，jIs a connection of area I and area j, IiAnd OiIs the population migration in and out number of area I, IjAnd OjIs the population migration in and out number, D, of the region ji，jIs the distance between the centers of the regions; since the association between different regions is studied here, the association of a region with itself is ignored and its value is set to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910400753.4A CN110297875B (en) | 2019-05-15 | 2019-05-15 | Method and device for evaluating contact demand compactness among functional areas of city |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910400753.4A CN110297875B (en) | 2019-05-15 | 2019-05-15 | Method and device for evaluating contact demand compactness among functional areas of city |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110297875A CN110297875A (en) | 2019-10-01 |
| CN110297875B true CN110297875B (en) | 2021-08-10 |
Family
ID=68026814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910400753.4A Active CN110297875B (en) | 2019-05-15 | 2019-05-15 | Method and device for evaluating contact demand compactness among functional areas of city |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110297875B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476449B (en) * | 2019-10-09 | 2022-05-24 | 北京交通大学 | Subway station operation time interval division method based on improved k-means clustering algorithm |
| CN110909759B (en) * | 2019-10-10 | 2020-12-18 | 重庆特斯联智慧科技股份有限公司 | Urban area hierarchical management system and method based on population big data |
| CN111246379A (en) * | 2020-01-13 | 2020-06-05 | 北京工业大学 | Method for distinguishing city functional area by using mobile phone signaling data |
| CN111310340B (en) * | 2020-02-19 | 2022-08-16 | 中南大学 | Urban area interaction abnormal relation identification method and equipment based on human movement |
| CN112614336B (en) * | 2020-11-19 | 2021-12-07 | 南京师范大学 | Traffic flow modal fitting method based on quantum random walk |
| CN114727300A (en) * | 2022-02-08 | 2022-07-08 | 北京邮电大学 | Gateway station deployment method based on gravity model and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354782A (en) * | 2015-11-06 | 2016-02-24 | 东南大学 | Adaptation method for intensive layout of park green land based on space correlation quantification model |
| CN107527293A (en) * | 2017-08-10 | 2017-12-29 | 中国科学院地理科学与资源研究所 | Group of cities space relationship Strength Analysis System based on statistical model |
| CN108242203A (en) * | 2016-12-23 | 2018-07-03 | 中兴通讯股份有限公司 | A kind of region partitioning method and device |
| CN108446470A (en) * | 2018-03-07 | 2018-08-24 | 广东国地规划科技股份有限公司 | Medical facilities analysis method of reachability based on track of vehicle data and population distribution |
| CN109308549A (en) * | 2017-11-20 | 2019-02-05 | 章文洁 | A kind of City complex activity analysis method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496076B (en) * | 2011-11-30 | 2015-05-27 | 广州市交通规划研究院 | Macroscopic, mid-scope and microscopic multilevel urban parking demand prediction model integrated system |
| JP6597166B2 (en) * | 2015-10-20 | 2019-10-30 | トヨタ紡織株式会社 | Animal cell regeneration speed control method and regeneration speed control apparatus |
| CN106096631B (en) * | 2016-06-02 | 2019-03-19 | 上海世脉信息科技有限公司 | A kind of floating population's Classification and Identification analysis method based on mobile phone big data |
| CN109299438B (en) * | 2018-09-21 | 2023-01-17 | 东南大学 | Public transport facility supply level evaluation method based on network appointment data |
-
2019
- 2019-05-15 CN CN201910400753.4A patent/CN110297875B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354782A (en) * | 2015-11-06 | 2016-02-24 | 东南大学 | Adaptation method for intensive layout of park green land based on space correlation quantification model |
| CN108242203A (en) * | 2016-12-23 | 2018-07-03 | 中兴通讯股份有限公司 | A kind of region partitioning method and device |
| CN107527293A (en) * | 2017-08-10 | 2017-12-29 | 中国科学院地理科学与资源研究所 | Group of cities space relationship Strength Analysis System based on statistical model |
| CN109308549A (en) * | 2017-11-20 | 2019-02-05 | 章文洁 | A kind of City complex activity analysis method and system |
| CN108446470A (en) * | 2018-03-07 | 2018-08-24 | 广东国地规划科技股份有限公司 | Medical facilities analysis method of reachability based on track of vehicle data and population distribution |
Non-Patent Citations (2)
| Title |
|---|
| "新疆省际经济联系与地缘经济";刘守威;《区域经济》;20190502;第60-71页 * |
| "湖北省城市经济联系与区域经济发展研究";魏珊;《经济实证》;20180228;第127-130页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110297875A (en) | 2019-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110297875B (en) | Method and device for evaluating contact demand compactness among functional areas of city | |
| Zhao et al. | Predicting taxi demand at high spatial resolution: Approaching the limit of predictability | |
| Chen et al. | Delineating urban functional areas with building-level social media data: A dynamic time warping (DTW) distance based k-medoids method | |
| Shahriar et al. | Prediction of EV charging behavior using machine learning | |
| Beiró et al. | Predicting human mobility through the assimilation of social media traces into mobility models | |
| Luo et al. | Explore spatiotemporal and demographic characteristics of human mobility via Twitter: A case study of Chicago | |
| Yu et al. | Analysing the spatial-temporal characteristics of bus travel demand using the heat map | |
| Kim et al. | Ridership patterns at subway stations of Seoul capital area and characteristics of station influence area | |
| Duan et al. | Prediction of city-scale dynamic taxi origin-destination flows using a hybrid deep neural network combined with travel time | |
| D’Silva et al. | Predicting the temporal activity patterns of new venues | |
| She et al. | Weighted network Voronoi Diagrams for local spatial analysis | |
| Cai et al. | Estimating small‐area populations by age and sex using spatial interpolation and statistical inference methods | |
| CN110059770B (en) | Adaptive task distribution method and device based on position prediction and related components | |
| CN106682427A (en) | Personal health condition assessment method and device based position services | |
| CN110134865A (en) | A kind of commuting passenger's social recommendation method and platform based on urban public transport trip big data | |
| Williams et al. | Measuring individual regularity in human visiting patterns | |
| Lima et al. | Spatial dissemination metrics for location-based social networks | |
| Rubio et al. | Adaptive non-parametric identification of dense areas using cell phone records for urban analysis | |
| Epelde et al. | Beach carrying capacity management under Covid-19 era on the Basque Coast by means of automated coastal videometry | |
| Zanini et al. | Understanding resident mobility in Milan through independent component analysis of Telecom Italia mobile usage data | |
| Xue et al. | Multi-source data-driven identification of urban functional areas: A case of Shenyang, China | |
| CN111182463B (en) | Regional real-time passenger flow source analysis method and device | |
| Fan et al. | Understanding collective human movement dynamics during large-scale events using big geosocial data analytics | |
| Gong et al. | Spatio-temporal parking behaviour forecasting and analysis before and during COVID-19 | |
| Gammelli et al. | Recurrent flow networks: A recurrent latent variable model for density estimation of urban mobility |
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 |