특허-상표 연계 비즈니스 인텔리전스를 위한 텍스트 분석 기반의 비즈니스 영역 식별

Abstract

This study presents a novel approach for identifying new business opportunities by analyzing the linkage between patents and trademarks leveraging text analytics. Initially, we utilize topic modeling to analyze the descriptions of goods and services in trademarks, with a particular focus on trademarks that do not share similar group codes. Using the Latent Dirichlet Allocation (LDA) model, the descriptions in the trademarks are segmented into multiple business groups based on similarities. Subsequently, we define business areas by measuring their similarity to the industry classifications represented by the Standard Industrial Classification (SIC) system. To this end, we propose a novel weighted cosine similarity. Leveraging the proposed similarity, we align each patent with one of the predefined business groups extracted from the trademark data. Based on this approach, we can identify business areas closely related to the technological capabilities of tech-based firms. In the case study, we showed that business areas are identified through the alignment between the customized goods and service groups and SIC from trademark data of global technology-based firms.