基于专利说明书语义分析的潜在竞争对手识别研究  

Research on Identification of Potential Competitors Based on the Semantic Analysis of Patent Specification

作　　者：史敏[1] 罗建[1] 蔡丽君 Shi Min;Luo Jian;Cai Lijun(Business School,Hunan Agricultural University,Changsha 410128)

机构地区：[1]湖南农业大学商学院,长沙410128

出　　处：《情报学报》2020年第11期1171-1181,共11页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金项目“基于专利语义分析的潜在竞争对手识别方法研究”(71774052)。

摘　　要：基于专利说明书的语义分析开展潜在竞争对手识别研究,不仅能够为企业尽早发现未来可能给自己致命一击的竞争对手,为企业的战略制定提供决策支持,也能够丰富潜在竞争对手研究理论。专利说明书的背景技术和发明内容中蕴含着丰富的市场和技术信息,基于专利说明书构建了背景相似性、解决方案相似性和时间轴的三维潜在竞争对手初步识别框架。基于LDA语义分析技术,构建了包括搜集和预处理专利数据、建立语料库、初步识别潜在竞争对手和判别潜在竞争对手四个步骤在内的潜在竞争对手识别流程。以水环境领域为实例,证明了该潜在竞争对手识别方法的可行性和有效性。Based on the semantic analysis of patent specification,the research of potential competitor identification can help enterprises determine strong competitors early on,provide information for strategic decision-making,and enrich the research theory of potential competitors.The background technology and invention content of the patent specification contain rich market and technical information.A three-dimensional preliminary identification framework of potential competitors,including background similarity,solution similarity,and time axis,is constructed based on the patent specification.Based on LDA semantic analysis technology,this study constructs a potential competitor identification process,including four steps:collecting and preprocessing patent data,building a corpus,initially identifying potential competitors,and confirming potential competitors.Taking the field of water environment as an example,the feasibility and effectiveness of the method are proved.

关 键 词：专利 潜在竞争对手 识别 语义分析 

分 类 号：G306[文化科学]