基于知识图谱推理的风险车辆识别方法研究

doi:10.3969/j.issn.1674-0696.2022.01.04

摘要/Abstract

摘要： 为了快速识别高速公路风险车辆，采用知识图谱推理的识别方法，研究了高速公路运行车辆多元历史信息与安全风险之间的潜在联系。首先，确定了风险车辆类型和文本数据的来源，建立了考虑一对多、多对一和多对多关系的表示学习模型；然后，以最小化对数损失为目标，基于开放世界假设进行了样本训练；最后，采用随机游走推理模型进行知识推理，构建了高速公路风险车辆知识图谱。结果表明：建立的模型能兼顾准确度和计算效率，有效识别高速公路运行的潜在风险；语义关系识别领域的知识图谱技术可应用于高速公路运行风险预警管控。

关键词: 交通工程；运行风险；知识图谱；知识推理；表示学习

Abstract: In order to quickly identify highway risk vehicles, the potential relationship between multiple historical information of highway vehicles and safety risk was studied by using the identification method of knowledge graph reasoning. Firstly, the types of risk vehicles and the sources of text data were determined, and a representation learning model considering 1-to-N, N-to-1 and N-to-N relationships was established. Then, aiming at minimizing the logarithmic loss, the sample training was carried out based on the open world hypothesis. Finally, the random walk reasoning model was used for knowledge reasoning, and the knowledge graph of highway risk vehicles was constructed. The results show that the proposed model can balance the accuracy and efficiency, and effectively identify the potential risks of expressway operation. The knowledge graph technology in the field of semantic relationship recognition can be applied to the early warning and control of highway operation risk.

Key words: traffic engineering; operational risk; knowledge graph; knowledge reasoning; representation learning

中图分类号:

U492.8

俞山川，谢耀华，陈晨，周健. 基于知识图谱推理的风险车辆识别方法研究[J]. 重庆交通大学学报（自然科学版）, 2022, 41(01): 22-28.

YU Shanchuan, XIE Yaohua, CHEN Chen, ZHOU Jian. Risky Vehicle Identification Method Based on Knowledge Graph Reasoning[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(01): 22-28.

参考文献

［1］王昊奋，漆桂林，陈华钧.知识图谱：方法、实践与应用［M］.北京：电子工业出版社，2019.
WANG Haofen, QI Guilin, CHEN Huajun. Knowledge Graph: Method, Practice and Application［M］. Beijing：Publishing House of Electronics Industry, 2019.
［2］左毅，张桂林，吴蔚，等.面向战场海空目标识别的知识图谱应用［J］.指挥信息系统与技术，2019，10(3)：1-5.
ZUO Yi, ZHANG Guilin, WU Wei, et al. Knowledge graph application for battlefield airborne/maritime target intelligent recognition ［J］. Command Information System
and Technology, 2019, 10(3): 1-5.
［3］ PHAM T. An improvement method for semantic mapping database to ontology［J/OL］. Journal of Computer Science and Cybernetics, 2018, 34(3): 187-198.https:∥
www.researchgate.net/publication/331954996_ An_Improvement_Method_for_Semantic_Mapping_Database_to_Ontology.
［4］ ALLAHYARI M, POURIYEH S, ASSEFI M, et al. A brief survey of text mining: Classification, clustering and extraction techniques ［EB/OL］. (2017-07-11)［2020-09-12
］. https:∥www.researchgate.net/profile/Mehdi-
Allahyari/publication/318336890_A_Brief_Survey_of_Text_Mining_Classification_Clustering_and_Extraction_Techniques/links/5964fe450f7e9b2a367cd73b/A-Brief-Survey-
of-Text-Mining-Classification-Clustering-and-Extraction-Techniques.pdf.
［5］陈恒，祁瑞华，朱毅，等.球坐标建模语义分层的知识图谱补全方法［J］.计算机工程与应用, 2021, 57(15): 101-108.
CHEN Heng, QI Ruihua, ZHU Yi, et al.Knowledge graph comple-tion method for semantic hierarchies of spherical coordinate modeling［J］. Computer Engineering and
Applications, 2021, 57(15): 101-108.
［6］ HE Shizhu, LIU Kang, JI Guoliang, et al. Learning to represent know-ledge graphs with Gaussian embedding［C］∥ Proceedings of the 24th ACM International on
Conference on Information and Knowledge Management. Melbourne, Australia: ACM, 2015: 623-632.
［7］ XIAO Han, HUANG Minlie, YU Hao, et al. TransG: A generative model for knowledge graph embedding ［EB/OL］(2016-08-10)［2020-10-10］.
https:∥www.researchgate.net/profile/Han-Xiao-
4/publication/282000528_TransG_A_Generative_Mixture_Model_for_Knowledge_Graph_Embedding/links/57ab4fe008ae0932c97122f2/TransG-A-Generative-Mixture-
Model-for-Knowledge-Graph-Embedding.pdf.
［8］ NICKEL M, TRESP V, KRIEGEL H. A three-way model for collec-tive learning on multi-relational data ［C/OL］∥ Proceedings of the 28th International Conference on
International Conference on Machine Learning, ICML 2011. Washington D.C., USA: ［s.n.］, 2011: 809-816. https:∥www.mendeley.com/catalogue/0e9d5ae2-405a-35d1-
8895-916deb25df24/.
［9］ BORDES A, GLOROT X, WESTON J, et al. A semantic matching energy function for learning with multi-relational data［J］. Machine Learning, 2014, 94(2): 233-259.
［10］ SOCHER R, CHEN D, MANNING C, et al. Reasoning with neural tensor networks for knowledge base completion［C/OL］∥ Proceedings of Advances in Neural
Information Processing Systems 2013. https:∥ www.mendeley.com/catalogue/c9bd3ac9-e813-38e8-9f2c-27206832765b/.
［11］ WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes ［C/OL］∥Proceedings of the National Conference on Artificial
Intelligence 2014. Québec City, Canada: ［s.n.］, 2014: 1112-1119.https:∥www.mendeley.com/catalogue/4ba28f41-289c-3cc0-b624-a8ea6d56b23a/.
［12］ JI Guoliang, HE Shizhu, XU Liheng, et al. Knowledge graph embedd-ing via dynamic mapping matrix ［EB/OL］. (2016-03-01) ［2020-09-
20］.http:∥www.nlpr.ia.ac.cn/cip/~liukang/liukang Page File/Knowledge%20 Graph%20 Embedding%20 via%20 Dynamic%20 Mapping%20 Matrix.pdf.
［13］ LIN Yankai, LIU Zhiyuan, SUN Maosong, et al. Learning entity and relation embeddings for knowledge graph completion［C/OL］∥Proceedings of 29th AAAI
Conference on Artificial Intelligence. Austin, USA: ［s.n.］, 2015: 2181-2187. http:∥nlp.csai.tsinghua.edu.cn/~lyk/pub lications/aaai2015_transr.pdf.
［14］ DU Yuchuan, PAN Ning, XU Zihao, et al. Pavement distress detection and classification based on YOLO network［J］. The International Journal of Pavement
Engineering, 2020(1): 1-14.
［15］ LAO Ni, COHEN W W. Relational retrieval using a combination of path-constrained random walks ［J］. Machine Learning, 2010, 81 (1): 53-67.
［16］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，2020，12（4）：136-147.
SUN Xinrui, MENG Yu, WANG Wenle.Identification of traffic events from Weibo based on knowledge graph and target detection［J］. Data Analysis and Knowledge
Discovery,2020,12(4):136-147.
［17］彭乾慧.领域知识图谱的自动化构建［D］.重庆：重庆大学，2017.
PENG Qianhui. Domain Knowledge Graph Auto-Construction［D］. Chongqing: Chongqing University, 2017.
［18］胡卓.面向知识图谱的表示学习算法的研究与应用［D］.成都：电子科技大学，2020.
HU Zhuo. Research and Application of Representation Learning Algorithm for Knowledge Graph ［D］. Chengdu: University of Electronic Science and Technology of
China, 2020.
［19］张美玉，林崇，简琤峰.基于路径排序算法的STEP知识推理技术研究［J］.浙江工业大学学报，2020，48(2)：126-132，187.
ZHANG Meiyu, LIN Chong, JIAN Chengfeng. Research on STEP knowledge reasoning technology based on path ranking algorithm［J］. Journal of Zhejiang University of
Technology, 2020, 48(2): 126-132, 187.
［20］余传明，王峰，安璐.基于深度学习的领域知识对齐模型研究：知识图谱视角［J］.情报学报，2019，38（6）：641-654.
YU Chuanming, WANG Feng, AN Lu. Research on the domain knowledge alignment model based on deep learning: The knowledge graph perspective ［J］. Journal of
The China Society for Scientific and Technology Information, 2019, 38(6): 641-654.

[1]	陶健，王文君，庞夺峰，殷传峰. 高速公路危险货物运输人员暴露风险实时评价分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(03): 43-48.
[2]	牛世峰1，李贵强2，刘恩全3. 基于Logit模型的城乡结合部不同车型安全性分析[J]. 重庆交通大学学报（自然科学版）, 2020, 39(01): 28-33.
[3]	陈立辉1,2 ，郭忠印1. 高速公路连续下坡路段大货车速度特征研究[J]. 重庆交通大学学报（自然科学版）, 2019, 38(08): 86-91.
[4]	王征，陶健，王文君. 城市快速路危险货物运输风险动态评估[J]. 重庆交通大学学报（自然科学版）, 2019, 38(06): 96-102.
[5]	胡志刚，胡佳斌，乔现玲. 不同响度音乐对单调声音环境下驾驶疲劳缓解实验研究[J]. 重庆交通大学学报（自然科学版）, 2017, 36(9): 73-79.
[6]	冯雯，李可军. 交通事故死亡人数与太阳活动的统计关系分析[J]. 重庆交通大学学报（自然科学版）, 2015, 34(1): 91-94.
[7]	凌天清，张睿卓，宁华宇，袁明. 膨胀型沥青阻燃剂阻燃性能研究[J]. 重庆交通大学学报（自然科学版）, 2011, 30(5): 948-951.
[8]	霍娅敏，陈坚，何湘锋，梁艳洁. 城乡客运一体化公交线路补贴规模测算模型[J]. 重庆交通大学学报（自然科学版）, 2011, 30(1): 81-84.
[9]	谭忆秋,蓝碧武,纪伦,尚云飞. 隧道路面沥青常用阻燃剂改性技术研究方法[J]. 重庆交通大学学报（自然科学版）, 2009, 28(4): 711-714.
[10]	石勇. 货运企业运输安全综合评价研究[J]. 重庆交通大学学报（自然科学版）, 2008, 27(6): 1135-1138.
[11]	曹智翔，黄显贵. 基于GPS??GIS的道路交通安全预报研究[J]. 重庆交通大学学报（自然科学版）, 2004, 23(4): 82-84.
[12]	覃光焱，杨志刚. 用危险预警系统实现汽车的主动安全性[J]. 重庆交通大学学报（自然科学版）, 2002, 21(4): 114-118.