Population spatial distribution prediction method and system based on POIs data

A technology of spatial distribution and prediction method, which is applied in the direction of prediction, data processing application, complex mathematical operations, etc., and can solve problems such as the stagnation of research results, the difficulty of realizing the spatialization of population at a fine spatial scale, and the difficulty of reflecting the characteristics of population distribution at a fine scale. , to achieve spatial precision improvement, fine-scale spatial population prediction, and high precision effects
CN110458333AInactive Publication Date: 2019-11-15SOUTH CHINA AGRI UNIV
0 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
SOUTH CHINA AGRI UNIV
Publication Date
2019-11-15
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a population spatial distribution prediction method and system based on POIs data, and the method comprises the steps: dividing a to-be-predicted region into q grids, and enabling each grid to be a region with a preset area; counting the number of the POIs in the q grids; taking the number of the POIs as an input variable, and inputting the input variable into a preset BPNNmodel; and outputting a population distribution prediction result in each grid. Compared with population spatialization research using night light and land utilization data as auxiliary data, the spatial precision of the population spatialization research using POIs is greatly improved. Rapid and high-spatial-resolution population density spatial prediction can be realized and spatial distribution prediction of population is realized by utilizing a machine learning BPNN model, and the prediction result is relatively high in precision. POIs are introduced to serve as single auxiliary data, spatial distribution prediction of population is achieved through a BPNN model, and fine-scale population spatialization prediction can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of Internet big data, in particular to a method and system for predicting population spatial distribution based on POIs data. Background technique

[0002] Mastering population information can provide scientific support for regional sustainable development research and planning. The spatialized population can better approach the actual spatial distribution of the population, break the boundaries of traditional administrative regions, and realize the integration of information such as population, resources and environment. Therefore, the spatialization of population has become an important research hotspot.

[0003] At present, population spatialization mainly uses auxiliary variables related to population distribution for regional interpolation, and then guides population redistribution. Often, the quality and appropriateness of the auxiliary variables used will affect the accuracy and fine-scale of the results on th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More