The Identification of Industrial Clusters and their Spatial Characteristics Based on Natural Semantics

Cluster identification based on input-output tables has long been limited in its effectiveness due to slow updates and issues of mutual exclusion. This study presents a novel method that leverages enterprise big data and semantic similarity to identify industrial clusters. Using the electronic information industry cluster in the Pearl River Delta (PRD) as an empirical example, we demonstrate the efficacy of our approach. Our analysis reveals that the PRD's electronic-information industry cluster comprises 27 industries, aligning closely with the results obtained from the input-output table calculations. Building on this cluster identification, our study further investigates the industrial association and spatial collaborative distribution characteristics among cluster enterprises. This study proposes a method to rapidly identify industrial clusters, and quantitatively evaluate industrial linkages and the spatial coordination of industrial clusters from the perspective of individual enterprises. The proposed method has significant implications for urban planners and policy makers in terms of helping them understand the context, relationship, and spatial synergy of industrial clusters.