网约车出行需求预测方法

doi:10.12066/j.issn.1007-2861.2211

摘要/Abstract

摘要：

随着互联网出行方式的迅速变化, 城市居民快速增长的网约车 (Internet private hire vehicle, IPHV) 出行需求与服务车辆资源之间的供需矛盾日渐突出. 针对网约车出行需求预测基础理论的研究, 对国内外大量文献进行了梳理和分析. 首先分析了网约车用户出行影响因素; 然后从时间维度和事件维度详细综述了网约车出行需求预测的内容、方法和关键技术, 对比了各类预测方法的优缺点; 最后, 总结了既有研究存在的主要问题, 并进一步提出了未来的研究方向.

关键词: 网约车, 出行特性, 需求预测, 时间维度, 事件维度

Abstract:

With the development of Internet travel mode, the contradiction between the demand of taxi service and the supply of vehicle resources is increasingly prominent. In view of the basic theoretical research on travel demand forecast for Internet private hire vehicles (IPHVs), a large number of domestic and foreign research literature are summarized and analyzed. Firstly, this paper analyzes the travel behavior characteristics of IPHV users, and then summarizes the contents, methods and key technologies of IPHV demand forecast from time dimension and event dimension. Finally, main problems in the study of IPHV demand forecast are discussed, and potential research topics in the future are suggested.

Key words: Internet private hire vehicle (IPHV), travel characteristics, demand forecast, time dimension, event dimension

中图分类号:

U492.4

席殷飞, 刘钟锴, 杨佩云, 郁烨, 张奇, 刘志远. 网约车出行需求预测方法[J]. 上海大学学报(自然科学版), 2020, 26(3): 328-341.

XI Yinfei, LIU Zhongkai, YANG Peiyun, YU Ye, ZHANG Qi, LIU Zhiyuan. Travel demand forecast methods for Internet private hire vehicles[J]. Journal of Shanghai University（Natural Science Edition）, 2020, 26(3): 328-341.

图/表 4

参考文献 79

[1]	梁婷婷. 智能出行平台下的城市出租车需求预测研究[D]. 长春: 吉林大学, 2016.
[2]	中商产业研究院. 中国网约车市场现状及发展前景研究报告 [EB/OL].[2018-03-23] https://www.askci.com/news/chanye/20180914/1600501132066_5.shtml.
[3]	Zheng Y, Capra L, Wolfson O, et al. Urban computing: concepts, methodologies, and applications[J]. ACM Transaction on Intelligent Systems and Technology, 2014,5(3):38.
[4]	林玉川. 移动智能出行平台用户行为研究[D]. 厦门: 厦门大学, 2014.
[5]	唐军. 基于系统动力学的城市网约车出行需求发展趋势研究[D]. 西安: 长安大学, 2017.
[6]	林园. 网约车条件下居民出行方式选择研究[D]. 成都: 西南交通大学, 2018.
[7]	高永, 安健. 网络约租车对出行方式选择及交通运行的影响[J]. 城市交通, 2016,14(5):1-8.
[8]	王一帆. 基于打车软件的出租车服务模式优化研究[D]. 上海: 上海交通大学, 2014.
[9]	黎景壮. 基于 QPSO_RBF 神经网络的网约车需求量预测模型[J]. 广西大学学报 (自然科学版), 2018,43(2):700-709.
[10]	贾兴无. 基于网约车数据的居民出行需求特征分析及需求预测[J]. 交通工程, 2018,18(5):39-45.
[11]	Dawes M. Perspectives on the ridesourcing revolution: surveying individual attitudes toward Uber and Lyft to inform urban transportation policymaking [D]. Cambridge, MA: Massachusetts Institute of Technology, 2016.
[12]	Farber H S. Why you cannot find a taxi in the rain and other labor supply lessons from cab drivers[J]. Quarterly Journal of Economics, 2014,130(4):1975-2026. doi: 10.1093/qje/qjv026
[13]	Zhang K F, Chen S. A framework for passengers demand prediction and recommen-dation[C]// IEEE International Conference on Services Computing. 2016: 340-347.
[14]	贺国光, 李宇, 马寿峰. 基于数学模型的短时交通流预测方法探讨[J]. 系统工程理论与实践, 2000(12):51-56.
[15]	Ahmed M S, Cook A R. Analysis of freeway traffic time-series data by using Box-Jenkins techniques[J]. Transportation Research Record, 1979,722:1-9.
[16]	Nihan N L, Holmesland K O. Use of the box and Jenkins time series technique in traffic forecasting[J]. Transportation, 1980,2(9):125-143.
[17]	Kim C, Hobeika A G. Short-term demand forecasting model from real-time traffic data[C]// Proceedings of the Infrastructure Planning and Management. 1993: 540-550.
[18]	王均, 关伟. 基于 Kalman 滤波的城市环路交通流短时预测研究[J]. 交通与计算机, 2006(5):16-19.
[19]	Chien S I, Kuchipudi C M. Dynamic travel time prediction with real-time and historic data[J]. Journal of Transportation Engineering, 2003,129(6):608-616. doi: 10.1061/(ASCE)0733-947X(2003)129:6(608)
[20]	杨高飞, 徐睿, 秦鸣, 等. 基于 ARMA 和卡尔曼滤波的短时交通预测[J]. 郑州大学学报 (工学版), 2017,2:36-40.
[21]	Jiang X, Adeli H. Dynamic wavelet neural network model for traffic flow forecasting[J]. Journal of Transportation Engineering, 2005,131(10):771-779. doi: 10.1061/(ASCE)0733-947X(2005)131:10(771)
[22]	曹征. 基于小波变换的交通流短时预测模型研究[D]. 北京: 北京交通大学, 2010.
[23]	Disbro J E, Frame M. Traffic flow theory and chaotic behavior[J]. Transportation Research Record Journal of the Transportation Research Board, 1989,1225:109-115.
[24]	张勇. 交通流的非线性分析、预测和控制[D]. 北京: 北京交通大学, 2011.
[25]	Forbes G J, Hall F L. The applicability of catastrophe theory in modelling freeway traffic operations[J]. Transportation Research Part A: General, 1990,24(5):335-344. doi: 10.1016/0191-2607(90)90046-9
[26]	唐铁桥, 黄海军. 用燕尾突变理论来讨论交通流预测[J]. 数学研究, 2005,38(1):112-116.
[27]	Davis G A, Nihan N L. Nonparametric regression and short-term freeway traffic forecasting[J]. Journal of Transportation Engineering, 1991,117(2):178-188. doi: 10.1061/(ASCE)0733-947X(1991)117:2(178)
[28]	丁涛杰. 基于GPS 数据的交通速度估计及短时预测研究[D]. 长沙: 国防科学技术大学, 2014.
[29]	Smith B L, Demetsky M J. Short-term traffic flow prediction: neural network approach[J]. Transportation Research Record, 1994,1453:98-104.
[30]	Dougherty M S, Cobbett M R. Short-term inter-urban traffic forecasts using neural networks[J]. International Journal of Forecasting, 1997,13(1):21-31.
[31]	Dia H. An object-oriented neural network approach to short-term traffic forecasting[J]. European Journal of Operational Research, 2001,131(2):253-261. doi: 10.1016/S0377-2217(00)00125-9
[32]	李松, 刘力军, 翟曼. 改进粒子群算法优化 BP 神经网络的短时交通流预测[J]. 系统工程理论与实践, 2012,32(9):2045-2049.
[33]	卢建中, 程浩. 改进 GA 优化 BP 神经网络的短时交通流预测[J]. 合肥工业大学学报 (自然科学版), 2015,38(1):127-131.
[34]	吕宏义. 基于支持向量回归机的路段平均速度短时预测方法研究[D]. 北京: 北京交通大学, 2008.
[35]	孙朝东, 梁雪春. 改进的花授粉算法优化 SVM 在交通流中的应用[J]. 计算机工程与设计, 2016,37(10):2717-2721.
[36]	Voort M V D, Dougherty M, Watson S. Combining kohonen maps with arima time series models to forecast traffic flow[J]. Transportation Research Part C:Emerging Technologies, 1996,4(5):307-318. doi: 10.1016/S0968-090X(97)82903-8
[37]	Liu H. The forecast of dynamic traffic flow[C]// International Conference on Traffic and Transportation Studies Traffic and Transportation Studies. 2000: 507-512.
[38]	谭满春, 李英俊, 徐建闽. 基于小波消噪的 ARIMA 与 SVM 组合交通流预测[J]. 公路交通科技, 2009,26(7):127-132.
[39]	Yu G, Hu J, Zhang C. Short-term traffic flow forecasting based on Markov chain model[C]// Proceedings of Intelligent Vehicles Symposium. 2003: 208-212.
[40]	Tan G, Shi H, Wang F. Short-term traffic flow prediction based on parallel quasi-newton neural network[C]// IEEE 2009 International Conference on Measuring Technology and Mechatronics Automation. 2009: 305-308.
[41]	刘芹, 徐建闽. 基于云模型的短时交通流预测方法研究[J]. 计算机工程与设计, 2012,33(5):1953-1957.
[42]	Moreira M L, Gama J, Feffeira M, et al. Predicting taxi-passenger demand using streaming data[J]. IEEE Transactions on Intelligent Transportation, 2013,14(3):1393-1402.
[43]	林永杰, 邹难. 基于运营系统的出租车出行需求短时预测模型[J]. 东北大学学报 (自然科学版), 2016 (9):1235-1240.
[44]	王芮. 基于 GPS 数据的城市出租车出行需求研究[D]. 济南: 山东大学, 2016.
[45]	Chiang M F, Hoang T A, Lim E P. Where are the passengers: a grid-based gaussian mixture model for taxi bookings[C]// Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. 2015: 1-10.
[46]	Deng D X, Shahabi C, Demiryurek U, et al. Latent space model for road networks to predict time-varying traffic[C]// Proceedings of the 22th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 1525-1534.
[47]	Tong Y, Chen Y, Zhou Z, et al. The simpler the better: a unified approach to predicting original taxi demands on large-scale online platforms[C]// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017: 1653-1662.
[48]	Nie Y. How can the taxi industry survive the tide of ride sourcing evidence from Shenzhen, China[J]. Transportation Research Part C: Emerging Technologies, 2017,79:242-256. doi: 10.1016/j.trc.2017.03.017
[49]	Yao H, Wu F, Ke J, et al. Deep multi-view spatial-temporal network for taxi demand prediction[J]. Machine Learning, 2018: 2588-2595.
[50]	Geng X, Li Y, Wang L, et al. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019,33:3656-3663. doi: 10.1609/aaai.v33i01.33013656
[51]	聂笃宪, 林健英, 林奕敏, 等. “互联网+”时代的出租车资源配置建模与分析[J]. 东莞理工学院学报, 2016,23(1):24-31.
[52]	樊文壮, 胡文力. 基于模糊分析的区域出租车资源紧缺程度评价研究[J]. 电脑知识与技术, 2016,12(7):158-159.
[53]	张娟, 何启明. “互联网+”出租车资源配置优化研究[J]. 自动化与仪器仪表, 2016(7):240-241.
[54]	刘嘉琪, 邹泞憾, 周梓楠, 等. 互联网时代出租车供需匹配及补贴方案确定[J]. 经济数学, 2016,33(2):103-110.
[55]	逯强, 张岩. 基于供需分析的城市网约车资源配置模型[J]. 牡丹江师范学院学报 (自然科学版), 2016,4(97):12-15.
[56]	朱家明, 刘玲, 孟康, 等. 基于AHP-熵值的不同时空出租车资源供求匹配研究: 以上海市为例[J]. 太原师范学院学报 (自然科学版), 2016,15(1):52-58.
[57]	陈文龙. 网约车模式下基于轨迹数据的出租汽车运力规模测算[D]. 西安: 长安大学, 2018.
[58]	Yang C, Gonzales E. Modeling taxi trip demand by time of day in New York[J]. Transportation Research Record Journal of the Transportation Research Board, 2014,2429:110-120. doi: 10.3141/2429-12
[59]	Daniel F G. Local exclusive cruising regulation and efficiency in taxicab markets[J]. Journal of Transport Economics and Policy, 2005,39(2):155-166.
[60]	杨英俊, 赵祥模. 基于小波神经网络的出租车保有量预测模型[J]. 公路交通科技, 2012,29(8):136-141. doi: 103969/jissn1002-0268201208023
[61]	李敏杰. 大型活动区域交通疏散模型及其应急策略研究[D]. 天津: 天津工业大学, 2009.
[62]	章辉. 大型活动交通需求预测和疏散方案研究[D]. 武汉: 武汉理工大学, 2007.
[63]	John B. Strategic transport planning, demand analysis of transport infrastructure and transport services for the 27th summer Olympiad held in Sydney[J]. Journal of Transportation Engineering and Information, 2004,2(2):14-30.
[64]	Latoski S P, Dunn W M, Wagenblast B. Managing travel for planned special events[J]. Special Events, 2003,11:14.
[65]	王晓光, 耿玲虹, 赵锋. 城市大型活动中的交通需求与疏散分析[J]. 交通科技与经济, 2009(4):10-13.
[66]	赵跃萍. 大型活动事件下的城市交通需求预测方法研究[D]. 武汉: 武汉理工大学, 2008.
[67]	赵会珍, 郝力文, 李中山. 城市大型活动交通需求预测研究[J]. 物流技术, 2014,33(19):305-307.
[68]	Yang C, Gonzales E. Modeling taxi trip demand by time of day in New York[J]. Transportation Research Record Journal of the Transportation Research Board, 2014,2429:110-120. doi: 10.3141/2429-12
[69]	Tseng P J, Hung C C, Chang T H, et al. Real-time urban traffic sensing with GPS equipped Probe Vehicles[C]// International Conference on ITS Telecommunications. 2013: 306-310.
[70]	孙贵治. 基于出租车 GPS 轨迹数据的热点区域出行需求预测[D]. 北京: 北京交通大学, 2019.
[71]	陈红丽. 基于出租车 GPS 数据的居民出行时空规律和出行热点区域研究[D]. 昆明: 云南大学, 2016.
[72]	Ashbrook D S T. Using GPS to learn significant locations and predictmovement across multiple users[J]. Personal and Ubiquitous Computing, 2003,7(5):275-286. doi: 10.1007/s00779-003-0240-0
[73]	Gong L S, Yamamoto T. Identification of activity stop locations in GPS trajectories by density-based clustering method combined with support vector machines[J]. Journal of Modern Transportation, 2015,23(3):202-213. doi: 10.1007/s40534-015-0079-x
[74]	Zong F, Bai Y, Wang X, et al. Identifying travel mode with GPS data using support vector machines and genetic algorithm[J]. Information, 2015,6:212-227. doi: 10.3390/info6020212
[75]	李追日. 基于手机定位数据的城市道路交通需求推估及分析[D]. 北京: 北京大学, 2016.
[76]	邓博. 基于手机 App 调查数据的出行信息提取方法研究[D]. 武汉: 武汉理工大学, 2018.
[77]	余琳玲. 基于移动通信数据的城市行人定位及出行方式分析[D]. 北京: 北京邮电大学, 2018.
[78]	张晓鹏. 基于多源数据融合的城市出行需求预测方法研究[D]. 长春: 吉林大学, 2018.
[79]	张凯. 乘客出行预测与推荐方法研究[D]. 天津: 天津大学, 2017.