信息工程大学学报2026，Vol.27Issue(3)：282-290,9.DOI:10.3969/j.issn.1671-0673.2026.03.005
图注意力网络融合地理知识图谱的位置预测
Location Prediction with Graph Attention Network and Geographic Knowledge Graph
摘要
Abstract
To address the limitations of existing location prediction methods in geographic semantic fu-sion and users'geographic preference modeling,a graph attention network method for location predic-tion enhanced by a geographic knowledge graph is proposed.A hierarchical geographic knowledge graph with multi-source geographical data is constructed to map users,points of interest,and multi-granularity geographic entities into a unified semantic space.On this basis,a spatial and relation-aware graph attention network together with a spatiotemporal-aware sequential encoder is employed to model users'global geographic preferences and local spatiotemporal transition patterns,respectively.Experiments on the Foursquare-NYC and Foursquare-TKY datasets show that the mean reciprocal rank(MRR)of the proposed method are improved by 19.52%and 4.10%,respectively,compared with those of the strongest baseline.Experimental results demonstrate that the proposed method can effectively improve the accuracy of next location prediction.关键词
位置预测/地理知识图谱/图注意力网络/基于位置的社交网络Key words
location prediction/geographic knowledge graph/graph attention network/location-based social networks分类
天文与地球科学引用本文复制引用
李庆祥,张衡,齐凯,宋世博,赵旭翔,罗灿灿..图注意力网络融合地理知识图谱的位置预测[J].信息工程大学学报,2026,27(3):282-290,9.基金项目
河南省自然科学基金项目(252300420301) （252300420301）
