基于词向量数据场轨迹引力的多中心识别和空间交互分析

doi:10.11821/dlyj020190849

摘要/Abstract

摘要：

多中心化是分散城市人口,疏解交通拥堵,调节职住失衡,应对“大城市病”的重要手段。针对轨迹大数据,先利用词向量描述其空间特征和行为规律,再结合数据场理论表达城市区域对轨迹的吸引强度,并完成多中心识别,最后借鉴复杂网络理论对多中心空间交互规律进行探索和挖掘。结果表明：① 郑州市轨迹吸引强度呈核心强、外围弱、沿线蔓延的圈层空间分布形态,识别出的21个多中心轨迹引力差异较大,区域吸引能力不均衡;② 外围次级中心的区域引力强度和交互频次低,交互方向主要指向一级中心,呈现出外溢型多中心结构,为了实现其应有的分散疏解作用,还需加强统筹规划,带动其科学发展。提出基于词向量数据场轨迹引力的多中心识别分析方法,对于轨迹隐含的出行规律描述更加完整,对轨迹引力的表达更准确,从流动角度呈现了多中心的演化机理,为城市规划实践提供了新思路。

关键词: 词向量, 数据场, 多中心, 空间交互, 轨迹

Abstract:

Polycentric structure is an important method of dispersing urban population, relieving traffic congestion, adjusting the imbalance of job-housing, and dealing with "big city disease". First of all, word vector is used to describe the spatial characteristics and behavior rules of the trajectory big data, and vector operation is used to reflect the correlation between the origin points and destination points of the trajectories. In addition, the spatial grid of Zhengzhou city is divided, the gravity of grid units to mobile targets is measured by using the gravitational model of data field theory, and the recognition of polycentric structure is completed. At last, the interaction rules of the polycentric structure are explored with the assistance of the complex network theory, and the relationships between the polycentric nodes are reflected by the in-and-out intensity, net flow ratio and chain weight. The results show that: (1) The gravity strength of trajectories presents a circular spatial pattern with a strong core and weak peripheries, and the region with high gravity spreads along the main roads. There are significant differences in the unbalanced gravity of trajectories among the identified 21 centers. Urban elements and moving targets spread from the saturated core urban area to the periphery along the main traffic routes. The spatial distribution of polycentric structure presents a typical overflow pattern of dense inside and sparse outside. (2) The regional gravity intensity and interaction frequency of the peripheral sub-centers are low, and the interaction direction mainly goes towards the primary centers in the core urban area. Although the planning prospect of the peripheral centers is broad, due to the late planning, remote location and insufficient supporting facilities, their attraction to the surrounding areas is limited. And it will take a long time to achieve the planning objectives. In order to make the sub-centers decentralize better, it is necessary to strengthen the overall planning and guide the scientific development of the sub-centers. A polycentric structure recognition method and spatial interaction analysis method based on the trajectory gravity of word vector data field are proposed. The trajectory word vector describes the spatial information and travel pattern information in a comprehensive way, the trajectory gravity intensity expressed by the potential value of data field is more accurate, and the polycentric spatial interaction structure analyzed in a complex network is clearer. The evolution mechanism of polycentric structure is presented from the perspective of flow. This is a more suitable polycentric analysis method for trajectory data, which provides a new idea for urban planning.

Key words: word vector, data field, polycentric, spatial interaction, trajectory

李欣. 基于词向量数据场轨迹引力的多中心识别和空间交互分析[J]. 地理研究, 2021, 40(1): 230-246.

LI Xin. Urban polycentric recognition and spatial interaction analysis based on word vector data field trajectory gravity[J]. GEOGRAPHICAL RESEARCH, 2021, 40(1): 230-246.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

图10

图11

参考文献 29

[1]	李婷, 裴韬, 袁烨城, 等. 人类活动轨迹的分类、模式和应用研究综述. 地理科学进展, 2014,33(7):938-948.
	[ Li Ting, Pei Tao, Yuan Yecheng, et al. A review on the classification, patterns and applied research of human mobility trajectory. Progress in Geography, 2014,33(7):938-948.]. DOI: 10.11820/dlkxjz.2014.07.0.
[2]	杨格格, 宋辞, 裴韬, 等. 北京对外交通枢纽乘客OD时空分布特征. 地球信息科学学报, 2016,18(10):1374-1383.
	[ Yang Gege, Song Ci, Pei Tao, et al. Passengers′ OD temporal-spatial distribution characteristics of the external traffic hubs in Beijing. Journal of Geo-information Science, 2016,18(10):1374-1383]. DOI: 10.3724/SP.J.1047.2016.01374.
[3]	桂智明, 向宇, 李玉鉴. 基于出租车轨迹的并行城市热点区域发现. 华中科技大学学报: 自然科学版, 2012,40(S1):187-190.
	[ Gui Zhiming, Xiang Yu, Li Yujian. Parallel discovering of city hot spot based on taxi trajectories. Journal of Huazhong University of Science and Technology: Nature Science Edition, 2012,40(S1):187-190.]. DOI: CNKI:SUN:HZLG.0.2012-S1-045
[4]	Liu Y, Wang F H, Yu X, et al. Urban land uses and traffic ‘source-sink areas′: Evidence from GPS-enabled taxi data in Shanghai. Landscape and Urban Planning, 2012,106(1):73-87. DOI: 10.1016/j.landurbplan.2012.02.012.
[5]	Scholz R W, Lu Y M. Detection of dynamic activity patterns at a collective level from large-volume trajectory data. International Journal of Geographical Information Science, 2014,28(5):946-963. DOI: 10.1080/13658816.2013.869819.
[6]	Jahnke M, Ding L, Karja K, et al. Identifying origin/destination hotspots in floating car data for visual analysis of traveling behavior. Progress in Location-Based Services, Berlin: Springer International Publishing 2016: 253-269.
[7]	Zhang P D, Deng M, Shi Y, et al. Detecting hotspots of urban residents′ behaviors based on spatio-temporal clustering techniques. GeoJournal, 2016,82(5):923-935. DOI: 10.1007/s10708-016-9720-4. doi: 10.1007/s10708-016-9720-4
[8]	周勍, 秦昆, 陈一祥, 等. 基于数据场的出租车轨迹热点区域探测方法. 地理与地理信息科学, 2016,32(6):51-56, 127.
	[ Zhou Qing, Qin Kun, Chen Yixiang, et al. Hotspots detection from taxi trajectory data based on data field clustering. Geography and Geo-Information Science, 2016,32(6):51-56, 127.]. DOI: 10.3969/j.issn.1672-0504.2016.06.009.
[9]	刘瑜, 肖昱, 高松, 等. 基于位置感知设备的人类移动研究综述. 地理与地理信息科学, 2011,27(4):8-13.
	[ Liu Yu, Xiao Yu, Gao Song, et al. A review on morphological rehabilitation based on rule-oriented classification. Geography and Geo-Information Science, 2011,27(4):8-13.]. DOI: CNKI:SUN:DLGT.0.2011-04-003.
[10]	韩昊英, 于翔, 龙瀛. 基于北京公交刷卡数据和兴趣点的功能区识别. 城市规划, 2016,40(6):52-60.
	[ Han Haoying, Yu Xiang, Long Ying. Identifying urban functional zones using bus smarts card data and points of interest in Beijing. City Planning Review, 2016,40(6):52-60.]. DOI: 10.11819/cpr20160609a.
[11]	龙瀛, 张宇, 崔承印. 利用公交刷卡数据分析北京职住关系和通勤出行. 地理学报, 2012,67(10):1339-1352. doi: 10.11821/xb201210005
	[ Long Ying, Zhang Yu, Cui Chengyin. Identifying commuting pattern of Beijing using bus smart card data. Acta Geographica Sinica, 2012,67(10):1339-1352.]. DOI: 10.11821/xb201210005.
[12]	王波, 甄峰, 张浩. 基于签到数据的城市活动时空间动态变化及区划研究. 地理科学, 2015,35(2):151-160.
	[ Wang Bo, Zhen Feng, Zhang Hao. The dynamic changes of urban space-time activity and activity zoning based on check-in data in Sina web. Scientia Geographica Sinica, 2015,35(2):151-160.]. DOI: 10.13249/j.cnki.sgs.2015.02.151.
[13]	程静, 刘家骏, 高勇. 基于时间序列聚类方法分析北京出租车出行量的时空特征. 地球信息科学学报, 2016,18(9):1227-1239. doi: 10.3724/SP.J.1047.2016.01227
	[ Cheng Jing, Liu Jiajun, Gao Yong. Analyzing the spatio-temporal characteristics of Beijing′s OD trip volume based on time series clustering method. Journal of Geo-information Science, 2016,18(9):1227-1239.]. DOI: 10.3724/SP.J.1047.2016.01227.
[14]	陈世莉, 陶海燕, 李旭亮, 等. 基于潜在语义信息的城市功能区识别: 广州市浮动车GPS时空数据挖掘. 地理学报, 2016,71(3):471-483. doi: 10.11821/dlxb201603010
	[ Chen Shili, Tao Haiyan, Li Xuliang, et al. Discovering urban functional regions using latent semantic information: Spatiotemporal data mining of floating cars GPS data of Guangzhou. Acta Geographica Sinica, 2016,71(3):471-483.]. DOI: 10.11821/dlxb201603010.
[15]	周博, 马林兵, 胡继华, 等. 基于轨迹数据场的热点区域提取及空间交互分析: 以深圳市为例. 热带地理, 2019,39(1):117-124. doi: 10.13284/j.cnki.rddl.003097
	[ Zhou Bo, Ma Linbing, Hu Jihua, et al. Extraction of urban hotspots and analysis of spatial interaction based on trajectory data field: A case study of Shenzhen city. Tropical Geography, 2019,39(1):117-124.]. DOI: 10.13284/j.cnki.rddl.003097.
[16]	陈泽东, 谯博文, 张晶. 基于居民出行特征的北京城市功能区识别与空间交互研究. 地球信息科学学报, 2018,20(3):291-301. doi: 10.12082/dqxxkx.2018.170531
	[ Chen Zedong, Qiao Bowen, Zhang Jing. Identification and spatial interaction of urban functional regions in Beijing based on the characteristics of residents' traveling. Journal of Geo-information Science, 2018,20(3):291-301.]. DOI: 10.12082/dqxxkx.2018.170531
[17]	赵鹏祥. 基于轨迹聚类的城市热点区域提取与分析方法研究. 武汉: 武汉大学博士学位论文, 2015: 94-95.
	[ Zhao Pengxiang. Research on the method of extracting and analyzing urban hotspots based on trajectory clustering. Wuhan: Doctoral Dissertation of Wuhan University, 2015: 94-95.]
[18]	Zhong C, Arisona S M, Huang X F, et al. Detecting the dynamics of urban structure through spatial network analysis. International Journal of Geographical Information Science, 2014,28(11):2178-2199. DOI: 10.1080/13658816.2014.914521. doi: 10.1080/13658816.2014.914521
[19]	Bengio Y, Ducharme R, Vincent P, et al. A neural probabilistic language model. Journal of Machine Learning Research, 2000,3(6):932-938. DOI: 10.1007/3-540-33486-6_6.
[20]	李德毅, 刘常昱, 杜鹢, 等. 不确定性人工智能. 软件学报, 2004,15(11):1583-1594.
	[ Li Deyi, Liu Changyu, Du Yi, et al. Artificial intelligence with uncertainty. Journal of Software, 2004,15(11):1583-1594.]. DOI: CNKI:SUN:RJXB.0.2004-11-000.
[21]	Watts D J, Strogatz S H. Collective dynamics of 'small-world' networks. Nature, 1998,393(6684):440-442. DOI: 10.1038/30918. doi: 10.1038/30918 pmid: 9623998
[22]	Barabasi A L, Albert R. Emergence of scaling in random networks. Science, 1999,286(5439):509-512. DOI: 10.1126/science.286.5439.509. pmid: 10521342
[23]	王晓原, 张敬磊, 吴芳. 交通流数据清洗规则研究. 计算机工程, 2011,37(20):191-193. doi: 10.3969/j.issn.1000-3428.2011.20.066
	[ Wang Xiaoyuan, Zhang Jinglei, Wu Fang. Research on traffic flow data cleaning rules. Computer Engineering, 2011,37(20):191-193.]. DOI: 10.3969/j.issn.1000-3428.2011.20.066.
[24]	仇培元, 陆锋, 张恒才, 等. 蕴含地理事件微博客消息的自动识别方法. 地球信息科学学报, 2016,18(7):886-893. doi: 10.3724/SP.J.1047.2016.00886
	[ Qiu Peiyuan, Lu Feng, Zhang Hengcai, et al. Automatic identification method of micro-blog messages containing geographical events. Journal of Geo-Information Science, 2016,18(7):886-893.]. DOI: 10.3724/SP.J.1047.2016.00886.
[25]	李欣, 孟德友. 基于路网相关性的分布式增量交通流大数据预测方法. 地理科学, 2017,37(2):209-216. doi: 10.13249/j.cnki.sgs.2017.02.006
	[ Li Xin, Meng Deyou. Distributed incremental traffic flow big data forecasting method based on road network correlation. Scientia Geographica Sinica, 2017,37(2):209-216.]. DOI: CNKI:SUN:DLKX.0.2017-02-006.
[26]	刘康, 仇培元, 刘希亮, 等. 利用词向量模型分析城市道路交通空间相关性. 测绘学报, 2017,46(12):2032-2040.
	[ Liu Kang, Qiu Peiyuan, Liu Xiliang, et al. Measuring traffic correlations in urban road system using word embedding model. Acta Geodaetica et Cartographica Sinica, 2017,46(12):2032-2040.]. DOI: 10.11947/j.AGCS.2017.20170166.
[27]	李欣. 基于时空切分和词向量相似性的轨迹伴随模式挖掘. 中山大学学报自然科学版, 2019,58(5):35-43.
	[ Li Xin. Trajectory big data accompanying patterns mining method based on spatial-time Hausdorff distance segmentation and word vector similarity. Acta Scientiarum Naturalium Universitatis Sunyatsen, 2019,58(5):35-43]. DOI: 10.13471/j.cnki.acta.snus.2019.05.003.
[28]	淦文燕, 李德毅, 王建民. 一种基于数据场的层次聚类方法. 电子学报, 2006,34(2):258-262.
	[ Gan Wenyan, Li Deyi, Wang Jianmin. An hierarchical clustering method based on data fields. Chinese Journal of Electronics, 2006,34(2):258-262.]. DOI: 10.3321/j.issn:0372-2112.2006.02.014.
[29]	秦昆, 周勍, 徐源泉, 等. 城市交通热点区域的空间交互网络分析. 地理科学进展, 2017,36(9):1149-1157. doi: 10.18306/dlkxjz.2017.09.011
	[ Qin Kun, Zhou Qing, Xu Yuanquan, et al. Spatial interaction network analysis of urban traffic hotspots. Progress in Geography, 2017,36(9):1149-1157.]. DOI: 10.18306/dlkxjz.2017.09.011.

	出租车				电动车
	主中心	副中心	区级组团	特殊功能区	主中心	副中心	区级组团	特殊功能区
一级热点	A	CF	I	-	A	CF	IJ	-
二级热点	B	D	HJ	-	B	D	H	-
三级热点	-	-	-	-	-	-	K	-
不显著	-	E	KLM	-	-	E	LM	-
三级冷点	-	-	O	-	-	-	NO	PS
二级冷点	-	-	-	PS	-	-	-	Q
一级冷点	-	G	N	QR	-	G	-	R