Development of a Knowledge Base for Reasoning Penalty for Traffic Violations Based on Event Evolutionary Graph
-
摘要: 我国道路交通安全法律法规体系不断完善，要求交警部门针对具体的交通违法行为给予不同程度的处罚，为了响应国家以智慧化推动治理现代化的号召，可利用事理图谱技术构建道路交通领域知识库，揭示道路交通违法行为事件之间的逻辑关系，能快速且有效辅助处理交通违章事件。以开源数据为基础，面向道路交通违法行为构建事件语料库，通过事件抽取、关系抽取等步骤，构建交通违法事理图谱，在此基础上，实现了交通违法问答系统。研究结果表明：利用所提模型抽取道路交通违法行为事件的分类评价指标F1值达到0.832，识别率很高。此外，基于事理图谱的交通违法问答系统展示了事理图谱技术在道路交通领域具备良好的应用前景。Abstract: With continuous improvement of laws and regulations related to road safety in China, traffic police departments are required to issue different penalties for specific traffic violations. In response to the call and to improve the capacity of"intelligent governance", this article proposes to develop a knowledge base for traffic violations and accidents with event evolutionary graph, which can be used to reason appropriate penalty for traffic violations& accidents quickly and efficiently. This paper uses open-source data to develop the knowledge base required for processing traffic violations/accidents and creates an event evolutionary graph through extracting traffic events and their relationship. Moreover, a knowledge base system for traffic violations/accidents is developed. The experimental results show that the proposed system offers a F1 score of 0.832 when classifying traffic violations and accidents, which indicates that the event evolutionary graph is a good tool for reasoning the penalty of traffic violations and accidents.
-
Key words:
- traffic safety /
- traffic violation /
- event evolutionary graph /
- knowledge base system /
- road traffic
-
图 2 交通违法事理图谱基本构建过程示意图
Figure 2. Schematic diagram of basic construction process of the traffic violation evolutionary graph
图 4 道路交通违法问答系统框架
Figure 4. Framework of the question answering system of road traffic violations
表 1 酒驾醉驾行为及处罚内容
Table 1. Drink-driving, drunk driving and penalties
违法行为内容 处罚事件内容 饮酒驾驶 暂扣6个月机动车驾驶证+1 000~2 000元罚款+一次记满12分 再次饮酒驾驶 10日以下拘留+1 000~2 000元罚款+吊销驾驶证+2年内不得重新取得机动车驾驶证 饮酒和醉酒驾驶发生重大交通事故构成犯罪 追究刑事责任+吊销驾驶证+终身禁驾 饮酒驾驶营运机动车 15日拘留+5 000元罚款+吊销驾驶证+5年内不得重新取得驾驶证 醉酒驾驶 约束至酒醒+吊销驾驶证+5年内不得重新取得驾驶证+追究刑事责任 醉酒驾驶营运机动车 约束至酒醒+吊销机动车驾驶证+追究刑事责任+10年内不得重新取得机动车驾驶证+重新取得驾驶证后不得驾驶营运机动车 
下载: 导出CSV
表 2 道路交通违法行为涉及要素
Table 2. Elements involved in road traffic violations
节点要素 具体描述 包括实体 法律条款 中华人民共和国颁布施行的道路交通法律、法规及相关交通管理规章条款，违法行为及行政处罚的参考依据 《中华人民共和国道路交通安全法》 《中华人民共和国道路交通安全法实施条例》等 违法行为 违反《中华人民共和国道路交通安全法》及相关的法律、法规和相关交通管理规章的行为 酒驾、超速、超员、疲劳驾驶、逆行、不按规定让行等 处罚事件 依照交通管理法律、法规和规章的规定，对道路交通违章行为人所作的行政处罚 记分、警告、罚款、吊扣驾驶证、拘留等
下载: 导出CSV
表 3 北京市道路交通安全违法行为及处罚记分标准（部分）
Table 3. Road traffic violations and penalty standards in Beijing (Part)
违法行为 行为依据 处罚依据 记分 警告 罚款/元 暂扣/月 拘留/d 吊销 造成交通事故后逃逸，构成犯罪的 法第七十条、条例第八十八条 法第一百零一条第二款 未取得驾驶证驾驶机动车的 法第十九条第一款 法第九十九条第一款第一项、第二款 500 15以下 吊销（终生） 驾驶机动车在高速公路上行驶低于规定时速20%以下的 条例第七十八条 法第九十条 警告 驾驶中型以上载客汽车在高速公路上行驶超过规定时速50%的 法第四十二条，条例第四十五条、四十六条、七十八条，办法第三十九条 法第九十九条第一款第四项、第二款 12 1 800 可以吊销 醉酒后驾驶机动车的 法第二十二条第二款 法第九十一条第二款 吊销（5年） 因饮酒后驾驶机动车被处罚，再次饮酒后驾驶机动车的 法第二十二条第二款 法第九十一条第一款 2 000 1以上10以下 吊销 注：上述条款中，法是指《中华人民共和国道路交通安全法》、条例是指《中华人民共和国道路交通安全法实施条例》、办法是指《北京市实施<中华人民共和国道路交通安全法>办法》。
下载: 导出CSV
表 4 问题分类
Table 4. Classification of user questions
问题标识 类别名称 涉及款目 问题描述（范例） LEG 询问法律条款 A→B/C 违法行为A触发的处罚是什么？
怎样处罚违法行为A？PUN 询问处罚 A→D/E/F/G/H/I 违法行为A的行为依据/处罚依据是什么？
违法行为A有什么行为依据/处罚依据？LEG_PUN 询问法律条款和处罚 A→B/C & A→D/E/F/G/H/I 违法行为A的行为依据/处罚依据是什么，触发的处罚是什么？
违法行为A的行为依据/处罚依据是什么，怎样进行处罚？PEC 询问违法行为 B/C/D/E/F/G/H/I→A 什么违法行为的行为依据/处罚依据是B/C？
什么违法行为为记D分？UNKOWN 其他 A 直接输入违法行为A 注：A~I依次分别代表违法行为、行为依据、处罚依据、记分、警告、罚款、暂扣（月）、拘留（日）、吊销；此处的“违法行为”特指道路交通违法行为。
下载: 导出CSV
-
[1] WORLD HEALTH ORGANIZATION. Global status report on road safety 2018[R]. Geneva: World Health Organization, 2018. [2] 中华人民共和国统计局. 中国统计年鉴[M]. 北京: 中国统计出版社, 2019.National Bureau of Statistics. China statistical yearbook[M]. Beijing: China Statistics Press, 2019. (in Chinese) [3] 裴玉龙, 马骥. 道路交通事故道路条件成因分析及预防对策研究[J]. 中国公路学报, 2003(4): 78-83. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200304017.htmPEI Y L, MA J. Research on countermeasures for road condition causes of traffic accidents[J]. China Journal of Highway and Transport, 2003(4): 78-83. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL200304017.htm [4] 李杰, 曾叙砜, 李平, 等. 道路交通安全文献的知识可视化综述[J]. 交通信息与安全, 2020, 38(1): 13-19. doi: 10.3963/j.jssn.1674-4861.2020.01.002LI J, ZENG X F, LI P, et al. Visualization review of road traffic safety literature[J]. Journal of Transport Information and Safety, 2020, 38(1): 13-19. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2020.01.002 [5] 毛敏, 喻翔. 道路交通事故致因分析[J]. 公路交通科技, 2002(5): 125-127. doi: 10.3969/j.issn.1002-0268.2002.05.036MAO M, YU X. Analysis of traffic accident causation[J]. Journal of Highway and Transportation Research and Development, 2002(5): 125-127. (in Chinese) doi: 10.3969/j.issn.1002-0268.2002.05.036 [6] 王磊, 吕璞, 林永杰. 高速公路交通事故影响因素分析及伤害估计[J]. 中国安全科学学报, 2016, 26(3): 86-90. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201603016.htmWANG L, LYU P, LIN Y J. Traffic accidents on freeways: influencing factors analysis and injury severity evaluation[J]. China Safety Science Journal, 2016, 26(3): 86-90. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201603016.htm [7] HEZAVEH A M, NORDFJAERN T, MAMDOOHI A R, et al. Predictors of self-reported crashes among Iranian drivers: Exploratory analysis of an extended driver behavior questionnaire[J]. Promet-Traffic & Transportation, 2018, 30(1): 35-43. http://www.ingentaconnect.com/content/doaj/03535320/2018/00000030/00000001/art00004 [8] MASAKI I. A brief history of ITS[M]. Cambridge: Masachusetts Institute of Technology, 1999. [9] 张可, 齐彤岩, 刘冬梅, 等. 中国智能交通系统(ITS)体系框架研究进展[J]. 交通运输系统工程与信息, 2005(5): 10-15. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT200505002.htmZHANG K, QI T Y, LIU D M, et al. The latest achievements of Chinese national ITS architecture[J]. Journal of Transportation Systems Engineering and Information Technology, 2005(5): 10-15. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT200505002.htm [10] 万文佳, 孙烨垚, 于丰泉. 智能化道路基础设施的交通安全应用研究[C]. 第十五届中国智能交通年会, 中国深圳: 中国智能交通协会, 2020.WAN W J, SUN Y Y, YU F Q. Research on traffic safety application of intelligent road infrastructure[C]. The 15th ITS China Congress, Shenzhen, China: ITS China, 2020. (in Chinese) [11] SINGHAL A. Introducing the knowledge graph: things, not strings[EB/OL]. (2012-5-16)[2020-10-01]. https://www.blog.google/products/search/introducing-knowledge-graphthings-not/. [12] 曹倩, 赵一鸣. 知识图谱的技术实现流程及相关应用[J]. 情报理论与实践, 2015, 38(12): 127-132. https://www.cnki.com.cn/Article/CJFDTOTAL-QBLL201512026.htmCAO Q, ZHAO Y M. The realization process of knowledge map technology and its relevant application[J]. Information Studies: Theory & Application, 2015, 38(12): 127-132. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QBLL201512026.htm [13] 刘挺. 从知识图谱到事理图谱[EB/OL]. (2017-11-16)[2020-10-01]. https://blog.csdn.net/tgqdt3ggamdkhaslzv/article/details/78557548.LIU T. From knowledge graph to event evolutionary graph[EB/OL]. (2017-11-16)[2020-10-01]. https://blog.csdn.net/tgqdt3ggamdkhaslzv/article/details/78557548. (in Chinese) [14] 刘焕勇, 薛云志. 事理图谱: 下一代知识图谱[EB/OL]. (2018-12-25)[2020-10-01]. https://blog.csdn.net/lhy2014/article/details/85247268.LIU H Y, XUE Y Z. Event evolutionary graph: Next-generation knowledge graph[EB/OL]. (2018-12-25)[2020-10-01]. https://blog.csdn.net/lhy2014/article/details/85247268. (in Chinese) [15] 周京艳, 刘如, 李佳娱, 等. 情报事理图谱的概念界定与价值分析[J]. 情报杂志, 2018, 37(5): 31-36. doi: 10.3969/j.issn.1002-1965.2018.05.006ZHOU J Y, LIU R, LI J Y, et al. Study on the concept and value of intelligence event evolutionary graph[J]. Journal of Intelligence, 2018, 37(5): 31-36. (in Chinese) doi: 10.3969/j.issn.1002-1965.2018.05.006 [16] 刘焕勇. 事理图谱版Magi: 实时事理逻辑知识库(事理图谱)终身学习项目-EventKGNELL (学迹)[EB/OL]. (2020-3-18)[2020-10-01]. https://zhuanlan.zhihu.com/p/114155171.LIU H Y. Magi: Real-time event logical knowledge base lifelong learning project-EventKGNELL[EB/OL]. (2020-3-18)[2020-10-01]. https://zhuanlan.zhihu.com/p/114155171. (in Chinese) [17] 田依林, 李星. 基于事理图谱的新冠肺炎疫情网络舆情演化路径分析[J]. 情报理论与实践, 2021, 44(3): 76-83. https://www.cnki.com.cn/Article/CJFDTOTAL-QBLL202103011.htmTIAN Y L, LI X. Analysis on the evolution path of COVID-19 network public opinion based on the event evolutionary graph[J]. Information Studies: Theory & Application, 2021, 44(3): 76-83. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QBLL202103011.htm [18] 冯钧, 王云峰, 邬炜, 等. 城市内涝事理图谱构建方法及应用[J]. 河海大学学报(自然科学版), 2020, 48(6): 479-487. https://www.cnki.com.cn/Article/CJFDTOTAL-HHDX202006001.htmFENG J, WANG Y F, WU Wei, et al. Construction method and application of event logic graph for urban waterlogging[J]. Journal of Hohai University (Natural Sciences), 2020, 48(6): 479-487. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HHDX202006001.htm [19] 张海, 崔宇路, 余露瑶, 等. 基于数据挖掘的智慧课堂教学行为事理图谱研究[J]. 远程教育杂志, 2020, 38(2): 80-88. https://www.cnki.com.cn/Article/CJFDTOTAL-YCJY202002008.htmZHANG H, CUI Y L, YU L Y, et al. Study of classroom event logic graph of intelligent teaching based on method of data mining[J]. Journal of Distance Education, 2020, 38(2): 80-88. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YCJY202002008.htm [20] 朱福勇, 刘雅迪, 高帆, 等. 基于图谱融合的人工智能司法数据库构建研究[J]. 扬州大学学报(人文社会科学版), 2019, 23(6): 89-96. https://www.cnki.com.cn/Article/CJFDTOTAL-YZDR201906009.htmZHU F Y, LIU Y D, GAO F, et al. Research on artificial intelligence judicial database construction based on graph fusion[J]. Journal of Yangzhou University (Humanities & Social Sciences), 2019, 23(6): 89-96. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YZDR201906009.htm [21] 孙鑫瑞, 孟雨, 王文乐. 基于知识图谱与目标检测的微博交通事件识别[J]. 数据分析与知识发现, 2020, 4(12): 136-147. doi: 10.11925/infotech.2096-3467.2020.0596SUN X R, MENG Y, WANG W L. Identifying traffic events from Weibo with knowledge graph and target detection[J]. Data Analysis and Knowledge Discovery, 2020, 4(12): 136-147. (in Chinese) doi: 10.11925/infotech.2096-3467.2020.0596 [22] 姬艳涛, 林通, 王犇. 我国公安交通管理研究的总体态势与前沿问题: 基于科学文献计量的可视化分析[J]. 中国人民公安大学学报(自然科学版), 2019, 25(2): 68-75. doi: 10.3969/j.issn.1007-1784.2019.02.014JI Y T, LIN T, WANG B. The general situation and frontier of public security traffic management research in China based on scientometrics[J]. Journal of People's Public Security University of China (Science and Technology), 2019, 25(2): 68-75. (in Chinese) doi: 10.3969/j.issn.1007-1784.2019.02.014 [23] 马社强, 丁立民, 刘东, 等. 我国道路交通安全状况及挑战[J]. 中国人民公安大学学报(自然科学版), 2020, 26(4): 35-41. https://www.cnki.com.cn/Article/CJFDTOTAL-GOAN202004006.htmMA S Q, DING L M, LIU D, et al. Status and challenge of road traffic safety in China[J]. Journal of People's Public Security University of China (Science and Technology), 2020, 26(4): 35-41. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GOAN202004006.htm [24] 徐雷, 潘珺. 事件表示方式及其语义表示模型研究[J]. 情报杂志, 2019, 38(6): 159-167. https://www.cnki.com.cn/Article/CJFDTOTAL-QBZZ201906024.htmXU L, PAN J. Research on the way of event representation and its semantic representation model[J]. Journal of Intelligence, 2019, 38(6): 159-167. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QBZZ201906024.htm [25] 赵妍妍, 秦兵, 车万翔, 等. 中文事件抽取技术研究[J]. 中文信息学报, 2008(1): 3-8. https://www.cnki.com.cn/Article/CJFDTOTAL-MESS200801002.htmZHAO Y Y, QIN B, CHE W X, et al. Research on Chinese event extraction[J]. Journal of Chinese Information Processing, 2008(1): 3-8. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MESS200801002.htm [26] LI X, ROTH D. Learning question classifiers: The role of semantic information[J]. Natural Language Engineering, 2006, 12(3): 229-249. http://www.researchgate.net/profile/Xin_Li236/publication/220597341_Learning_question_classifiers_the_role_of_semantic_information_Nat_Lang_Eng/links/5691d8ea08aee91f69a5221a.pdf [27] 文勖, 张宇, 刘挺, 等. 基于句法结构分析的中文问题分类[J]. 中文信息学报, 2006(2): 33-39. https://www.cnki.com.cn/Article/CJFDTOTAL-MESS200602004.htmWEN X, ZHANG Y, LIU T, et al. Syntactic structure parsing based Chinese question classification[J]. Journal of Chinese Information Processing, 2006(2): 33-39. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MESS200602004.htm -
点击查看大图
图(5) / 表(4)
计量
- 文章访问数: 1569
- HTML全文浏览量: 744
- PDF下载量: 114
- 被引次数: 0