Abstract:  With the wide use of mobile devices and location-based services, they have brought a mass of spatial-
temporal data, and the check-in data record the movement pattern of people in detail. Analyzing check-in data can improve the quality of location-based services, in which the trip recommendation is a significant research orientation. The existing studies of trip recommendation usually address the case of user’s traveling alone to meet the demand of individual user in the recommended route as much as possible. Travel together is a common phenomenon, and the research on group trip recommendation has the vital significance. For this requirement, this paper proposes a group trip recommendation with the goal of getting a trip route which can make high satisfaction for the overall group and satisfaction difference small between individuals in the group, and this route is optimal and is equitable for all the members. How to coordinate the demand of each user in the group is a vital issue in group trip recommendation. This paper proposes a dynamic aggregation preference (DAP) strategy for the dynamic feature when searching a route in view of the weakness in average strategy and no misery strategy which are usually employed in aggregation users’ preferences. According to the degree of satisfaction for current individual, DAP adjusts the group preference model dynamically that can guarantee the overall group high satisfaction and individuals satisfaction small difference. Based on DAP strategy, this paper constructs the route evaluation model, grades the satisfaction of route and returns the route with the highest score. Using check-in data sets from Gowalla and Foursquare social networking websites, this paper evaluates the efficiency of the proposed algorithms with extensive experiments under a wide range of parameter settings, verifies the effectiveness of the algorithms.

Key words: trip recommendation, group recommendation, check-in data, location-based service

摘要： 移动设备和基于位置的服务的广泛应用带来了大量的时空数据，签到数据详细记录了人们出行的移动模式，分析签到数据可以提高基于位置服务的质量，其中旅游路线推荐是重要的研究方向。现有的路线推荐的研究通常只考虑用户独自出行的情况，推荐的路线尽可能满足单个用户需求。结伴出行是旅游中常见的现象，研究群体的旅游路线推荐具有重要的意义。针对此需求，提出了群体旅游路线推荐问题，目标是为群体推荐一条能够使群体整体满意度大，个体满意度差异小，即对群体内所有成员较公平的最优群体旅游路线。通过分析聚合用户偏好时通常采用的平均数策略与无痛苦策略在推荐结果方面存在的不足，针对搜索路线时所具有的动态性特点，提出了一种动态聚合用户偏好的策略（dynamic aggregation preference，DAP）。DAP策略根据当前个体满意度，动态调整群体偏好模型，保证了推荐结果对群体整体满意度较高的同时，个体差异度小。基于DAP策略，建立路线评价模型，对路线进行满意度评分，返回分值最高的路线。利用Gowalla和Foursquare社交网站真实的签到数据集进行了充分实验，验证了算法在不同参数设置下的有效性。

关键词: 旅游路线推荐, 群体推荐, 签到数据, 基于位置的服务