标准文本查重与条款指标提取比对技术应用研究

打开文本图片集

Abstract：Inorder tosolve the technical problems standard content duplicate checking and index extraction key terms，basedon thecomparative analysisexisting technical methods，this paper uses the model basedon text cosine similarityandregular expression method toachieve theaccurateextractionand similaritycalculation standard text， main terms and technical indicators.The research results this paper can provide strong support for the preparation， application and project evaluation standards，and also play an important role in promotingcoordination among standardsand avoiding the repetition standard content.

Keywords：standard;duplicate contentchecking;clause extraction;indicator extraction;similaritycalculation

0 引言

高，获取方式也变得更加便捷。（剩余5117字）