计算机应用 ›› 2016, Vol. 36 ›› Issue (6): 1762-1766.DOI: 10.11772/j.issn.1001-9081.2016.06.1762

• 行业与领域应用 • 上一篇    

基于用户兴趣和兴趣点流行度的个性化旅游路线推荐

吴清霞, 周娅, 文缔尧, 贺正红   

  1. 桂林电子科技大学 计算机科学与工程学院, 广西 桂林 541004
  • 收稿日期:2015-11-17 修回日期:2016-01-07 出版日期:2016-06-10 发布日期:2016-06-08
  • 通讯作者: 吴清霞
  • 作者简介:吴清霞(1989-),女,山西运城人,硕士研究生,主要研究方向:数据挖掘、推荐系统;周娅(1966-),女,湖北荆州人,教授,硕士,主要研究方向:数据库、数据挖掘、地理信息系统;文缔尧(1992-),男,湖南长沙人,硕士研究生,主要研究方向为:数据挖掘、地理信息系统;贺正红(1988-),男,湖北仙桃人,硕士研究生,主要研究方向:海量数据管理。
  • 基金资助:
    广西科技攻关计划项目(桂科攻1598019-3);广西教育厅高校科技项目(2013YB095);广西信息实验科学中心重点项目(20130111);桂林电子科技大学研究生创新项目(GDYCSZ201465)。

Personalized trip itinerary recommendation based on user interests and points of interest popularity

WU Qingxia, ZHOU Ya, WEN Diyao, HE Zhenghong   

  1. School of Computer Science and Engineering, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
  • Received:2015-11-17 Revised:2016-01-07 Online:2016-06-10 Published:2016-06-08
  • Supported by:
    This work is partially supported by the Guangxi Key Science and Technology Program (1598019-3), the University Science and Technology Project of Guangxi Education Department (2013YB095), the Key Project of Guangxi Information and Experimental Science Center (20130111), the Innovation Project of Graduate Education of Guilin University of Electronic Technology (GDYCSZ201465).

摘要: 针对传统的旅游路线推荐算法推荐准确率不高的缺陷,提出一种基于兴趣点(POI)流行度和用户兴趣偏好的个性化旅游路线推荐(PTIR)算法。首先通过分析得到用户真实的历史旅游足迹;然后根据用户在每个景点的逗留时间提出基于时间的用户兴趣偏好;最后在给定的旅行时间限制、起点和终点下,设计最优旅游路线计算方法。在Flickr社交网站的真实数据集上进行实验,结果显示,相比传统的只考虑POI流行度的算法,该个性化旅游路线推荐算法的准确率和召回率都有较大提升;相比只考虑用户兴趣偏好的算法,该个性化旅游路线推荐算法的准确率和召回率也有所提高。实验结果表明综合考虑POI流行度和用户兴趣偏好能使路线推荐得更准确。

关键词: 旅游路线推荐, 兴趣点, 用户兴趣, 定向问题, 整数规划

Abstract: In order to solve the problem of low recommendation precision in the traditional trip itinerary recommendation algorithm, a novel Personalized Trip Itinerary Recommendation (PTIR) algorithm based on Points Of Interest (POI) popularity and user interests was proposed. Firstly, the user's real-life travel histories were obtain by analyzing the data. Then user interests based on the time were proposed according to the stay time of each scenic spot. Finally, a calculation method of optimal trip itinerary was designed under the given travel time limits, start and end points. The experimental results of a Flickr data set show that, compared with the traditional algorithm with only considering POI popularity, the precision and recall of the proposed PTIR algorithm based on the POI popularity and user interests were greatly improved; and compared with the traditional algorithm with only considering the user interests, the precision and recall of the proposed PTIR algorithm based on the points of interest and user interests were also improved. The experimental results show that considering both the POI popularity and user interests can make the itinerary recommendation more precise.

Key words: trip itinerary recommendation, Points Of Interest (POI), user interest, orienteering problem, Integer Programming (IP)

中图分类号: