CN116193369A - Resident population generation rate estimation method based on mobile phone signaling data - Google Patents
Resident population generation rate estimation method based on mobile phone signaling data Download PDFInfo
- Publication number
- CN116193369A CN116193369A CN202211603529.3A CN202211603529A CN116193369A CN 116193369 A CN116193369 A CN 116193369A CN 202211603529 A CN202211603529 A CN 202211603529A CN 116193369 A CN116193369 A CN 116193369A
- Authority
- CN
- China
- Prior art keywords
- population
- land
- living
- base station
- residential
- 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
- 230000011664 signaling Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008878 coupling Effects 0.000 claims abstract description 7
- 238000010168 coupling process Methods 0.000 claims abstract description 7
- 238000005859 coupling reaction Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims abstract description 5
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 238000010276 construction Methods 0.000 claims description 27
- 230000002776 aggregation Effects 0.000 claims description 22
- 238000004220 aggregation Methods 0.000 claims description 22
- 238000011160 research Methods 0.000 claims description 22
- 238000011835 investigation Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000000611 regression analysis Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000001419 dependent effect Effects 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000004622 sleep time Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 abstract description 46
- 238000011161 development Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013488 ordinary least square regression Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000000586 desensitisation Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 241000208140 Acer Species 0.000 description 1
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000013604 expression vector Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000036578 sleeping time Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses a living population generation rate estimation method based on mobile phone signaling data, which comprises the following steps of 1) data preparation and processing; step 2), coupling building data and mobile phone signaling data; and 3) constructing a multi-scale geographic weighted regression Model (MGWR), and exploring regression relations among living variables which change along with different space positions, wherein the regression model coefficients are population generation rate values of different living buildings. The invention establishes a multi-scale geographic weighted regression model by utilizing the relationship between the residential population and land, considers the difference of the residential population generation rates of different buildings, and can obtain more accurate population generation rate values through signaling data so as to provide basis for planning annual residential population distribution prediction.
Description
Technical Field
The invention relates to the technical field of resident population investigation, in particular to a resident population generation rate estimation method based on mobile phone signaling data.
Background
The population density refers to population number of living on a unit area of land, the number relation between people and consumed substance space is reflected, and the population density is an important index for researching population space distribution characteristics. At present, the method for realizing population spatialization by simulating urban population space distribution mainly comprises two types, namely a face interpolation method and a statistical model method. The surface interpolation method is mainly used for regional conversion of population data, namely, the input population data is spread on a geographic space grid with a certain scale through interpolation analysis, so that the conversion of population information expression vectors is realized. The statistical model rule is to realize regional population estimation by establishing a relationship between population and influencing factors. The land utilization density method is widely applied due to the fact that data are easy to obtain and high in simulation precision, and is a common method in a population density estimation model. The method can effectively solve the problem that census data and geographic data based on administrative district investigation are not matched. However, since the existing research is concentrated in the geographic and mapping fields, only aiming at realizing the current living population space, the living population density index research oriented to the guidance planning practice is lacking.
In the field of urban planning, residential demographics are an important starting point for planning demand. The living population distribution forecast can meet the development demands of urban infrastructure and public service from the supply angle, and has important value for the local government to formulate comprehensive development planning and guarantee public service provision. In the study oriented to living population distribution prediction, prediction methods such as multi-agent models, grey theory prediction and the like are widely applied, the simulation precision of most studies is high, but the study scale is generally large, and population distribution conditions on fine plots can not be predicted mainly in counties and streets. Few building scale demographics simulation researches based on multi-agent model from bottom to top are poor in large-scale and high-efficiency application and popularization. Other studies related to population density in the planning field are mostly subject to influence of occupied space structure, living area planning and built environment on traveling. The population density of living beings only appears as a factor or measure, and is rarely a direct research object.
In general, many measures of population density in existing studies are based on land area, and there is insufficient focus on urban land development intensity. The index of the population density of living with the building area as a unit can effectively predict traffic demands based on land blocks (buildings), provide a basis reference for the development intensity of living land, and avoid the resource waste phenomena of living room empty, supply and demand and the like. Unfortunately, researches are rarely involved at present, and in planning practice, a conventional investigation method and a method for analogizing similar cities are often adopted in a residential population density index determination method taking building area as a unit, so that the prediction accuracy is not high, and therefore, an index research facing planning practice application is urgently provided.
The invention provides a new concept, namely the generation rate of living population, namely the population number of unit building area on various living lands, reflecting the population distribution condition on different types of living lands. The expression is as follows:
residential population generation rate = total residential population/total residential building area
The occupancy rate is different from the occupancy density, the former is measured in terms of building area, and the latter is measured in terms of floor area. Clearly, due to the effects of floor height, building density, etc., it is more appropriate to use building area metrics in estimating the population of living. In addition to being related to building area, the number of living population is also affected by the type of living. The difference of population density in residential areas with different environmental conditions is large, in general, the matching of the residential areas with three types of residents is poor, the residential areas are mainly small and medium-sized, the residential population is mostly rigid demand population with poor economic conditions, the population density is large, and the residential areas with low-density residents are relatively sparse. Thus, obtaining the generation rate of living population over different land types facilitates a more scientific prediction of living population size and distribution. In addition to estimating the population, the population generation rate can also guide the land development scale of the residential area.
In the presently disclosed patent, there are also several patents related to the field of population estimation methods, for example, patent application CN20181087801.4 discloses a population distribution calculation method, in which, firstly, a base station point generates a Thiessen polygon, and then, each Thiessen polygon is used to control the data calculation precision of a corresponding base station, so that the data quality is ensured to a certain extent, and the characteristics of original mobile phone signaling data distribution are also reserved to a greater extent; the population distribution calculation method for comprehensively planning the online population distribution thermodynamic diagram and the mobile phone signaling data features can improve the accuracy of mobile phone signaling big data spatial distribution calculation according to the online population distribution thermodynamic diagram with higher position positioning accuracy, and further improve the spatial resolution of mobile phone signaling data with higher time continuity features; but it cannot distinguish the differences of different functional buildings and cannot obtain the generation rate of living population.
Patent publication number CN 106708962A discloses a city population distribution method based on building attributes, which comprises the following specific steps: acquiring all building information and surrounding interest point information of the building in the electronic map according to the longitude and latitude coordinate range of the city; inquiring an electronic map aiming at a certain demographic region, determining coordinates of the demographic region, and inquiring population total number of the region; screening all buildings in the demographic region according to the building position and the boundary angular point coordinates of the demographic region; inferring social activity attributes of the building; setting population attraction coefficients of different social activity attribute types of buildings in different unit areas, and distributing population in a demographic region to each building in the region to obtain population distribution of building grades; and traversing each demographic region of the city to obtain city demographics. The method is applied to urban population distribution of building grades, can effectively solve the problem of coarse urban population distribution scale and embody population distribution time difference, but mainly deduces activity attributes of buildings through types of POIs around the buildings and the like, so that time-efficient building population distribution conditions are obtained, and meanwhile, the determination of population attraction coefficients of building unit areas of different social activity attribute types lacks strict demonstration, so that stable resident population values of a certain area cannot be obtained, and basis cannot be provided for prediction of resident population distribution.
Disclosure of Invention
In order to solve the defects in the prior art, the invention constructs a living population generation rate estimation model based on mobile phone signaling data and provides a non-investigation estimation method of living population generation rate.
In order to achieve the purpose of the invention, the technical scheme adopted by the invention is as follows:
the resident population generation rate estimation method based on the mobile phone signaling data is characterized by comprising the following steps of:
step 1), data preparation and processing
Judging living places through mobile phone signaling data to count living population numbers of the TAZ_CB of the base station aggregation cells; building classification is carried out on land investigation data through urban land classification and planning construction land standard (GB 50137-2011);
step 2), coupling building data and mobile phone signaling data
Dividing land data in a research area according to a TAZ_CB boundary, taking the TAZ_CB boundary as a statistics unit to obtain the total building area of each residential land, and then performing space connection to obtain a base station aggregation cell layer comprising the total building area and the population number of living;
step 3), multiscale geo-weighted regression analysis
Considering the influence of space location factors on the generation rate of living population, expanding a traditional linear regression model, taking the living population number as a dependent variable, taking the building area of various residential land as an independent variable, constructing a multi-scale geographic weighted regression Model (MGWR), exploring the regression relation among living variables which change along with different space positions, and constructing a multi-scale geographic weighted regression model formula:
wherein Y is i The population of living for the ith TAZ_CB; beta bwj (u i ，v i ): class j residential use for class i TAZ_CBThe occupancy population generation rate of the land; bwj is the optimal bandwidth for the j-th residential land; k is the number of independent variables; x is x ij The total building area for the j-class residential land of the i-th taz_cb; epsilon i Is a random error term;
obtaining the beta of each place through a multi-scale geographic weighted regression model bwj (u i ，v i ) I.e., the occupancy characteristics of different types of residential buildings as a function of location are analyzed, and the value can be used to predict the population count of newly built residential buildings in a base station aggregated cell.
Further, the method for dividing the base station aggregated cell (taz_cb) in step 1) includes the following steps:
1) Generating a base station-based Thiessen polygon in an ArcGIS;
2) The boundary of the TAZ_CB is coincident with the Thiessen polygon boundary formed by the service range of the base station so as to facilitate data statistics and reduce irregular base station gathering cells such as long strips, bending, corners and the like as much as possible;
3) Each TAZ_CB should contain more than 5 Thiessen polygons formed by base stations to reduce errors caused by difficulty in accurately distinguishing the actual coverage area of the base stations, and in areas with lower base station densities, the number is not less than 3;
4) The number of TAZ_CBs is kept above 80 as much as possible, and the land size of each TAZ_CB is about 1-3km 2 To cope with subsequent regression analysis, the size of the land is determined by the population density of the region, and the size of the land for gathering the cells of the region with large population density is small.
Further, the method for judging the residence based on the mobile phone signaling data in the step 1) comprises the following steps:
firstly, determining the sleep time of most residents in the period from 1:00 to 7:00 according to the living characteristics of residents in a research area, wherein the mobile phone signaling is inactive and occupies relatively fixed base stations in the period, considering the condition that one living cell spans two or more base stations, and the base stations where the resident mobile phone signaling is positioned are relatively fixed at 2-3 base stations on the periphery of the base stations in the sleep period, so that the residence time of each resident in the sleep period is averagely two hours on average on each base station;
for a user who is used to shutdown during sleeping, if the shutdown location is consistent with the startup location, judging that the user is a residence location, and judging that the startup location is consistent with the judgment standard as follows: if the distance between the base station where the last signaling data is located before the power-off in the previous day and the base station where the first signaling data is located after the power-on in the next day is less than 500 meters, the power-on and power-off places are consistent, and the residence place of the user is the base station where the power-off in the previous day is located. And completing residence identification of each user according to the logic, and then carrying out space association on the base station residence population statistics table and the base station service range to obtain residence population of each base station service range. And finally, obtaining the population of the residence of each base station aggregated cell through space statistics.
Further, in the step 1), the building classification standard classifies the building according to the "urban land classification and planning construction land standard (GB 50137-2011), and urban living lands may be classified into three types of R11 (one type of living land), R21 (two types of living land), and R31 (three types of living land), and if village type land (H14) exists in the urban area, the three types of living lands are included in the present example land classification.
Further, the specific steps of the step 2) are as follows:
2.1 Using a space connection tool for the land survey data and the building area data in ArcGIS software, correlating the building area data to the land survey data, and summarizing the building areas to obtain various building area data of each land;
2.2 Using an "intersection" tool in ArcGIS software to intersect the land survey data with the TAZ CB boundary,
the living land area within each taz_cb is obtained, and the total area of each living building within each taz_cb boundary is counted.
2.3 And (3) superposing the population number of each TAZ_CB obtained in the step (1) and the total building area of each residential land of each TAZ_CB obtained in the step (2) through a superposition analysis tool of ArcGIS software to obtain a base station aggregation cell layer comprising the total building area and the population number.
The invention overcomes the defect that the traditional common least squares (OLS) regression is adopted by the technicians in the field, the OLS model is a global model, the space is considered to be homogeneous, namely, the data of each TAZ_CB are assumed to be independent and have no space relation, so that the overall evaluation of the generation rate of living population can only be carried out, and a certain average of regression parameters in a research area can be obtained. However, due to the differences between taz_cbs, there is spatial heterogeneity in the residential demographics and regression parameters should vary with changes in spatial geographic location. Thus, spatial instability of the resident population generation rate over local regions is ignored, potentially resulting in poor model fit.
The classical geographic weighted regression model (GWR) adopts an optimal average scale for all variables, but in practical situations, the spatial influence scales of different parameters may be different, and large errors are easily caused. Thus, allowing regression using the respective optimal bandwidths for different independent variables eliminates the constraint that the variables vary on the same spatial scale, thereby reducing overfitting. Briefly, multi-scale geo-weighted regression (MGWR) allows for different spatial proportions of the relationship between each interpretation variable and dependent variable, with stronger fitting interpretation of large scale data. Since factors such as location, price, accessibility, etc. are not all the same in the living population distribution influence mechanism. Thus, the present invention employs a specific MGWR model to more closely follow the actual demographic procedure.
The invention has the advantages that compared with the prior art,
1) The invention solves the technical problems that the Ordinary Least Squares (OLS) regression is adopted by the technicians in the prior art, and the spatial instability of the generation rate of living population on each local area is ignored, so that the model fitting is poor. The multi-scale geographic weighted regression Model (MGWR) of the invention allows different space proportions of the relation between each interpretation variable and the dependent variable, has stronger fitting interpretation power on large-scale data and is more suitable for the distribution of actual population.
2) The invention establishes the regression model by utilizing the relationship between the residential population and land utilization, and can distinguish different buildings to determine the residential population difference through the multi-scale geographic weighted regression model, thereby being capable of accurately obtaining the residential population generation rate so as to provide basis for planning annual residential population distribution prediction.
Drawings
Fig. 1 is a flowchart of a method for estimating the generation rate of living population based on mobile phone signaling data according to the present invention.
FIG. 2 is a schematic diagram of a research unit in the Kunshan region of the example.
FIG. 3 is a graph of population and population density distribution of living beings in a range of a centralized construction area of a Kunshan city according to an embodiment.
Fig. 4 is a population of living LISA cluster map.
Fig. 5 is a graph of R21 class regression coefficient salient region profiles.
Fig. 6 is a graph of the R31 regression coefficient salient region distribution.
Fig. 7 is a case zone map in this embodiment.
Fig. 8 is a flowchart of the application prediction in the present embodiment.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples. The following examples are only for more clearly illustrating the technical solutions of the present invention and are not intended to limit the scope of protection of the present application.
In this example, kunshan city, jiangsu province was selected as the study city. The most developed Yangtze river delta of Chinese economy in Kunshan, shanghai, west O-Su, is an advanced industrial base internationally known in the east gate of Jiangsu province. The number of the resident population of the Kunshan is large, employment posts and external population are more, and the accurate identification of the scale and distribution of the resident population has great practical significance for the index city planning.
In this example, the city concentrated construction area of Kunshan was selected as the investigation range, i.e., the investigation range was about 660 square kilometers. In addition, the research range is subdivided into a central urban area and a peripheral area, wherein the central urban area is a middle east line, a middle north line, a middle south line and a Chang Jiagao speed enclosing range, and the area is about 150 square kilometers; the peripheral area is an area in the research area except the central urban area, and the area is about 510 square kilometers.
The research unit of this embodiment embodies two dimensions of a base station service area and a base station aggregated cell (taz_cb). First, a Thiessen polygon divided by base station location points is used as a basic research unit for visualizing the service range and data space of a base station. Considering that the service range of the base station is interfered by topography, buildings and the like, situations of negligence, reselection and the like of the mobile phone terminal when the base station is selected possibly occur to influence positioning. In order to improve the accuracy of the study, the present embodiment uses the base station aggregated cells as the study unit, i.e. taz_cb (TAZ Cell-Based), where each taz_cb includes several base station service areas. The specific method for dividing TAZ_CB is as follows:
(1) Generating a base station-based Thiessen polygon in an ArcGIS;
(2) The boundary of the TAZ_CB is coincident with the Thiessen polygon boundary formed by the service range of the base station so as to facilitate data statistics and reduce irregular base station gathering cells such as long strips, bending, corners and the like as much as possible;
(3) Each TAZ_CB should contain more than 5 Thiessen polygons formed by base stations to reduce errors caused by difficulty in accurately distinguishing the actual coverage area of the base stations, and in areas with lower base station densities, the number is not less than 3;
(4) The number of TAZ_CBs is kept above 80 as much as possible, and the land size of each TAZ_CB is about 1-3km 2 To cope with subsequent regression analysis, the size of the land is determined by the population density of the region, and the size of the land for gathering the cells of the region with large population density is small. Finally, as shown in fig. 2, 2609 base station service ranges within the scope of the present embodiment are aggregated to 212 taz_cbs. The central urban area comprises 1268 base station service ranges and 98 TAZ_CBs; the peripheral area contains 1341 base station service areas, 114 taz_cbs.
The mobile phone signaling data used in the embodiment is mobile phone signaling data of 2017 of China mobile communication operators in a research area obtained by team scientific research projects. Firstly, carrying out data sample expansion, data desensitization, redundant data rejection, merging ping-pong data, cleaning drifting data and other pre-processing works. Further, the present embodiment mines the population distribution of the study unit from the cell phone signaling data. The current mobile user volume of the kunshan reaches about 180 ten thousand, and accounts for 70% of the total population of the kunshan. And determining a basic sample expansion rate according to the market share and the effective data extraction proportion, further determining different population sample expansion rate correction coefficients according to population characteristics, expanding samples one by one according to each population, and summarizing to obtain an expanded population.
In the aspect of residence identification, firstly, according to residence characteristics of residents in a research area, determining sleeping time of most residents in a period from 1:00 to 7:00, wherein mobile phone signaling is not active in the time period, and an occupied base station is relatively fixed. Considering that the range of the base station is smaller, a living cell spans two or more base stations, and the base station where the resident mobile phone signals are located is relatively fixed at 2-3 base stations around the base station during sleeping, so that the residence time of each resident during sleeping is two hours on average on each base station. For a user who is used to shutdown during sleeping, if the shutdown location is consistent with the startup location, judging that the user is a residence location, and judging that the startup location is consistent with the judgment standard as follows: if the distance between the base station where the last signaling data is located before the power-off in the previous day and the base station where the first signaling data is located after the power-on in the next day is less than 500 meters, the power-on and power-off places are consistent, and the residence place of the user is the base station where the power-off in the previous day is located. And completing residence identification of each user according to the logic, and then carrying out space association on the base station residence population statistics table and the base station service range to obtain residence population of each base station service range. And finally, obtaining the population of the residence of each base station aggregated cell through space statistics.
According to the conditions, the living population in the research range is 166.7 thousands of people, and 7 is 6 in 2017 and 6 in 6: 00-8: the total of 198135 travel OD data in the 00-peak hours.
The city land present data selected for this embodiment is derived from 2017 Kunshan city construction land present data. The land type of the land present data is divided according to the "classification of urban land and planning construction land standard (GB 50137-2011)" and is totally 35 categories. Finally, a total of 9626 plots were counted in the statistical study. Considering that a building may be crossed by the boundary of the base station aggregation cells, that is, one building is divided into two base station aggregation cells, the building areas are counted to two base station aggregation cells according to the building base area ratio. The following table is a description of the land building data attribute field:
| field name | Description of the invention |
| LandID | Land parcel ID |
| LandName | Land parcel name |
| Nature | Land type |
| LANDACRG | Area of land |
| BUACREAGE | Building area |
And (3) based on the living population identified by the mobile phone signaling data, the living population number and living population density distribution condition (shown in figure 3, left: living population number distribution map and right: living population density distribution map) in the range of the centralized construction area of Kunshan city are obtained by utilizing GIS visualization. The living population distribution of Kunshan city is relatively scattered and mainly concentrated in the south of central urban areas and flower bridge areas. The living population density is distributed in a finger shape in the whole, and besides planar areas such as a central urban area and a flower bridge area, areas with higher living population density also comprise banded areas of Kuntai roads along the northeast direction, liu Fengdong roads along the southeast direction, roads such as the east of flowers An Lu, S224 and the like. The population density of living beings gradually decreases from the central urban area to the periphery except for the flower bridge area.
To reveal the regional structure morphology of the spatial variable of the living population of Kunshan, the spatial correlation degree of the attribute value of each regional unit and the same attribute value of the adjacent units is checked, and the spatial autocorrelation analysis is carried out on the living population.
The present embodiment selects the moland index to measure spatial correlation. The Morlan index is an important index for measuring the spatial correlation, and can be used for determining whether the correlation exists between the geographic entities within a certain spatial range, and the value range is generally between-1.0 and 1.0. If Moran's I > 0, the spatial positive correlation is represented, the larger the value thereof, the more remarkable the spatial correlation is as the spatial distribution positions are gathered; moran's I < 0 shows that the spatial correlation is negative, and the smaller the value is, the more remarkable the spatial correlation is along with the dispersion of the spatial distribution position; if Moran's I =0, the spatial distribution is random.
The molan index includes a global molan index and a local molan index. Global Moran index (Global Moran's I) is used to verify the spatial pattern of the entire study area, reflecting whether or not space is clustered or outliers, i.e., reflecting the degree of correlation between regional geographic element attribute values of spatially contiguous. The Local Moran index (Local Moran's I) is used to reflect the specific region where the aggregation or outlier occurs, i.e. to calculate the correlation degree of each region unit of the space with the same attribute value of the neighboring region units.
Global morgan index and LISA cluster map (fig. 4) construction was performed separately using Geoda software. When Moran's I is more than 0, the data shows positive correlation in space, the larger the value is, the more obvious the spatial correlation is, and otherwise, the negative correlation is; moran's I is 0, the space is random. Moran's I > 0, P < 0.05, Z > 1.96 for the population of living, indicating that there is significant spatial positive correlation at 95% confidence and spatial aggregation characteristics, the following table is Moran's I parameter results:
| variable(s) | Moran’s I | P value | Z value |
| Population count of living | 0.1850 | 0.0010 | 6.4166 |
As shown in FIG. 4, the flower bridge region, the Kunshan station patch, and the sink park patch exhibit high-high concentrations, with the population high-value regions being spatially adjacent to one another, forming the core region of the Kunshan city population distribution. The flower bridge area is close to Shanghai city, the living cost is low, a large number of cross-city commuter population is attracted, and the living population concentration degree is high. The Kunshan station area and the melting park area form a high aggregation area because of the centralized distribution of large residential communities such as a new brocade garden, a melting park, a Yongping home, a Shimao butterfly bay, a maple Jing Yuan and the like. The low-low aggregation areas are distributed at the periphery of the central urban area, and most of the low-low aggregation areas are non-construction land areas.
As shown in fig. 1, the central idea of the living population generation rate estimation method based on mobile phone signaling data is to build a regression model by using the relationship between living population and land utilization, and estimate living population generation rate so as to provide basis for planning annual living population distribution prediction. The model comprises the steps of constructing a basic database, preprocessing data, coupling data, multi-scale geographic weighted regression, constructing the population generation rate of the segmented region, and the like, and specifically comprises the following steps:
step 1), data preparation and processing
In the aspect of land data, the construction classification is carried out on land investigation data according to the urban land classification and planning construction land standard (GB 50137-2011) in the scope of a research area.
In the aspect of mobile phone signaling data, except for early works such as data sample expansion, data desensitization, redundant data rejection, ping pong data merging, drift data cleaning and the like, after residential places are identified, a base station residential population statistics table is spatially associated with a base station service range, so that residential population of each base station service range is obtained. And finally, obtaining the living population of each TAZ_CB through space statistics.
Step 2), coupling building data and mobile phone signaling data
Dividing land data in a research area according to a TAZ_CB boundary, taking the TAZ_CB boundary as a statistics unit to obtain the total building area of each residential land, and then performing space connection to obtain a base station aggregation cell layer comprising the total building area and the population number of living;
the method specifically comprises the following steps: 2.1 Using a space connection tool for the land survey data and the building area data in ArcGIS software, correlating the building area data to the land survey data, and summarizing the building areas to obtain various building area data of each land;
2.2 Using an "intersection" tool in ArcGIS software to intersect the land survey data with the TAZ CB boundary,
the living land area within each taz_cb is obtained, and the total building area of each living building within each taz_cb boundary is counted.
2.3 Superposing the population number of each TAZ_CB obtained in the step (1) and the total building area of each residential land of each TAZ_CB obtained in the step (2) through a superposition analysis tool of ArcGIS software to obtain a base station aggregation cell layer comprising the total building area and the population number of each building
Step 3), multiscale geo-weighted regression analysis
Considering the influence of space location factors on the generation rate of living population, expanding a traditional linear regression model, taking the living population number as a dependent variable, taking the building area of various residential land as an independent variable, constructing a multi-scale geographic weighted regression Model (MGWR), exploring the regression relation among living variables which change along with different space positions, and constructing a multi-scale geographic weighted regression model formula:
wherein Y is i The population of living for the ith TAZ_CB; beta bwj (u i ，v i ): a living population generation rate for the j-th residential land of the i-th taz_cb; bwj is the optimal bandwidth for the j-th residential land; k is the number of independent variables; x is x ij The total building area for the j-class residential land of the i-th taz_cb; epsilon i Is a random error term;
obtaining the beta of each place through a multi-scale geographic weighted regression model bwj (u i ，v i ) The living population generation rate is used for analyzing the living population generation rate characteristics of each area of different living building types along with the change of the position;
the construction steps of the multi-scale geographic weighted regression model in the embodiment are as follows:
(1) a precondition for using a multi-scale geo-weighted regression Model (MGWR) is that there is a spatial correlation of the variables. Taking the practical significance of the model into consideration, the MGWR is constructed by taking the construction areas of four types of land, namely R11 (type-residential land), R21 (type-residential land), R31 (type-three residential land) and H14 (village construction land), as independent variables. And (5) carrying out Morand index test on each index by using GeoDa software. The test results are shown in the following table. Each variable Moran's I is more than 0, P is less than 0.05, and Z is more than 1.96, which shows that the significant positive correlation exists under the 95% confidence coefficient of each variable, the space aggregation characteristic exists, and the conditions for establishing the MGWR model are met. The following table is the Moran's I test table:
(2) meanwhile, in order to avoid excessive multiple collinearity among the alternative variables, SPSS software is used for carrying out multiple collinearity test on each variable. Pearson correlation coefficient ρ xy Displaying that the correlation coefficient of each variable is not more than 0.7; the variance expansion factor tests showed that the VIF values were all less than 1.1, and that the variables were considered to have no multiple collinearity. The following table is the respective variable pearson correlation coefficient:
| variable(s) | R11 | R21 | R31 | H14 |
| R11 | 1 | |||
| R21 | 0.148 | 1 | ||
| R31 | 0.077 | 0.079 | 1 | |
| H14 | 0.093 | -0.228 | -0.035 | 1 |
(3) The geographical weighted regression model is used as a local model, and the regression coefficient is obtained by regression calculation of the observation point and sample points in a certain range around the observation point. The spatial weight matrix is used to measure the relationship between the sample points and determine whether the sample points are involved in the estimation. The spatial kernel function sets a functional relation between the spatial weight and the distance from the geographical position of the observation point to the geographical position of the adjacent sample, and determines the attenuation condition of the spatial weight value along with the distance. The present embodiment selects the Bi-square function to set the spatial weight value.
(4) Bandwidth is an important parameter in the geographic weighted regression to judge the range of the samples to be estimated, and is the distance or the number of the spatial neighborhood. The bandwidth is classified into a fixed type and an adaptive type. The fixed type uses a fixed distance threshold as the bandwidth, and the adaptive bandwidth creates a nuclear surface by distributing the density of sample points. Considering that the sample points are not uniformly distributed in the method, the self-adaptive bandwidth can better balance the overall bias error and standard deviation, and the self-adaptive bandwidth setting method is selected. Aiming at two optimal bandwidth size determining methods of Cross Validation (CV) and red pool information (Akaike information criterion, AICc) which are commonly used at present, the embodiment selects and applies the AICc criterion which is wider to estimate the optimal bandwidth.
The multi-scale geographic weighted regression model results:
and constructing a multi-scale geographic weighted regression model by using MGWR2.2 software to obtain a resident population generation rate regression result. Tables 4-11 show the mean, standard deviation, minimum, median, and maximum values of the regression coefficients of the respective variables. Tables 4-12 represent values of the optimal Bandwidth parameters (Bandwidth) for the various variables in the MGWR model. The model diagnosis results in tables 4-13 include the sum of Squares of residuals (Residual square), effective Number (Effective Number), square root of normalized sum of Squares (Sigma), AICc, R2 Adjusted.
Tables 4-11 resident population generation rate MGWR regression coefficient descriptive statistics
| Variable(s) | Average value of | Standard deviation of | Minimum value | Median of | Maximum value |
| R11 | 0.001 | 0.023 | -0.032 | -0.001 | 0.091 |
| R21 | 0.013 | 0.007 | 0.006 | 0.011 | 0.047 |
| R31 | 0.031 | 0.003 | 0.026 | 0.032 | 0.035 |
| H14 | -0.036 | 0.510 | -4.354 | 0.014 | 1.287 |
Tables 4-12 resident population generation rate MGWR model variable bandwidth settings
| Variable(s) | Bandwidth |
| R11 | 44 |
| R21 | 48 |
| R31 | 209 |
| H14 | 48 |
TABLE 4-13 resident population generation rate MGWR model diagnostic results
| Fitting parameters | Numerical value |
| Residual Squares | 3.09E9 |
| Effective Number | 31 |
| Sigma | 6878 |
| AICc | 4389 |
| R2 | 0.676 |
| R2 Adjusted | 0.621 |
The MGWR model regression results show that the regression coefficients of the same variable at different spatial positions are different, and the corresponding regression coefficients are different in significance. In this example, since the proportion of R21 and R31 plots passing the significance test is high, regression results were analyzed by taking two types of residential plots, R21 and R31, as examples.
As shown in fig. 5, the average residential population generation rate for the two-class residential land is 130 people per ten thousand square meters. The variable coefficients are significantly affected by space, and the coefficient distribution shows significant spatial differences. Overall, the spatial distribution pattern of the R21 population generation rate shows the characteristics of high south, low north and high east. The generation rate of living population in the northern newcastle and western subsidiary metropolitan areas is lowest and is less than 100 people per ten thousand square meters; the high value is distributed in the areas of the south newcastle and flower bridge, and the highest value reaches 400 people/ten thousand square meters. Zhang Puzhen of the south New City is close to the Kunshan exit processing area, labor-intensive enterprises gather, the foreign population is quite dense, and the area of the residential building of people is smaller than that of other areas. Meanwhile, nearby industries are densely populated, and a certain proportion of supporting staff dormitories are also one of reasons for the high estimated generation rate of living population. The flower bridge area is used as a first station for connecting Shanghai kun, the geographic position of the flower bridge area is even closer to the city center than some peripheral areas of Shanghai, and many people working in Shanghai select a new city of the flower bridge with lower living cost, so that the living population of the flower bridge area is dense, and the building area of people average residence is about 25m 2 . The generation rate of living population of the bridge new city is also obviously higher than that of the bridge old town area. In addition to the concentration of the population distribution, the spatial distribution trend of the coefficient can also reflect the lower space percentage of the new urban housing in the flower bridge area and the south. According to the regression results, it can be concluded that if the house yield loss is not considered, the three-family house calculation is performed, and the number of houses in most areas in Kunshan city is two. This level is not achieved for the bridge area and the south newcastle area.
The average rate of generation of the R31 class land occupancy is 310 people/ten thousand square meters. The population generation rate distribution of the three types of residential land is relatively balanced. Relatively high value regions occur in urban and north regions and in south marginal regions. The kunshan industry development has attracted a large number of extraneous employment populations, limited by revenue levels, which reside primarily in rural areas around suburban junctions and industrial areas in rented form, and have not had much demands on the living environment. Three types of living land with relatively poor living conditions are often preferred when the enterprise does not provide a dormitory. The urban and north areas such as Xinle brocade gardens, yuan garden Xincun villages, power villages and the like distributed near the purple bamboo roads are areas for housing, namely areas surrounding the industrial area, and the area of each residence is relatively small. For western regions, there are a large number of plant dormitories since the industrial sites are intensively distributed and closely adjacent to the western su-state industrial park, and while three types of residences are not distributed much, the residential population generation rate is high.
As shown in fig. 7, the present embodiment is to more conveniently acquire the resident population distribution prediction model parameter, that is, the resident population generation rate. The index not only can evaluate the condition of the people living in each area, but also can provide basis for recent living population distribution prediction, land development intensity control and even housing space percentage evaluation, and provide guidance suggestion for refined city and traffic planning. The embodiment predicts the population number of the living in the base station aggregated cells by means of the population generation rate model and provides basic data support for traffic demand prediction. The base station aggregation cell is located in a city core area, and the land layout diagram in 2020 comprises the following 7 types of residential lands, and the specific situation is shown in the table below. Except for the Kero gate of the inter-city square of the Zhongxing, other living areas are all residential lands (2016).
The residence population on the R21 class land of the case base station aggregation cell is predicted by using the constructed MGWR model, and the prediction flow is shown in fig. 8 and mainly comprises the following contents:
first, the living population generation rate of each type of residence land of each base station aggregation cell is obtained by the MGWR model. And determining the coefficient value of the base station aggregation cell according to the location of the case. Finally, the population of the second class residential land of the base station aggregated cell is predicted to be 11788 persons by combining the total building area and the coefficient value. Based on which the subsequent traffic demand predictions can be further developed.
The embodiment of the invention can also analogize the model construction of the employment post generation rate, namely the employment post generation rate=total employment post number/total building area, and the employment post generation rate estimation method based on the mobile phone signaling data has the central idea that a regression model is built by utilizing the relationship between the employment post and the land utilization so as to estimate the employment post generation rate, so as to provide basis for planning annual employment population distribution prediction. Similar to the resident population generation rate model, the model comprises the steps of constructing a basic database, preprocessing data, coupling data, multi-scale geographic weighted regression, constructing segment indexes and the like. Because the steps of data processing, employment population and land construction data coupling and the like are the same as the steps of the residential population generation rate model, the invention can also adopt a multi-scale geographic weighted regression Model (MGWR) to construct the employment post generation rate model in order to further optimize the employment post generation rate model similar to the residential population generation rate model. A precondition for using the MGWR model is that the variables have a correlation in space. In view of the practical significance of the model, the MGWR model is built to incorporate 9 independent variables of public management and public service land (a), commercial service construction land (B), industrial land (M), residence land (R), public construction land (U), road and traffic construction land (S), green and square land (G), logistics storage land (W), construction land (H).
While the applicant has described and illustrated the embodiments of the present invention in detail with reference to the drawings, it should be understood by those skilled in the art that the above embodiments are only preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not to limit the scope of the present invention, but any improvements or modifications based on the spirit of the present invention should fall within the scope of the present invention.
Claims (7)
1. The resident population generation rate estimation method based on the mobile phone signaling data is characterized by comprising the following steps of:
step 1), data preparation and processing
Judging living places through mobile phone signaling data to count living population numbers of the TAZ_CB of the base station aggregation cells; building classification is carried out on land investigation data through urban land classification and planning construction land standard;
step 2), coupling building data and mobile phone signaling data
Dividing land survey data in a research area range according to a TAZ_CB boundary, taking the TAZ_CB boundary as a statistics unit to obtain the total building area of various residential lands, and then performing space connection to obtain a base station aggregation cell layer comprising the total area of various residential buildings and the population of the residential buildings;
step 3), multiscale geo-weighted regression analysis
Considering the influence of space location factors on the generation rate of living population, taking the living population number as a dependent variable, taking the building areas of various residential land as independent variables, constructing a multi-scale geographic weighted regression model, exploring the regression relation among living variables which change along with different space positions, and constructing a multi-scale geographic weighted regression model formula as follows:
wherein Y is i The population of living for the ith TAZ_CB; beta bej (u i ，v i ) A living population generation rate for the j-th residential land of the i-th taz_cb; bwj is the optimal bandwidth for the j-th residential land; k is the number of independent variables; x is x ij The total building area for the j-class residential land of the i-th taz_cb; epsilon i Is a random error term;
obtaining the beta of each place through a multi-scale geographic weighted regression model bwj (u i ，v i ) I.e., the occupancy characteristics of different residential buildings as a function of location can be analyzed and this value can be used to predict the population of newly built residential buildings in a given base station aggregation cell.
2. The method for estimating a resident population generation rate based on mobile phone signaling data according to claim 1, wherein: the base station aggregated cell (TAZ_CB) dividing method comprises the following steps:
(1) Generating a base station-based Thiessen polygon in an ArcGIS;
(2) The boundary of the TAZ_CB is coincident with the Thiessen polygon boundary formed by the service range of the base station so as to facilitate data statistics and reduce base station gathering cells in irregular shapes of long strips, bending and corners as much as possible;
(3) Each TAZ_CB should contain more than 5 Thiessen polygons formed by base stations to reduce errors caused by difficulty in accurately distinguishing the actual coverage area of the base stations, and in areas with lower base station densities, the number is not less than 3;
(4) The number of TAZ_CBs is kept above 80 as much as possible, and the land size of each TAZ_CB is about 1-3km 2 To cope with subsequent regression analysis, the size of the land is determined by the population density of the region, and the size of the land for gathering the cells of the region with large population density is small.
3. The method for estimating a residential population generation rate based on mobile phone signaling data as claimed in claim 1, wherein the method for determining a residential place based on mobile phone signaling data comprises the steps of:
firstly, determining the sleep time of most residents in the period from 1:00 to 7:00 according to the living characteristics of residents in a research area, wherein the mobile phone signaling is inactive and occupies relatively fixed base stations in the period, considering the condition that one living cell spans two or more base stations, and the base stations where the resident mobile phone signaling is positioned are relatively fixed at 2-3 base stations on the periphery of the base stations in the sleep period, so that the residence time of each resident in the sleep period is averagely two hours on average on each base station;
for a user who is used to shutdown during sleeping, if the shutdown location is consistent with the startup location, judging that the user is a residence location, and judging that the startup location is consistent with the judgment standard as follows: if the distance between the base station where the last signaling data is located before the power-off in the previous day and the base station where the first signaling data is located after the power-on in the next day is less than 500 meters, the power-on and power-off sites are consistent, the residence of the user is the base station where the power-off in the previous day, residence identification of each user is completed according to the logic, and then the residence population statistics table of the base station is spatially associated with the service range of the base station, so that residence population of each service range of the base station is obtained. And finally, obtaining the population of the residence of each base station aggregated cell through space statistics.
4. The method of generating a rate estimate of a population of living being based on mobile phone signaling data as set forth in claim 1,
the construction is classified according to the "urban land classification and planning construction land standard (GB 50137-2011), and urban living lands are classified into three types, i.e., R11 (one type of residential land), R21 (two types of residential land), and R31 (three types of residential land), and if village construction land (H14) is present in the urban area, the three types of residential lands are incorporated into the present land classification.
5. The method of generating a rate estimate of a population of living being based on mobile phone signaling data as set forth in claim 1,
the specific steps of the step 2) are as follows:
2.1 Using a space connection tool for the land survey data and the building area data in ArcGIS software, correlating the building area data to the land survey data, and summarizing the building areas to obtain various building area data of each land;
2.2 Intersecting the land survey data with the taz_cb boundaries using an "intersecting" tool in ArcGIS software to obtain the living land area within each taz_cb, thereby counting the total building area of each living building within each taz_cb boundary.
2.3 And (3) superposing the population number of each TAZ_CB obtained in the step (1) and the total building area of each residential land of each TAZ_CB obtained in the step (2) through a superposition analysis tool of ArcGIS software to obtain a base station aggregation cell layer comprising the total building area and the population number.
6. The method for estimating the generation rate of living population based on the mobile phone signaling data according to claim 1, wherein the "urban land classification and planning construction land standard" in the step 1) is a version of the urban land classification and planning construction land standard (GB 50137-2011) issued by the residential and urban and rural construction.
7. The method for estimating the generation rate of living population based on mobile phone signaling data according to claim 1, wherein the step of constructing the multi-scale geographic weighted regression model is as follows:
1) A precondition for using a multi-scale geo-weighted regression Model (MGWR) is that there is a spatial correlation of the variables. Taking the practical significance of the model into consideration, constructing MGWR by taking the building area of the residential land as an independent variable;
2) Multiple collinearity checks are performed on the variables using SPSS software. If the pearson correlation coefficient shows that the respective variable correlation coefficient does not exceed 0.7; the variance expansion factor test shows that the VIF values are all smaller than 1, and the variables can be considered to have no multiple collinearity;
3) The method comprises the steps that a geographic weighted regression model is used as a local model, regression coefficients are obtained through regression calculation of observation points and sample points in a certain range around the observation points, a spatial weight matrix is used for measuring the relation between the sample points, whether the sample points participate in estimation or not is judged, a spatial kernel function is provided with a functional relation between spatial weights and the geographic position of the observation points and the geographic position distance between adjacent samples, and the attenuation condition of the spatial weights along with the distance is determined;
4) The self-adaptive bandwidth can better weigh the overall bias error and standard deviation, select the self-adaptive bandwidth setting method, and select and apply the wider AICc criterion to estimate the optimal bandwidth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211603529.3A CN116193369B (en) | 2022-12-13 | 2022-12-13 | Resident population generation rate estimation method based on mobile phone signaling data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211603529.3A CN116193369B (en) | 2022-12-13 | 2022-12-13 | Resident population generation rate estimation method based on mobile phone signaling data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116193369A true CN116193369A (en) | 2023-05-30 |
| CN116193369B CN116193369B (en) | 2023-10-27 |
Family
ID=86431709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211603529.3A Active CN116193369B (en) | 2022-12-13 | 2022-12-13 | Resident population generation rate estimation method based on mobile phone signaling data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116193369B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008243130A (en) * | 2007-03-29 | 2008-10-09 | Nomura Research Institute Ltd | Population estimation device and program |
| US20140032271A1 (en) * | 2012-07-20 | 2014-01-30 | Environmental Systems Research Institute (ESRI) | System and method for processing demographic data |
| CN105761190A (en) * | 2016-02-01 | 2016-07-13 | 东南大学 | Urban community vacancy rate dynamic monitoring method based on mobile phone location data |
| CN110728433A (en) * | 2019-09-19 | 2020-01-24 | 重庆市交通规划研究院 | Land parcel resident population measuring and calculating method based on mobile phone signaling |
| JP2020030727A (en) * | 2018-08-24 | 2020-02-27 | 株式会社ケイズ | Population estimation system |
| CN111126678A (en) * | 2019-12-09 | 2020-05-08 | 深圳市市政设计研究院有限公司 | Traffic generation prediction method based on big data |
| US20200213865A1 (en) * | 2017-06-13 | 2020-07-02 | South China University Of Technology | Method of user proportion investigation and population estimation in a region for mobile communication operators |
| WO2020238631A1 (en) * | 2019-05-31 | 2020-12-03 | 南京瑞栖智能交通技术产业研究院有限公司 | Population type recognition method based on mobile phone signaling data |
| CN112954623A (en) * | 2021-02-02 | 2021-06-11 | 苏州丽景智行交通工程咨询有限公司 | Resident occupancy rate estimation method based on mobile phone signaling big data |
| WO2021237812A1 (en) * | 2020-05-29 | 2021-12-02 | 南京瑞栖智能交通技术产业研究院有限公司 | Urban travel mode comprehensive identification method based on mobile phone signaling data and including personal attribute correction |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190104822A (en) * | 2018-03-02 | 2019-09-11 | 주식회사 케이티 | System and method for estimating living population |
-
2022
- 2022-12-13 CN CN202211603529.3A patent/CN116193369B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008243130A (en) * | 2007-03-29 | 2008-10-09 | Nomura Research Institute Ltd | Population estimation device and program |
| US20140032271A1 (en) * | 2012-07-20 | 2014-01-30 | Environmental Systems Research Institute (ESRI) | System and method for processing demographic data |
| CN105761190A (en) * | 2016-02-01 | 2016-07-13 | 东南大学 | Urban community vacancy rate dynamic monitoring method based on mobile phone location data |
| US20200213865A1 (en) * | 2017-06-13 | 2020-07-02 | South China University Of Technology | Method of user proportion investigation and population estimation in a region for mobile communication operators |
| JP2020030727A (en) * | 2018-08-24 | 2020-02-27 | 株式会社ケイズ | Population estimation system |
| WO2020238631A1 (en) * | 2019-05-31 | 2020-12-03 | 南京瑞栖智能交通技术产业研究院有限公司 | Population type recognition method based on mobile phone signaling data |
| CN110728433A (en) * | 2019-09-19 | 2020-01-24 | 重庆市交通规划研究院 | Land parcel resident population measuring and calculating method based on mobile phone signaling |
| CN111126678A (en) * | 2019-12-09 | 2020-05-08 | 深圳市市政设计研究院有限公司 | Traffic generation prediction method based on big data |
| WO2021237812A1 (en) * | 2020-05-29 | 2021-12-02 | 南京瑞栖智能交通技术产业研究院有限公司 | Urban travel mode comprehensive identification method based on mobile phone signaling data and including personal attribute correction |
| CN112954623A (en) * | 2021-02-02 | 2021-06-11 | 苏州丽景智行交通工程咨询有限公司 | Resident occupancy rate estimation method based on mobile phone signaling big data |
Non-Patent Citations (3)
| Title |
|---|
| 朱守杰;杜世宏;李军;商硕硕;杜守基;: "融合多源空间数据的城镇人口分布估算", 地球信息科学学报, no. 08 * |
| 董南;杨小唤;黄栋;韩冬锐;: "引入城市公共设施要素的人口数据空间化方法研究", 地球信息科学学报, no. 07 * |
| 詹庆明;杨苏舒;肖琨;高思航;严淑琴;: "基于手机信令数据的武汉市人口迁入成因研究", 地理信息世界, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116193369B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gao et al. | Discovering spatial interaction communities from mobile phone d ata | |
| García et al. | A comparative analysis of cellular automata models for simulation of small urban areas in Galicia, NW Spain | |
| CN102520464B (en) | Regional waterlogging forecasting system and forecasting method thereof | |
| CN110728433B (en) | Land occupation population measuring and calculating method based on mobile phone signaling | |
| Li et al. | Land suitability assessment for supporting transport planning based on carrying capacity and construction demand | |
| CN116341967A (en) | Park green scheme evaluation and optimization method, device and equipment based on GIS model and storage medium | |
| CN111432417A (en) | Sports center site selection method based on mobile phone signaling data | |
| CN114897228A (en) | Public facility layout inspection method based on population distribution and road network | |
| CN117114210B (en) | Barrier-free public facility layout optimization method, device, equipment and storage medium | |
| Zhou et al. | Residential-employment mixed use and jobs-housing balance: A case study of Shenzhen, China | |
| CN117151800A (en) | Rural land foundation land price assessment method | |
| CN116193369B (en) | Resident population generation rate estimation method based on mobile phone signaling data | |
| Long et al. | Mapping parcel-level urban areas for a large geographical area | |
| CN116882819A (en) | Urban park green space service capability evaluation method and system under low-carbon background | |
| Yang et al. | Evaluation of urban spatial equality based on accessibility to economic activities: Beijing as a case study | |
| CN115829811A (en) | County public service facility configuration evaluation method and system | |
| KR20050063615A (en) | Method for providing surface roughness in geographic information system | |
| CN115146990A (en) | Urban vitality quantitative evaluation method integrating multi-source geographic big data | |
| Rahman | Quantifying urban form-compactness versus sprawl: An analysis of Chittagong and Sylhet metropolitan cities | |
| Mao et al. | Population spatialization at building scale based on residential population index—A case study of Qingdao city | |
| CN111506879A (en) | Population spatialization measuring and calculating method and device based on multi-source perception data | |
| Mohammadi et al. | On the spatial dependencies of human mobility and urban energy consumption | |
| CN114363823B (en) | Population density monitoring method and system based on MR (magnetic resonance) resident places and building outlines | |
| Jirwankar et al. | An Assessment of Land Use Changes Influenced By Urbanization: Implication with Spatial Distribution of Land Using Remote Sensing Technique | |
| Adam et al. | Revisiting urban models with information and communication technology data? Some examples from Brussels |
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 |