A Multi-level Graph Clustering and Partitioning Method for Residential Polygons

Abstract

The present invention proposes a multi-level graph clustering method for residential polygons. Residential polygons, as an important surface element, have complex shape features and attribute features. In order to realize the cluster analysis of residential polygons, Based on the attribute characteristics of polygon data, the present invention combines the characteristics of spatial cognition criteria and human cognition, firstly obtains the adjacency information between polygons, and combines the similarity measurement indexes of five polygons (namely: shape narrow length, size, concave-convex property) , distance and connectivity) to measure the similarity between polygons, then normalize the similarity value and determine the weight of each index, then use the multi-level graph partition algorithm to cluster the polygons, and finally use the silhouette coefficient to cluster The clustering results obtained by this method are analyzed and evaluated, which makes the clustering results obtained by this method more objective and reliable.

Description

technical field [0001] The invention relates to the scientific research field of geographical information, in particular to a multi-level graph clustering and division method of residential polygons. Background technique [0002] In geographic information system, residential polygon is an important surface feature object, which has complex shape features and attribute features. The cluster analysis of polygons is a research hotspot and research difficulty in the fields of spatial data mining and geographic information science. [0003] Polygons are different from one-dimensional point data. They have distinct geometric features, spatial relationships, and semantic attributes. Clustering and analysis of polygons using various metrics can provide a basis for deeper mining of data information. When performing cluster analysis, not only must choose a spatial clustering algorithm with excellent effect, but also select a suitable spatial similarity index to measure the similarity...

AI Technical Summary

Problems solved by technology

[0003] Polygons are different from one-dimensional point data. They have distinct geometric features, spatial relationships, and semantic attributes. Clustering and analysis of polygons using various metrics can provide a basis for deeper mining of data information. When performing cluster analysis, not only must choose a spatial clustering algorithm with excellent effect, but also select a suitable spatial similarity index to measure the similarity between polygons. Many existing cluster analysis algorithms simplify polygons into points, or It only considers the non-spatial attributes and simple geometric attributes of polygons, and does not fully consider the shape characteristics and spatial relationships of polygons, which limits its application.

[0004] Therefore, at present, in order to conduct an objective and reliable clustering effect analysis on the polygonal data information of residential areas, it is impossible to obtain deeper information mining only through the simplified one-dimensional point data.

Images