Construction method of Geographic Knowledge Graph based on Micro-Annotation

This paper discusses the construction method of geographic knowledge map based on the combination of geographic information system (GIS) and artificial intelligence. In this paper, a construction method based on micro-annotation is proposed. By optimizing the process of data acquisition and annotation, representative texts are selected for annotation, and iterative training is performed to improve the efficiency and accuracy of entity relation extraction. A structured data collection framework is designed, natural language processing technology is used to automatically extract key information from geographic text, and the geographic knowledge map is constructed for experimental verification. The results show that the proposed method is superior to traditional methods in terms of construction cost, training speed and extraction accuracy. At the end of the paper, the limitation and future direction of the research are discussed, which provides a reference for the further study of geographical knowledge map.