A framework of urban profiling system was proposed based on a large number of urban history express data for urban data analysis through making full use of the express sheet information, including time, address and item. The data of several express companies were gathered and pre-processed by means of data completion, address conversion, item type extraction and data format conversion method. And four indicators were proposed: delivering frequency, time, address and item. Based on Xi’an real historical data set, express data of different social groups and urban areas in the city was analyzed, respectively, and an urban profiling was made through data analysis results. In combination with the actual situation of the society, a reasonable explanation of the laws and anomalies was made in the analysis results. Finally, urban profiling results were integrated and demonstrated through a visualization platform. Results show that the proposed urban profiling system can detect the law and anomaly of the delivery behavior between different social groups and regions.
Fig.1Visualization analysis framework of urban profilingusing express big data
实验组号
Sr
Sc
Rc/%
Ra/%
1
87
81
87
93.1
2
92
83
92
90.2
3
85
82
85
96.5
4
86
81
86
94.2
5
90
88
90
98.7
6
94
88
94
93.6
7
90
82
90
91.1
8
87
81
87
93.1
9
92
86
92
93.4
10
96
90
96
93.7
Tab.1Results of item type extraction algorithm inexpress data
信息类别
数据子项
样例
快递信息
运单号
602670843721
寄件时间
2016 09|2016 38
快递公司
顺丰速运
寄件人信息
寄件人电话
9852e4d457j3s...
地址经纬度
117.316453 31.855327
收件人信息
收件人电话
15i42d35098d1...
地址经纬度
108.989858 34.252365
物品信息
物品类型
鞋类箱包
学校信息
学校名称
XXX大学
学校类型
本科院校
学校属性
理工
Tab.2Sample of express data after data pre-processing
高校
寄递频次
寄递用户量
学校人数
西安交通大学
19 728
11 430
38 000
西北工业大学
17 627
10 097
28 000
长安大学
18 128
11 096
33 000
西安电子科技大学
17 023
10 579
30 000
陕西师范大学
12 643
8 159
25 900
西北大学
13 352
8 337
25 000
Tab.3Statistics of college express information
Fig.2Express network of one college in China
Fig.3Distribution of university’s delivery time
Fig.4Comparison of delivery time distribution betweenuniversities and companies
Fig.5Comparison of the types of items delivered by universities and companies
Fig.6Distribution of university express items
Fig.7Top5 items purchased in March and November by universities of different levels
Fig.8Urban area division of Xi 'an
Fig.9Distribution of delivery time in high-end residential areas
Fig.10Distribution of express items of high-grade community
Fig.11Receipt time distribution between different types of regions
Fig.12Top5 item types purchased by users in different regions
Fig.13Visualization system interface Interface of express big data urban profiling system
[1]
谭旭. 基于物流数据的快递网络分析与建模[D]. 杭州: 浙江大学, 2015. TAN Xu. Analysis and modeling of express delivery network based on logistics data [D]. Hangzhou: Zhejiang University, 2015.
[2]
郝晟. 面向侦查的快递数据分析挖掘系统[D]. 天津: 天津大学,2014. HAO Miao. Express data analysis and mining system for investigation [D]. Tianjin: Tianjin University, 2014.
[3]
文杰锋. 快递物流配送异常检测方法研究[D]. 重庆: 重庆邮电大学, 2016. WEN Jie-feng. Research on abnormal detection methods for express delivery logistics [D]. Chongqing: Chongqing University of Posts and Telecommunications, 2016.
[4]
GAO F, ZHAO Q L. Evidential reasoning-based airline network design for long-haul transportation in express delivery[J]. Tehnicki Vjesnik-Technical Gazette, 2017, 24 (5): 1551- 1559
[5]
刘二超. 快递服务便利店选址问题研究[D]. 北京: 清华大学, 2014. LIU Er-chao. Study on the location of express service convenience stores [D]. Beijing: Tsinghua University, 2014.
[6]
TANG S Y, DENG G M. Based on the theory of grey system to forecast China's business volume of express services[J]. Modern Economy, 2015, 6 (2): 283
doi: 10.4236/me.2015.62025
[7]
YIN S, JIANG Y C, TIAN Y, et al. A data-driven fuzzy information granulation approach for freight volume forecasting[J]. IEEE Transactions on Industrial Electronics, 2017, 64 (2): 1447- 1456
doi: 10.1109/TIE.2016.2613974
[8]
李万彪, 余志, 龚峻峰, 等 基于关系数据模型的犯罪网络挖掘研究[J]. 中山大学学报: 自然科学版, 2014, 53 (5): 1- 7 LI Wan-xi, YU Zhi, GONG Jun-feng, et al Criminal network mining based on relational data model[J]. Journal of Sun Yatsen University: Natural Science, 2014, 53 (5): 1- 7
[9]
范文兵, 吴宇昊. 基于SaaS模式的快递投递业务系统设计[J]. 计算机应用, 2017, 37(增 1): 312-316. FAN Wen-bing, WU Yu-hao. Design of integrated express delivery system based on SaaS[J]. Journal of Computer Applications, 2017, 37(Suppl. 1): 312-316.
[10]
GUO B, ZHANG D Q, YU Z W, et al. Extracting social and community intelligence from digital footprints[J]. Journal of Ambient Intelligence and Humanized Computing, 2014, 5 (1): 1- 2
[11]
GUO B, LI J, YU Z, et al CityTransfer: transferring inter-and Intra-City knowledge for chain store site recommendation based on multi-Source urban data[J]. Wearable and Ubiquitous Technologies, 2018, 1 (4): 135
[12]
KOOTI F , GRBOVIC M , AIELLO L, et al. Analyzing Uber's Ride- sharing economy [C]// International Conference. International World Wide Web Conferences Steering Committee, 2017: 574-582.
[13]
YUAN J, ZHENG Y, XIE X. Discovering regions of different functions in a city using human mobility and POIs [C] // ACM 18th SIGKDD International Conference on Knowledge Discovery and Data mining. Beijing: ACM, 2012: 186-194.
[14]
DENG C, ZHAO H, ZHANG Z S, et al. Fast and accurate neural word segmentation for chinese[J]. Association for Computational Linguistics, 2017, 608- 615
[15]
CHEN X , SHI Z , QIU X , et al Adversarial multi-criteria learning for Chinese word segmentation[J]. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017, 1193- 1203
[16]
JENSEN P Network-based predictions of retail store commercial categories and optimal locations[J]. Physical Review E, 2006, 74 (3): 035101
[17]
ZHANG J, HUANG D G, HUANG K Y, et al. λ-active learning based microblog-oriented Chinese word segmentation [J]. Journal of Tsinghua University: Science and Technology, 2018, 58 (3): 260- 265
[18]
JENSEN P. Analyzing the localization of retail stores with complex systems tools [C]// International Symposium on Intelligent Data Analysis. 2009: 10-20.
[19]
LATHIA N, QUERCIA D, CROWCROFT J. The hidden image of the city: sensing community well-being from urban mobility [C]// International Conference on Pervasive Computing. 2012: 91-98.
[20]
MACKINLAY A Event studies in economics and finance[J]. Journal of Economic Literature, 1997, 35 (1): 13- 39
