CN115186009A - Urban population daily change spatialization method and system based on interest point data - Google Patents
Urban population daily change spatialization method and system based on interest point data Download PDFInfo
- Publication number
- CN115186009A CN115186009A CN202210825574.7A CN202210825574A CN115186009A CN 115186009 A CN115186009 A CN 115186009A CN 202210825574 A CN202210825574 A CN 202210825574A CN 115186009 A CN115186009 A CN 115186009A
- Authority
- CN
- China
- Prior art keywords
- population
- population distribution
- poi
- distribution
- coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
Abstract
The invention relates to a method and a system for spatializing the change of an urban population in a day based on interest point data, wherein the method comprises the following steps: classifying the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories; dividing each POI category by time periods based on the population distribution characteristics, and setting the population distribution weight of each POI category in different time periods; performing core density calculation on each POI category to obtain a core density coefficient, and determining a total population distribution coefficient of all POI categories according to the core density coefficient and population distribution weight; determining the total population distribution coefficient of each administrative district according to the total population distribution coefficient and a preset administrative district spatial distribution diagram, and determining the population distribution number of unit population distribution coefficients of each administrative district according to the total population number and the total population distribution coefficient of each administrative district. The invention carries out more refined quantitative simulation of population space distribution at different moments on population spatialization, and can calculate the population space distribution at any time point in the day by taking hour as a unit.
Description
Technical Field
The invention relates to the technical field of population distribution estimation, in particular to a method and a system for spatializing the daily variation of urban population based on point of interest data.
Background
The population data is the basic data reflecting the socioeconomic situation of a country or a region, and the spatial distribution of population is the comprehensive reflection of the socioeconomic phenomenon. At present, each country still obtains basic statistical data of population in a census mode, however, the statistical demographic data is mostly in units of administrative districts, and the census time interval is long. But the spatial distribution of the population within any one administrative area is not uniform. Therefore, population data in administrative areas acquired by the existing statistical method hardly reflect population distribution differences in the same administrative unit, and therefore population spatialization in the administrative unit is brought forward. The spatially processed population spatial distribution data is convenient to fuse with other multi-source data such as resource and environment data, social problem data, economic statistical data and the like, and can better provide scientific support for urban planning, economic decision, disaster prevention, crime management, reasonable public resource allocation, environmental protection and other researches.
At present, there are various population data spatialization methods, such as population density-distance attenuation models, interpolation methods, land use type influence models, multi-source data fusion models, and the like. Previous studies have mostly spatialized population data for a single indicator factor, particularly for land use types. Or simply interpolating demographic data, such as Point of Interest (POI) data or a neighborhood of residents, to reflect the spatial distribution of the population. The population spatialization model established based on the land utilization type is widely applied, but the method assumes that the same land utilization type has the same population density and cannot finely depict the spatial difference of the population.
Most of the current population spatialization methods are based on population census data once in 10 years or yearly-based yearbook demographic data, and the dynamic change situation of the population in the year is difficult to reflect. With the development of Remote Sensing (RS) and Geographic Information Systems (GIS), multi-source data is continuously accumulated, and a data base and technical support are provided for the fine-scale population spatialization research. The population data spatialization is gradually developed from a single indicating factor and a simple interpolation method to multi-source data, and a fusion model is more and more perfect.
From the development of the existing population spatialization technology, the traditional method is difficult to reflect the population distribution condition with a finer scale, the obtained population space distribution data are static, the change characteristics of population along with time cannot be reflected, and the requirements of the fields of urban emergency management, post-disaster rescue, loss assessment and the like on population difference space distribution at different time points in the day cannot be met.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method and a system for spatializing the daily change of urban population based on point of interest data.
In order to achieve the purpose, the invention provides the following scheme:
a city population day-to-day variation spatialization method based on point of interest data comprises the following steps:
classifying the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories;
dividing each POI category by time periods based on population distribution characteristics, and setting population distribution weights of the POI categories in different time periods;
performing core density calculation on each POI category to obtain a core density coefficient, and determining a total population distribution coefficient of all POI categories according to the core density coefficient and the population distribution weight;
and determining the total population distribution coefficient of each administrative district according to the total population distribution coefficient and a preset administrative district spatial distribution diagram, and determining the population distribution number of unit population distribution coefficients of each administrative district according to the total population number of each administrative district and the total population distribution coefficient so as to realize spatialization of population distribution of each administrative district.
Preferably, the POI categories include: a first scenic spot, a second scenic spot, a catering service, a first science and education culture service, a second science and education culture service, a service facility, an office location, a residential area, a shopping service, a financial insurance service, a motor vehicle service, a sports leisure service, a healthcare service, and others; wherein the first scenic spot comprises a park and a sight; the second scenic spot comprises a city square; the first science and education culture service comprises middle school, primary school and kindergarten; the second science and education culture service comprises a college.
Preferably, the time-interval division of each POI category based on the population distribution characteristics, and the setting of the population distribution weight of each POI category in different time intervals includes:
dividing each POI category into a population concentrated distribution time period and a non-population concentrated distribution time period according to the population distribution characteristics;
and setting the population distribution weight of each POI category in the population concentration distribution time period to be 1, and setting the population distribution weight of each POI category in the non-population concentration distribution time period to be a value less than 1.
Preferably, the calculation formula of the nuclear density coefficient is as follows:
wherein, F h (x) The method comprises the following steps of taking a kernel density coefficient, wherein K represents a kernel function, n is the number of POI data, a variable x is n POI sample points which are independently distributed, h is a search radius, and the calculation formula of h is as follows:
wherein SD represents the standard deviation, D m Is the median distance.
Preferably, the determining a total population distribution coefficient of all the POI categories according to the kernel density coefficient and the population distribution weight includes:
according to formula A i ＝F i *γ i Calculating a population distribution coefficient of each POI category; wherein A is i The population distribution coefficient for the ith POI category, F i The nuclear density coefficient, γ, for the ith POI class i The demographic distribution weight for the ith POI category;
according to formula B i ＝(A i -Min(A i )/(Max(A i )-Min(A i ) Normalizing the population distribution coefficient to obtain a normalized result; wherein, B i Population distribution coefficient A for different POI categories i The normalization processing result of (a);
according to the formula
Calculating the population distribution coefficient; wherein B is all POI categories B i And summing the obtained population distribution coefficients.
Preferably, the calculation formula of the population distribution coefficient total amount of each administrative district is as follows:
wherein, B county Summing the calculated total value of population distribution coefficients B corresponding to all grids in the spatial range of each administrative region; j is the number of said grid into which said administrative distinction is divided; b is j Is the population distribution coefficient of the jth grid in the region of the administrative district.
Preferably, the calculation formula of the population distribution number of the population distribution coefficient of each administrative district unit is as follows:
wherein, POP county The population for the administrative district; and the POPs are population distribution numbers of the unit population distribution coefficients of the administrative areas, and are used as the spatial calculation results of the population of the administrative areas.
A city population day-to-day variation spatialization system based on point of interest data comprises:
the category dividing unit is used for carrying out category division on the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories;
the weight determining unit is used for dividing each POI category by time periods based on population distribution characteristics and setting population distribution weights of the POI categories in different time periods;
the general population distribution coefficient determining unit is used for performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining general population distribution coefficients of all the POI categories according to the kernel density coefficient and the population distribution weight;
and the spatialization unit is used for determining the population distribution coefficient total amount of each administrative area according to the general population distribution coefficient and a preset administrative area spatial distribution diagram, and determining the population distribution amount of each administrative area unit population distribution coefficient according to the general population amount of each administrative area and the population distribution coefficient total amount so as to realize spatialization of population distribution of each administrative area.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a method and a system for spatializing the change of an urban population in a day based on point of interest data, wherein the method comprises the following steps: classifying the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories; dividing each POI category by time periods based on population distribution characteristics, and setting population distribution weights of the POI categories in different time periods; performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining a total population distribution coefficient of all POI categories according to the kernel density coefficient and the population distribution weight; and determining the total population distribution coefficient of each administrative district according to the total population distribution coefficient and a preset administrative district spatial distribution diagram, and determining the population distribution number of unit population distribution coefficients of each administrative district according to the total population number of each administrative district and the total population distribution coefficient so as to realize spatialization of population distribution of each administrative district. In the specific embodiment provided by the invention, the mouth spatialization is considered to be more finely and quantitatively simulated in the population space distribution at different times in the day on the time scale in the day, and the population space distribution at any time point in the day can be calculated by taking hours as a unit.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flowchart of a method for spatializing daily variation of a city population based on point of interest data according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of population spatialization techniques at different time intervals during the day according to an embodiment of the present invention;
FIG. 3 is a schematic view of a spatial distribution of POIs in a park attraction in an embodiment of the present invention;
FIG. 4 is a schematic view of a spatial distribution of a food service POI in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a population distribution coefficient of POIs of an 8-point early park attraction in an embodiment provided by the present invention;
fig. 6 is a schematic diagram of a population distribution coefficient of an POI of 8 breakfast in an embodiment of the present invention;
FIG. 7 is a graph illustrating the total population distribution coefficient at 8 o' clock in an example provided by the present invention;
FIG. 8 is a graphical illustration of a 12 PM population distribution coefficient in an embodiment provided by the present invention;
FIG. 9 is a graphical illustration of a 6 PM population distribution coefficient in an embodiment provided by the invention;
FIG. 10 is a graphical illustration of a total population distribution factor at 24 pm in an embodiment of the present invention;
FIG. 11 is a schematic diagram illustrating the 6 th district population distribution in Beijing, 8 am in accordance with an embodiment of the present invention;
FIG. 12 is a schematic illustration of the population distribution in 6 Beijing urban areas at 12 noon according to an embodiment of the present invention;
FIG. 13 is a schematic illustration of the 6 th cell population distribution in Beijing city at 6 PM according to an embodiment of the present invention;
fig. 14 is a schematic diagram of population distribution in 6 beijing urban areas at 24 pm in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, the inclusion of a list of steps, processes, methods, etc. is not limited to only those steps recited, but may alternatively include additional steps not recited, or may alternatively include additional steps inherent to such processes, methods, articles, or devices.
The invention aims to provide a method and a system for spatializing the daily variation of urban population based on point-of-interest data, which can carry out more precise quantitative simulation on population spatialization and population space distribution at different moments.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a method for spatializing daily variation of a city population based on point of interest data in an embodiment provided by the present invention, and as shown in fig. 1, the present invention provides a method for spatializing daily variation of a city population based on point of interest data, including:
step 100: classifying the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories;
step 200: dividing each POI category by time periods based on population distribution characteristics, and setting population distribution weights of the POI categories in different time periods;
step 300: performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining a total population distribution coefficient of all POI categories according to the kernel density coefficient and the population distribution weight;
step 400: and determining the total population distribution coefficient of each administrative district according to the total population distribution coefficient and a preset administrative district spatial distribution diagram, and determining the population distribution number of unit population distribution coefficients of each administrative district according to the total population number of each administrative district and the total population distribution coefficient so as to realize spatialization of population distribution of each administrative district.
Optionally, the point of interest POI data in this embodiment includes four pieces of information: the name, the category, the coordinate and the classification are emerging data resources with the characteristics of large sample size, dynamic updating and the like. The method can intuitively and effectively reflect the spatial distribution conditions of different surface elements of a city, and is closely related to the time-space characteristics of human activities, so that the simulation and prediction of the spatial distribution of population at different moments in the day can be realized on the basis.
Preferably, the POI categories include: a first scenic spot, a second scenic spot, a catering service, a first science and education culture service, a second science and education culture service, a service facility, an office location, a residential area, a shopping service, a financial insurance service, a motor vehicle service, a sports leisure service, a healthcare service, and others; wherein the first scenic spot comprises a park and a sight; the second scenic spot comprises a city square; the first science and education culture service comprises middle school, primary school and kindergarten; the second science and education culture service comprises a college.
Preferably, the step 200 specifically includes:
dividing each POI category into a population concentrated distribution time period and a non-population concentrated distribution time period according to the population distribution characteristics;
and setting the population distribution weight of each POI category in the population concentration distribution time period to be 1, and setting the population distribution weight of each POI category in the non-population concentration distribution time period to be a value less than 1.
Fig. 2 is a schematic diagram of a process of population spatialization technology at different time intervals in a day according to an embodiment of the present invention, as shown in fig. 2, a first process in this embodiment first performs category division on POI data according to a population activity aggregation characteristic of each POI category, each category is divided into a population concentrated distribution time interval and a non-population concentrated distribution time interval according to a population distribution characteristic, and population distribution weights of each POI category at different time intervals are set, as shown in table 1. For convenience of calculation, a weight set to 0-1,0 indicates that there is no population distribution in the time period, a weight greater than 0 indicates that there is population distribution in the time period, and the closer the weight is to 1, the more concentrated the distribution of population is.
TABLE 1 PowerPoint of interest (POI) Categories population distribution weights at different time periods during the day
In this embodiment, only the working days are considered for the scientific and educational services (school, primary school, kindergarten) and the office locations (company, enterprise, government agency).
Preferably, the calculation formula of the nuclear density coefficient is as follows:
wherein, F h (x) The method comprises the following steps of taking a kernel density coefficient, wherein K represents a kernel function, n is the number of POI data, a variable x is n POI sample points which are independently distributed, h is a search radius, and the calculation formula of h is as follows:
wherein D is the Euclidean distance between each two POI sample points, D m SD represents the standard deviation of the median euclidean distance.
As an alternative embodiment, h may be set to 1km or 100m in the calculation.
Preferably, the determining a total population distribution coefficient of all the POI categories according to the kernel density coefficient and the population distribution weight includes:
according to formula A i ＝F i *γ i Calculating a population distribution coefficient of each POI category; wherein A is i The population distribution coefficient, F, for the ith POI category i The nuclear density coefficient, γ, for the ith POI class i The demographic distribution weight for the ith POI category;
according to formula B i ＝(A i -Min(A i )/(Max(A i )-Min(A i ) Normalizing the population distribution coefficient to obtain a normalized result; wherein, B i Population distribution coefficient A for different POI categories i The normalization processing result of (a);
according to the formula
Calculating the population distribution coefficient; wherein B is all POI categories B i And summing the obtained population distribution coefficients.
Preferably, the calculation formula of the population distribution coefficient total amount of each administrative district is as follows:
wherein, B county Summing the calculated total value of population distribution coefficients B corresponding to all grids in the spatial range of each administrative region; j is the number of said grid into which said administrative distinction is divided; b is j Is the population distribution coefficient of the jth grid in the region of the administrative district.
As shown in fig. 2, in the second process of this embodiment, a population distribution coefficient is calculated for each POI category, the spatial aggregation degree of the POIs of different categories directly reflects the spatial distribution state of the population, and the higher the POI aggregation degree is, the higher the reflected population aggregation degree is. According to the method, the aggregation degree of POI of each category is quantified by using kernel density analysis, a kernel density coefficient (formula 2) is obtained by performing kernel density calculation on POI of each category, and then the population distribution coefficient of the POI category is obtained by combining the population distribution weights of different POI categories determined in the step 1. In order to eliminate the influence caused by the dimension difference of the calculation results of different POI categories, the population distribution coefficients of different POI categories need to be normalized, and then summed to obtain the total population distribution coefficient (formula 3) of all POI categories.
The method for calculating the nuclear density coefficient of each POI category comprises the following steps:
the search radius of the POI is obtained by formula (1). Wherein SD represents the standard deviation, D m And n is the number of POIs (points of interest) which are median distances.
Equation (2) is a calculation equation of the nuclear density, F h (x) For the kernel density coefficient, K represents the kernel function, h is the search radius, which can be set to 1km or 100m in the calculation, and the variable x is the independent componentN POI sample points of the cloth.
The population distribution coefficient calculation formula is as follows:
A i ＝F i *γ i (3)
B i ＝(A i -Min(A i )/(Max(A i )-Min(A i )) (4)
in the formulae (3) to (5), A i Population distribution coefficient for the ith POI category, F i Is the nuclear density coefficient, γ, of the iPoi class i Population distribution weight for the ith POI category, B i Population distribution coefficient A for different POI categories i Normalizing the result, B being all POI categories B i And summing the obtained population distribution coefficients.
Preferably, the calculation formula of the population distribution number of the population distribution coefficient of each administrative district unit is as follows:
wherein, POP county The population for the administrative district; and the POPs are population distribution numbers of the unit population distribution coefficients of the administrative areas, and are used as the spatial calculation results of the population of the administrative areas.
In this embodiment, the last process is spatialization of population distribution in each administrative district, the spatial distribution map of the administrative district is overlapped on the basis of the total population distribution coefficient obtained in the process 2, the total population distribution coefficient of each administrative district is calculated through spatial overlapping operation, then the population distribution number of the unit population distribution coefficient of each administrative district is calculated on the basis of the total population number of each administrative unit and the total population distribution coefficient of the administrative district obtained through calculation, and spatialization of population distribution in each administrative district is realized on the basis of the population distribution number.
The formula of the population spatialization calculation is as follows:
in the formula, B county The total value calculated by summing the population distribution coefficients B corresponding to all the grids (grids) in the spatial range of each administrative district (assuming that the administrative district is divided into j grids) j The value of the population distribution coefficient of the jth grid (grid) in a certain administrative area. POP is the calculation result of each administrative district population spatialization, and POP county And B, calculating the obtained total population distribution coefficient spatial distribution data by the flow 2 for the total population number of the administrative district.
In the embodiment, the prior art scheme is considered not to support the population spatialization at a certain moment in the day, the existing population spatialization research is mainly carried out by taking years or decades as units, annual population space distribution data are obtained, and the requirement of rapid development and change of the current society on population distribution difference at different moments in the day cannot be met, and the requirement of the population space distribution at a certain moment in the day cannot be met under the emergency condition. Therefore, on the time scale in the day, the population space distribution at different moments in the day is more finely simulated, and the population space distribution at any time point in the day can be calculated by taking the hour as a unit. The specific application process is as follows:
the population spatialization calculation process of the patent is illustrated by taking four moments in the morning at 8 o 'clock, at noon at 12 o' clock, at afternoon at 6 o 'clock and at 24 o' clock in the evening in six regions (including a hai lake region, a stone landscape mountain region, a Fengtai region, a West city region, a east city region and a sunward region) in Beijing city as an example.
(1) POI category population distribution weight determination
In the process of spatialization of population in six areas in Beijing city at different times of day, POI categories, corresponding time periods and population distribution weights are firstly set according to the POI categories, the corresponding time periods and the population distribution weights which are divided in the table 1. The spatial distribution of 2 types of POI data, such as scenic spots and catering services, is shown in fig. 3 and 4. Referring to the population distribution influence weights determined in procedure 1, the population distribution influence weights of the scenic spots (parks, attractions) at four moments of early 8 (belonging to the period of 00-17), midday 12 (belonging to the period of 8 00-17), afternoon 6 (belonging to other periods), and evening 24 (belonging to other periods) are 1,1,0 and 0, respectively. Population distribution impact weights at 8 am (belonging to time period 6 00-9), 12 am (belonging to time period 11 00-14), 6 pm (belonging to time period 17-23), 24 pm (belonging to other time periods) are 1,1,1 and 0.
(2) POI population distribution coefficient calculation of each category
And (3) performing nuclear density coefficient calculation on 14 POI categories in 6 regions in Beijing city by using a formula (1) and a formula (2) in GIS software arcmag according to a reference process 2, wherein the search radius is set to be 1km during calculation, and the size of a data grid is set to be 1km. And then multiplying the calculated POI core density coefficient of each category by the population distribution influence weight corresponding to the POI category at 8 o 'clock, 12 o' clock at noon, 6 o 'clock in afternoon and 24 o' clock in the evening (formula 3) to obtain the population distribution coefficient of each POI category at different moments. Wherein, fig. 5 and fig. 6 are the population distribution coefficients of the scenic spots (park scenic spots) and the catering service POI at the 8 th earliest point respectively.
The population distribution coefficients of the POI categories at different times are normalized by using formula (4), and the population distribution coefficient normalization processing results of all the POI categories corresponding to 4 times of 8 am, 12 pm, 6 pm and 24 pm are summed by using formula (5), so as to obtain the total population distribution coefficient of all the POI types at each time (as shown in fig. 7 to 10).
(3) Spatialization of population distribution at different times of day
According to the formula (6) in the process 3, the total value of the population distribution coefficients of the six beijing urban areas at different times is calculated, the calculation result is shown in table 2, and the population number of each area is combined, based on the formula (7), the population distribution spatialization calculation of each area at different times is performed, so that the population distribution results of the six beijing urban areas at different times are obtained (as shown in fig. 11 to 14).
TABLE 2 Total value of population distribution coefficient of six areas and different times in Beijing city
Corresponding to the method, the embodiment also provides a city population daily change spatialization system based on the point of interest data, which includes:
the category dividing unit is used for carrying out category division on the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories;
the weight determining unit is used for dividing each POI category by time periods based on population distribution characteristics and setting population distribution weights of the POI categories in different time periods;
the general population distribution coefficient determining unit is used for performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining general population distribution coefficients of all the POI categories according to the kernel density coefficient and the population distribution weight;
and the spatialization unit is used for determining the population distribution coefficient total amount of each administrative area according to the general population distribution coefficient and a preset administrative area spatial distribution diagram, and determining the population distribution amount of each administrative area unit population distribution coefficient according to the general population amount of each administrative area and the population distribution coefficient total amount so as to realize spatialization of population distribution of each administrative area.
The invention has the following beneficial effects:
the invention considers the spatialization method of population at different time intervals in the day for the first time, and realizes the quantitative estimation of population distribution at different time intervals in the day. The calculation model provided by the invention can quantify the population space distribution state at any time point in the day.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principle and the embodiment of the present invention are explained by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A city population day-to-day variation spatialization method based on interest point data is characterized by comprising the following steps:
the method comprises the steps of classifying POI data based on population activity gathering characteristics to obtain a plurality of POI categories;
dividing each POI category by time periods based on population distribution characteristics, and setting population distribution weights of the POI categories in different time periods;
performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining a total population distribution coefficient of all POI categories according to the kernel density coefficient and the population distribution weight;
and determining the total population distribution coefficient of each administrative district according to the total population distribution coefficient and a preset administrative district spatial distribution diagram, and determining the population distribution number of unit population distribution coefficients of each administrative district according to the total population number of each administrative district and the total population distribution coefficient so as to realize spatialization of population distribution of each administrative district.
2. The method of spatio-temporal variation of urban population based on point-of-interest data according to claim 1, characterized in that the POI categories comprise: a first scenic spot, a second scenic spot, a catering service, a first science and education culture service, a second science and education culture service, a service facility, an office location, a residential area, a shopping service, a financial insurance service, a motor vehicle service, a sports leisure service, a healthcare service, and others; wherein the first scenic spots comprise parks and sights; the second scenic spot comprises a city square; the first science and education culture service comprises middle school, primary school and kindergarten; the second science and education culture service comprises a college.
3. The method for spatializing the day-to-day variation of the urban population based on the point-of-interest data as claimed in claim 1, wherein the step of dividing each POI category by time periods based on the population distribution characteristics and setting the population distribution weight of each POI category in different time periods comprises the steps of:
dividing each POI category into a population concentrated distribution time period and a non-population concentrated distribution time period according to the population distribution characteristics;
and setting the population distribution weight of each POI category in the population concentration distribution time period to be 1, and setting the population distribution weight of each POI category in the non-population concentration distribution time period to be a value less than 1.
4. The method for spatializing the daily variation of the urban population based on the point of interest data as claimed in claim 1, wherein the calculation formula of the kernel density coefficient is as follows:
wherein, F h (x) The method comprises the following steps of taking a kernel density coefficient, wherein K represents a kernel function, n is the number of POI data, a variable x is n POI sample points which are independently distributed, h is a search radius, and the calculation formula of h is as follows:
wherein SD represents the standard deviation, D m Is the median distance.
5. The method of spatialization of daily variation of urban population based on point-of-interest data according to claim 1, wherein said determining the total population distribution coefficient of all POI categories according to the kernel density coefficient and the population distribution weight comprises:
according to formula A i ＝F i *γ i Calculating a population distribution coefficient of each POI category; wherein A is i The population distribution coefficient for the ith POI category, F i The nuclear density coefficient, γ, for the ith POI class i The demographic distribution weight for the ith POI category;
according to formula B i ＝(A i -Min(A i ))/(Max(A i )-Min(A i ) Normalizing the population distribution coefficient to obtain a normalized result; wherein, B i Population distribution coefficient A for different POI categories i The normalization processing result of (a);
according to the formula
Calculating the population distribution coefficient; wherein B is all POI categories B i And summing the obtained population distribution coefficients.
6. The method for spatializing the daily change of the urban population based on the point-of-interest data as claimed in claim 5, wherein the total population distribution coefficient of each administrative district is calculated by the following formula:
wherein, B county Summing the calculated total value of population distribution coefficients B corresponding to all grids in the spatial range of each administrative region; j is the number of said grid into which said administrative distinction is divided; b is j For the j-th grid in the region of the administrative districtPopulation distribution coefficient.
7. The method for spatializing the daily variation of the population of a city based on the point-of-interest data as claimed in claim 6, wherein the calculation formula of the population distribution number of the population distribution coefficient of each administrative region unit is as follows:
wherein, POP county The total population number for the administrative district; and the POPs are population distribution numbers of the unit population distribution coefficients of the administrative areas, and are used as the spatial calculation results of the population of the administrative areas.
8. A city population day-to-day variation spatialization system based on point of interest data is characterized by comprising:
the category dividing unit is used for carrying out category division on the POI data based on the population activity gathering characteristics to obtain a plurality of POI categories;
the weight determining unit is used for dividing each POI category into time periods based on population distribution characteristics and setting population distribution weights of the POI categories in different time periods;
the general population distribution coefficient determining unit is used for performing kernel density calculation on each POI category to obtain a kernel density coefficient, and determining general population distribution coefficients of all the POI categories according to the kernel density coefficient and the population distribution weight;
and the spatialization unit is used for determining the population distribution coefficient total amount of each administrative area according to the general population distribution coefficient and a preset administrative area spatial distribution diagram, and determining the population distribution amount of each administrative area unit population distribution coefficient according to the general population amount of each administrative area and the population distribution coefficient total amount so as to realize spatialization of population distribution of each administrative area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825574.7A CN115186009A (en) | 2022-07-13 | 2022-07-13 | Urban population daily change spatialization method and system based on interest point data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825574.7A CN115186009A (en) | 2022-07-13 | 2022-07-13 | Urban population daily change spatialization method and system based on interest point data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115186009A true CN115186009A (en) | 2022-10-14 |
Family
ID=83519044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210825574.7A Pending CN115186009A (en) | 2022-07-13 | 2022-07-13 | Urban population daily change spatialization method and system based on interest point data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186009A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708962A (en) * | 2016-11-30 | 2017-05-24 | 中山大学 | Urban population distribution method based on building properties |
| CN110097264A (en) * | 2019-04-18 | 2019-08-06 | 华南理工大学 | A kind of measure of group of cities space and economic relation intensity |
| CN110428126A (en) * | 2019-06-18 | 2019-11-08 | 华南农业大学 | A kind of urban population spatialization processing method and system based on the open data of multi-source |
| CN112925870A (en) * | 2021-03-15 | 2021-06-08 | 北京师范大学 | Population spatialization method and system |
| CN114529043A (en) * | 2022-01-05 | 2022-05-24 | 深圳大学 | Urban space grouping method |
-
2022
- 2022-07-13 CN CN202210825574.7A patent/CN115186009A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106708962A (en) * | 2016-11-30 | 2017-05-24 | 中山大学 | Urban population distribution method based on building properties |
| CN110097264A (en) * | 2019-04-18 | 2019-08-06 | 华南理工大学 | A kind of measure of group of cities space and economic relation intensity |
| CN110428126A (en) * | 2019-06-18 | 2019-11-08 | 华南农业大学 | A kind of urban population spatialization processing method and system based on the open data of multi-source |
| CN112925870A (en) * | 2021-03-15 | 2021-06-08 | 北京师范大学 | Population spatialization method and system |
| CN114529043A (en) * | 2022-01-05 | 2022-05-24 | 深圳大学 | Urban space grouping method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Exploring the effect of air pollution on social activity in China using geotagged social media check-in data | |
| Neena et al. | Model performance metrics and process diagnostics for boreal summer intraseasonal variability | |
| Xu et al. | Combining AHP with GIS in synthetic evaluation of environmental suitability for living in China's 35 major cities | |
| Mitchell et al. | Assessing mid-latitude dynamics in extreme event attribution systems | |
| Greger | Spatio‐Temporal Building Population Estimation for Highly Urbanized Areas Using GIS | |
| CN110503485B (en) | Geographical region classification method and device, electronic equipment and storage medium | |
| Wang et al. | Spatiotemporal variability in long-term population exposure to PM2. 5 and lung cancer mortality attributable to PM2. 5 across the Yangtze River Delta (YRD) region over 2010–2016: A multistage approach | |
| Kumar | Mapping solar energy potential of southern India through geospatial technology | |
| Yu et al. | An assessment of air-quality monitoring station locations based on satellite observations | |
| Zhan et al. | How do greenspace landscapes affect PM2. 5 exposure in Wuhan? Linking spatial-nonstationary, annual varying, and multiscale perspectives | |
| Réquia Júnior et al. | A spatial multicriteria model for determining air pollution at sample locations | |
| Bai et al. | A Geographic Information System (GIS)-based approach to adaptation to regional climate change: a case study of Okutama-machi, Tokyo, Japan | |
| CN111881573B (en) | Population space distribution simulation method and device based on urban inland inundation risk assessment | |
| Bakirci | Correlations for optimum tilt angles of solar collectors: a case study in Erzurum, Turkey | |
| Thompson et al. | Developing effective sampling designs for monitoring natural resources in Alaskan national parks: An example using simulations and vegetation data | |
| Jafari et al. | An optimum slope angle for solar collector systems in kerman using a new model for diffuse solar radiation | |
| Herrera et al. | Creating extreme weather time series through a quantile regression ensemble | |
| Wei et al. | Dynamic assessment of spatiotemporal population distribution based on mobile phone data: a Case Study in Xining City, China | |
| CN115186009A (en) | Urban population daily change spatialization method and system based on interest point data | |
| Molinari et al. | North Atlantic decadal variability and the formation of tropical storms and hurricanes | |
| Ge et al. | Links Between the Large‐Scale Circulation and Daily Air Quality Over Central Eastern China During Winter | |
| Mohammadi et al. | Temporal and spatial analysis of thermal stress and its trend in Iran | |
| CN111582683B (en) | Urban public service facility supply efficiency evaluation method based on network heat | |
| Phithakkitnukoon et al. | Temporary Migration Flow Inference and Analysis From Perspective of Mobile Phone Network Data | |
| Tobler | Movement modeling on the sphere |
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 |