共享单车用户骑行起讫点时空特征分析

李福; 徐良杰; 陈国俊; 朱然博

doi:10.3963/j.jssn.1674-4861.2022.03.015

共享单车用户骑行起讫点时空特征分析

doi: 10.3963/j.jssn.1674-4861.2022.03.015

李福^1,,
徐良杰^{1, 2, ,},
陈国俊¹,
朱然博¹

1.
武汉理工大学交通与物流学院武汉 430063
2.
湖北文理学院汽车与交通工程学院湖北襄阳 441053

基金项目:

国家自然科学基金项目 71701159

武汉理工大学自主创新研究基金项目 205202003

详细信息

作者简介:
李福（1998—），硕士研究生. 研究方向：交通大数据分析与管理. E-mail：532900131@qq.com

通讯作者:
徐良杰（1968—），博士，教授. 研究方向：交通运输规划与管理、交通流与管控等.E-mail：laurrie119@163.com

中图分类号: U491.2+6
计量
- 文章访问数: 878
- HTML全文浏览量: 318
- PDF下载量: 49
- 被引次数: 0
出版历程
- 收稿日期: 2020-12-23
- 网络出版日期: 2022-07-25

An Analysis of Spatial-temporal Characteristics of Origin and Destination of Shared-bike Users

LI Fu^1
,,
XU Liangjie^{1, 2
, ,},
CHEN Guojun¹,
ZHU Ranbo¹

1.
School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430063, China
2.
School of Automotive and Traffic Engineering, Hubei University of Arts and Science, Xiangyang 441053, Hubei, China

摘要

摘要: 针对共享单车的供需失衡、分布不均问题，研究了共享单车用户骑行起讫点的聚集区分布以及不同区域的骑行时间特征，为共享单车的调度运营提供理论支撑。基于用户的骑行订单数据，采用均值漂移算法对骑行起讫点进行聚类学习，得到共享单车的骑行聚集区分布；随后采用spearman相关系数来衡量骑行时间特征的相似度，对不同骑行聚集区的借车与还车量的累计差值的时间序列曲线进行聚类处理，划分出6类典型的骑行特征，并对不同骑行特征所在地的兴趣点（POI）进行因子分析，结果表明：在空间上，共享单车的骑行聚集区的空间分布与所在区域的城市路网的布局形式存在较大关联，不同时间段的骑行聚集区的分布大致相同，仅在出行量上存在差异。骑行聚集区的骑行特征与土地利用性质之间存在相关性，例如，对于骑行特征为1天内借车量小于还车量的骑行聚集区，其主导因子为商业用地，占比为0.4；对于1天内用户的借车量大于还车量的骑行聚集区，其主导因子为住宅用地，占比为0.57。多种用地性质混合的区域，借还车的差值较小且易产生波动。此外，同一类型的骑行时间特征的主导因子占比在工作日与非工作日会产生变化，同一区域的骑行时间特征在工作日与非工作日存在差异。
- 城市交通 /
- 共享单车 /
- 出行OD /
- 空间聚类 /
- 时间聚类
Abstract: In a view of the frequent imbalance between supply and demand and uneven distribution of shared bikes over space, this paper studies the origin-destination distribution of shared-bike users and the temporal characteristics of riding demand in different areas, so as to provide theoretical support for dispatch operations of shared-bike systems. Based on riding data of users, the mean-shift algorithm is used to cluster the origin and destination points of riding, and the distribution of areas with a high riding record is obtained. Then, Spearman correlation coefficient is used to measure the similarity of temporal characteristics of riding demand. Six typical temporal characteristics of riding demand are extracted by clustering the temporal cumulative differences between the volumes of rented and returned bikes in different areas. The relationship between temporal characteristics of riding demand and land use (represented by point of interest, POI)is studied by factor analysis. The results show that the spatial distribution of aggregation areas of shared bikes is basically correlated to the spatial pattern of the urban road network in the area. There is little variation for the distribution of aggregation areas in different time periods, and the only difference is the volume of bike riding in different areas. Besides, it shows that temporal characteristics of riding demand and land use are related. Commercial land use is the dominating factor for the areas where the number of rented bicycles is less than that of returned bicycles in one day, which accounts for 40% of the total. For the areas where the number of rented bicycles is larger than that of returned bicycles in one day, residential land use is the dominating factor, accounting for 57% of the total. In areas with mixed land use, the difference between bicycle renting and returning is small and prone to fluctuate. In addition, the proportion of dominant factors of a temporal characteristics of riding demand may change between weekday and weekend, and the temporal characteristics of riding demand in a region are different between weekday and weekend.
- urban transportation /
- shared-bike /
- travel OD /
- spatial clustering /
- temporal clustering

HTML全文

图 1 骑行起点与其最近的第50个点的距离分布曲线

Figure 1. The distance distribution curve between the starting point of riding and its nearest 50th point

下载: 全尺寸图片幻灯片

图 2 骑行起讫点的聚类结果

Figure 2. Clustering results of starting and ending points of riding

下载: 全尺寸图片幻灯片

图 3 聚类结果

Figure 3. Clustering results of working days and non-working days, peak and average peak

下载: 全尺寸图片幻灯片

图 4 不同类型POI区域的平均每日出行量

Figure 4. Average daily trips in different types of POI areas

下载: 全尺寸图片幻灯片

图 5 6类典型的时间序列曲线

Figure 5. Six typical time series curves

下载: 全尺寸图片幻灯片

图 6 不同骑行时间特征的初始特征值方差占比

Figure 6. Proportion of variance of initial eigenvalues of different riding temporal characteristics

下载: 全尺寸图片幻灯片

图 7 借少还多型区域的非工作日骑行特征

Figure 7. Riding characteristics of non-working days in the area of "borrowing less and repaying more"

下载: 全尺寸图片幻灯片

图 8 借少还多型区域的非工作日骑行特征

Figure 8. Riding characteristics of non-working days in the area of"borrowing less and repaying more"

下载: 全尺寸图片幻灯片

图 9 先还后借型、先借后还型区域的非工作日骑行特征

Figure 9. Riding characteristics of non-working days in the areas of"return before borrowing"and "borrowing before returning"

下载: 全尺寸图片幻灯片

图 10 借少波动型、借多波动型区域的非工作日骑行特征

Figure 10. The characteristics of non-working day riding in the area of "borrowing less with volatility" and "borrowing more with volatility"

下载: 全尺寸图片幻灯片

表 1 用户订单数据集包含的内容及格式

Table 1. Content and format of user order data set

订单编号	用户编号	单车编号	单车类型	起始时间	起点位置	终点位置
1893973	451147	210617	2	2017-05-14 22：16：50	wx4snhx	wx4snhj
4657992	1061133	465394	1	2017-05-14 22：16：52	wx4dr59	wx4dquz
2965085	549189	310572	1	2017-05-14 22：16：51	wx4fgur	wx4fu5n
$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $	$ \vdots $

下载: 导出CSV

表 2 骑行时间特征所对应的骑行聚集区域位置

Table 2. The location of riding gathering area corresponding to riding time characteristics

骑行时间特征	骑行聚集区域位置
借少还多型	万国城MOMA、胡大饭馆、四季明福烤鸭店、当代MOMA、地坛公园、后现代城、北京电子科技职业学院、北京市第二十二中学、华彬中心、庆丰公园、北京中医药大学（西校区）、北京工业大学附属中学
借多还少型	铁路宿舍1号楼、长途兴物业小区、三源里南小街小区、惠新里社区、建外soho西区、呼家楼街道呼北小区、和平里街道地坛社区-花园小区、人民日报社住宅楼、樱花园小区、麦子店小区、东郊民巷32号院、东山墅、呼家楼南公交站、胜古北里、金台里
先还后借型	地铁国贸站、地铁东四站、地铁四惠站、北京东站北、京师律师大厦、新加坡大使馆、关东店公交站、北京市燃气集团、三宇大厦、太阳宫公园、国贸DNA写字楼、地铁永安里站、北京市社会事业合作开发服务中心、北京市市政工程管理处第二管理所、圣英商务中心、朝内小街
先借后还型	红北社区、英国大使馆、丽都苑、东大桥地铁站、东十四条地铁站、东直门地铁站、第二单身宿舍、呼家楼西里、全国农业展览馆、新中西里社区、四得公园、新源里小区、朝阳区财政局、浩鸿园、明城墙遗址公园、金台路北
借少波动型	北三条10-1、呼家楼西里南街、北京中医药大学、健安东路、北京市民政局、西园、三阳居四季涮肉、北京国际饭店、工体西路5号楼、东河沿小区、朝阳公园、清华附中朝阳学校
借多波动型	中国国际展览中心、北京中医药大学（东校区）、地铁东单站、中纺里社区、东方新天地、全国农业展览馆、农丰里小区、北新桥小学、司法部、爱家国际商业中心、怡思苑、朝阳区道路养护中心、北京惠通万利商业管理有限公司、北京国贸

下载: 导出CSV

参考文献(22)

[1]	王光荣. 共享单车发展问题系统探究[J]. 长安大学学报(社会科学版), 2017, 19(2): 30-35. doi: 10.3969/j.issn.1671-6248.2017.02.005 WANG G R. Systematic research on bicycle-sharing development[J]. Journal of Chang'an University(Social Science Edition), 2017, 19(2): 30-35. (in Chinese) doi: 10.3969/j.issn.1671-6248.2017.02.005
[2]	HAMILTON T L, WICHMAN C J. Bicycle infrastructure and traffic congestion: Evidence from DC's capitalbikeshare[J]. Journal of Environmental Economics and Management, 2018 (87): 72-93.
[3]	CAMPBELL K B, BRAKEWOOD C. Sharing riders: How bikesharing impacts bus ridership in New York City[J]. Transportation Research Part A: Policy and Practice, 2017(100): 264-282.
[4]	MATEO-BABIANO I, KUMAR S, MEJIA A. Bicyclesharing in Asia: A stakeholder perception and possible futures[J]. Transportation Research Procedia, 2017(25): 4970-4982.
[5]	袁朋伟, 董晓庆, 翟怀远, 等. 基于Nested Logit模型的共享单车选择行为研究[J]. 交通运输系统工程与信息, 2018, 18 (5): 191-196+210. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201805028.htm YUAN PW, DONG X Q, ZHAI H Y et al. Choice behavior of bike-sharing based on nested logit model[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 191-196+210. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201805028.htm
[6]	ZHANG Y, THOMAS T, BRUSSEL M, et al. Exploring the impact of built environment factors on the use of public bikes at bike stations: Case study in Zhongshan, China[J]. Journal of Transport Geography, 2017(58): 59-70.
[7]	ZHAO D, ONG G P, WANG W, et al. Effect of built environment on shared bicycle reallocation: A case study on Nanjing, China[J]. Transportation Research Part A: Policyand Practice, 2019(128): 73-88.
[8]	TANG Y, PAN H, FEI Y. Research on users' frequency of ride in Shanghai Minhang bike-sharing system[J]. Transportation Research Procedia, 2017(25): 4983-4991.
[9]	HANDY S, BOARNET M, EWING R, et al. How the built environment affects physical activities: views from urban planning[J]. American Journal of Preventive Medicine, 2002(2): 64-73.
[10]	EL-ASSI W, MAHMOUD M S, HABIB K N. Effects of built environment and weather on bike sharing demand: A stationlevel analysis of commercial bike sharing in Toronto[J]. Transportation, 2017, 44(3): 589-613. doi: 10.1007/s11116-015-9669-z
[11]	MENG M, ZHANG J, WONG Y D, et al. Effect of weather conditions and weather forecast on cycling travel behavior in Singapore[J]. International Journal of Sustainable Transportation, 2016, 10(9): 773-780. doi: 10.1080/15568318.2016.1149646
[12]	徐家红, 周继彪, 马昌喜, 等. 基于二元有序概率的共享单车满意度评估方法[J]. 交通信息与安全, 2021, 39(3): 136-141+151. doi: 10.3963/j.jssn.1674-4861.2021.03.017 XU J H, ZHOU J B, MA C X, et al. An evaluation method for bicycle sharing satisfaction based on a bivariateordered probit model[J]. Journal of Transport Information and Safety, 2021, 39(3): 136-141+151. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2021.03.017
[13]	李兴华, 张昕源, 成诚, 等. 考虑移步需求的无桩型共享单车动态调度研究[J]. 交通运输系统工程与信息, 2020, 20 (3): 182-189. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202003029.htm LI X H, ZHANG X Y, CHENG C, et al. Dynamic repositioning model for free-floating bike sharing system considering shifting demand[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3): 182-189. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202003029.htm
[14]	蒋塬锐, 贾顺平, 李军. 基于调度池的共享单车调度研究[J]. 交通信息与安全, 2019, 37(5): 124-132. doi: 10.3963/j.issn.1674-4861.2019.05.016 JIANG Y R, JIA S P, LI J. A study of bicycle-sharing scheduling based on scheduling pool[J]. Journal of Transport Information and Safety, 2019, 37(5): 124-132. (in Chinese) doi: 10.3963/j.issn.1674-4861.2019.05.016
[15]	孙启鹏, 曾开邦, 张锴琦, 等. 北京市共享单车出行的时空规律与需求预测研究[J]. 交通运输系统工程与信息, 2022, 22(1): 332-338. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202201035.htm SUN Q P, ZENG K B, ZHANG K Q, et al. Spatiotemporal travel patterns and demand prediction of shared bikes in Beijing[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1): 332-338. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202201035.htm
[16]	曹旦旦, 范书瑞, 张艳, 等. 基于长短期记忆神经网络模型的共享单车短时需求量预测[J]. 科学技术与工程, 2020, 20 (20): 8344-8349. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202020050.htm CAO D D, FAN S R, ZHANG Y, et al. Short-term demand forecasting of shared bicycles based on long short-term memory neural network model[J]. Science Technology and Engineering, 2020, 20(20): 8344-8349. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202020050.htm
[17]	李福, 徐良杰, 朱然博, 等. 基于XGBoost算法的共享单车借车需求量预测[J]. 武汉理工大学学报(交通科学与工程版), 2021, 45(5): 880-884. doi: 10.3963/j.issn.2095-3844.2021.05.013 LI F, XU L J, ZHU R B, et al. Study on demand forecasting of rental volume of bike-sharing based on XGBoost algorithm[J]. Journal of Wuhan University of Technology(Transportation Sicence & Engineering), 2021, 45(5): 880-884. (in Chinese) doi: 10.3963/j.issn.2095-3844.2021.05.013
[18]	邓力凡, 谢永红, 黄鼎曦. 基于骑行时空数据的共享单车设施规划研究[J]. 规划师, 2017, 33(10): 82-88. doi: 10.3969/j.issn.1006-0022.2017.10.015 DENG L F, XIE Y H, HUANG D X. Bicycle-sharing facility planning base on riding spatio-temporal data[J]. Planners, 2017, 33(10): 82-88. (in Chinese) doi: 10.3969/j.issn.1006-0022.2017.10.015
[19]	杨永崇, 柳莹, 李梁. 利用共享单车大数据的城市骑行热点范围提取[J]. 测绘通报, 2018(8): 68-37. https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201808014.htm YANG Y C, LIU Y, LI L. Urban cycling hot spot extraction based on sharing-bikes' big data[J]. Bulletin of Surveying and Mapping, 2018(8): 68-37. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201808014.htm
[20]	高楹, 宋辞, 郭思慧, 等. 接驳地铁站的共享单车源汇时空特征及其影响因素[J]. 地球信息科学学报, 2021, 23(1): 155-170. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX202101017.htm GAO Y, SONG C, GUO S H, et al. Spatial-temporal characteristics and influencing factors of source and sink of docklesssharing bicycles connected to subway stations[J]. Journal of Geo-information Science, 2021, 23(1): 155-170. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX202101017.htm
[21]	高向东, 黎扬进, 刘秀航, 等. 改进均值漂移算法的焊缝特征点识别分析[J]. 华南理工大学学报(自然科学版), 2019, 47(4): 132-137. https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG201904019.htm GAO X D, LI Y J, LIU X H, et al. Weld seam feature point recognition analysis based on improved mean-shift algorithm[J]. Journal of South China University of Technology (Natural Science Edition), 2019, 47(4): 132-137. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HNLG201904019.htm
[22]	梁吉业, 冯晨娇, 宋鹏. 大数据相关分析综述[J]. 计算机学报, 2016, 39(1): 1-18. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201601001.htm LIANG JY, FENG CJ, SONG P. A Survey on correlation analysis of big data[J]. Chinese Journal of Computers, 2016, 39(1): 1-18. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201601001.htm