基于专利特征抽取的技术树构建方法研究  

Research on Construction of Technology Tree Based on Patent Feature Extraction

作　　者：翟东升[1] 夏军[1] 张杰[1] 李倩[1] 栾博杨 

机构地区：[1]北京工业大学经济与管理学院

出　　处：《情报学报》2015年第7期717-724,共8页Journal of the China Society for Scientific and Technical Information

基　　金：国家科技支撑计划项目(2012BAH34F00);北京市自然科学基金项目(9132005)

摘　　要：技术树可以辅助识别特定技术领域的核心技术，支持决策过程。但目前技术树主要集中于产品、技术、功能单个维度的展示，缺乏维度的结合。本文在主谓宾（SAO）结构抽取的基础上，添加宾语补足语的内容，对专利的标题与摘要进行主谓宾-宾补（SAO-C）结构的抽取，并将抽取的专利特征进行分类、汇总、标注，以TRIZ理论为基础，结合句法结构和语言的层级关系构建多维度技术树。为了证明该方法的可行性，构建了“隐形眼镜消毒”技术领域的技术树。Technology tree is a useful tool for supporting a decision making process to identify the core technologies in a specific technology area. However, the traditional technology trees only display a single dimension of product, technology or function, lacking of the combination of multi-dimensional. This research adds the complement on the basis of Subject- Action-Object （SAO） structures. The Subject-Action-Object-Complement（SAO-C） Structures are extracted from the title and abstract of the patents. Then the extracted patent semantic features are subtotaled and tagged based on TRIZ to build a multi-dimensional technology tree, combining with syntactic structure and hierarchical relationship of language. To demonstrate the feasibility of the proposed approach, this research developed a technology tree regarding ＂ contact lens remove bacteria technology.

关 键 词：技术树 专利特征 SAO—C TRIZ 

分 类 号：G306[文化科学] G350