文本大数据分析技术在铁路行车安全领域的应用研究

保障铁路行车安全是铁路工作的重点,通过铁路事故调查报告等文本数据对事故原因进行分析,是提高铁路行车安全的重要手段之一。但由于铁路系统存在海量的非结构化事故故障文本数据,难以进行有效检索和分析,因此提出铁路行车安全领域文本大数据分析总体框架,包括文本数据从集成、存储到处理、计算,再到检索、分析及应用的全部流程,并对基于铁路领域文本数据的全文检索、特征提取等文本大数据分析关键技术进行研究。最后以某铁路局集团公司的事故故障追踪报告为样本,进行事故故障报告的全文检索、故障词云展示及关联性分析,取得了良好效果。

Application of Text Big Data Analysis Technique in the Field of Railway Train Operation Safety

Guaranteeing train operation safety is the priority for railway department.It is one of major approaches for improving train operation safety to analyze accident cause through such text data as railway accident investigation report.Considering that railway system has enormous non-construction accident and failure text data which are difficult to be searched and analyzed,the paper puts forward the general framework of text data analysis of railway train operation safety,including the whole process from text data integration,storage,processing,calculating,searching,analysis to application.The paper also carries out a research based on railway text data analysis technique such as full-text search and feature extraction.In conclusion,the paper takes the accident investigation report of a CR branch company as a sample and implements full-text search,cloud display of failure words and correlation analysis of it,obtaining a good result.