计算机科学与探索 ›› 2019, Vol. 13 ›› Issue (9): 1471-1480.DOI: 10.3778/j.issn.1673-9418.1810017

• 学术研究 • 上一篇    下一篇

移动情景和用户轨迹感知的众包服务推荐

姜芸,何伟,崔立真,杨倩,刘磊   

  1. 1.山东大学 软件学院,济南 250101
    2.山东省软件工程重点实验室,济南 250101
  • 出版日期:2019-09-01 发布日期:2019-09-06

Mobile Context and User Trajectory Awareness Crowdsourcing Service Recommendation

JIANG Yun, HE Wei, CUI Lizhen, YANG Qian, LIU Lei   

  1. 1.School of Software, Shandong University, Jinan 250101, China
    2.Shandong Key Laboratory of Software Engineering, Jinan 250101, China
  • Online:2019-09-01 Published:2019-09-06

摘要: 随着移动互联网的快速发展和智能终端设备的迅速普及,服务类型与服务内容的日新月异,为移动用户带来严重的移动信息过载问题,如何为用户提供更好的服务推荐是亟待解决的难题。提出了一个移动情景和用户轨迹感知的众包服务推荐策略,首先对历史日志中的位置坐标通过聚类算法聚合成区域,然后挖掘出用户在不同移动情景下的轨迹模式,进而提取出移动规则并判断每条规则所属的情景;在进行众包服务推荐时,通过实时感知到的位置轨迹和移动情景信息,预测用户即将到达的位置区域,从而将区域内的众包服务推送给该用户。提出的预测方法避免了额外增加用户执行任务的时间、行程、费用等成本,给用户推荐更适合的任务,提高用户服务满意度。

关键词: 移动情景, 服务推荐, 移动众包, 轨迹预测, 任务推荐

Abstract: With the rapid development of mobile Internet and the rapid popularization of intelligent terminal equipment, service types and service contents are changing with each passing day, which brings serious mobile information overload problem for mobile users. How to provide better service recommendation for users is a difficult problem to be solved. This paper proposes a mobile scenario and user trajectory awareness crowdsourcing service recommendation strategy. Firstly, the location coordinates in the history log are clustered into regions by clustering algorithm, and then the trajectory patterns of users are mined in different mobile scenarios, and the movement rules are extracted and the scenarios of each rule are judged. When recommending crowdsourcing services, the user's upcoming location area is predicted by real-time perceived location trajectory and mobile scenario information, thus the crowdsourcing services in the area are pushed to the user. The forecasting method proposed in this paper avoids the additional cost of the time, journey and cost of the users to perform the task. It can recommend more suitable tasks to the users and improve the satisfaction of the users service.

Key words: mobile context, service recommendation, mobile crowdsourcing, trajectory prediction, task recommendation