基于文本挖掘的专利技术主题分析研究综述  

A Review of Technical Topic Analysis Based on Text Mining

作　　者：胡阿沛[1] 张静[1] 雷孝平[1] 张晓宇[1] 

机构地区：[1]中国科学技术信息研究所北京100038

出　　处：《情报杂志》2013年第12期88-92,61,共6页Journal of Intelligence

摘　　要：为应对专利数量巨大和技术的日益复杂给专利技术主题分析带来的挑战,以及利用文本挖掘技术的专利技术主题分析近来成为研究热点。首先介绍文本挖掘的概念和其发展历史。其次,对目前基于文本挖掘的专利技术主题分析方法进行了归纳,包括主题词词频分析、共词分析、文本聚类分析和与引文聚类结合的分析方法,总结其常用的分析工具并介绍新的科学图谱分析软件——SciMAT。最后总结基于文本挖掘的专利技术主题分析方法的优点与不足,为其将来的研究提供建议。To cope with the challenges of patent technical topic analysis presented by huge amounts of patent documents and increasingly sophisticated technology, this paper uses text mining technology to assist technical topic analysis and get researchers ＇ focus in recent years. Firstly, the concept of text mining and its development history are introduced. Secondly, the methods of analyzing patent technical topic based on text mining is summarized, including word frequency analysis, co-word analysis, text clustering analysis and analysis combined with citation clustering. Some important analytical tools and a new science mapping analysis software tool SciMAT are introduced. Final- ly, the paper points out the advantages and deficiencies of technical topic analysis based on text mining and future research direction.

关 键 词：文本挖掘 技术主题 专利分析 词频分析 共词分 析文本聚类 

分 类 号：G353.1[文化科学—情报学]