摘要
轨道交通故障信息记录冗杂,需要人力手工分类,导致隐患信息不能被挖掘。文章首先建立轨道交通故障信息语料库,其次向量化故障信息,使用K-means聚类算法进行分类,再次应用隐含狄利克雷分布(Latent Dirichlet Allocation,LDA)主题模型抽取主题,找出轨道交通的故障规律,最后建立基于文本识别的轨道交通故障信息分类流程和算法体系。
The record of rail transit fault information is redundant,and manual classification is required,which makes the hidden danger information cannot be mined.The corpus of rail transit fault information is established,the fault information is vectorized,the K-means clustering algorithm is used to classify,and then the Latent Dirichlet Allocation(LDA)topic model is used to extract the theme,and the fault law of rail transit is found.The classification process and algorithm system of rail transit fault information based on text recognition are established.
作者
寇戈
侯玉茹
李德奎
KOU Ge;HOU Yuru;LI Dekui(School of Computer Science and Technology,Liaocheng University,Liaocheng Shandong 252000,China)
出处
《信息与电脑》
2023年第8期105-107,共3页
Information & Computer