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.

基于投入产出表的聚类识别长期以来由于更新缓慢和互斥问题而限制了其有效性。本研究提出了一种利用企业大数据和语义相似性来识别产业集群的新方法。我们以珠江三角洲（PRD）电子信息产业集群为例，证明了我们方法的有效性。我们的分析显示，珠三角电子信息产业集群由27个产业组成，与投入产出表计算的结果非常吻合。在此集群识别的基础上，我们的研究进一步探讨了集群企业之间的产业关联和空间协同分布特征。本研究提出了一种快速识别产业集群的方法，从个体企业的角度定量评价产业集群的产业联系和空间协调性。该方法对于城市规划者和政策制定者了解产业集群的背景、关系和空间协同作用具有重要意义。