EXPLORING URBAN FUNCTIONAL ZONES BASED ON MULTI-SOURCE SEMANTIC KNOWLEDGE AND CROSS MODAL NETWORK

Abstract

Abstract. The refined identification of urban functional zones can provide important basic data and decision-making basis for the formulation of urban spatial development planning, effective relaxation of urban spatial development planning, effective relaxation of urban functions, and optimal allocation of resource space. The multi-source spatiotemporal data represented by multi-source geographic data, social perception data, and thematic data have been widely used in various fields, providing new data sources for the refined identification of urban functional areas. However, there are significant differences in the data generation sources, collection methods, and storage organization formats of multi-source data. In this paper, we propose a method for exploring urban functional zones based on Multi-source Semantic knowledge and deep Coupling Model (MSCM). Our approach integrates information from multiple sources and incorporates the semantics of urban functional zones into a knowledge graph, enabling effective fusion and mining of multi-source data.This method can improve the credibility and precision of the results, providing a richer research perspective for refined urban functional zoning. The results of this paper have important theoretical value and practical significance for the construction of identification, labelling, and monitoring tools for engineering smart cities.