基于POI的出租车停靠位置选择算法研究  

Research on the algorithm of choosing taxi stops based on POI

作　　者：徐焕君 余靖[1] 苑帅 张玉停 Xu Huanjun;Yu Jing;Yuan Shuai;Zhang Yuting(School of Information Science and Engineering,Yanshan University,Qinhuangdao 066004)

机构地区：[1]燕山大学信息科学与工程学院,秦皇岛066004

出　　处：《高技术通讯》2021年第11期1154-1163,共10页Chinese High Technology Letters

基　　金：国家自然科学基金(61872311,61973261)资助项目。

摘　　要：基于兴趣点(POI),采用图论中判定节点重要度的方法,根据节点在路网中的基本信息,建立一种判定节点重要度的通用节点重要度(GNI)算法。针对不同场所出租车需求量不同的问题,建立了一种不同模式下的出租车按需分配呼叫模型。以GNI算法为基础,获得基于POI的专用节点重要度(DNI)算法。采用杠杆原理,同时类比多边形获取“重心”的方法,分析DNI算法下节点重要度排名结果,获得出租车最佳停靠位置,通过实验验证了该DNI算法的实用性及有效性。Based on point of interest(POI)and adopting the method of determining the importance of nodes in graph the-ory,a general node importance(GNI)algorithm for determining the importance of nodes is established according to the basic information of the nodes in the road network.Aiming at the problem of the different demand for taxis in different places,an on-demand taxi call model with different modes is established.Based on the GNI algorithm,a dedicated node importance(DNI)algorithm based on POI is obtained.Using the principle of leverage and making an analogy with the method of obtaining the‘center of gravity’for polygons,the ranking results of node importance under the DNI algorithm are analyzed to obtain the best taxi parking stand,and the practicality and effectiveness of the DNI algorithm are verified through experiments.

关 键 词：兴趣点(POI) 节点重要度 通用节点重要度(GNI)算法 呼叫模型 专用节点重要度(DNI)算法 

分 类 号：U491[交通运输工程—交通运输规划与管理]