计算机科学与探索2024，Vol.18Issue(3)：755-767,13.DOI:10.3778/j.issn.1673-9418.2211098
异质图嵌入的地理不敏感时空兴趣点推荐方法
Geographically Insensitive Spatial-Temporal POI Recommendation Based on Het-erogeneous Graph Embedding
摘要
Abstract
The increasingly large scale of location-based social networks(LBSN)promotes the rapid development of point-of-interest(POI)recommendation business.POI geospatial distance directly adopted by traditional methods is difficult to simulate the highly random behavior path of users.And the point-of-interest recommendation process brings sensitivity to the location distance measurement.Meanwhile,the sparse POI check-in data of users in social networks are also easy to have a huge impact on the recommendation accuracy.To solve the above issues,geographi-cally insensitive spatio-temporal POI recommendation model based on heterogeneous graph embedding(GIPR)is proposed.Firstly,the user behavior sequence is introduced to construct the spatial and temporal topological diagram of the behavior POI.The weighted spatial path is used to represent the relative location distance.It can not only con-form to the characteristics of user behavior,but also reduce the sensitivity of the recommendation process to the dis-tance between POI,thus enhancing the ability to explain the recommendation results.As for heterogeneous and highly sparse interaction data,the proposed recommendation method can learn the complete LBSN heterogeneous graph from local and global perspectives,and integrate richer user and POI features.Finally,the long-term and short-term preferences of users are extracted through the attention layer to achieve more personalized POI recommendation.Ex-periments on two large-scale real datasets Foursquare and Gowalla show that GIPR has higher recommendation ac-curacy and stronger interpretability.关键词
兴趣点(POI)/异质图嵌入/地理不敏感/POI时空拓扑图Key words
point-of-interest(POI)/heterogeneous graph embedding/geographically insensitive/POI spatial-temporal topology graph分类
信息技术与安全科学引用本文复制引用
李曼文,张月琴,张晨威,张泽华..异质图嵌入的地理不敏感时空兴趣点推荐方法[J].计算机科学与探索,2024,18(3):755-767,13.基金项目
国家自然科学基金(61702356,51901152) （61702356,51901152）
教育部产学合作协同育人项目(2020021680113) （2020021680113）
山西省回国留学人员科研资助项目(2020-040).This work was supported by the National Natural Science Foundation of China(61702356,51901152),the Industry University Coopera-tion Education Program of the Ministry of Education of China(2020021680113),and the Research Project Supported by Scholarship Council of Shanxi Province(2020-040). （2020-040）
