CN115049159B - Population distribution prediction method and device, storage medium and electronic equipment - Google Patents
Population distribution prediction method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115049159B CN115049159B CN202210965718.9A CN202210965718A CN115049159B CN 115049159 B CN115049159 B CN 115049159B CN 202210965718 A CN202210965718 A CN 202210965718A CN 115049159 B CN115049159 B CN 115049159B
- Authority
- CN
- China
- Prior art keywords
- population
- target
- data
- traffic cell
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention discloses a population distribution prediction method and device, a storage medium and electronic equipment. Wherein the method comprises the following steps: acquiring multi-source space-time big data of a target city from a multi-source space-time big database, wherein the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data; acquiring a resident population of the target city in a target time period based on a parameter regression analysis model, and determining an age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; determining the number of resident populations of the target cell in the target time period based on a population space increment distribution model and the resident populations, the age structure of the resident populations and the population flow number. The method solves the technical problem that the urban population distribution cannot be accurately predicted in the related technology.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a population distribution prediction method and apparatus, a storage medium, and an electronic device.
Background
The urban population distribution simulation prediction technology in the related technology mainly adopts population total and distribution statistics survey data, social economy and environmental facility data and mobile phone signaling data; the population quantity distribution simulation calculation method is characterized in that a simple linear regression Model (SLR), a Geographical Weighted Regression (GWR) Model, a multi-agent Model (ABM), a Gravity Model (Gravity Model), a Space increment Model (Incremental Space Model), a Machine Learning and Artificial Neural Network (Machine Learning and Artificial Neural Network) Model and the like are applied to spatialization of current population data or population quantity distribution simulation calculation based on social economy and environmental facility data, and population distribution base map data are provided for academic research and government planning. However, the related art has the following problems:
(1) There is a lack of quantitative measures of demographic factors interaction relationships and mechanisms of action. Whether a simple linear regression model, a geographic weighted regression model or machine learning such as an artificial neural network, etc., the correlation between the population number of the resident population and the population distribution factor is basically obtained by numerically fitting the relationship between the population distribution and the influencing factor, which lacks accurate and detailed measures for the correlation between the population distribution factors of the urban resident population.
(2) A systematic simulation model capable of simultaneously and accurately simulating a plurality of key factors influencing the urban population distribution is lacked. The existing model is only aimed at a certain problem, the assumed conditions of the model are ideal, the model is not close to the real situation of a complex urban system, and the model which considers numerous key factors influencing population distribution such as population social and economic attributes, geographic information and the like and accurately simulates the urban systematization is lacked.
(3) There is a lack of real-time dynamic prediction of urban residential population distribution. Most of the existing models are used for carrying out population data spatialization on the basis of population distribution total quantity, current population distribution is basically measured and calculated on the basis of current social and economic attributes and geographic information data, and time sequence prediction is not carried out along the time axis to the future. Real-time and dynamic simulation prediction cannot be performed on urban population distribution, so that a simulation result cannot reflect real conditions in time, and the application range of the simulation result is narrow.
Disclosure of Invention
The embodiment of the invention provides a population distribution prediction method and device, a storage medium and electronic equipment, which at least solve the technical problem that the urban population distribution cannot be accurately predicted in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a population distribution prediction method, including: acquiring multi-source space-time big data of a target city from a multi-source space-time big database, wherein the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and Internet POI (point of interest) data; acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; determining the number of resident populations of the target cell in the target time period based on a population space increment distribution model and the resident populations, the age structure of the resident populations and the population flow number.
According to another aspect of the embodiments of the present invention, there is also provided a population distribution prediction apparatus, including: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring multi-source space-time big data of a target city from a multi-source space-time big database, and the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data; the second obtaining unit is used for obtaining the resident population of the target city in the target time period based on the parameter regression analysis model and determining the age structure of the resident population based on the time sequence prediction model; the third acquisition unit is used for acquiring the population flow number of the target city among different cells in the target time period based on the migrating random utility selection model; and the determining unit is used for determining the number of the resident population of the target cell in the target time period based on the population space increment distribution model, the resident population, the age structure of the resident population and the population floating number.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the population distribution prediction method through the computer program.
According to a further aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the above-mentioned population distribution prediction method when running.
In the embodiment of the invention, multi-source space-time big data of a target city are obtained from a multi-source space-time big database, wherein the multi-source space-time big data comprise mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data; acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; the method for determining the number of the residential population of the target cell in the target time period based on the population space incremental distribution model, the residential population, the age structure of the residential population and the population floating number can realize real-time dynamic prediction of the residential population distribution due to the fact that population difference prediction models are built through multidimensional factors, and further solve the technical problem that the urban population distribution cannot be accurately predicted in the related technology.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of an application environment of an alternative population distribution prediction method according to an embodiment of the invention;
FIG. 2 is a schematic illustration of an environment in which an alternative population distribution prediction method may be used, according to an embodiment of the present invention;
FIG. 3 is a schematic flow diagram of an alternative population distribution prediction method according to an embodiment of the present invention;
FIG. 4 is a schematic flow diagram of an alternative demographic distribution prediction method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an alternative demographic pattern prediction according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an alternative demographic pattern prediction according to an embodiment of the present invention;
FIG. 7 is a graphical illustration of an alternative demographic spatial partitioning prediction result, in accordance with an embodiment of the present invention;
FIG. 8 is a graphical illustration of alternative spatial partitioning predictions for a population distribution pattern in accordance with an embodiment of the present invention;
FIG. 9 is a schematic diagram of an alternative demographic distribution prediction apparatus according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an alternative electronic device according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the embodiments of the present invention, 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 the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an aspect of the embodiments of the present invention, there is provided a population distribution prediction method, which may be applied, but not limited, to the application environment shown in fig. 1 as an alternative implementation. The terminal equipment 102, the network 104 and the server 106 are used for human-computer interaction with the user. The user 108 and the terminal device 102 can perform human-computer interaction, and a human mouth distribution prediction application client is operated in the terminal device 102. The terminal device 102 includes a human-machine interaction screen 1022, a processor 1024, and a memory 1026. The human-computer interaction screen 1022 is used to present an interface of the target city population distribution; the processor 1024 is used for acquiring a multi-source heterogeneous data set of the power operation and maintenance. The memory 1026 is used to store multi-source spatiotemporal big data.
In addition, the server 106 includes a database 1062 and a processing engine 1064, and the database 1062 is used for storing multi-source spatio-temporal big data. Processing engine 1064 is configured to: acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; determining the number of resident populations of the target cell in the target time period based on a population space increment distribution model and the resident populations, the age structure of the resident populations and the population flow number.
As another alternative, the above-described method of knowledge graph construction described herein may be applied to FIG. 2. As shown in fig. 2, a user 202 and an electronic device 204 may interact with each other. The electronic device 204 includes a memory 206 and a processor 208. In this embodiment, the electronic device 204 may, but is not limited to, determine the number of residential population of the target cell in the target time period by referring to the operation performed by the terminal device 102.
Alternatively, the terminal device 102 and the electronic device 204 may be, but not limited to, a mobile phone, a tablet computer, a notebook computer, a PC, and the like, and the network 104 may include, but is not limited to, a wireless network or a wired network. Wherein, this wireless network includes: WIFI and other networks that enable wireless communication. Such wired networks may include, but are not limited to: wide area networks, metropolitan area networks, and local area networks. The server 106 may include, but is not limited to, any hardware device capable of performing computations. The server may be a single server, a server cluster composed of a plurality of servers, or a cloud server. The above is merely an example, and this is not limited in this embodiment.
In order to solve the above technical problem, as an alternative implementation manner, as shown in fig. 3, an embodiment of the present invention provides a population distribution predicting method, including the following steps:
s302, multi-source space-time big data of a target city are obtained from a multi-source space-time big database, wherein the multi-source space-time big data comprise mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data;
s304, acquiring the resident population of the target city in the target time period based on the parameter regression analysis model, and determining the age structure of the resident population based on the time sequence prediction model;
s306, acquiring the population flow number of the target city among different cells in the target time period based on the emigration random utility selection model;
and S308, determining the resident population number of the target cell in the target time period based on the population space increment distribution model, the resident population, the age structure of the resident population and the population flow number.
In the embodiment of the invention, multi-source space-time big data of a target city are obtained from a multi-source space-time big database, wherein the multi-source space-time big data comprise mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data; acquiring a resident population of the target city in a target time period based on a parameter regression analysis model, and determining an age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; the method for determining the number of the resident population of the target cell in the target time period based on the population space incremental distribution model, the resident population, the age structure of the resident population and the population floating number can realize real-time dynamic prediction of the distribution of the resident population due to the fact that the population difference prediction model is built through multidimensional factors, and further solve the technical problem that the urban population cannot be accurately predicted in the related technology.
In one or more embodiments, the multi-source space-time big database is constructed according to the mobile phone signaling data, the satellite remote sensing big data, the basic geographic information data, the statistical census data and the Internet interest point POI data;
wherein, the mobile phone signaling data comprises: age label, gender label, resident information, residential area grid number and grid residential population number;
the satellite remote sensing big data mainly comprises remote sensing and land utilization data;
the basic geographic information data comprise all levels of administrative division maps and road network data of the target city;
the statistical census data comprises population, land, traffic and socioeconomic data;
the internet POI data includes, for example, quantity distribution data and house price data of commercial facilities, industrial facilities, public service facilities. In one or more embodiments, the obtaining the resident population of the target city for the target time period based on the parametric regression analysis model includes:
obtaining the resident population of the target city in the target time period through a formula (1):
wherein R is t Number of urban residential population in t time period, R t-1 Is the urban population number of the (t-1) time period,is the whole-market population raising ratio of the (t-1) time period, rho LAR t-1 The population density of the time period (t-1) relative to the area of the construction land;for the annual growth rate of the total domestic production value of the current city in the historical time period,the total area of the construction land of the current city in the time period t,the model constant, the regression fitting parameter of the urban population number in the period (t-1), the regression fitting parameter of the full-urban population fostering ratio in the period (t-1), the regression fitting parameter of the population density of the period (t-1) relative to the construction land area, the regression fitting parameter of the annual average growth rate of the total domestic production value of the city in the historical time period, and the regression fitting parameter of the total construction land area of the city in the period (t) are sequentially included.
In one or more embodiments, the determining an age structure of the residential population based on a temporal prediction model comprises:
determining an age structure of the resident population based on equation (2):
wherein, the first and the second end of the pipe are connected with each other,expressed as a random variable from the t period to the t-p period,the disturbance term is from a time period t to a time period t-q, and the sequence is a random sequence;is a regression parameter of the random variable,regression parameters for the random sequence;
random variation when the model is used to calculate aging rateThe aging rate in t-1 period of time of 82308230p is shown; when the model is used to calculate the percent minorsThe percentages of minors in a t-period and a t-1 period in sequence;in the middle, WN is pure random sequence white noise,is the variance of the white noise.
In one or more embodiments, the obtaining the population flow amount of the target city among different cells in the target period based on the migrating stochastic utility selection model comprises:
acquiring the probability of the target type residents to select to migrate from the traffic cell i to the traffic cell j in the target time period by the formula (3):
F=;Representing the probability of choosing to stay in traffic cell i when the target group resident compares traffic cell i with traffic cell j within time period (t-1) to t,for the housing price of the traffic cell i during the t-1 period,for the housing price of the traffic cell j during the t-1 period,for the reachability of the location of the traffic cell i,for location reachability of traffic cell j,for the number of bus station lines in the traffic cell i,for the number of bus station lines in traffic cell j,the number of employment posts of the traffic cell i in the t-1 time period,the number of employment posts of the traffic cell j in the t-1 time period,for the position relation coefficient of the traffic cell i,coefficient of relationship between position and location for traffic cell j, L i,j BUPoi being the distance from the traffic cell i to j i BUPoi, a Business-type POI Density for traffic cell i during t-1 hours j For the business-type POI density for traffic cell j during time t-1,the regression coefficients generated by maximum likelihood estimation calibration;
and acquiring the number of the residential population which is migrated from the traffic cell i to the traffic cell j based on the probability of migrating from the traffic cell i to the traffic cell j.
In one or more embodiments, the population distribution prediction method further comprises:
residents are classified into the following six groups according to age stage and gender: a first group comprising underage males under 18 years old;
second group comprising minor females under 18 years of age
Third group comprising male inhabitants aged 19-59
Fourth group comprising female inhabitants aged 19-59
Fifth group including older men over 60
A sixth group comprising older females older than 60 years old.
In one or more embodiments, the determining the resident population quantity of the target cell for the target time period based on the population space incremental distribution model and the resident population, the age structure of the resident population, and the population flow quantity comprises:
acquiring newly-increased residential population of different groups from t-1 to t;
determining the number of target group resident population allocated to immigration in traffic cell i from t-1 to t based on formula (4):
Wherein, the first and the second end of the pipe are connected with each other,allocating the number of target group resident population migrating into the target city for the time period from t-1 to t,is the proportion of the attraction function obtained according to the space increment model;
Wherein, theIs the coefficient of the inhabitation attraction of a traffic community i, i belongs to [1, 27101 ]];
The inhabitation attraction coefficient is obtained by the formula (6):
wherein, the first and the second end of the pipe are connected with each other,for the housing price of the traffic zone i at the time period of t-1,for location reachability of traffic cell i at time t,the employment post number of the traffic cell i at the time of t-1,BUPoi, the number of residential population of the traffic cell i at time t-1 i For the commercial POI density for traffic cell i at time t-1,sequentially estimating variable parameters for experience;
based on theAcquiring the number of the resident population of the traffic cell i in different groups in the t period through formulas (7) and (8)And the number of residential population of the traffic cell i at the time point t:
Wherein i ∈ [1,6].
Based on the foregoing embodiment, in an application embodiment, as shown in fig. 4, the population distribution prediction method includes the following steps:
(1) The embodiment of the invention constructs a multi-source space-time big database through data cleaning, integration, transformation and protocol based on economic census data, mobile phone signaling big data, house price transaction data, POI data, city construction statistics yearbook data, OSM road network data and the like.
(2) Based on a multivariate spatiotemporal big database, the relationship and the mechanism of action among the main factors of the population distribution of the residents are quantitatively measured by applying multisource spatiotemporal big data. The method is characterized by comprising the following steps of researching space-time patterns and change rules of urban population total scale growth, urban population age structure, urban resident population emigration behavior selection influence factors, urban resident attraction evaluation indexes and the like, selecting main influence factors through correlation analysis, principal component analysis, factor analysis and the like, and researching influence effects and action mechanisms through existing data.
(3) And constructing a living population distribution system simulation model based on multi-source space-time big data. Firstly, classifying residents according to different characteristics on the basis of multi-source space-time big data of a reference year, considering main residence selection influence factors such as room price, accessibility, employment activity, living activity, business activity, public facilities and the like on the basis of a random utility theory, system dynamics and a utility maximization principle, respectively establishing a discrete selection model prediction model for microscopic behavior activities of residence migration selection of different populations, and solving to obtain a space-time dynamic evolution result of city stock population migration selection under a reference scene. And then considering the migration and flow of the population among cities and the natural increase of the total amount of the population of the cities, constructing a housing attractiveness coefficient, using a space increment distribution model for reference, constructing a newly-added population space increment distribution model, carrying out space distribution on newly-added population of the cities, simultaneously considering government planning and unit population density limitation, controlling the newly-added population by policy control factors for partial areas, and establishing a housing population distribution system simulation model based on multi-source space-time big data to simulate the formation and evolution of the housing population pattern of the cities.
(4) The improvement of the space-time granularity of data is realized through a large space-time database, particularly mobile phone signaling data in the large space-time database, the hysteresis effect of certain influence factors and certain instantaneity influence factors are comprehensively considered, a space-time dynamic prediction model is built, and the real-time dynamic prediction of the distribution of the resident population is realized based on a high-refresh data source and a model framework.
Specifically, taking the XX city population prediction in 2015 as a reference year and 2020 as a prediction year as an example, the population distribution prediction method further includes:
(1) The main factors of the distribution of the resident population are quantitatively measured by applying multi-source space-time big data:
the multi-source space-time big data mainly comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet POI data.
In the embodiment of the invention, the mobile phone signaling data is mainly used for acquiring the distribution data and the migration data of the urban classification permanent population, and specifically comprises information such as age tags (minor population, labor population and old population), sex tags (male and female), resident information, residential area grid numbers, grid residential population number and the like, and identifies different types of permanent population, population residential area distribution and population migration conditions. The basic geographic information data comprises base maps of administrative districts of all levels of XX city and road network data, and traffic facility level related indexes (road network density, road intersection density, the number of bus stops and the number of subway lines in a traffic cell) and location reachability are counted on the basis of a road network. The statistical and general survey data mainly comprise population, land, traffic, socioeconomic data, such as seventh population general survey data, total GDP amount, GDP growth rate, construction land area, aging rate, immature proportion and the like. Internet POI data mainly includes quantity distribution data and house price data such as commercial facilities, industrial facilities, public service facilities, and the like. The satellite remote sensing big data mainly comprises remote sensing and land utilization data products.
The embodiment of the invention establishes the influence action relationship between the total population of urban living population and the factors such as labor supply, urban economic condition, construction land supply and the like based on the theory of a central place and the theory of labor regional division; the response relations between city population living selection behaviors and house prices, between traffic facilities and accessibility, between business facilities and the like are constructed on the basis of a human-ground relation theory, a bidding theory, a ethology, a population theory and the like, and a living attraction measuring function considering the positions, the business activities, the traffic accessibility and the house prices is constructed on the basis of a city circle layer structure, a city facility layout and a behavior science research. The method integrates population-land-traffic-economy and other subsystems, and supports the action and mechanism of main factors of urban resident population based on the massive data of a space-time large database.
(2) Simulating a model and predicting in real time for a resident population distribution system based on multi-source space-time big data:
(1) for case cities, predicting the total population of living cities at t time point by adopting a parameter regression methodThe model is as follows:
wherein R is t Number of urban residential population in t period, R t-1 Is the urban population number of the (t-1) time period,the breeding ratio of the whole-market population in the (t-1) period is rho LAR t-1 The population density of the time period (t-1) relative to the area of the construction land;for the annual increase rate of the total domestic production value of the current city in the historical time period,the total area of the construction land of the current city in the time period t,model constants, the number of urban resident population at the time point (t-1), the overall urban population fostering ratio at the time point (t-1), the population density of the time point relative to the area of the construction land, the annual average growth rate of the domestic total production value of the city in the last 5 years and the regression fitting parameters of the total area of the construction land of the city at the time point (t) are sequentially set.
(2) Adopting a time sequence prediction method to predict the age structure of urban resident population, wherein the dependent variables are as follows:
aging rate of urban population at time t(proportion of population in the population size of the population over 60 years old);
Percent minors of urban population at time t(proportion structure in population scale of residents under 18 years old, etc.).
Based on the population aging rate and the percentage of minors over the past years, a time series model is used for predictive fitting. Determining a hysteresis order according to a partial autocorrelation function (PACF) and an autocorrelation function (ACF) test result of actual data, and establishing an ARMA (p, q) model by adopting an autoregressive moving average method, wherein the model function is as follows:
wherein, the first and the second end of the pipe are connected with each other,expressed as a random variable from period t to period t-p,the disturbance term is from a time period t to a time period t-q, and the sequence is a random sequence;is a regression parameter of the random variable,regression parameters for the random sequence;
random variables when the model is used to calculate aging RateThe aging rate in t-1 period of time of 82308230p is shown; when the model is used to calculate the percent minorsThe time period t and the time period t-1 are sequentially arranged.(ii) percent minor during t-p period;in the middle, WN is pure random sequence white noise,is the variance of the white noise.
(3) Construction of immigration random utility selection model
And (3) respectively constructing a logit model for each group of individual stock residents at the (t-1) moment (namely the reference year) to select whether the residents migrate:
the residents are classified into the following 6 categories according to the social and economic characteristics: (t-1) group a resident population number of the time zone iWhere i ∈ [1, 27101 ]]And is an integer.
1) Underage 18 years old male;
2) Underage 18 years old;
3) A male resident between 19 and 59 years old;
4) Female residents 19-59 years old;
5) Elderly men over 60 years old;
6) Elderly women over 60 years old;
explained variableIndicating the probability (0 for the emigration, 1 for the non-emigration) that a (a =1,2, \8230; 6) class residents chose to continue to live in traffic cell i when comparing traffic cells i and j during the period (t-1) to t (predicted year). Explanatory variables include:for the housing price of the traffic cell i during the t-1 period,for the housing price of the traffic cell j during the t-1 period,for location reachability of traffic cell i,for location reachability of traffic cell j,for the number of lines at bus stations in traffic cell i,for the number of bus station lines in traffic cell j,the number of employment posts of the traffic cell i in the t-1 time period,the employment post number of the traffic cell j in the t-1 time period,the position relation coefficient of the traffic cell i,coefficient of relationship between position and location for traffic cell j, L i,j BUPoi being the distance from traffic cell i to j i Business type POI Density, BUPoi for traffic cell i during t-1 hours j For the business-type POI density for traffic cell j during time t-1,the regression coefficients, which are generated by maximum likelihood estimation calibration, are generated by maximum likelihood estimation calibration. Obtaining a logistic model expressed in a probabilistic form:
According to the spatial distribution state of the residents in different groups, the regression model is used to obtain the probability that the class a residents selectively transfer from the traffic cell i to the traffic cell j in the time period from (t-1) to tThe probability a is a ratio of the population living in the traffic cell i migrating to the traffic cell j. The population of residents migrating from traffic cell i to traffic cell j is:。
(4) population space increment distribution model construction based on inhabitation attraction coefficient
For the time period from the city (t-1) to t, the total newly-increased residential populationConsider the group structure of the residents. Percent aging of whole market newly-increased population given by exogenous birth Ag t Percent of minors UAg t And givenThe sex structure of the population of (1), male population ratio SR t Calculating to obtain 1 to 6 types of the total newly added population, wherein the number of 6 types of population is obtained by the following formula:
1) Underage adult males under 18 years old;
2) Underage women under 18 years old;
3) Male residents 19-59 years old;
4) Female residents 19-59 years old;
5) Elderly men over 60 years old;
6) Elderly women over the age of 60 years old;
then, living zone distribution is carried out on the living population of each group to be distributed in the whole city according to the living attraction, and the living population number of the group a which is migrated to the traffic zone i is distributed in the period from (t-1) to (t)Comprises the following steps:
global increments are assigned to the regions according to the scale of the attraction function from the spatial increment model
Wherein, the first and the second end of the pipe are connected with each other,for the occupancy attraction coefficient of the traffic cell i, the attraction variable is expressed by a multivariate formula in the form of a kobu-douglas function, i.e. in the form of a product of the powers of the parameters:
the housing price of the traffic zone i for the time period t-1,for location reachability of traffic cell i at time t,the number of employment posts of the traffic cell i at the time of t-1,BUPoi, the number of residential population of the traffic cell i at time t-1 i The commercial POI density for traffic cell i at time t-1,the variable parameters are in turn empirically estimated.
After the incremental distribution and the stock selection are synthesized, the final output result of the invention, namely the number of the resident population grouped at the time point t of the traffic cell i is obtainedAnd the number of residential population of the traffic cell i at the time point t:
In one embodiment, the urban population distribution dynamic simulation prediction technology based on multi-source space-time big data is applied to the XX city expansion example, and the specific contents are as follows:
(1) The method comprises the following steps of quantitatively measuring main factors of population distribution by using multi-source space-time big data:
the concrete space-time big data sources for XX city permanent population distribution pattern simulation prediction in 2020 are shown in table 1, and mainly include mobile phone signaling data, basic geographic information data, statistical and census data and internet POI data.
Based on statistics, urban geographic methods, past research and the above, the main influence factors forming the distribution of the residential population, such as house price, traffic facilities, accessibility, commercial facilities, occupation and the like, are respectively calculated, quantized and extracted.
(2) Dynamic model establishment and simulation prediction of urban residential population distribution
Based on space-time big data and main influence factors and action mechanisms of population distribution of residents, a linear regression model and an autoregressive sliding average model are constructed, the total quantity and age structure of urban population are modeled and predicted, then a dynamic prediction model of urban population space-time distribution based on a location selection model and an incremental distribution model is utilized to respectively simulate and calculate an XX city stock population migration and migration pattern and a newly-added population space distribution pattern, and a simulation prediction result of the XX city population distribution pattern in 2020 is comprehensively obtained.
(3) Predicted results
Comparing the prediction result of the 2020 residential population distribution with the true value of the residential population distribution of a certain operator corrected based on the 7 th census data of the 2020, as shown in fig. 5 and 6, from the viewpoint of the prediction accuracy of the XX city global residential population distribution, the simulation prediction result of the XX city residential population distribution pattern in the 2020 is more consistent with the actual result, the prediction accuracy reaches 71.3%, and the XX city permanent population distribution pattern is more accurately predicted; as shown in fig. 7 and fig. 8, from the perspective of prediction accuracy of the population distribution of the inhabited people in different regional spatial scales, the prediction accuracy in the five-ring can reach 69.2%, and the prediction accuracy in the six-ring is 68.8%; from the scale of administrative districts, the prediction accuracy of the central urban district such as the district A can reach 74.1%, the district B69.7%, the district C78.1% and the district D91.1%. The overall prediction precision and the spatial region prediction precision are both better, and particularly the prediction precision is highest in a central urban area and the like.
The embodiment of the invention also has the following beneficial technical effects:
and (3) based on multi-source space-time big data, combining population distribution data, and revealing the characteristics of population distribution formation and evolution space-time regularity. The multi-source space-time big data has the advantages of large sample size, strong timeliness, wide coverage range, low acquisition cost, fine space-time granularity and the like, and can overcome the limitations of traditional statistical data and survey data in the aspects of data size, timeliness, human and material investment, practical process and the like. The embodiment of the invention quantitatively determines the interrelation among the main factors of the resident population distribution based on the multi-source space-time big data, and then dynamically predicts the resident population distribution in real time after constructing the simulated model of the resident population distribution system based on the multi-source space-time big data.
In the quantitative determination of the interrelation among the main factors of the residential population distribution, the method is different from the mode that the research on the main factors of the residential population distribution, the interrelation and the action mechanism is not comprehensive and thorough in the prior art, and the method is based on demographics, system dynamics, urban system complex rules and the like, comprehensively and scientifically excavates the dimensions of multiple systems such as population, social economy, traffic, land and the like, the distribution of population and the internal rules of living migration and flow, accurately recognizes and clarifies the main factors and the action mechanism of the residential population distribution, and provides a base for all social practices and scientific researches based on the population distribution and human activities.
Compared with the existing traditional method, the method has the advantages that the simple and practical principle, the scientific and reasonable principle and the accurate simulation principle cannot be considered in the building process of the living population distribution system simulation model. According to the embodiment of the invention, the resident population pattern is promoted to dynamic evolution from a static slice, the angles of stock updating migration and incremental space distribution are considered, based on a random utility theory, a distance attenuation effect, a resident attraction principle and a utility maximization principle, and the main factors and action mechanisms of the resident population are considered, so that a resident discrete selection model and an incremental distribution model are respectively constructed, the rationality of model algorithm design is optimized, the model space precision and the simulation result accuracy are improved, and the limitation of the existing model is broken through.
In the real-time dynamic prediction of the residential population distribution, different from the situation that the evolution law of the residential population distribution is not considered in the existing research and technology, the time sequence prediction is only carried out based on autoregression, or the time sequence prediction cannot be carried out only based on other current-period data through numerical fitting to measure and calculate the residential population distribution. The embodiment of the invention constructs the real-time dynamic residential population distribution prediction technology based on multi-source space-time big data, comprehensively considers the mutual influence rules of the residential population distribution in the current period and complex systems such as nature, social economy and the like, constructs the real-time dynamic residential population distribution prediction technology with high space-time resolution, high dynamic refreshing, variable scale and flexible regulation and control, breaks through the defect that the existing technology only carries out static simulation, and really realizes the real-time dynamic evolution, growth and prediction of the residential population distribution.
It should be noted that for simplicity of description, the above-mentioned method embodiments are shown as a series of combinations of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
According to another aspect of the embodiment of the invention, a population distribution predicting device for implementing the population distribution predicting method is also provided. As shown in fig. 9, the apparatus includes:
the system comprises a first obtaining unit 902, a second obtaining unit, a third obtaining unit and a fourth obtaining unit, wherein the first obtaining unit 902 is used for obtaining multi-source space-time big data of a target city from a multi-source space-time big database, and the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data;
a second obtaining unit 904, configured to obtain the residential population of the target city in the target time period based on the parametric regression analysis model, and determine an age structure of the residential population based on the time sequence prediction model;
a third obtaining unit 906, configured to obtain, based on a migration random utility selection model, population mobility numbers of the target city among different cells in the target time period;
a determining unit 908 configured to determine the number of residential population of the target cell in the target time period based on the population space increment distribution model and the residential population, the age structure of the residential population, and the population floating number.
In the embodiment of the invention, multi-source space-time big data of a target city are obtained from a multi-source space-time big database, wherein the multi-source space-time big data comprise mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data; acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model; acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model; and in the method, because the population difference prediction model is constructed through multidimensional factors, the real-time dynamic prediction of the distribution of the resident population can be realized, and the technical problem that the urban population cannot be accurately predicted in the related technology is solved.
In one or more embodiments, the population distribution predicting apparatus further includes:
the building unit is used for building the multi-source space-time big database according to the mobile phone signaling data, the satellite remote sensing big data, the basic geographic information data, the statistical census data and the Internet interest point POI data;
wherein, the mobile phone signaling data comprises: age label, gender label, residence information, residential area grid number and grid population number;
the satellite remote sensing big data mainly comprises remote sensing and land utilization data;
the basic geographic information data comprises all levels of administrative division maps and road network data of the target city;
the statistical census data comprises population, land, traffic and socioeconomic data;
the internet POI data includes, for example, quantity distribution data and house price data of commercial facilities, industrial facilities, public service facilities.
In one or more embodiments, the second obtaining unit 904 includes:
a first obtaining module, configured to obtain a residential population of the target city in the target time period according to formula (1):
wherein R is t Number of urban residential population in t period, R t-1 The number of urban resident population in the (t-1) time period,the breeding ratio of the whole-market population in the (t-1) period is rho LAR t-1 The population density of the time period (t-1) relative to the area of the construction land;for the annual increase rate of the total domestic production value of the current city in the historical time period,is the total area of the construction land of the current city in the time period t,sequentially comprises a model constant, regression fitting parameters of urban population number in the period (t-1), regression fitting parameters of full-urban population fostering ratio in the period (t-1), andt-1) regression fitting parameters of population density relative to the construction land area in the time period, regression fitting parameters of the annual average growth rate of the domestic production total value of the city in the historical time period, and regression fitting parameters of the total construction land area of the city in the time period t.
In one or more embodiments, the third obtaining unit 906 further includes:
a first determination module to determine an age structure of the resident population based on equation (2):
wherein the content of the first and second substances,expressed as a random variable from the t period to the t-p period,the disturbance term from the t time interval to the t-q time interval is formed, and the sequence is a random sequence;is a regression parameter of the random variable,regression parameters for the random sequence;
random variation when the model is used to calculate aging rateThe aging rate in t-1 period of time of 82308230p is shown; when the model is used to calculate the percent minorsThe percentages of minors in a t-period and a t-1 period in sequence;in (1),WN is a pure random sequence white noise,is the variance of the white noise.
In one or more embodiments, the third obtaining unit 906 includes:
a second obtaining module, configured to obtain, by using a formula (3), a probability that the target type residents select to migrate from the traffic cell i to the traffic cell j in the target time period:
(3)
F=;Representing the probability of choosing to stay in traffic cell i when the target group resident compares traffic cell i with traffic cell j within time period (t-1) to t,for the housing price of the traffic cell i during the t-1 period,for the housing price of the traffic cell j during the t-1 period,for location reachability of traffic cell i,for location reachability of traffic cell j,for the number of bus station lines in the traffic cell i,for the number of bus station lines in traffic cell j,the number of employment posts of the traffic cell i in the t-1 time period,the number of employment posts of the traffic cell j in the t-1 time period,the position relation coefficient of the traffic cell i,coefficient of relationship between position and location for traffic cell j, L i,j BUPoi being the distance from traffic cell i to j i Business type POI Density, BUPoi for traffic cell i during t-1 hours j For the business-type POI density for traffic cell j during time t-1,the regression coefficients generated by maximum likelihood estimation calibration;
and the third acquisition module is used for acquiring the number of the resident population which is migrated from the traffic cell i to the traffic cell j based on the probability of migrating from the traffic cell i to the traffic cell j.
In one or more embodiments, the population distribution predicting apparatus further includes:
a dividing unit for dividing the residents into the following six groups according to age stages and genders: a first group comprising underage males under 18 years old;
second group comprising minor females under 18 years of age
Third group comprising male inhabitants aged 19-59
Fourth group comprising female inhabitants aged 19-59
Fifth group including older men over 60
A sixth group comprising older females older than 60 years old.
In one or more embodiments, the determining unit 908 includes:
the fourth acquisition module is used for acquiring newly-added residential population of different groups in the time period from t-1 to t;
determining the number of target group resident population allocated to immigration of traffic cell i in the period from t-1 to t based on formula (4):
Wherein the content of the first and second substances,allocating the number of target group resident population migrating into the target city for the time period from t-1 to t,is the proportion of an attraction function obtained according to the space increment model;
Wherein, theIs the coefficient of the inhabitation attraction of the traffic cell i, i belongs to [1, 27101 ]];
The inhabitation attraction coefficient is obtained by the formula (6):
wherein the content of the first and second substances,the housing price of the traffic zone i for the time period t-1,for location reachability of traffic cell i at time t,the number of employment posts of the traffic cell i at the time of t-1,BUPoi, the number of residential population of the traffic cell i at time t-1 i For the commercial POI density for traffic cell i at time t-1,sequentially estimating variable parameters for experience;
based on theObtaining different groups of traffic cells i in t time period through formulas (7) and (8)Number of other residential populationAnd the number of residential population of the traffic cell i at the time point t:
Wherein i ∈ [1,6].
According to another aspect of the embodiment of the present invention, there is also provided an electronic device for implementing the above population distribution prediction method, where the electronic device may be a client or a server as shown in fig. 1. The present embodiment takes the electronic device as a server as an example for explanation. As shown in fig. 10, the electronic device comprises a memory 1002 and a processor 1004, the memory 1002 having stored therein a computer program, the processor 1004 being arranged to execute the steps of any of the method embodiments described above by means of the computer program.
Optionally, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of a computer network.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, multi-source space-time big data of a target city are obtained from a multi-source space-time big database, wherein the multi-source space-time big data comprise mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet POI (point of interest) data;
s2, acquiring the resident population of the target city at the target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model;
s3, acquiring the population flow number of the target city among different cells in the target time period based on the emigration random utility selection model;
and S4, determining the number of the resident population of the target cell in the target time period based on the population space increment distribution model, the resident population, the age structure of the resident population and the population floating number.
Alternatively, it can be understood by those skilled in the art that the structure shown in fig. 10 is only an illustration, and the electronic device may also be a terminal device such as a smart phone with a network security detection function (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 10 is a diagram illustrating a structure of the electronic device. For example, the electronics may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 10, or have a different configuration than shown in FIG. 10.
The memory 1002 may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for predicting the population distribution in the embodiment of the present invention, and the processor 1004 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002, so as to implement the method for predicting the population distribution. The memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1002 can further include memory located remotely from the processor 1004, which can be coupled to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 1002 may be, but not limited to, specifically configured to store information such as multi-source spatiotemporal big data. As an example, as shown in fig. 10, the memory 1002 may include, but is not limited to, the first obtaining unit 902, the second obtaining unit 904, the third obtaining unit 906, and the determining unit 908 in the population distribution predicting apparatus, and may also include, but is not limited to, other module units in the population distribution predicting apparatus, which is not described in detail in this example.
Optionally, the above-mentioned transmission device 1006 is used for receiving or sending data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 1006 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices so as to communicate with the internet or a local area Network. In one example, the transmission device 1006 is a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
In addition, the electronic device further includes: a display 1008 for displaying the set state value of the protocol analysis plug-in; and a connection bus 1010 for connecting the respective module parts in the above-described electronic apparatus.
In other embodiments, the electronic device may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting a plurality of nodes through a network communication. The nodes may form a Peer-To-Peer (P2P) network, and any type of computing device, such as a server, a terminal, and other electronic devices, may become a node in the blockchain system by joining the Peer-To-Peer network.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from a computer-readable storage medium, the processor executing the computer instructions to cause the computer device to perform the method for predicting a population distribution, wherein the computer program is arranged to execute the steps of any of the method embodiments described above.
Alternatively, in the present embodiment, the above-mentioned computer-readable storage medium may be configured to store a computer program for executing the steps of:
the method comprises the following steps of S1, obtaining multi-source space-time big data of a target city from a multi-source space-time big database, wherein the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data;
s2, acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model;
s3, acquiring the population flow number of the target city among different cells in the target time period based on the migration random utility selection model;
and S4, determining the resident population number of the target cell in the target time period based on the population space increment distribution model, the resident population, the age structure of the resident population and the population flow number.
Alternatively, in this embodiment, a person skilled in the art may understand that all or part of the steps in the methods of the foregoing embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, read-Only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, and including instructions for causing one or more computer devices (which may be personal computers, servers, or network devices) to execute all or part of the steps of the method according to the embodiments of the present invention.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is only a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be an indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or in other forms.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art of the embodiment of the present invention can make several improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (9)
1. A method for predicting a population distribution, comprising:
acquiring multi-source space-time big data of a target city from a multi-source space-time big database, wherein the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data;
acquiring the resident population of the target city in a target time period based on a parameter regression analysis model, and determining the age structure of the resident population based on a time sequence prediction model;
acquiring the population flow number of a target city among different cells in the target time period based on a migration random utility selection model;
determining the number of resident populations of the target cell in the target time period based on the population space incremental distribution model and the resident populations, the age structure of the resident populations and the population floating number, comprising:
acquiring newly-increased residential population of different groups from t-1 to t;
determining the number of target group resident population allocated to immigration of traffic cell i in the period from t-1 to t based on formula (4):
Wherein the content of the first and second substances,allocating the number of target group resident population migrating into the target city for the time period from t-1 to t,is the proportion of an attraction function obtained according to the space increment model;
Wherein, theIs the coefficient of the inhabitation attraction of the traffic cell i, i belongs to [1, 27101 ]];
The inhabitation attraction coefficient is obtained by the formula (6):
wherein, the first and the second end of the pipe are connected with each other,the housing price of the traffic zone i for the time period t-1,for location reachability of traffic cell i at time t,the number of employment posts of the traffic cell i at the time of t-1,BUPoi, the number of residential population of the traffic cell i at time t-1 i The commercial POI density for traffic cell i at time t-1,sequentially estimating variable parameters for experience;
based on theObtaining the number of the resident population of different groups of the traffic cell i in the t period through formulas (7) and (8)And the number of residential population of the traffic cell i at the time point t:
Wherein i ∈ [1,6].
2. The method of claim 1, wherein prior to obtaining the multi-source spatio-temporal big data of the target city from the multi-source spatio-temporal big database, further comprising:
constructing the multi-source space-time big database according to the mobile phone signaling data, the satellite remote sensing big data, the basic geographic information data, the statistical census data and the Internet POI (point of interest) data;
wherein, the mobile phone signaling data comprises: age label, gender label, residence information, residential area grid number and grid population number;
the satellite remote sensing big data mainly comprises remote sensing and land utilization data;
the basic geographic information data comprises all levels of administrative division maps and road network data of the target city;
the statistical census data comprises population, land, traffic and socioeconomic data;
the internet POI data includes quantity distribution data and rate data of commercial facilities, industrial facilities, public service facilities.
3. The method of claim 1, wherein obtaining the resident population of the target city for the target time period based on the parametric regression analysis model comprises:
obtaining the resident population of the target city in the target time period through formula (1):
wherein R is t Number of urban residential population in t period, R t-1 The number of urban resident population in the (t-1) time period,the breeding ratio of the whole-market population in the (t-1) period is rho LAR t-1 The population density of the time period (t-1) relative to the area of the construction land;for the annual increase rate of the total domestic production value of the current city in the historical time period,is the total area of the construction land of the current city in the time period t,the model constant, the regression fitting parameter of the urban population number in the period (t-1), the regression fitting parameter of the full-urban population fostering ratio in the period (t-1), the regression fitting parameter of the population density of the period (t-1) relative to the construction land area, the regression fitting parameter of the annual average growth rate of the total domestic production value of the city in the historical time period, and the regression fitting parameter of the total construction land area of the city in the period (t) are sequentially included.
4. The method of claim 1, wherein determining the age structure of the resident population based on a time series prediction model comprises:
determining an age structure of the resident population based on equation (2):
wherein the content of the first and second substances,expressed as a random variable from period t to period t-p,the disturbance term is from a time period t to a time period t-q, and the sequence is a random sequence;is a regression parameter of the random variable,regression parameters for the random sequence;
random variables when the model is used to calculate aging RateThe aging rate in t-1 period of 8230and t-p period is shown; when the model is used to calculate the percent minorsThe percentage of minors in the t period and the t-1 period in turn;WN is pure random sequence white noise,is the variance of the white noise.
5. The method of claim 1, wherein obtaining the population mobility number of the target city among different cells in the target period based on the migrating stochastic utility selection model comprises:
acquiring the probability that the target type residents selectively migrate from the traffic cell i to the traffic cell j in the target time period through a formula (3):
F=;Indicating the probability of choosing to continue residing in traffic cell i when the target group resident compares traffic cell i with traffic cell j during the time period (t-1) to t,for the housing price of the traffic cell i during the t-1 period,for the housing price of the traffic cell j during the t-1 period,for the reachability of the location of the traffic cell i,for location reachability of traffic cell j,for the number of lines at bus stations in traffic cell i,for the number of bus station lines in traffic cell j,the employment post number of the traffic cell i in the t-1 time period,the number of employment posts of the traffic cell j in the t-1 time period,for the position relation coefficient of the traffic cell i,coefficient of relationship between position and location for traffic cell j, L i,j BUPoi being the distance from traffic cell i to j i BUPoi, a Business-type POI Density for traffic cell i during t-1 hours j For the business-type POI density for traffic cell j during time t-1,generating regression coefficients for the calibration by maximum likelihood estimation;
and acquiring the number of the residential population which is migrated from the traffic cell i to the traffic cell j based on the probability of migrating from the traffic cell i to the traffic cell j.
6. The method of claim 5, further comprising:
residents are classified into the following six groups according to age stage and gender:
a first group comprising underage males under 18 years old;
a second group comprising minor females under 18 years old;
a third group comprising male inhabitants aged 19-59;
a fourth group comprising female inhabitants aged 19-59;
a fifth group comprising older men over 60 years old;
a sixth group comprising older females older than 60 years old.
7. A population distribution prediction apparatus, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring multi-source space-time big data of a target city from a multi-source space-time big database, and the multi-source space-time big data comprises mobile phone signaling data, satellite remote sensing big data, basic geographic information data, statistical census data and internet interest point POI data;
the second obtaining unit is used for obtaining the resident population of the target city in the target time period based on the parameter regression analysis model and determining the age structure of the resident population based on the time sequence prediction model;
the third acquisition unit is used for acquiring the population flow number of the target city among different cells in the target time period based on the migrating random utility selection model;
a determining unit, configured to determine the number of the residential population of the target cell in the target time period based on a population space incremental distribution model and the residential population, the age structure of the residential population, and the population floating number, including:
acquiring newly-added residential population of different groups in the time period from t-1 to t;
determining the number of target group resident population allocated to immigration in traffic cell i from t-1 to t based on formula (4):
Wherein, the first and the second end of the pipe are connected with each other,allocating the number of target group resident population migrating into the target city for the time period from t-1 to t,is the proportion of an attraction function obtained according to the space increment model;
Wherein, theIs the coefficient of the inhabitation attraction of a traffic community i, i belongs to [1, 27101 ]];
The inhabitation attraction coefficient is obtained by the formula (6):
wherein, the first and the second end of the pipe are connected with each other,the housing price of the traffic zone i for the time period t-1,for the accessibility of the location of the traffic cell i at time t,the employment post number of the traffic cell i at the time of t-1,BUPoi, the number of residential population of the traffic cell i at time t-1 i The commercial POI density for traffic cell i at time t-1,sequentially estimating variable parameters for experience;
based on theObtaining the number of the resident population of different groups of the traffic cell i in the t period through formulas (7) and (8)And the number of residential population of the traffic cell i at the time point t:
Wherein i ∈ [1,6].
8. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 6 by means of the computer program.
9. A computer-readable storage medium, comprising a stored program, wherein the program when executed performs the method of any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210965718.9A CN115049159B (en) | 2022-08-12 | 2022-08-12 | Population distribution prediction method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210965718.9A CN115049159B (en) | 2022-08-12 | 2022-08-12 | Population distribution prediction method and device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115049159A CN115049159A (en) | 2022-09-13 |
CN115049159B true CN115049159B (en) | 2022-10-21 |
Family
ID=83168198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210965718.9A Active CN115049159B (en) | 2022-08-12 | 2022-08-12 | Population distribution prediction method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115049159B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115525872B (en) * | 2022-10-13 | 2023-09-15 | 北京城建交通设计研究院有限公司 | Two-step Bayesian estimation method for building scale population fused with position data |
CN115878964B (en) * | 2023-03-01 | 2023-11-24 | 北京市城市规划设计研究院 | Method, apparatus, device and storage medium for determining resident population |
CN116150230B (en) * | 2023-03-02 | 2023-08-29 | 重庆市规划和自然资源信息中心 | Dynamic housing population registration monitoring method based on multiple spatial scales |
CN117151344B (en) * | 2023-10-26 | 2024-02-02 | 乘木科技(珠海)有限公司 | Digital twin city population management method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190066137A1 (en) * | 2017-04-24 | 2019-02-28 | The Chicago TREND Corporation | Systems and methods for modeling impact of commercial development on a geographic area |
CN110490787A (en) * | 2019-07-25 | 2019-11-22 | 沈振江 | A kind of method for building up of the multiple agent model of residential location choice |
CN111126678B (en) * | 2019-12-09 | 2023-03-31 | 深圳市市政设计研究院有限公司 | Traffic generation prediction method based on big data |
-
2022
- 2022-08-12 CN CN202210965718.9A patent/CN115049159B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115049159A (en) | 2022-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115049159B (en) | Population distribution prediction method and device, storage medium and electronic equipment | |
Long et al. | Mapping block-level urban areas for all Chinese cities | |
Samat et al. | Modelling land use changes at the peri-urban areas using geographic information systems and cellular automata model | |
Pinto et al. | A cellular automata model based on irregular cells: application to small urban areas | |
CN113191023B (en) | Crowd-sourcing-aware task allocation and user recruitment model cross-validation method and system | |
Zhao et al. | LandSys: an agent-based Cellular Automata model of land use change developed for transportation analysis | |
Doyle et al. | Population mobility dynamics estimated from mobile telephony data | |
CN109214863B (en) | Method for predicting urban house demand based on express delivery data | |
CN102750411A (en) | Urban dynamic micro-simulation method based on multi-agent discrete choice model | |
Li et al. | Agent-based modelling of the spatial pattern of leisure visitation in forests: a case study in Wallonia, south Belgium | |
CN108154258A (en) | Forecasting Methodology, device, storage medium and the processor of air source heat pump load | |
CN116437291A (en) | Cultural circle planning method and system based on mobile phone signaling | |
Tanton | Spatial microsimulation: developments and potential future directions | |
Zhang et al. | Unveiling transit mobility structure towards sustainable cities: An integrated graph embedding approach | |
Malleson et al. | Optimising an agent-based model to explore the behaviour of simulated burglars | |
CN110276387A (en) | A kind of generation method and device of model | |
Leprêtre et al. | Fitness landscapes analysis and adaptive algorithms design for traffic lights optimization on SIALAC benchmark | |
Lei et al. | Effects of local, network and systemic dependence on urban development | |
CN115049158B (en) | Method, system, storage medium and terminal for predicting running state of urban system | |
Wu et al. | A BP neural network-based GIS-data-Driven Automated Valuation framework for Benchmark Land Price | |
Alhmoud et al. | Short-term load forecasting for Jordan’s power system using neural network based different | |
Correia et al. | Applying a structured simulation-based methodology to assess carpooling time–space potential | |
CN111008730A (en) | Crowd concentration degree prediction model construction method and device based on urban space structure | |
Xu et al. | Federated learning for interpretable short-term residential load forecasting in edge computing network | |
Triantakonstantis et al. | Analyzing urban sprawl in Rethymno, Greece |
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 |