网约车出行需求影响因素多尺度空间异质性分析

doi:10.13229/j.cnki.jdxbgxb.20230789

摘要/Abstract

摘要：

为探索不同出行距离尺度下网约车出行需求影响机理，基于多源数据对不同距离网约车出行需求进行分析。以长短距离网约车出行需求为因变量构建多尺度地理加权回归模型，揭示道路网、土地利用、人口分布和公共交通等建成环境因素对长短距离网约车出行需求的影响及其空间异质性。结果表明：MGWR的拟合结果优于传统地理加权回归模型和最小二乘法模型，长短距离网约车出行需求影响因素具有显著的空间异质性；主干路密度在市中心与短距离网约车出行需求呈正相关，在城市外围与长距离网约车出行需求呈负相关；人口密度在城市外围与长距离网约车出行需求呈正相关，在中心城区与短距离网约车出行需求呈负相关；短距离网约车在市中心与公共交通之间存在竞争，长距离网约车在城市周边补充公共交通服务的不足。研究结果有助于动态优化车辆配置调度，促进网约共享出行的可持续发展。

关键词: 交通运输系统工程, 网约共享出行, 空间异质性, 建成环境, 多尺度地理加权回归

Abstract:

In order to explore the influential mechanism of multi-scale ride-hailing travel demand， the travel demand of ride-hailing are analyzed based on the multi-source data. Constructs a multi-scale geographically weighted regression （MGWR） model with short and long distance ride-hailing travel demand as the dependent variable. The effects of built environmental attributes such as road network， land use， population density and public transportation on the demand for ride-hailing and their spatial heterogeneity were revealed. The model results show that the fit of the multi-scale geographical weighted regression model is better than the traditional geographical weighted regression （GWR） model and the ordinary least square （OLS） model， and the influential factors for ride-hailing travel demand have significant spatial heterogeneity. The primary roads density is positively correlated with the short-distance ride-hailing in the city center， and negatively correlated with long-distance ride-hailing in the city periphery. Population density is positively correlated with long-distance ride-hailing in the suburbs， and negatively correlated with the demand for short-distance ride-hailing in the central urban area. Short-distance ride-hailing competes with public transport in the urban centers， while long-distance ride-hailing complements the lack of public transport services around the city. The findings can not only dynamically optimize vehicle configuration and scheduling， but also promote the sustainable development of ride-hailing and shared mobility.

Key words: engineering of communications and transportation system, ride-hailing shared mobility, spatial heterogeneity, built environment, multi-scale geographically weighted regression

中图分类号:

U491

潘义勇,徐家聪,尤逸文,全勇俊. 网约车出行需求影响因素多尺度空间异质性分析[J]. 吉林大学学报(工学版), 2025, 55(5): 1567-1575.

Yi-yong PAN,Jia-cong XU,Yi-wen YOU,Yong-jun QUAN. Multi-scale spatial heterogeneity analysis of influencing factors of ride-hailing travel demand[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1567-1575.

图/表 6

图1

表1

表2

表3

表4

图2

参考文献 25

[1]	陈喜群. 网约共享出行研究综述[J]. 交通运输系统工程与信息, 2021, 21(5): 77-90.
	Chen Xi-qun. A survey of research on network-sharing travel [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(5): 77-90.
[2]	Gehrke S R, Felix A, Reardon T G. Substitution of ride-hailing services for more sustainable travel options in the greater Boston region[J]. Transportation Research Record, 2019, 2673(1): 438-446.
[3]	Acheampong R A, Siiba A, Okyere D K, et al. Mobility-on-demand: An empirical study of internet-based ride-hailing adoption factors, travel characteristics and mode substitution effects[J]. Transportation Research Part C: Emerging Technologies, 2020, 115: 102638.
[4]	钟军, 林岩, 杭宇. 中国城市网约车服务对公交使用量的影响[J]. 交通运输系统工程与信息, 2020, 20(5): 234-239.
	Zhong Jun, Lin Yan, Hang Yu. Impact of ride-hailing service on use of public transport in China's cities [J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(5): 234-239.
[5]	Javid M A, Abdullah M, Ali N. Travellers' perceptions about ride-hailing services in Lahore: An extension of the theory of planned behavior[J]. Asian Transport Studies, 2022, 8: 100083.
[6]	袁亮, 吴佩勋. 城市居民对网约车与出租车的选择意愿及影响因素研究: 基于江苏省调查数据的 Logistic 分析[J]. 软科学, 2018, 32(4): 120-123.
	Yuan Liang, Wu Pei-xun. Study on the choice and influence factors of urban residents' selection of network-booking and taxis: Logistic analysis based on the survey data of Jiangsu province[J]. Soft Science, 2018, 32(4): 120-123.
[7]	Hou Y, Garikapati V, Weigl D, et al. Factors influencing willingness to pool in ride-hailing trips[J]. Transportation Research Record, 2020, 2674(5): 419-429.
[8]	Huang G, Qiao S, Yeh A G O. Spatiotemporally heterogeneous willingness to ridesplitting and its relationship with the built environment: A case study in Chengdu, China[J]. Transportation Research Part C: Emerging Technologies, 2021, 133: 103425.
[9]	Barajas J M, Brown A. Not minding the gap: Does ride-hailing serve transit deserts?[J]. Journal of Transport Geography, 2021, 90: 102918.
[10]	Zheng Z, Zhang J, Zhang L, et al. Understanding the impact of the built environment on ride-hailing from a spatio-temporal perspective: A fine-scale empirical study from China[J]. Cities, 2022, 126: 103706.
[11]	Wang S, Noland R B. Variation in ride-hailing trips in Chengdu, China[J]. Transportation Research Part D: Transport and Environment, 2021, 90: 102596.
[12]	许心越,孔庆雪,李建民,等.建成环境对轨道交通客流的时空异质性影响分析[J].交通运输系统工程与信息,2023,23(4):194-202.
	Xu Xin-yue, Kong Qing-xue, Li Jian-min, et al. Analysis of spatio-temporal heterogeneity impact of built environment on rail transit passenger flow[J]. Journal of Transportation Systems Engineering and Information Technology, 2023,23(4):194-202.
[13]	尹超英,邵春福,王晓全,等.考虑空间异质性的建成环境对通勤方式选择的影响[J].吉林大学学报: 工学版, 2020,50(2):543-548.
	Yin Chao-ying, Shao Chun-fu, Wang Xiao-quan, et al. Influence of built environment on commuting mode choice considering spatial heterogeneity[J]. Journal of Jilin University (Engineering and Technology Edition), 2020,50(2):543-548.
[14]	Yu H, Peng Z R. Exploring the spatial variation of ridesourcing demand and its relationship to built environment and socioeconomic factors with the geographically weighted Poisson regression[J]. Journal of Transport Geography, 2019, 75: 147-163.
[15]	马书红,廖国美,黄岩, 等. 建成环境对交通小区地铁通勤客流的异质性影响[J].吉林大学学报:工学版, 2024, 54 (7): 1913-1922.
	Ma Shu-hong, Liao Guo-mei, Huang Yan, et al. Heterogeneity of built environment on commuter passenger flow of subway in traffic analysis zones[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54 (7): 1913-1922.
[16]	An R, Wu Z, Tong Z, et al. How the built environment promotes public transportation in Wuhan: A multiscale geographically weighted regression analysis[J]. Travel Behaviour and Society, 2022, 29: 186-199.
[17]	龙雪琴,赵欢,周萌,等.成都市建成环境对网约车载客点影响的时空分异性研究[J].地理科学,2022,42(12):2076-2084.
	Long Xue-qin, Zhao Huan, Zhou Meng, et al. Spatiotemporal heterogeneity of the impact of built environment in Chengdu on online car-hailing passengers' pick-up points[J]. Scientia Geographica Sinica, 2022, 42(12): 2076-2084.
[18]	Liu X, Gong L, Gong Y, et al. Revealing travel patterns and city structure with taxi trip data[J]. Journal of Transport Geography, 2015, 43: 78-90.
[19]	Chen C, Feng T, Ding C, et al. Examining the spatial-temporal relationship between urban built environment and taxi ridership: Results of a semi-parametric GWPR model[J]. Journal of Transport Geography, 2021, 96: 103172.
[20]	Hayes A F, Cai L. Using heteroskedasticity-consistent standard error estimators in OLS regression: An introduction and software implementation[J]. Behavior Research Methods, 2007, 39: 709-722.
[21]	Du M, Cheng L, Li X, et al. Spatial variation of ridesplitting adoption rate in Chicago[J]. Transportation Research Part A: Policy and Practice, 2022, 164: 13-37.
[22]	Thompson E S, Saveyn P, Declercq M, et al. Characterisation of heterogeneity and spatial autocorrelation in phase separating mixtures using Moran's I[J]. Journal of Colloid and Interface Science, 2018, 513: 180-187.
[23]	Vandenbulcke G, Dujardin C, Thomas I, et al. Cycle commuting in Belgium: Spatial determinants and 're-cycling'strategies[J]. Transportation Research Part A: Policy and Practice, 2011, 45(2): 118-137.
[24]	Moran P A P. Notes on continuous stochastic phenomena[J]. Biometrika, 1950, 37(1): 17-23.
[25]	Brunsdon C, Fotheringham A S, Charlton M E. Geographically weighted regression: A method for exploring spatial nonstationarity[J]. Geographical Analysis, 1996, 28: 281-298.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

变量	描述	平均值	标准差
因变量
LDT	工作日长距离网约车订单量	1 280.19	3 796.45
SDT	工作日短距离网约车订单量	1 280.37	6 034.85
道路网指标
主干路X₁	主干路密度/（km·km^-2）	3.63	3.33
次干路X₂	次干路密度/（km·km^-2）	6.44	13.19
支路X₃	支路密度/（km·km^-2）	4.06	3.44
土地利用指标
人口分布X₄	人口密度/（人·km^-2）	3 928.26	6 048.32
餐饮服务X₅	餐饮服务设施POI数量	24.08	41.51
公司企业X₆	公司企业POI数量	23.85	40.70
购物服务X₇	购物服务设施POI数量	67.51	119.56
金融服务X₈	金融服务设施POI数量	3.04	7.17
科教服务X₉	科教文化服务设施POI数量	15.48	25.57
生活服务X₁₀	生活服务设施POI数量	68.14	117.94
休闲服务X₁₁	休闲服务设施POI数量	9.31	16.78
医疗服务X₁₂	医疗机构设施POI数量	8.90	14.93
政府机构X₁₃	政府单位POI数量	11.55	17.36
住宿服务X₁₄	酒店住宿设施POI数量	3.45	9.04
商务住宅X₁₅	小区住宅POI数量	8.69	18.44
风景名胜X₁₆	景点服务设施POI数量	0.93	2.76
公共交通指标
地面公交X₁₇	公交站点数量	4.63	4.48
地铁X₁₈	地铁站点数量	0.65	1.91

变量	长距离网约车	短距离网约车	空间自相关			VIF
变量	回归系数	回归系数	Moran's I	Z值	P值	VIF
LDT			0.452	193.613	0.000
SDT			0.376	161.972	0.000
主干路	0.063^***	0.057^***	0.102	43.361	0.000	1.112
人口分布	0.200^***	0.164^***	0.359	156.490	0.000	1.441
公司企业	0.103^***	0.093^***	0.201	86.061	0.000	1.601
购物服务	0.253^***	0.190^***	0.205	88.196	0.000	2.325
休闲服务	0.266^***	0.264^***	0.255	108.842	0.000	2.077
医疗服务	-0.115^***	-0.160^***	0.103	44.025	0.000	1.622
商务住宅	0.256^***	0.465^***	0.323	137.649	0.000	2.279
地面公交	-0.052^***	-0.250^***	0.297	125.970	0.000	2.167

模型	长距离网约车出行需求（LDT）				短距离网约车需求（SDT）
模型	AIC_C	R²	R²_Adj	带宽	AIC_C	R²	R²_Adj	带宽
OLS	3 344.308	0.602	0.600	1 734	3 540.129	0.554	0.552	1 734
GWR	1 311.593	0.936	0.914	75	1 250.937	0.938	0.917	75
MGWR	627.878	0.953	0.939	［61，417］	-312.400	0.974	0.966	［47，1 733］

变量		平均值	标准差	最小值	中位数	最大值	带宽
LDT	常数项	-0.118	0.240	-0.332	-0.217	0.824	61
	主干路	0.019	0.069	-0.118	0.002	0.536	61
	人口分布	0.078	0.088	-0.129	0.069	0.719	97
	公司企业	0.008	0.069	-0.213	0.001	0.399	61
	购物服务	0.038	0.111	-0.139	-0.002	0.496	409
	休闲服务	0.114	0.145	-0.029	0.046	0.746	61
	医疗服务	0.054	0.035	0.007	0.040	0.154	417
	商务住宅	0.030	0.088	-0.204	0.010	0.472	61
	地面公交	0.059	0.088	-0.039	0.025	0.479	68
SDT	常数项	-0.143	0.165	-0.236	-0.205	0.760	61
	主干路	0.013	0.055	-0.060	0.000	0.499	59
	人口分布	0.024	0.052	-0.098	0.005	0.322	61
	公司企业	0.005	0.050	-0.180	0.001	0.359	61
	购物服务	0.018	0.070	-0.196	0.003	0.483	47
	休闲服务	0.053	0.111	-0.011	0.005	0.580	61
	医疗服务	0.004	0.037	-0.073	-0.001	0.241	54
	商务住宅	0.049	0.109	-0.060	0.004	0.573	47
	地面公交	-0.006	0.000	-0.007	-0.006	-0.005	1 733