A multi-agent-based urban population spatial distribution estimation method and device

Abstract

The invention relates to the field of population spatial distribution, and discloses a multi-agent-based urban population spatial distribution estimation method and device. The method comprises the steps of acquiring input public service facility environment factors around multiple buildings in a research area influencing urban multi-agent population spatial distribution; establishing an urban multi-agent population spatial distribution estimation model; calculating and comparing the comprehensive attraction of all the buildings in the multi-agent search range and the comprehensive attractionof the building where the multi-agent is located currently according to the model; judging whether the multi-agent moves to any building in a search range or not, ending operation and outputting an operation result when a preset model operation termination condition is met, otherwise, returning to the model to continue to calculate; outputting results. According to the invention, the urban population spatial distribution estimation model is established according to the environmental factors of the public service facilities around the building influencing living selection, and a population spatial distribution result that are more consistent with actual conditions in life can be obtained.

Description

technical field [0001] The invention relates to the field of population spatial distribution, and discloses a multi-agent-based urban population spatial distribution estimation method and device. Background technique [0002] Cities are the concentration of population, capital and technology. As human settlements, the development of cities is closely related to population distribution. The spatial distribution of population refers to the geographical distribution of population at a certain point in time, which is the spatial manifestation of population process and the core issue of population geography research. The spatial distribution of population is closely related to urban planning and economic development, and is also the key to solving the shortage of natural resources and uneven regional development. [0003] The currently widely used population distribution data is usually based on the administrative division as a unit, and the typical population distribution data ...

AI Technical Summary

Problems solved by technology

[0003] The currently widely used population distribution data is usually based on the administrative division as a unit, and the typical population distribution data obtained through census, sampling statistics, etc. have the following three deficiencies in practical applications: First, the time resolution is low The national census is held every 10 years, and the data update cycle is long, which makes it difficult to accurately reveal the population change situation; second, the spatial resolution is low, and the population data obtained with the administrative district as the unit is evenly distributed within the administrative unit, which cannot reflect the population data Third, it is not conducive to multi-source data fusion and comprehensive spatial analysis. There is a problem of spatial mismatch between statistical data based on administrative districts and physical geographic units, which limits multidisciplinary interaction based on demographic data.

[0006] However, when the multi-agent model in the prior art considers the factors affecting residents’ living choices, it considers the attribute factors of the buildings and buildings themselves, and does not consider the environmental factors of the public service facilities around the buildings and buildings. With the rapid development of the urban economy, the living choices of residents are actually more related to the public service facilities around the houses and buildings. Therefore, the spatial distribution of the urban population obtained by the existing technical research is less consistent with the actual situation in the lives of residents. , the practical significance is not strong

Images