基于区域划分的出租车统一推荐算法

Taxi unified recommendation algorithm based on region partition

针对在极端天气或交通繁忙时乘客无法快速搭乘出租车到达目的地的问题,提出一种基于区域划分的出租车统一推荐算法,不仅提供普通打车服务,同时提供拼车服务。首先,将区域作为旅程标识,在旅程匹配方面化不可能为可能;其次,在拼车服务中算法将两对路线相近的乘客进行即时匹配,帮乘客拼车共乘;最后,选取绕远时间比例最小的出租车推荐给用户。使用包含14747辆出租车的全球定位系统(GPS)数据对算法进行评估,与Call Cab系统相比虽然在减少的总里程数上下降了10%左右,但每次拼车平均只需要多花费6%的时间,且降低的送达乘客总里程数同样达到30%,不仅大幅度减少汽车尾气的排放,同时在用户更加关注的时间消耗方面表现更佳。

In extreme weather or traffic, passengers cannot get a taxi to the destination quickly, thus a taxi unified recommendation algorithm based on region partition was proposed to provide common taxi service and carpooling service. First of all, the region was regarded as the logo of journey, making the journey matching possible. Secondly, in the earpooling service, the similar routes of two passengers were matched in real-time to help passenger carpool sharing. Finally, the taxi with the minimum percentage of bypass time was selected to recommend to the user. The Global Positioning System （GPS） data of 14 747 taxis was used to evaluate the proposed algorithm. Compared with CallCab system, the total mileage of the proposed algorithm was dropped by about 10%, while the carpooling time was only raised by 6% on average, as well as the total passenger mileage was reduced by 30%. Experimental results show that the proposed algorithm not only can significantly reduce the emission of automotive exhaust, but also has better performance in terms of time consumption.