| 基于自然语言处理的交通拥堵程度评价 |
| 陈洪昕1, 崔健1, 张佐1,2, 姚丹亚1 |
| 1. 清华大学自动化系, 北京 100084; 2. 清华信息科学与技术国家实验室, 北京 100084 |
| Assessment of the level of congestion based on natural language processing |
| CHEN Hongxin1, CUI Jian1, ZHANG Zuo1,2, YAO Danya1 |
| 1. Department of Automation, Tsinghua University, Beijing 100084, China; 2. Tsinghua National Laboratory for Information Science and Technology, Beijing 100084, China |
摘要:
| |||
| 摘要近年来, 微博等社交媒体上出现了越来越多的道路交通信息。微博交通数据能够有效补充传统交通数据, 为交通分析提供一个新维度。该文以微博数据为基础, 总结了人们用自然语言表达交通拥堵程度的常用方式, 采用模糊评价方法量化不同人用自然语言描述交通拥堵时的主观感受; 采用模糊推理方法进行数据融合, 综合评价多人用自然语言描述同一路段道路通行状况时该路段的交通拥堵程度。实验选取3个路段拍摄一定时长的实际路况视频, 邀请受试者随机抽取视频片段并对该时刻的交通状况做出主观评价。实验融合评价结果与百度地图发布的实时路况具有一致性, 验证了该方法的可行性。 | |||
| 关键词 ：交通工程,评价方法,模糊推理,自然语言 | |||
| Abstract：In recent years, an increasing amount of traffic information has been posted on social media such as micro-blogs. This information provides a new opportunity for traffic analysis using micro-blog traffic data to supplement traditional traffic data. The micro-blog data has been analyzed to identify frequently-used natural language description of traffic conditions with fuzzy assessments used to quantify the subjective feelings of different people describing traffic congestion with natural language. The fuzzy reasoning data fusion method aggregated evaluations by different people describing the congestion of the same section of a road. Videos were collected from three road segments with observers invited to evaluate the road traffic conditions in the videos. The integration results are similar to the real-time traffic scenarios released by Baidu Map, which verify the feasibility of this fuzzy method. | |||
| Key words：transportation engineeringassessment methodfuzzy reasoningnatural language | |||
| 收稿日期: 2015-06-10 出版日期: 2016-04-01 | |||
| |||
| 通讯作者:姚丹亚,研究员,E-mail:yaody@tsinghua.edu.cnE-mail: yaody@tsinghua.edu.cn | |||
| 引用本文: |
| 陈洪昕, 崔健, 张佐, 姚丹亚. 基于自然语言处理的交通拥堵程度评价[J]. 清华大学学报（自然科学版）, 2016, 56(3): 287-293. CHEN Hongxin, CUI Jian, ZHANG Zuo, YAO Danya. Assessment of the level of congestion based on natural language processing. Journal of Tsinghua University(Science and Technology), 2016, 56(3): 287-293. |
| 链接本文: |
| http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2016.21.034或 http://jst.tsinghuajournals.com/CN/Y2016/V56/I3/287 |
图表:
 |
| 表1 不同语气副词描述交通拥堵打分结果 |
 |
| 表2 语气副词对应严重程度打分结果 |
 |
| 表3 自然语言评价道路拥堵程度打分表 |
 |
| 图1 对于时间间隔的各模糊子集隶属函数 |
 |
| 表4 TＧS型模糊推理规则 |
 |
| 图2 3个路段交通拥堵状况变化图 |
参考文献:
| [1] 祝付玲. 城市道路交通拥堵评价指标体系研究[D]. 南京:东南大学, 2006.ZHU Fuling. Research on Index System of Urban Traffic Congestion Measures[D]. Nanjing:Southeast University, 2006. (in Chinese) [2] Schrank D L, Lomax T J. The 2007 Urban Mobility Report[M]. Texas, USA:Texas Transportation Institute, Texas A & M University, 2007. [3] Transportation Research Board. Highway Capacity Manual[M]. Washington DC, USA:TRB, National Research Council, 2000. [4] JTG B01-2003, 公路工程技术标准[S]. 北京:中华人民共和国交通运输部, 2003.JTGB01-2003, Highway Technical Standard[S]. Beijing:Ministry of Transportation of the People's Republic of China, 2003. (in Chinese) [5] 饭田恭敬编著. 《交通工程学》[M]. 邵春福, 杨海, 石其信, 等译. 北京:人民交通出版社, 1994.Iida Yasukyung. Traffic Engineering[M]. Shao Chunfu, YANG Hai, SHI Qixin, et al. Trans. Beijing:China Communications Press, 1994. (in Chinese) [6] Quiroga C A. Performance measures and data requirements for congestion management systems[J]. Transportation Research Part C:Emerging Technologies, 2000, 8(1):287-306. [7] J. d'Abadie R R, Ehrlich T F. Contrasting time-based and distance-based measures for quantifying traffic congestion levels:Analysis ofNew Jersey Counties[J]. Transportation Research Record:Journal of the Transportation Research Board, 2002(1817):143-148. [8] 公安部, 建设部. 城市道路交通管理评价指标体系(2002年版)各类城市评价指标明细表[J]. 道路交通管理. 2002(6):45-46.Ministry of Public Security, Ministry of Construction. The Evaluation Index System of Urban Road Traffic Management (2002 Edition)-Urban Evaluation Index[J]. Road Traffic Management. 2002(6):45-46. (in Chinese) [9] DB11T 785-2011, 城市道路交通运行评价指标体系[S]. 北京:北京市交通委员会, 2011.DB11T 785-2011, Urban Road Traffic Performance Index[S]. Beijing:Beijing Municipal Commission of Transport, 2011. (in Chinese) [10] 北京交通发展研究中心, 北京四通智能交通系统集成有限公司, 北京交通大学. 交通拥堵评价研究报告, k06006[R]. 北京:北京交通发展研究中心、北京四通智能交通系统集成有限公司、北京交通大学, 2007.Beijing Transportation Research Center, Beijing Stone Intelligent Transportation System Integration Co., LTD, Beijing Jiaotong University. Traffic Congestion Evaluation, k06006[R]. Beijing:Beijing Transportation Research Center, Beijing Stone Intelligent Transportation System Integration Co., LTD, Beijing Jiaotong University, 2007(in Chinese) [11] 郭继孚, 刘梦涵, 于雷等. 北京市交通拥堵宏观评价指标体系开发及其应用[C]//2007第三届中国智能交通年会. 南京:东南大学出版社, 2007:341-346.GUO Jifu, LIU Menghan, YU Lei, et al. Development and applications of macroscopic measurement of traffic congestion in Beijing[C]//The 3rd China Annual Conference on ITS 2007. Nanjing:Southeast University Press, 2007:341-346. (in Chinese) [12] 全永燊, 郭继孚, 关积珍等. 交通拥堵评价研究及北京交通拥堵评价的实证分析[C]//2007第三届中国智能交通年会. 南京:东南大学出版社, 2007:1-6.QUAN Yongshen, GUO Jifu, GUAN Jizhen, et al. Research on traffic congestion evaluation and empirical analysis of Beijing[C]//The 3rd China Annual Conference on ITS 2007. Nanjing:Southeast University Press, 2007:1-6. (in Chinese) [13] 张雪莲, 于雷, 刘梦涵. 基于交通需求的路网交通拥堵评价模型[J]. 现代交通技术, 2008, 5(6):71-75.ZHANG Xuelian, YU Lei, LIU Menghan. Traffic demand-based traffic congestion measurement models for road networks[J]. Modern Transportation Technology, 2008, 5(6):71-75. (in Chinese) [14] 李洪兴, 汪培庄. 模糊数学[M]. 北京:国防工业出版社, 1993. LI Hongxing, WANG Peizhuang. Fuzzy Mathematics[M]. Beijing:National Defense Industry Press, 1993. (in Chinese) [15] 李洪兴, 汪培庄. 模糊系统理论与模糊计算机[M]. 北京:科学出版社, 1996.LI Hongxing, WANG Peizhuang. Fuzzy System Theory and Fuzzy Computer[M]. Beijing:Science Press, 1996. (in Chinese) |
相关文章:
|
