Space-time multi-scale interest point recommendation method

The invention relates to the technical field of data mining and recommendation systems, in particular to a time-space multi-scale interest point recommendation method. According to the method, learning of user behaviors is converted into learning of a potential state, space information is introduced in a mode of combining distance information, the moving characteristics of the user are effectively captured, and diversity of interest point recommendation is increased through a space-time multi-scale recommendation mode. 本发明涉及数据挖掘和推荐系统技术领域，具体涉及一种时空多尺度的兴趣点推荐方法；本发明将用户行为的学习转换成了潜在状态的学习，并以一种结合距离信息的方式引入空间信息，有效地捕捉了用户的移动特征，且时空多尺度的推荐方式增加了兴趣点推荐的多样性。