实时路况制约下基于内容的兴趣点推荐  

Content-based POI Recommendation in Real-time Traffic Constraint

作　　者：雷凯 刘树波[1] 李丹 李永凯[1] 

机构地区：[1]武汉大学计算机学院,武汉430072 [2]湖北省水利水电科学研究院,武汉430070

出　　处：《计算机工程》2017年第10期147-152,共6页Computer Engineering

基　　金：国家重点基础研究发展计划项目"面向数字城市的实时跨媒体信息存储与公众服务"(2011CB302306)

摘　　要：传统兴趣点推荐方法缺乏对用户所处位置和实时路况信息的考虑,推荐结果虽能满足用户偏好,但会导致出行时间增加。为此,提出一种考虑实时路况信息的推荐方法,利用基于内容的方法获取兴趣点支持度,使用实时路网状况获取实时路网支持度,融合基于内容的支持度和实时路网支持度,形成最终优化的推荐结果。实验结果表明,与基于内容的推荐方法相比,融合实时交通路况的推荐方法能节省更多的出行时间,具有较强的实用性。Traditional Point of Interest（POI） recommendation method does not consider the user＇ s location and real-time traffic information. Though it can satisfy the user＇ s preference, it leads to a big increase in travel time. A recommended method of considering the real-time traffic information is proposed. It uses content-based recommendation method to get POI support, and uses the real-time traffic conditions to obtain real-time network support,fusion based on the POI support and real-time network support, and gets the final recommendation results. Experimental results show that, compared with the content-based recommendation method,the recommendation method can save more travel time and has strong practicability.

关 键 词：兴趣点推荐 基于内容的推荐 实时路网 用户偏好模型 支持度 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]