地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (8): 1630-1641.doi: 10.12082/dqxxkx.2020.190380

• 地球信息科学理论与方法 • 上一篇    下一篇

基于DBSCAN算法的北京市顺丰快递服务设施集群识别与空间特征分析

张亚1,2,3(), 刘纪平4,*(), 周亮1,5, 王勇4, 李鹏飞1,2,3   

  1. 1.兰州交通大学测绘与地理信息学院,兰州 730070
    2.地理国情监测技术应用国家地方联合工程研究中心,兰州 730070
    3.甘肃省地理国情监测工程实验室,兰州 730070
    4.中国测绘科学研究院,北京100830
    5.中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室,北京 100101
  • 收稿日期:2019-07-17 修回日期:2019-11-25 出版日期:2020-08-25 发布日期:2020-10-25
  • 通讯作者: 刘纪平 E-mail:zhangya1549@163.com;liujp@casm.com
  • 作者简介:张 亚(1995— ),女,甘肃会宁人,硕士生,主要从事空间数据挖掘及分析研究。E-mail:zhangya1549@163.com
  • 基金资助:
    中国测绘科学研究院基本科研业务费项目(AR1904);国家重点研发计划项目(2016YFC0803106);国家重点研发计划项目(2017YBF0503601);兰州交通大学基金平台支持(201806)

Cluster Identification and Spatial Characteristics Analysis of Shunfeng Express Service Facilities based on the DBSCAN Algorithm in Beijing

ZHANG Ya1,2,3(), LIU Jiping4,*(), ZHOU Liang1,5, WANG Yong4, LI Peng fei1,2,3   

  1. 1. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China
    2. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China
    3. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China
    4. Chinese Academy of Surveying & Mapping, Beijing 100830, China
    5. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
  • Received:2019-07-17 Revised:2019-11-25 Online:2020-08-25 Published:2020-10-25
  • Contact: LIU Jiping E-mail:zhangya1549@163.com;liujp@casm.com
  • Supported by:
    The Basal Research Fund of Chinese Academy of Surveying and Mapping(AR1904);National Key Research and Development Program of China(2016YFC0803106);National Key Research and Development Program of China(2017YBF0503601);Funded by Lanzhou Jiaotong University Excellent Platform(201806)

摘要:

电子商务跨越式发展为快递物流行业注入了新鲜血液促使国民经济达到新的增站点,服务网点作为连接快递企业和用户之间的桥梁纽带,逐渐成为城市地理和物流地理的重要研究对象。本文以北京市顺丰快递服务网点为研究对象,首次将DBSCAN聚类算法和无人值守的智能快递柜引入城市物流快递行业研究中,综合使用核密度分析、Ripley's K函数等空间点模式分析方法,定量对比分析有人值守的合作网点和无人值守的智能快递柜两类顺丰快递服务网点的空间布局、集聚特征及影响因素。结果表明:① 基于密度的DBSCAN聚类算法能够快速有效地识别出任意形状的快递服务网点集群,算法识别出24个智能快递柜集群,14个合作网点集群;② 顺丰快递服务网点高密度区主要集中在人口密度大、经济繁华、交通便利的居住区和包含热门商圈的职住区附近,如双井、金融街、三里屯、学院路等;③ 合作网点和智能快递柜两类服务网点均呈集聚性分布,但集聚规模各不相同,具体表现为快递柜集聚规模明显大于合作网点,而集聚强度却小于合作网点;④ 智能快递柜集群密度大,服务半径小,更倾向服务于步行可达范围内的居住小区;合作网点集群密度小,服务半径大,服务对象随服务半径扩展至周边各大职区,对交通可达性的要求更高。⑤ 顺丰快递服务网点布局是地区经济水平、人口规模、交通状况、土地利用类型及城市功能区定位等多种因素综合作用的结果。

关键词: 快递服务网点, 空间分布特征, 集聚模式, 影响因素, DBSCAN算法, Ripley's K函数, 北京

Abstract:

The leap-forward development of e-commerce has injected fresh blood into the express delivery industry to promote the national economy. As a bridge between express delivery companies and users, service outlets have gradually become an important research object of urban geography and logistics geography.In this paper, by taking Shunfeng Express service outlets of Beijing as the research object,we introduced for the first time the DBSCAN clustering algorithm andunattended intelligent express cabinets into the urban logistics express industry. Spatial analysis methods such as the nuclear density analysis and Ripley's K function wereused to quantitatively compare and analyze the spatial pattern, agglomeration features, and influencing factors of the two types of Shunfeng Express service outlets, namely, manned cooperative outlets and unattended intelligent express cabinets.Results show that: (1) The density-based DBSCAN clustering algorithm can quickly and efficiently identify clusters of express service outlets of any arbitrary shape. The algorithm identified 24 intelligent express cabinet clusters and 14 cooperative network clusters. (2) The high-density area of Shunfeng Express service outlets was mainly concentrated in residential areas with large population density, economic prosperity, convenient transportation, and residential areas in popular business districts, such as Shuangjing, Financial Street, Sanlitun, and Xueyuan Road. (3) The spatial distribution of the two types of service outlets, namely, cooperative outlets and smart express cabinets, was in an agglomeration mode, but the scale of agglomeration was different. The scale of express cabinet agglomeration was significantly larger than that of cooperative outlets, while the intensity of agglomeration was smaller than that of cooperative outlets. (4) The intelligent express cabinet had a large cluster density and a smaller service radius, and was more inclined to serve residential areas within the walking distance; the cooperative network had a smaller cluster density and a larger service radius, and the service object extended to the surrounding major areas with the service radius, at the same time, the demand for traffic accessibility increased. (5) The layout of Shunfeng Express service outlets were the result of a combination of the regional economic level, population size, traffic conditions, land use types, and urban functional area positioning.

Key words: express service outlets, spatial distribution characteristics, influencing factor, agglomeration mode, DBSCAN algorithm, Ripley's K function, Beijing