标准大数据实践(2)——内容深度挖掘  

Standard Big Data Practice —— Deep Mining of Content(Part B)

作　　者：甘克勤[1] 张宝林[2] 张明[1] 于钢[1] 

机构地区：[1]中国标准化研究院 [2]国家标准化管理委员会信息中心

出　　处：《标准科学》2016年第2期35-39,101,共6页Standard Science

基　　金：中央基本科研业务费支撑项目"基于文本相似度计算的标准查新工具研究"(项目编号:252015Y-4003)资助

摘　　要：大数据时代,人们面对的问题不再是缺少数据,而是被数据淹没了,即所谓"人们淹没于数据,却饥饿于知识"[1]。面对这样的状况,仅靠传统的检索工具已经远远不能满足人们的需要。本文研究了标准文献内容挖掘的关键技术:OCR、正则提取、反向索引,以及标准文献碎片挖掘与检索的系统实现的业务流程、技术框架以及实现效果。In the era of big data, what people face is the overwhelming data instead of lacking of data, which is called ＂people drowned out by the data, but hunger for knowledge＂ [1]. Faced with such situation, people＇s needs can＇t be satisfied only by the traditional retrieval tool. This paper studies the key technologies of the literature mining of standards literature, including OCR, regular extraction, inverted index, as well as system implementation of business process, technology framework and implementation effect of literature mining and retrieval of standard pieces.

关 键 词：文本挖掘 标准 碎片化 

分 类 号：F203[经济管理—国民经济]