基于频繁序列挖掘的后续行程序列推荐

Successive Travel Sequence Recommendation Based on Frequent Sequence Mining

个性化旅游发展迅速,已有方法主要集中在单个旅游产品推荐上,而旅游行程存在明显的序列性,并受到当前已有行程轨迹影响。因此,提出一种旅行中后续行程序列的推荐方法 SeqRem,基于所有用户的行程序列挖掘频繁序列模式,并以此为依据利用最大点权独立集方法对用户的历史行程序列进行分割,以发现最优序列推荐内容。实验证明,SeqRem在单点推荐和序列推荐准确率与召回率均具有较好效果。

Personalized tourism has become the tendency.Current approaches mainly focus on single product recommendations.However,the travel routes have obvious sequential characteristics,and they are affected by existing routes.A successive travel sequence recommendation approach SeqRem is proposed,it mines the frequent sequence pattern of all the travelers,and use maximum weighted in.dependent set to cut a user’s historical routes while discover optimum successive sequence.Experiments demonstrate that SeqRem performs well in terms of precision and recall rates.