融合全局和局部特征的下一个兴趣点推荐方法

随着海量移动数据的积累,下一个兴趣点推荐已成为基于位置的社交网络中的一项重要任务.目前,主流方法倾向于从用户近期的签到序列中捕捉局部动态偏好,但忽略了历史移动数据蕴含的全局静态信息,从而阻碍了对用户偏好的进一步挖掘,影响了推荐的准确性.为此,提出一种基于全局和局部特征融合的下一个兴趣点推荐方法.该方法利用签到序列中的顺序依赖和全局静态信息中用户与兴趣点之间、连续签到之间隐藏的关联关系建模用户移动行为.首先,引入两类全局静态信息,即User-POI关联路径和POI-POI关联路径,学习用户的全局静态偏好和连续签到之间的全局依赖关系.具体地,利用交互数据以及地理信息构建异构信息网络,设计关联关系表示学习方法,利用相关度引导的路径采样策略以及层级注意力机制获取全局静态特征.然后,基于两类全局静态特征更新签到序列中的兴趣点表示,并采用位置与时间间隔感知的自注意力机制来捕捉用户签到序列中签到之间的局部顺序依赖,进而评估用户访问兴趣点概率,实现下一个兴趣点推荐.最后,在两个真实数据集上进行了实验比较与分析,验证了所提方法能够有效提升下一个兴趣点推荐的准确性.此外,案例分析表明,建模显式路径有助于提...

Next Point-of-interest Recommendation Approach with Global and Local Feature Fusion

As considerable amounts of mobility data have been accumulated, next point-of-interest (POI) recommendation has become one of the important tasks in location-based social networks. Existing approaches for next POI recommendation mainly focus on capturing local dynamic preferences from user''s recent check-in records, but ignore global static information in historical mobility data. As a result, it prevents further mining of user''s preferences and limits the recommendation accuracy. To this end, a global and local feature fusion based approach is proposed for next POI recommendation (GLNR). GLNR can model user dynamic behavior by taking advantage of the sequential dependencies between check-ins and the underlying relationships between entities contained in global static information. Two types of global static information are firstly introduced, i.e., user-POI association paths and POI-POI association paths, to learn user''s global static preferences and the global dependency between successive check-ins. Specifically, a heterogeneous information network is constructed based on interactive data and geographical information. To capture global static features, a relevance-guided path sampling strategy and a hierarchical attention based representation learning method are designed. Moreover, the representations of POIs in the user''s check-in sequence are updated based on the two types of global static features. Position and time interval aware self-attention mechanism are further utilized to model the sequential dependency between multiple check-ins. Then, the check-in probability is predicted and a set of next POIs is recommended for the target user. Finally, the extensive experiments are conducted on two real-world datasets to evaluate the performance of the proposed model GLNR. Experimental results validate the superiority of GLNR for improving recommendation accuracy. Besides, the case study indicates that the explicit paths in the global static information help GLNR to provide interpretable recommendations.