北京市四环内街区尺度下的主题混合模式挖掘

doi:10.12082/dqxxkx.2020.190594

摘要/Abstract

摘要：

城市是多样性聚集的场所,且多元化和差异性日益增强,故探究土地混合利用具有一定的现实意义。现有的土地混合研究大多以POI（Point of Interest）为研究基础,着眼于城市主题的研究较少。本文采用百度POI数据,在街区尺度下考虑POI共现以提取主题,并挖掘北京市四环内的主题混合模式,其结果可以为城市规划及其建设提供参考。首先,采用LDA（Latent Dirichlet Allocation）主题模型得出街区的主题向量以及主题的POI共现模式;其次,引入多样性指数对街区的混合度进行度量,并依据自然断裂法将街区分为高混合街区、中等混合街区、低混合街区3类;最后,为了探究3类街区中的主题混合模式,先采用多元线性回归找出不同类街区中对混合度影响显著的主题,在此基础上对街区中的混合模式进行提取。结果表明：高混合街区的主题混合模式都是茶座餐厅主题与其他主题的混合;中等混合街区中的混合模式大多是以公司企业主题与住宅（商铺）主题再结合其他主题的混合;低混合街区中最典型的2种模式是茶座餐厅主题主导与风景名胜主题主导的接近单一的模式。不同的模式也体现了不同混合区的特征及其之间的差异,有助于对城市深度理解,从而为混合城市的建设提供参考。

关键词: 街区, LDA, POI共现, 主题, 主题混合模式, 混合度, TF-IDF, 多元线性回归

Abstract:

Cities with different land use types influenced by rapid urbanization and urban expansion support various human activities, such as shopping, eating, living, working, and recreation. The mixed use of land can stimulate the vitality of the city, enable the city togather enough people at different points in time, thus producing more interaction, promoting diversified consumption, and improving the economic and social benefits of the city.Mixed characteristics of land use types in cities gain more popularity in many researches due to the huge practical meanings. However, previous researches on mixed characteristics calculation mainly focused on POI data,and there is a lack of consideration for detecting urban topics. Human activities usually take place in different types of points of interest, the potential relationships and spatial interactions between the different types of adjacent POIs can work together to express the potential semantics of locations. In this paper, from an urban topic perspective, a method for the consideration of the relationship between POIs was proposed, and the Hill Numbers Diversity Index was applied to calculate the mixed degree of topics at the block level. Specifically,LDA (Latent Dirichlet Allocation) topic model was firstly used to generate topic vectors of the block and the co-occurrence patterns of POIs. Secondly, the diversity index was introduced to measure the mixed degree of blocks. Then, according to the Goodness of Variance Fit (GVF) and the nature break method, the blocks wereclassified into three groups: (1) high mixed blocks, (2) medium mixed blocks, and (3) low mixed blocks. Finally, multiple linear regression was applied based on mixed degree and topics in the blocksto uncover the significant topics and mixed pattern.Results show that different mixed blocks haddifferent mixed patterns.For high mixed blocks, the topic of teahouse restaurant was significant; the topics of company, enterprise, and residence weresignificant in medium mixed blocks; and the most typical two patterns in low mixed blocks werethe existence of landscape and famous scenery topic and teahouse restaurant topic. To sum up,starting from the urban topic, this paper reveals the mixed pattern of block, and the results show thatdifferent mixed patterns reflect the characteristics of different mixed areas and present certain rules in spatial distribution, which is conducive to the deep understanding of the cityareas, so as to provide a reference for the construction of Beijing mixed city, and also provide suggestions for other mixed cities.

Key words: block, LDA, POI co-occurrence, topic, topic mixed pattern, topic mixed degree, TF-IDF, multiple linear regression

刘菁菁, 刘雨思, 伊迪升, 杨静, 张晶. 北京市四环内街区尺度下的主题混合模式挖掘[J]. 地球信息科学学报, 2020, 22(6): 1370-1382.DOI:10.12082/dqxxkx.2020.190594

LIU Jingjing, LIU Yusi, YI Disheng, YANG Jing, ZHANG Jing. Extracting Mixed Topic Patterns within Downtown Beijing at the Block Level[J]. Journal of Geo-information Science, 2020, 22(6): 1370-1382.DOI:10.12082/dqxxkx.2020.190594

图/表 18

图1

表1

表2

图2

表3

图3

表4

图4

图5

图6

表5

表6

图7

表7

图8

表8

图9

表9

参考文献 32

[1]	黄毅. 城市混合功能建设研究[D]. 上海:同济大学, 2008.
	[ Huang Y. A study of urban mixed-use development in theory and practice: The case of Shanghai[D]. Shanghai:Tongji University, 2008. ]
[2]	Gao S, Janowicz K, Couclelis H. Extracting urban functional regions from points of interest and human activities on location-based social networks[J]. Transactions in GIS, 2017,21(3):446-467.
[3]	Bordoloi R, Mote A, Sarkar P P. Quantification of land use diversity in the context of mixed land use[J]. Procedia-Social and Behavioral Sciences, 2013,104:563-572.
[4]	Maleki M Z, Zain M F M, Ismail A. Variables communalities and dependence to factors of street system, density, and mixed land use in sustainable site design[J]. Sustainable Cities and Society, 2012,3:46-53.
[5]	龚咏喜, 李贵才, 林姚宇. 土地利用对城市居民出行碳排放的影响研究[J]. 城市发展研究, 2013,20(9):112-118.
	[ Gong Y X, Li G C, et al. Impact of land use on urban household travel carbon emissions[J]. Urban Development Studies, 2013,20(9):112-118. ]
[6]	包宇. 城市土地混合利用测度研究——以深圳市为例[J]. 湖北农业科学, 2016,55(22):5794-5797.
	[ Bao Y. Measure of mixed urban land use: Case of Shenzhen city[J]. Hubei Agricultural Sciences, 2016,55(22):5794-5797. ]
[7]	Cervero R, Kockelman K. Travel demand and the 3Ds: density, diversity, and design[J]. Transportation Research Part D: Transport and Environment, 1997,2(3):199-219.
[8]	李苗裔, 马妍, 孙小明, 等. 基于多源数据时空熵的城市功能混合度识别评价[J]. 城市规划, 2018,42(2):97-103.
	[ Li M Y, Ma Y, Sun X M. Application of spatial and temporal entropy based on multi-source data for measuring the mix degree of urban functions[J]. City Planning Review, 2018,42(2):97-103. ]
[9]	Lou J. Entropy and Diversity[J]. Oikos, 2010,113(2):363-375.
[10]	宁晓平. 土地利用结构与城市活力的影响分析[D]. 深圳:深圳大学, 2016.
	[ Ning X P. Analysis of the influence of land use structure and urban vitality[D]. Shenzhen: Shenzhen University, 2016. ]
[11]	许思扬, 陈振光. 混合功能发展概念解读与分类探讨[J]. 规划师, 2012,28(7):105-109.
	[ Xu S Y, Chen Z G. Interpretation and classification of mixed function development concept[J]. Planners, 2012,28(7):105-109. ]
[12]	Yue Y, Zhuang Y, Yeh A G O, et al. Measurements of POI-based mixed use and their relationships with neighbourhood vibrancy[J]. International Journal of Geographical Information Systems, 2016,31(4):1-18.
[13]	康朝贵, 刘瑜, 邬伦. 城市手机用户移动轨迹时空熵特征分析[J]. 武汉大学学报·信息科学版, 2017,42(1):63-69.
	[ Kang C G, Liu Y, Wu L. An analysis of entropy of human mobility from mobile phone data[J]. Geomatics and Information Science of Wuhan University, 2017,42(1):63-69. ]
[14]	康雨豪, 王玥瑶, 夏竹君. 利用POI数据的武汉城市功能区划分与识别[J]. 测绘地理信息, 2018,43(1):81-85.
	[ Kang Y H, Wang YY, Xia Z Z. Identification and classification of wuhan urban districts based on POI[J]. Journal of Geomatics, 2018,43(1):81-85. ]
[15]	Zhao W F, Li Q Q and Li B J. Extracting hierarchical landmarks from urban POI data[J]. Journal of Remote Sensing, 2011,15(5):973-988.
[16]	Chi J, Jiao L, Dong T, et al. Quantitative identification and visualization of urban functional area based on POI data[J]. Journal of Geomatics, 2016,41(2):68-73.
[17]	Han H, Xiang Y U, Long Y. Identifying urban functional zones using bus smart card data and points of interest in Beijing[J]. City Planning Review, 2016,40(6):52-60.
[18]	Lynch K. Good city form[M]. Massachusetts: MIT press, 1984.
[19]	百度地图开放平台[EB/OL]: http://lbsyun.baidu.com/.
	[ Baidu Map Open Platform: http://lbsyun.baidu.com/.]
[20]	David M. Probabilistic topic models[J]. IEEE Signal Processing Magazine, 2010,27(6):55-65.
[21]	Blei D M, Ng A Y, Jordan M I. Latent dirichletallocation[J]. Journal of Machine Learning Research, 2003,3(1):993-1022.
[22]	Griffiths T L, Steyvers M. Finding scientific topics[J]. Proceedings of the National Academy of Sciences, 2004,101(1):5228-5235.
[23]	刘瑜, 詹朝晖, 朱递, 等. 集成多源地理大数据感知城市空间分异格局[J]. 武汉大学学报·信息科学版, 2018,43(3):327-335.
	[ Liu Y, Zhan Z H, Zhu D, et al. Incorporating multi-source big geo-data to sense spatial heterogeneity patterns in an urban space[J]. Geomatics and Information Science of Wuhan University, 2018,43(3):327-335. ]
[24]	刘瑜. 社会感知视角下的若干人文地理学基本问题再思考[J]. 地理学报, 2016,71(4):564-575.
	[ Liu Y. Revisiting several basic geographical concepts: A social sensing perspective[J]. Acta Geographica Sinica, 2016,71(4):564-575. ]
[25]	Huang J, Levinson D, Wang J, et al. Tracking job and housing dynamics with smartcard data[J]. Proceedings of the National Academy of Sciences, 2018,115(50):12710-12715. doi: 10.1073/pnas.1815928115
[26]	Wang B, Zhen F, Wei Z, et al. A theoretical framework and methodology for urban activity spatial structure in e-society: Empirical evidence for Nanjing city, China[J]. Chinese Geographical Science, 2015,25(6):672-683.
[27]	Zhen F, Tang J, Chen Y. Spatial distribution characteristics of residents' emotions based on Sina Weibo big data: A case study of Nanjing[M] //Big Data Support of Urban Planning and Management. Springer, Cham, 2018: 43-62.
[28]	秦萧, 甄峰. 大数据与小数据结合:信息时代城市研究方法探讨[J]. 地理科学, 2017,37(3):321-330.
	[ Qin X, Zhen F. Combination between big data and small data: New methods of urban studies in the information era[J]. Scientia Geographica Sinica, 2017,37(3):321-330. ]
[29]	刘瑜, 康朝贵, 王法辉. 大数据驱动的人类移动模式和模型研究[J]. 武汉大学学报·信息科学版, 2014,39(6):660-666.
	[ Liu Y, Kang C G, Wang F H. Towards big data-driven human mobility patterns and models[J]. Geomatics and Information Science of Wuhan University, 2014,39(6):660-666. ]
[30]	陈瑗瑗, 高勇. 利用社交媒体的位置潜语义特征提取与分析[J]. 地球信息科学学报, 2017,19(11):1405-1414.
	[ Chen Y Y, Gao Y. Extracting and analyzing latent semantic characteristics of locations using social media data. Journal of Geo-information Science, 2017,19(11):1405-1414. ]
[31]	李航. 统计学习方法—第二版[M]. 北京: 清华大学出版社, 2019.
	[ Li H. Statistical learning methods, second edition[M]. Beijing: Tsinghua University Press, 2019. ]
[32]	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[J]. 地球信息科学学报, 2018,20(3):291-301.
	[ Chen Z D, Qiao B W, Zhang J. Identification and spatial interaction of urban functional regions in Beijing based on the characteristics of residents' traveling[J]. Journal of Geo-information Science, 2018,20(3):291-301. ]

序号	属性字段名称	数据类型	作用描述
1	OBJECTID	Integer	唯一识别码
2	名称	String	POI点名称
3	x	Double	经度
4	y	Double	纬度
5	Type	String	POI类型

类别	名称	类别	名称
1	茶座甜品	13	科研机构
2	KTV	14	培训机构
3	展览馆	15	体育场馆
4	公司企业	16	图书馆
5	大学	17	餐厅
6	风景名胜	18	文化宫
7	购物中心	19	基础教育
8	集市	20	银行
9	商铺	21	游乐园
10	酒吧	22	住宅区
11	酒店	23	医院
12	剧院

街区1		街区216		街区345		街区360
POI类型	权重	POI类型	权重	POI类型	权重	POI类型	权重
游乐园	10.33	风景名胜	7.45	商铺	13.99	商铺	17.8
商铺	6.82	游乐园	1.44	餐厅	7.49	住宅区	9.30
公司企业	6.62	公司企业	0.69	酒吧	5.83	餐厅	9.28
餐厅	3.41	茶座甜品	0.36	住宅区	5.57	公司企业	6.18
风景名胜	3.37	基础教育	0.20	茶座甜品	5.35	酒店	1.99
茶座甜品	3.30	商铺	0.17	购物中心	2.20	茶座甜品	1.48

主题1	主题2	主题4	主题7	主题12	主题14
茶座甜品	风景名胜	酒吧	图书馆	购物中心	科研机构
餐厅	餐厅	餐厅	住宅区	商铺	商铺
商铺	酒店	茶座甜品	餐厅	餐厅	茶座甜品
培训机构	剧院	住宅区	商铺	茶座甜品	餐厅
公司企业	公司企业	商铺	银行	酒吧	基础教育
主题 15	主题 16	主题 17	主题 19	主题 20	主题 21
酒店	游乐园	公司企业	住宅区	体育场馆	大学
餐厅	茶座甜品	餐厅	商铺	餐厅	餐厅
商铺	公司企业	培训机构	餐厅	商铺	商铺
体育场馆	商铺	基础教育	公司企业	培训机构	茶座甜品
文化宫	购物中心	文化宫	酒店	公司企业	公司企业

回归模型	F	Sig.
高混合街区	16.706	0.000
中等混合街区	11.399	0.000
低混合街区	9.467	0.000