Geographic big data space latent mode analysis method based on topology analysis

Abstract

The invention discloses a geographic big data space latent pattern analysis method based on topology analysis, which comprises the following steps: acquiring urban road network data to obtain a street network diagram; performing feature description on the street network diagram by using urban traffic network statistical indexes, regularity features and topological features; calculating a Gini coefficient between the topological features; dividing a city into simplex forms by using the regularity features; using a topological mapper as a topological structure visualization tool of the features, identifying the simplex forms and converting the simplex forms into a complex form, and clustering the complex form into groups; and combining the clustered cities with economic development indexes of the corresponding cities to perform correlation analysis. The structure extracted by the method integrally reflects the regularity of each urban road network, discovers a potential substructure, and discovers that the structure division is related to the urban economic level and geographical location factors in combination with urban GDP total amount information.

Description

technical field [0001] The invention belongs to the technical field of surveying and mapping, and in particular relates to a method for analyzing spatial latent patterns of geographic big data based on topology analysis. Background technique [0002] In recent years, with the development of information and communication technology and the popularization of various sensors and positioning technologies, a large amount of spatial big data with space-time marks and capable of describing individual behaviors has been generated, including mobile phone positioning data, taxi data, shared bicycle data, bus Smart card data, social network data, video big data, etc., provide great opportunities for analyzing and understanding the dynamics of urban structures, the spatiotemporal patterns of human activities, and quantitatively understanding the socioeconomic environment. The rise of these big data with geographic attributes has also put forward new demands on the spatial mining capabil...

AI Technical Summary

Problems solved by technology

Dimensionality reduction methods such as PCA and t-SNE are usually used to analyze and visualize the potential low-dimensional structure of high-dimensional data. Although these analysis methods can maintain part of the local or global structure in the high-dimensional space in the embedded low-dimensional space , but ignores the original topology of high-dimensional data

Images