Abstract: Multi-source POI fusion refers to integrating POI datasets from different sources into a unified, accurate, and comprehensive database. POI data, as one of the crucial data resources for the National Geographic Information Public Service Platform (Tianditu), poses a key technological challenge in the construction of Tianditu—namely, how to effectively merge various POI data sources to continuously enhance the timeliness, accuracy, and richness of Tianditu's POI data. Research on methods for POI data fusion has garnered widespread attention in the fields of surveying and mapping, geographic information systems, as well as big data and artificial intelligence. Substantial progress has been made in this regard. However, due to the complexity and diversity of POI textual attributes, effectively determining the similarity of POI attributes remains a challenge in practical engineering applications. Given the urgent need for rapid updates to Tianditu's POI data and the shortcomings of current multiple-source POI data fusion methods, this paper proposes a multi-source POI fusion method based on a composite feature rule library. This method aims to provide technical support for the data updates and master database construction of Tianditu.

Key words: POI data, spatial data fusion, composite feature rule library, Tianditu, GIS