用于APP的缺陷文本自动分类与质量保证方法  被引量:10

Defect Text Automatic Classification and Quality Assurance Method for APP

在线阅读下载全文

作  者:郑翔[1] 王慧芳[1] 严娴峥 金丽娟 温桂平 何奔腾[1] ZHENG Xiang;WANG Huifang;YAN Xianzheng;JIN Lijuan;WEN Guiping;HE Benteng(College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China;Huzhou Power Supply Company,State Grid Zhejiang Electric Power Co.,Ltd,Huzhou 313000,China;Huayun Information Science and Technology Ltd,Hangzhou 310012,China)

机构地区:[1]浙江大学电气工程学院,杭州310027 [2]国网浙江省电力有限公司湖州供电公司,湖州313000 [3]浙江华云信息科技有限公司,杭州310012

出  处:《电力系统及其自动化学报》2020年第7期131-136,共6页Proceedings of the CSU-EPSA

摘  要:目前电力设备缺陷文本分类工作主要依靠人工,一方面效率低,另一方面容易发生误分类。本文提出了一种应用于APP的基于人机交互方式的缺陷文本自动分类和质量保证方法。首先,将国家电网提供的标准导则表示为树结构,在此基础上提出了基于树路径匹配的缺陷文本分类方法;然后,针对实际输入的电力设备缺陷文本存在的不完整、表述不清晰等问题,提出了基于人机交互的缺陷文本质量保证方法,在此基础上实现了分类结果的高准确率。采用Flask框架编写了用户交互界面,实现缺陷文本输入、缺失信息补充、分类结果展示等功能。最后通过大量文本测试,验证了方法的可行性和有效性。At present,the classification of power equipment defect texts mainly relies on labor. On the one hand,the corresponding efficiency is low;and on the other hand,misclassification is prone to occur. In this paper,a defect text automatic classification and quality assurance method is proposed for APP based on human-computer interaction. First,the standard guidelines provided by the State Grid are expressed as a tree structure,based on which the defect text classification method is presented on the basis of tree path matching. Then,aimed at the problems with the power equipment defect text from actual input such as incompleteness and unclear description,a defect text quality assurance method based on human-computer interaction is proposed,thus realizing high accuracy of classification results. The user interactive interface is written under the Flask framework,thereby realizing functions such as defect text input,missing information supplementation,and display of classification result. Finally,the feasibility and effectiveness of the proposed method are verified through a large number of test texts.

关 键 词:电力设备缺陷文本 树路径匹配 人机交互 Flask框架 

分 类 号:TP274[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象