交通运输研究2024，Vol.10Issue(3)：20-28,9.DOI:10.16503/j.cnki.2095-9931.2024.03.003
基于RoBERTa-BiGRU-CRF的交通事故处置流程文本信息抽取
Text Information Extraction of Traffic Accident Disposal Process Based on RoBERTa-BiGRU-CRF
摘要
Abstract
To address the existing issue of insufficient extraction in recognizing traffic accident emergency information and improve the accuracy of emergency processing knowledge extraction,a method for extract-ing the traffic accident process based on pre-training model and hybrid deep learning networks was proposed aiming at the complexity of natural language description of traffic accident text information.Firstly,the disposal process entities of traffic accidents were defined from five aspects such as acci-dent characteristic,disposal agency,disposal measures,disposal effects,and task prediction,and these entity types were marked using BIO notation.Then,the word vectors generated by the RoBERTa pre-trained model were used as input,the BiGRU model was used for feature extraction,and the CRF model was used for conditional constraints to obtain the final entity type.Furthermore,time-series fu-sion was used to the traffic accident handling process extraction results obtained from RoBERTa-BiG-RU-CRF combined model,and the extracted results were stored and visualized using a graph data-base.Finally,using the text information of highway traffic accidents in Shaanxi Province as a sample data set,the performance of different pre-trained models and deep learning networks were compared,the effectiveness of the RoBERTa-BiGRU-CRF model was demonstrated through ablation experi-ments and validated through an example of one traffic accident.The results demonstrated that the Ro-BERTa-BiGRU-CRF combined model yielded superior extraction results with the F1 value of 99.77%.Research has shown that the proposed method can effectively extract key elements of the emergency response process for traffic accidents from textual information,achieve visual presentation of the re-sults of emergency response process extraction,and provide reference for emergency response deci-sion-making.关键词
交通安全/交通事故/实体抽取/预训练模型/深度学习/时序融合Key words
traffic safety/traffic accident/entity extraction/pre-trained model/deep learning/time-series fusion分类
交通工程引用本文复制引用
陈娇娜,张静,靳引利,王鹏..基于RoBERTa-BiGRU-CRF的交通事故处置流程文本信息抽取[J].交通运输研究,2024,10(3):20-28,9.基金项目
国家自然青年科学基金项目(52002315) （52002315）
国家重点研发计划项目(2019YFB1600700) （2019YFB1600700）
