Bipartite graph-based population flow network estimation method and system

Abstract

The invention discloses a bipartite graph-based population flow network estimation method and system. The method comprises the following steps: S1, converting migration proportion data into an immigration and emigration star structure network of each region, wherein the immigration and emigration star structure network refers to a network which takes the region as a central node and only has one node connected to the central node in other regions; s2, obtaining a bipartite graph network of the total number of migrated people in each region through the star structure network according to the conservation relation of the number of migrated and emigrated people in the region; s3, according to the flight operation data and the traffic mode proportion data, calculating to obtain the total number of immigrated or emigrated people of a certain region, and further calculating the total number of immigrated and emigrated people of all regions; and S4, according to the star-shaped structure network, calculating to obtain the human traffic on all migration lines, and obtaining a population flow network. The invention has the advantages of being easy to operate, high in interpretability and the like, and theoretical support can be provided for the application fields of large-scale epidemic disease prediction modeling, traffic planning, urban attraction evaluation and the like.

Description

technical field [0001] The present invention relates to the technical field of population mobility research, and more specifically, to a method and system for estimating population flow networks based on bipartite graphs. Background technique [0002] The population flow network refers to the population coupling relationship system among all regions within a certain range formed due to the change of the spatial position of individuals. It focuses on the flow and probability of population transfer between regions. Specifically, the population flow network is a network structure composed of nodes and edges. Nodes usually refer to geographical areas in the population flow network, and edges represent the population flow between these areas. The edge weight is one of the most important information of the population flow network. The edge weight of the population flow network is generally represented by the total number of migrations between two regions within a certain period of...

AI Technical Summary

Problems solved by technology

[0003] However, spatial mutual models, such as gravity models, radiation models, etc., are very dependent on statistical survey data of population mobility, and for regions that lack statistical data of population mobility, it is impossible to establish a suitable model to estimate the population mobility network

In addition, the fitting accuracy of this type of model is greatly affected by the spatial division scale, and it is difficult to guarantee the accuracy of the estimation results of large-scale population flow patterns under a uniform scale

Therefore, it is difficult for existing methods to estimate a large-scale dynamic population flow network to reflect the real human society

Images