典型文献
A Short Text Classification Model for Electrical Equipment Defects Based on Contextual Features
文献摘要：
The defective information of substation equipment is usually recorded in the form of text.Due to the irregular spoken expressions of equipment inspectors,the defect information lacks sufficient contextual information and becomes more ambiguous.To solve the problem of sparse data deficient of semantic features in classification process,a short text classification model for de-fects in electrical equipment that fuses contextual features is pro-posed.The model uses bi-directional long-short term memory in short text classification to obtain the contextual semantics of short text data.Also,the attention mechanism is introduced to assign weights to different information in the context.Meanwhile,this model optimizes the convolutional neural network parameters with the help of the genetic algorithm for extracting salient fea-tures.According to the experimental results,the model can effec-tively realize the classification of power equipment defect text.In addition,the model was tested on an automotive parts repair data-set provided by the project partners,thus enabling the effective ap-plication of the method in specific industrial scenarios.
文献关键词：
中图分类号：
作者姓名：
LI Peipei;ZENG Guohui;HUANG Bo;YIN Ling;SHI Zhicai;HE Chuanpeng;LIU Wei;CHEN Yu
作者机构：
School of Electrical and Electronic Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;CSG Smart Science&Technology Co.,LTD,Shanghai 201203,China;State Grid Shanghai Municipal Electric Power Company,Shanghai 200122,China
文献出处：
引用格式：
[1]LI Peipei;ZENG Guohui;HUANG Bo;YIN Ling;SHI Zhicai;HE Chuanpeng;LIU Wei;CHEN Yu-.A Short Text Classification Model for Electrical Equipment Defects Based on Contextual Features)[J].武汉大学自然科学学报（英文版）,2022(06):465-475
A类：
inspectors
B类：
Short,Text,Classification,Model,Electrical,Equipment,Defects,Based,Contextual,Features,defective,information,substation,equipment,usually,recorded,Due,irregular,spoken,expressions,lacks,sufficient,contextual,becomes,more,ambiguous,To,solve,problem,sparse,data,deficient,features,classification,process,short,model,electrical,that,fuses,posed,directional,long,term,memory,obtain,semantics,Also,attention,mechanism,introduced,assign,weights,different,Meanwhile,this,optimizes,convolutional,neural,network,parameters,help,genetic,algorithm,extracting,salient,According,experimental,results,can,tively,realize,power,In,addition,was,tested,automotive,parts,repair,set,provided,by,project,partners,thus,enabling,effective,ap,plication,method,specific,industrial,scenarios
AB值：
0.599116
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
