LBSN中利用深度学习的POI推荐方法  

POI recommendation method using deep learning in LBSN

作　　者：江涛 余松森 汪海涛[3] JIANG Tao;YU Song-sen;WANG Hai-tao(Department of Information Technology,Guangdong Technology College,Zhaoqing 526100,China;School of Software,South China Normal University,Foshan 528225,China;College of Information and Automation,Guangdong Polytechnic of Science and Trade,Guangzhou 510430,China)

机构地区：[1]广东理工学院信息技术学院,广东肇庆526100 [2]华南师范大学软件学院,广东佛山528225 [3]广东科贸职业学院信息与自动化学院,广东广州510430

出　　处：《计算机工程与设计》2022年第7期1856-1863,共8页Computer Engineering and Design

基　　金：国家自然科学基金面上基金项目(61572028);中国教师发展基金会基金项目(CTF120715);广东理工学院质量工程基金项目(JXGG202053、ZXKCYY20203);广东省普通高校特色创新类基金项目(2019GKTSCX038)。

摘　　要：提出一种基于位置的社交网络中利用深度学习的POI推荐方法。建立一个地理时空注意力网络,以发现总体序列依赖性和微妙的POI-POI关系;将签到序列中连续的地理距离和时间间隔信息加入到地理时空注意力网络中,建立用户个性化移动行为和挖掘用户个性化时空偏好;设计特定于上下文的共同注意力网络,通过从签到历史中自适应选择相关签到活动来学习更改用户偏好,使地理-时空门控循环单元网络(geographical-spatiotemporal gated recurrent unit network,GS-GRUN)能够区分不同签到的用户偏好程度。在Foursquare和Gowalla数据集上的实验结果表明,所提算法能够显著提升POI推荐方法的推荐匹配度。A POI recommendation method using deep learning in location-based social networks was proposed.A geo spatiotemporal attention network was established to simultaneously discover the overall sequence dependence and subtle POI-POI relationship.The continuous geographic distance and time interval information in the check-in sequence were added to GRU network to model user’s personalized mobile behavior and mine user’s personalized spatio-temporal preference.A context specific common attention network was designed to learn to change user preferences by adaptively selecting relevant check-in activities from the check-in history,which enabled GS-GRUN to distinguish different levels of user preferences.Experimental results on Foursquare and Gowalla datasets show that the proposed method can significantly improve the recommendation matching degree of POI recommendation method.

关 键 词：基于位置的社交网络 POI推荐 时空意识 注意力机制 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]