Urban functional area identification method based on multi-subspace model

Abstract

The invention discloses an urban functional area identification method based on a multi-subspace model. The method comprises the following steps: obtaining taxi track data and sign-in data in a research area; constructing a partition-oriented time sequence feature matrix C based on a visiting purpose; inputting the time sequence characteristic matrix C to a sparse subspace clustering algorithm, and calculating and obtaining a corresponding relationship between the geographic unit and the urban functional area; and obtaining a significant feature location of each functional area, and further identifying a main function of each functional area. According to the method, human activity information provided by geographic big data is utilized; the model based on the multiple subspaces overcomesthe defects in the prior art, can recognize the urban functional areas more accurately, analyzes the uniqueness and abundance of each functional area based on the geometrical properties of the subspaces, and provides fine quantitative index indication for the management and development of the urban functional areas.

Description

technical field [0001] The invention belongs to the technical field of geographic space information identification, and relates to an identification method of urban geographical information, in particular to an identification method of urban functional areas based on a multi-subspace model. Background technique [0002] Urban spatial structure is a core research content of urban geographic information science, and it is also a concentrated reflection of the relationship between man and land, because urban space has an impact on human production and activities when it is affected by human activities, and it involves urban planning and site selection. , as small as travel and location recommendations. In the analysis of urban spatial structure, the distribution of urban functional areas is the result presented in geographical space under the influence of many factors. [0003] There are many methods for analyzing urban functional areas, such as social surveys, but it takes ti...

AI Technical Summary

Problems solved by technology

The strict assumption of the single subspace algorithm facilitates the acquisition of feature patterns, and the distribution of functional areas can be obtained by clustering according to the relationship between samples and features. However, if the weight of sample information is small, it will be marginalized after feature expression , resulting in inaccurate clustering results

And there are feature differences between functional areas, using the same set of features cannot describe each functional area concisely and precisely

When the data is too large and the feature pattern is too complex, the assumption of the feature pattern of the single subspace model will limit the mining of features

so they cannot handle more complex data

[0006] Second, these models ignore the geometric meaning of the vector space

The geometric properties of the subspace are related to the characteristics of the urban functional area, and the existing technology ignores the discussion and consideration of this

Images