华东师范大学学报(自然科学版) ›› 2017, Vol. 2017 ›› Issue (5): 186-200.doi: 10.3969/j.issn.1000-5641.2017.05.017

• 位置服务 • 上一篇    下一篇

基于实时路况的top-k载客热门区域推荐

吴涛1, 毛嘉莉1, 谢青成1, 杨艳秋2, 王锦1   

  1. 1. 西华师范大学 计算机学院, 四川 南充 637000;
    2. 中国人民武装警察部队警官学院 电子技术系, 成都 610000
  • 收稿日期:2017-06-19 出版日期:2017-09-25 发布日期:2017-09-25
  • 通讯作者: 毛嘉莉,女,副教授,硕士生导师,研究方向为基于位置的服务.E-mail:maojl1231@163.com E-mail:maojl1231@163.com
  • 作者简介:吴涛,男,硕士研究生,研究方向为基于位置的服务.E-mail:850517937@qq.com
  • 基金资助:
    四川省教育厅重点基金项目(17ZA0381,13ZA0015);西华师范大学国家培育项目(16C005);西华师范大学英才科研基金(17YC158)

Top-k hotspots recommendation algorithm based on real-time traffic

WU Tao1, MAO Jia-li1, XIE Qing-cheng1, YANG Yan-qiu2, WANG Jin1   

  1. 1. College of Computer, China West Normal University, Nanchong Sichuan 637000, China;
    2. Department of Electronic Technology, Officers College of PAP, Chengdu 610000, China
  • Received:2017-06-19 Online:2017-09-25 Published:2017-09-25

摘要: 为降低城市出租车的空载率,缓解路网交通拥堵压力,亟需设计有效的出租车载客热门区域推荐方法.针对传统的出租车相关推荐方法忽略实际路况导致推荐精度较低的现状,提出了一个两阶段的载客热门区域实时推荐算法.首先,离线挖掘阶段,基于出租车历史轨迹数据集提取基于时段属性的载客热门区域;随后,在线推荐阶段,根据出租车请求位置及时间,结合实时路况设计潜在空载时间开销函数Tcost对载客热门区域进行评测排序,继而发现Top-k载客热门区域.基于出租车轨迹数据集的实验结果表明,结合实时交通状况的Top-k载客热门区域推荐方法以确保较小潜在空载时间开销,相较于传统的出租车推荐方法具有较好的有效性与鲁棒性.

关键词: 潜在空载时间开销函数, 实际路况, 热门区域, 推荐

Abstract: To cut down the no-load rate of taxis and relieve the traffic pressure, an effective hotspot recommendation method of picking up passenger is necessitated. Aiming at the problem of lower recommendation precision of traditional recommendation technique due to ignoring the actual road situation, we propose a two-phase real-time hotspot recommendation approach for picking up passenger. In the phase of offline mining, timebased hotspots are extracted by mining the history taxi trajectory dataset. In the phase of online recommendation, according to the position and time of taxi requests, a potential no-passenger time cost evaluation function that based on real-time road situation is presented to evaluate and rank hotspots, and obtain top-k hotspots of picking up passenger.Experimental results on taxi trajectory data show that, our proposal ensure smaller potential no-load time overhead due to considering real-time traffic conditions, and hence has good effectiveness and robustness as compared to the traditional recommendation approached.

Key words: potential no-passenger time cost function, real-time traffic, hotspot, recommendation

中图分类号: