Page 34 - 《软件学报》2020年第12期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2020,31(12):3700−3715 [doi: 10.13328/j.cnki.jos.005855] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

∗
基于多维上下文感知图嵌入模型的兴趣点推荐

1,2
1,2
1,2
陈劲松 , 孟祥武 , 纪威宇 , 张玉洁 1,2
1
(智能通信软件与多媒体北京市重点实验室(北京邮电大学),北京 100876)
2 (北京邮电大学 计算机学院,北京 100876)
通讯作者: 孟祥武, E-mail: mengxw@bupt.edu.cn

摘 要: 近些年来,兴趣点推荐系统已经逐渐成为移动推荐系统领域的研究热点之一.多种因素联合建模的方法
逐渐深入,如时间、空间、序列、社会化和语义信息被引入统一模型,以建模多维情景下的用户偏好.其中,嵌入学
习模型作为一种有效的多因素联合建模方法,在移动推荐领域有较好的性能.然而,多数嵌入学习的模型只是简单地
将显式因素,如时间戳、项目、区域、序列等嵌入到相同的空间,由于缺乏对用户和项目的语义特征的深层次挖掘,
在用户签到极端稀疏时,难以精准获取用户偏好.鉴于此,提出一种多维上下文感知的图嵌入模型——MCAGE.在
MCAGE 中,利用主题模型提取用户和项目间的潜在语义特征,并重新定义了一系列图的节点及关联规则,设计了更
有效的用户偏好公式,以此提升刻画移动用户偏好的精准度.最后,通过在真实数据集上的实验分析,证明了该模型
具有更好的推荐性能.
关键词: 移动推荐;语义特征;嵌入学习模型;主题模型
中图法分类号: TP18

中文引用格式: 陈劲松,孟祥武,纪威宇,张玉洁.基于多维上下文感知图嵌入模型的兴趣点推荐.软件学报,2020,31(12):
3700−3715. http://www.jos.org.cn/1000-9825/5855.htm
英文引用格式: Chen JS, Meng XW, Ji WY, Zhang YJ. POI Recommendation Based on Multidimensional Context-Aware Graph
Embedding Model. Ruan Jian Xue Bao/Journal of Software, 2020,31(12):3700−3715 (in Chinese). http://www.jos.org.cn/1000-
9825/5855.htm

POI Recommendation Based on Multidimensional Context-aware Graph Embedding Model

1,2
1,2
1,2
CHEN Jin-Song , MENG Xiang-Wu , JI Wei-Yu , ZHANG Yu-Jie 1,2
1 (Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia (Beijing University of Posts and
Telecommunications), Beijing 100876, China)
2 (School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China)
Abstract: In recent years, the point-of-interest (POI) recommendation system has gradually become one of the research hotspots in the
field of mobile recommendation systems. The method of joint modeling of multiple factors, such as time, space, sequence, socialization,
and semantic information, has been gradually introduced into a unified model to compute the user preferences under multidimensional
scenarios. As an effective multi-factor joint modeling method, the embedding learning model has better performance in the mobile
recommendation systems. However, many of the embedded learning models just simply embed the explicit factors, such as timestamps,
items, regions, sequences, etc. into the same space. Due to the lack of deep mining of user and item semantic features, it is hard to
accurately obtain user preferences when the users’ check-in data is extremely sparse. In view of this, a multi-dimensional context-aware
graph embedding model, called MCAGE, is proposed in this study. In MACGE model, the topic model is used to extract the potential
semantic features between users and items. Then, a series of graph nodes and association rules are redefined. To enhance the accuracy of

∗ 基金项目: 北京市教育委员会共建项目
Foundation item: Mutual Project of Beijing Municipal Education Commission, China
收稿时间: 2018-07-20; 修改时间: 2018-12-24; 采用时间: 2019-04-22