In the study of Location-Based Social Network (LBSN) sign-in data as the recommended point of interest for groups, there are some problems such as poor recommendation accuracy and high bias in recommendation results because of the unbalanced number and diversity of individual sign-in and the different degree of group user association. In this paper, a new group recommendation model is proposed. Firstly, the existing individual recommendation model is combined with the text retrieval idea and the threshold function to improve the user rating strategy. Secondly, the recommendation strategy is used to aggregate the individual recommendation list. Considering users' friends relationship, similarity and frequency of sign-in, lead into the user gregariousness weight and activity weight, and form a new group user preference model to make recommendation. The experimental results show that the improved scoring strategy can improve the accuracy of recommendation, and the new group weighting model which recommend the points of interest for the groups can improve the recommendation quality by reducing the recommended deviation.
展开▼
