基于反馈式文本分类技术自动识别项目标签  

Automatic Recognition of Item Labels Based on Feedback Text Classification Technology

作　　者：谢波 何凤 XIE Bo;HE Feng(Guangdong Investment and Credit Service Center Guangzhou 510030,China;Guangdong Bid Winning Data Technology Co.,Ltd.,Guangzhou 510030,China)

机构地区：[1]广东省投资和信用中心,广东广州510030 [2]广东中标数据科技股份有限公司,广东广州510030

出　　处：《现代信息科技》2021年第17期100-102,106,共4页Modern Information Technology

摘　　要：为对广东省投资项目在线审批监管平台积累的近40万个固定资产投资项目的产业类别进行分类,利于政府内部统计管理。在专家识别的人工打标签的方法基础上,进一步采用了线性支持向量机等分类算法,并基于反馈式文本分类机器学习原理再次识别了所有项目的标签类别,项目标签分类准确率由82%提升到91%。结果表明,反馈式文本分类技术,显著提高了项目分类的准确性。In order to classify the industry categories of the nearly 400,000 fixed assets investment projects accumulated by the online approval and supervision platform for investment projects in Guangdong Province,it is conducive to the government’s internal statistical management.Based on the manual labeling method recognized by experts,classification algorithms such as linear support vector machines are further adopted,based on the feedback text classification machine learning principle,the label categories of all items are recognized again,and the accuracy of project label classification has been improved by 82%to 91%.The results show that the feedback text classification technology significantly improves the accuracy of project labels classification.

关 键 词：项目标签 文本分类、词向量 分类器 线性支持向量机 反馈学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]