특허정보의 키워드 네트워크 분석 : SCM 특허 데이터를 중심으로

The patent has the detailed information about technology development activities. Analyzing the patent information using the social network analysis contains both patent citation relationship analysis and patent keyword network analysis. Although keyword network analysis usually select keywords based on the frequency of words in the patent, frequently used words do not necessarily mean meaningful words in the patent information. In this paper, we demonstrated alternative approach to improve the selection of keyword for the keyword network analysis based on topic model. First, we retrieved 2,724 abstracts of patent on the supply chain management between 1997 and 2016 from USPTO(www.uspto.gov) and EPO(www.epo.org). Second, we used LDA (latent Dirichlet allocation) algorithm to identify the major topics of the supply chain management patents, and extracted 15 keywords to describe these topics. Then, we built the structured data set through the preprocessing to perform the network analysis and visualization operation. Finally, we conducted component analysis and centrality analysis by using LDA-based DocumentTermMatrix(DTM). Component analysis provides three components in the supply chain management patents. For centrality analysis, degree centrality, betweenness centrality, and closeness centrality are identified. Contributions and further research were also discussed as a part of the conclusions.