基于手机信令数据的城市居民非通勤出行群体画像——以苏州市为例

doi:10.13249/j.cnki.sgs.2022.10.005

地理科学 ›› 2022, Vol. 42 ›› Issue (10): 1727-1734.doi: 10.13249/j.cnki.sgs.2022.10.005

基于手机信令数据的城市居民非通勤出行群体画像——以苏州市为例

付晓¹(), 陈梓丹¹, 黄洁²

1.东南大学交通学院，江苏南京 211189
2.中国科学院地理科学与资源研究所中国科学院区域可持续发展分析与模拟重点实验室，北京 100101

收稿日期:2021-10-19 修回日期:2022-02-15 接受日期:2022-07-15 发布日期:2022-10-20 出版日期:2022-10-30
作者简介:付晓（1988−），女，安徽蚌埠人，博士，副教授，主要从事居民活动与出行行为、多模式交通网络建模及交通大数据研究。E-mail: fuxiao@seu.edu.cn
基金资助:
教育部人文社会科学研究青年基金项目(21YJC790030);国家自然科学基金项目(42171403);东南大学至善青年学者支持计划(2242021R41162)

Non-work Travel Group Profiles of Urban Residents Based on Mobile Phone Signaling Data: A Case of Suzhou

Fu Xiao¹(), Chen Zidan¹, Huang Jie²

1. School of Transportation, Southeast University, Nanjing 211189, Jiangsu, China
2. Key Laboratory of Regional Sustainable Development Modeling, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China

Received:2021-10-19 Revised:2022-02-15 Accepted:2022-07-15 Online:2022-10-20 Published:2022-10-30
Supported by:
Humanities and Social Science Fund of Ministry of Education of the People's Republic of China(21YJC790030);National Natural Science Foundation of China(42171403);"Zhishan" Scholars Programs of Southeast University(2242021R41162)

摘要/Abstract

摘要：

构建考虑多维特征的城市居民非通勤出行群体画像概念模型，提出一种按序结合相关系数矩阵与二阶聚类的方法，以进行非通勤出行群体画像。利用苏州市手机信令数据，基于非通勤出行时空规律和社会属性将城市居民出行者进行群体划分，并结合城市居民非通勤出行群体画像概念模型对不同类型非通勤出行群体进行多维度解析。结果显示：① 城市居民出行者可划分为：活跃?波动?工作日主导型群体、非活跃?稳定?均衡型群体。② 不同类型非通勤出行群体画像在多维特征上存在显著差异。③ 根据群体画像标签关联分析，除显性关联外，群体画像不同标签间存在隐性关联。

关键词: 非通勤出行, 群体画像, 二阶聚类, 隐性标签关联, 大数据

Abstract:

A conceptual model of non-work travel group profile for urban residents is proposed in this paper, and a sequential combination of correlation coefficient matrix and two-step clustering method is applied to constructing the non-work travel group profiles. In the case study, using Suzhou mobile phone signaling data, the urban travelers are grouped based on spatiotemporal non-work travel information and social attributes. Combined with the conceptual model of non-work travel group profile, a detailed discussion on the group profiles of different types of non-work travelers is given. Results show that the urban travelers can be divided into two groups: active-fluctuating-workday oriented group and inactive-stable-balanced group. Significant differences exist in multi-dimensional features among different types of non-work travel group profiles. The association analysis of group profile labels shows that, in addition to the explicit association, there are implicit associations between different labels of group profile.

Key words: non-work travel, group profile, two-step clustering method, implicit label association, big data

中图分类号:

K901.2

付晓, 陈梓丹, 黄洁. 基于手机信令数据的城市居民非通勤出行群体画像——以苏州市为例[J]. 地理科学, 2022, 42(10): 1727-1734.

Fu Xiao, Chen Zidan, Huang Jie. Non-work Travel Group Profiles of Urban Residents Based on Mobile Phone Signaling Data: A Case of Suzhou[J]. SCIENTIA GEOGRAPHICA SINICA, 2022, 42(10): 1727-1734.

图/表 7

表1

图1

表2

表3

表4

图2

图3

参考文献 35

[1]	张文尝, 王成金, 马清裕. 中国城市居民出行的时空特征及影响因素研究[J]. 地理科学, 2007, 27(6): 737-742. doi: 10.3969/j.issn.1000-0690.2007.06.001
	Zhang Wenchang, Wang Chengjin, Ma Qingyu. Spatial-temporal characteristics of urban resident trips and influence factors in China. Scientia Geographica Sinica, 2007, 27(6): 737-742. doi: 10.3969/j.issn.1000-0690.2007.06.001
[2]	Curl A, Davison L. Transport Geography: Perspectives upon entering an accomplished research sub-discipline[J]. Journal of Transport Geography, 2014, 38: 100-105. doi: 10.1016/j.jtrangeo.2014.05.018
[3]	杨励雅, 王振波. 城市社区建成环境对居民日常出行行为的影响分析[J]. 经济地理, 2019, 39(4): 101-108. doi: 10.15957/j.cnki.jjdl.2019.04.013
	Yang Liya, Wang Zhenbo. Impact of residential built environment on daily travel behavior. Economic Geography, 2019, 39(4): 101-108. doi: 10.15957/j.cnki.jjdl.2019.04.013
[4]	Malik J, Bunch D S, Handy S et al. A deeper investigation into the effect of the built environment on the use of ridehailing for non-work travel[J]. Journal of Transport Geography, 2021, 91: 102952 doi: 10.1016/j.jtrangeo.2021.102952
[5]	Etminani Ghasrodashti R, Ardeshiri M. The impacts of built environment on home-based work and non-work trips: An empirical study from Iran[J]. Transportation Research Part A:Policy and Practice, 2016, 85: 196-207. doi: 10.1016/j.tra.2016.01.013
[6]	Huang A, Levinson D. Axis of travel: Modeling non-work destination choice with GPS data[J]. Transportation Research Part C:Emerging Technologies, 2015, 58: 208-223. doi: 10.1016/j.trc.2015.03.022
[7]	马静, 柴彦威, 张文佳. 北京市居民购物出行影响因素的空间分异[J]. 经济地理, 2009, 29(12): 2006-2011. doi: 10.15957/j.cnki.jjdl.2009.12.001
	Ma Jing, Chai Yanwei, Zhang Wenjia. A study on shopping behaviour of Beijing residents: The spatial differentiation of influencing factors. Economic Geography, 2009, 29(12): 2006-2011. doi: 10.15957/j.cnki.jjdl.2009.12.001
[8]	Li J, Kim C, Sang S. Exploring impacts of land use characteristics in residential neighborhood and activity space on non-work travel behaviors[J]. Journal of Transport Geography, 2018, 70(C): 141-147.
[9]	张杰, 陈骁. 家庭非通勤出行能耗影响机制——住区视角下的结构方程模型分析[J]. 城市发展研究, 2016, 23(3): 87-94. doi: 10.3969/j.issn.1006-3862.2016.03.013
	Zhang Jie, Chen Xiao. Influencing mechanism of household non-commuting travel energy: An application of structural equation model in a perspective of neighborhood form. Urban Development Studies, 2016, 23(3): 87-94. doi: 10.3969/j.issn.1006-3862.2016.03.013
[10]	Hou Y. Polycentric urban form and non-work travel in Singapore: A focus on seniors [J]. Transportation Research Part D: Transport and Environment, 2019, 73:245-275.
[11]	隽志才. 非工作活动生成和分配模式研究[J]. 交通运输系统工程与信息, 2011, 11(4): 124-128. doi: 10.3969/j.issn.1009-6744.2011.04.019
	Jun Zhicai. Generation and organization of household non-work activity stops. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(4): 124-128. doi: 10.3969/j.issn.1009-6744.2011.04.019
[12]	Martinson R J. Non-work travel characteristics in Calgary with a focus on trips made on foot and by bicycle [D]. Calgary: Graduate Studies, 2014.
[13]	张艳, 柴彦威. 北京城市中低收入者日常活动时空间特征分析[J]. 地理科学, 2011, 31(9): 1056-1064. doi: 10.13249/j.cnki.sgs.2011.09.005
	Zhang Yan, Chai Yanwei. The spatio-temporal activity pattern of the middle and the low-income residents in Beijing, China. Scientia Geographica Sinica, 2011, 31(9): 1056-1064. doi: 10.13249/j.cnki.sgs.2011.09.005
[14]	Fu X, Lam W H. Modelling joint activity-travel pattern scheduling problem in multi-modal transit networks[J]. Transportation, 2018, 45(1): 23-49. doi: 10.1007/s11116-016-9720-8
[15]	许熳灵, 付晓, 汤君友, 等. 天气因素对城市地铁客流时空分布的影响——基于智能交通卡数据的实证研究[J]. 地理科学进展, 2020, 39(1): 45-55. doi: 10.18306/dlkxjz.2020.01.005
	Xu Manling, Fu Xiao, Tang Junyou et al. Effects of weather factors on the spatial and temporal distributions of metro passenger flows: An empirical study based on smart card data. Progress in Geography, 2020, 39(1): 45-55. doi: 10.18306/dlkxjz.2020.01.005
[16]	Cufoglu A. User profiling—A short review[J]. International Journal of Computer Applications, 2014, 108(3): 1-9. doi: 10.5120/18888-0179
[17]	宋美琦, 陈烨, 张瑞. 用户画像研究述评[J]. 情报科学, 2019, 37(4): 171-177. doi: 10.13833/j.issn.1007-7634.2019.04.027
	Song Meiqi, Chen Ye, Zhang Rui. A review of user profile research. Information Science, 2019, 37(4): 171-177. doi: 10.13833/j.issn.1007-7634.2019.04.027
[18]	Mostafa M M, El-Masry A A. Citizens as consumers: Profiling e-government services’ users in Egypt via data mining techniques[J]. International Journal of Information Management, 2013, 33(4): 627-641. doi: 10.1016/j.ijinfomgt.2013.03.007
[19]	De Andrés J, Pariente B, Gonzalez-Rodriguez M et al. Towards an automatic user profiling system for online information sites: Identifying demographic determining factors[J]. Online Information Review, 2015, 39(1): 61-80. doi: 10.1108/OIR-06-2014-0134
[20]	Manley E, Zhong C, Batty M. Spatiotemporal variation in travel regularity through transit user profiling[J]. Transportation, 2018, 45(3): 703-732. doi: 10.1007/s11116-016-9747-x
[21]	林燕霞, 谢湘生. 基于社会认同理论的微博群体用户画像[J]. 情报理论与实践, 2018, 41(3): 142-148. doi: 10.16353/j.cnki.1000-7490.2018.03.027
	Lin Yanxia, Xie Xiangsheng. User portrait of diversified groups in micro-blog based on social identity theory. Information Studies: Theory & Application, 2018, 41(3): 142-148. doi: 10.16353/j.cnki.1000-7490.2018.03.027
[22]	Grison E, Gyselinck V, Burkhardt J M. Exploring factors related to users’ experience of public transport route choice: Influence of context and users profiles[J]. Cognition, Technology & Work, 2016, 18(2): 287-301.
[23]	Grison E, Burkhardt J M, Gyselinck V. How do users choose their routes in public transport? The effect of individual profile and contextual factors[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2017, 51: 24-37. doi: 10.1016/j.trf.2017.08.011
[24]	Agard B, Morency C, Trépanier M. Mining public transport user behaviour from smart card data[J]. IFAC Proceedings Volumes, 2006, 39(3): 399-404.
[25]	Rudloff C, Ray M. Detecting travel modes and profiling commuter habits solely based on GPS data [R]. Washington: Transportation Research Board 89th Annual Meeting, 2010.
[26]	黄文彬, 徐山川, 吴家辉, 等. 移动用户画像构建研究[J]. 现代情报, 2016, 36(10): 54-61. doi: 10.3969/j.issn.1008-0821.2016.10.009
	Huang Wenbin, Xu Shanchuan, Wu Jiahui et al. The profile construction of the mobile user. Journal of Modern Information, 2016, 36(10): 54-61. doi: 10.3969/j.issn.1008-0821.2016.10.009
[27]	郭继孚, 孙建平, 温慧敏, 等. 基于车载 OBD 数据的小汽车出行特征分析——以北京市为例[J]. 城市交通, 2017, 15(5): 70-77.
	Guo Jifu, Sun Jianping, Wen Huimin et al. Analysis of car travel feature based on on-board OBD data —Taking Beijing as an example. Urban Transport of China, 2017, 15(5): 70-77.
[28]	Li W, Li Y, Ban X et al. Exploring the relationships between the non-work trip frequency and accessibility based on mobile phone data[J]. Transportation Research Record, 2018, 2672(42): 91-102. doi: 10.1177/0361198118774170
[29]	王岩, 范子贤, 李成名, 等. 利用手机信令数据刻画不同人物画像[J]. 测绘通报, 2021, 1(1): 84 doi: 10.13474/j.cnki.11-2246.2021.0015
	Wang Yan, Fan Zixian, Li Chengming et al. Portraying of different characters based on mobile phone signaling data. Bulletin of Surveying and Mapping, 2021, 1(1): 84 doi: 10.13474/j.cnki.11-2246.2021.0015
[30]	Chiu T, Fang D, Chen J et al. A robust and scalable clustering algorithm for mixed type attributes in large database environment[C]// Doheon Lee. Proceedings of the seventh ACM SIGKDD international conference on knowledge discovery and data mining. New York: Association for Computing Machinery, 2001.
[31]	Rousseeuw P J. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20: 53-65. doi: 10.1016/0377-0427(87)90125-7
[32]	Salkind N J, Rainwater T. Exploring research [M]. New Jersey: Pearson Prentice Hall Upper Saddle River, NJ, 2006.
[33]	苏州市统计局, 国家统计局苏州调查队. 苏州统计年鉴(2020)[M]. 北京: 中国统计出版社, 2020.
	Suzhou Municipal Bureau of Statistics, Suzhou Survey Team of National Bureau of statistics. Suzhou statistical yearbook (2020). Beijing: China Statistics Press, 2020.
[34]	Wen J, Wei L, Zhou W et al. GCN-IA: User profile based on graph convolutional network with implicit association labels; Proceedings of the International Conference on Computational Science, F, 2020 [C]// Valeria V Krzhizhanovskaya. Computational Science – ICCS 2020. Amsterdam: Springer Cham, 2020.
[35]	Wei L, Zhou W, Wen J et al. MLP-IA: Multi-label user profile based on implicit association labels; Proceedings of the International Conference on Computational Science, F, 2019 [C]//João M F Rodrigues. Computational Science – ICCS 2019. Amsterdam: Springer Cham, 2019.

全球标识	位置区	基站编号	通讯时刻	经度	纬度
460****28	w****8	w****dbf	14:06:01	120°'92"	31°'75"
460****29	w****8	w****8pt	14:06:03	120°'03"	31°'93"
460****30	w****8	w****fnr	14:06:07	120°'87"	31°'20"

属性	标签	含义	分类
人口属性	性别	用户性别	男、女
	年龄段	用户年龄段	未成年、青年、中年、老年
	职业	用户职业	职业类别
位置属性	居住地行政区	用户居住地所在的行政区	根据研究区域行政区划进行分类
出行活跃度	出行频率	调查周期内日平均出行频率	高频、中频、低频
	出行时长	调查周期内日平均出行时长	长时、中时、短时
	出行距离	调查周期内日平均出行距离	长距离、中距离、短距离
出行规律性	出行稳定性	调查周期内日出行频次标准差	稳定型、波动型
出行规律性	工休出行差异	根据工作日非通勤出行频次日均值与休息日非通勤出行频次日均值作差所得	工作日主导型、均衡型、节假日主导型
出行习惯及偏好	出行时段	由用户出行频次占比最高的时段反映/时	0~7、7~9、9~12、12~17、17~19、19~24
	出行方式	由用户出行频次占比最高的出行方式反映	慢行、汽车、地铁
	主导活动	根据用户停留点POI属性及停留时间，假定用户停留时间最长的停留点POI属性为该用户的主导活动	公司企业、餐饮服务、交通设施服务（主要为公共交通）等14类

变量	性别	年龄段	职业	居住地行政区	出行频率	出行时长	出行距离	出行稳定性	工休出行差异	主导活动
性别	1.000	0.058	−0.021	0.022	−0.013	−0.010	0.004	0.012	−0.019	−0.038
年龄段		1.000	−0.010	0.013	0.009	0.011	0.043	0.024	−0.008	−0.021
职业			1.000	−0.015	−0.005	0.017	−0.003	−0.010	0.013	0.028
居住地行政区				1.000	−0.010	0.004	0.004	0.032	−0.014	0.024
出行频率					1.000	0.726	0.640	0.573	−0.210	0.012
出行时长						1.000	0.370	0.414	−0.220	0.002
出行距离							1.000	0.471	−0.130	−0.018
出行稳定性								1.000	−0.257	−0.032
工休出行差异									1.000	0.021
主导活动										1.000

编号	性别	年龄	职业	居住地经度(E)	居住地纬度(N)	日均出行时长/min	日均出行距离/km	出行频率/ (次/d)	出行频次方差	工休出行均值差	主导活动
1	男	31	其他行业	120°30'12"	31°10'30"	66.201	20.440	0.250	0.548	0.017	公司企业
2	男	29	餐饮业	120°44'44"	31°39'20"	15.554	2.906	0.125	0.447	0.008	餐饮服务
3	男	55	其他行业	120°31'12"	31°14'42"	20.036	7.599	1.750	2.915	−0.021	公司企业

基于手机信令数据的城市居民非通勤出行群体画像——以苏州市为例

Non-work Travel Group Profiles of Urban Residents Based on Mobile Phone Signaling Data: A Case of Suzhou

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 35

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	牛强, 盛嘉菲, 刘晓阳, 严雪心. 武汉市商业和公共服务设施对居民迁居的空间异质性影响[J]. 地理科学, 2023, 43(5): 860-868.
[2]	张文佳, 王雨润, 阴劼. 深圳市高学历人才迁入格局的时空演化与驱动因素——基于1980—2014年个体迁移大数据[J]. 地理科学, 2023, 43(2): 262-271.
[3]	张伟丽, 郝智娟, 王伊斌, 魏瑞博. 城市群人口流动空间网络及影响因素[J]. 地理科学, 2023, 43(1): 72-81.
[4]	何炬, 张文忠, 曹靖, 谌丽. 多源数据在城市体检中的有机融合与应用——以北京市为例[J]. 地理科学, 2022, 42(2): 185-197.
[5]	王波, 雷雅钦, 汪成刚, 汪磊. 建成环境对城市活力影响的时空异质性研究：基于大数据的分析[J]. 地理科学, 2022, 42(2): 274-283.
[6]	张环宙, 应舜, 吴茂英. 文化型旅游目的地游客感知意象的主题识别与非对称性效应——以运河城市绍兴为例[J]. 地理科学, 2022, 42(12): 2131-2140.
[7]	施响, 王士君, 王冬艳, 浩飞龙, 李卓伟. 中国市域间日常人口流动特征及影响因素[J]. 地理科学, 2022, 42(11): 1889-1899.
[8]	张文佳, 季纯涵, 谢森锴. 复杂网络视角下时空行为轨迹模式挖掘研究[J]. 地理科学, 2021, 41(9): 1505-1514.
[9]	丁亮, 钮心毅, 施澄. 多中心空间结构的通勤效率——上海和杭州的实证研究[J]. 地理科学, 2021, 41(9): 1578-1586.
[10]	汪丽, 曹小曙, 李涛. 不同出游时间视角下游客流动网络结构及其分异特征——以西安市为例[J]. 地理科学, 2021, 41(8): 1437-1447.
[11]	郭艳萍, 刘敏. 基于POI数据的山西省旅游景区分类及空间分布特征[J]. 地理科学, 2021, 41(7): 1246-1255.
[12]	浩飞龙, 张浩然, 王士君. 基于多交通模式的长春市公园绿地空间可达性研究[J]. 地理科学, 2021, 41(4): 695-704.
[13]	刘培学, 张捷, 张建新, 张金悦, 张迎莹. 旅游景区客流规模特征与影响因素研究——以江苏省204家景区为例[J]. 地理科学, 2021, 41(11): 1992-2001.
[14]	张景奇, 史文宝, 修春亮. POI数据在中国城市研究中的应用[J]. 地理科学, 2021, 41(1): 140-148.
[15]	王波, 甄峰, 孙鸿鹄. 基于社交媒体签到数据的城市居民暴雨洪涝响应时空分析[J]. 地理科学, 2020, 40(9): 1543-1552.