基于分类层次偏好树和用户间信任度的位置推荐方法

发布时间：2018-04-04 05:14

本文选题：位置社交网络　切入点：个人偏好　出处：《小型微型计算机系统》2015年08期

【摘要】：近年来,随着移动定位技术的发展和位置社交网络的日益普及,基于位置社交网络(Location Based Social Network,LBSN)的位置推荐技术越来越受到人们的关注和重视,并在旅游推荐、位置导航、广告推送等领域有着广泛的应用.目前大多数基于位置社交网络的位置推荐方法在用户偏好提取的过程中考虑因素过于单一,导致用户偏好提取不准确,而且未充分考虑社交网络中的用户间信任关系,造成推荐准确率不高.针对此问题,本文设计了特殊的用户偏好存储结构——分类层次偏好树来更加准确地提取个人偏好.在此过程中,本文充分考虑了习惯性偏好、偶然性偏好以及时间因素对用户偏好的影响,使用户偏好提取更加准确,同时,结合位置社交网络中的用户信任关系来进行位置推荐.实验结果表明,本文提出的位置推荐方法得到了较高的推荐准确率.
[Abstract]:In recent years, with the development of mobile location technology and the increasing popularity of location-based social network, the location-based location Based Social network LBSN-based location recommendation technology has attracted more and more attention, and has attracted more and more attention in tourism recommendation, location navigation.Advertising push and other fields have a wide range of applications.At present, most location-based social network-based location recommendation methods consider too single factors in the process of user preference extraction, which leads to inaccurate user preference extraction, and does not fully consider the trust relationship between users in social network.The recommendation accuracy is not high.In order to solve this problem, a special structure of user preference storage, classified hierarchical preference tree, is designed to extract personal preferences more accurately.In this process, the influence of habitual preference, contingency preference and time factor on user preference is fully considered, which makes the user preference extraction more accurate, at the same time,The location recommendation is based on the user trust relationship in the location social network.The experimental results show that the proposed location recommendation method has a high accuracy.
【作者单位】：东北大学信息科学与工程学院;
【基金】：国家自然科学基金项目(61272177)资助
【分类号】：TP391.3

【参考文献】