본 논문에서는 특허분석을 통해 산업 및 시장을 이끌어 갈 유망기술을 발굴할 수 있는 새로운 방법론을 제안하고자 한다. 접근 방법론은 다음과 같은 절차로 진행된다. 첫째, 개발된 기술을 상세히 명세하고 있는 특허 문서를 수집한다. 둘째, 비구조화된 특허 문서의 제목, 요약문 및 청구항을 구조화된 형태의 데이터로 변환한다. 셋째, 수집된 특허 문서의 제목, 요약문 및 청구항 집합 내 잠재되어 있는 상세한 기술 파악을 위해 토픽 모델링 기법 중 하나인 latent Dirichlet allocation(LDA)을 적용한다. 마지막으로 Bass 확산 모형을 적용하여 유망기술을 발굴한다. 실험적 검증을 위해 태양광 발전 시스템 기술과 관련된 특허 데이터를 한국 특허청(KIPO)으로부터 수집하여 분석하였으며, 그 결과 유기태양전지, 집광형 태양전지 모듈 등 6개의 유망 기술이 발굴되었다.
본 논문에서는 특허분석을 통해 산업 및 시장을 이끌어 갈 유망기술을 발굴할 수 있는 새로운 방법론을 제안하고자 한다. 접근 방법론은 다음과 같은 절차로 진행된다. 첫째, 개발된 기술을 상세히 명세하고 있는 특허 문서를 수집한다. 둘째, 비구조화된 특허 문서의 제목, 요약문 및 청구항을 구조화된 형태의 데이터로 변환한다. 셋째, 수집된 특허 문서의 제목, 요약문 및 청구항 집합 내 잠재되어 있는 상세한 기술 파악을 위해 토픽 모델링 기법 중 하나인 latent Dirichlet allocation(LDA)을 적용한다. 마지막으로 Bass 확산 모형을 적용하여 유망기술을 발굴한다. 실험적 검증을 위해 태양광 발전 시스템 기술과 관련된 특허 데이터를 한국 특허청(KIPO)으로부터 수집하여 분석하였으며, 그 결과 유기태양전지, 집광형 태양전지 모듈 등 6개의 유망 기술이 발굴되었다.
In this paper, we propose a new methodology to discover emerging technologies that lead the industry and market through patent analysis. The proposed methodology proceeds as follows. First, the patent documents including detailed descriptions on developed technologies are collected. Second, unstruct...
In this paper, we propose a new methodology to discover emerging technologies that lead the industry and market through patent analysis. The proposed methodology proceeds as follows. First, the patent documents including detailed descriptions on developed technologies are collected. Second, unstructured patent data such as title, abstract, and claims is converted into a structured data. Third, a topic modeling, latent Dirichelt allocation(LDA), is adopted to extract latent topics in the title, abstract, and claims of patent documents. Lastly, the emerging technologies are discovered by adopting Bass diffusion model. For experimental verification, the patent documents of photovoltaic power generation system technology are collected from the Korea Intellectual Property Office(KIPO). As a result, six emerging technologies such as organic solar cell and high concentrating photovoltaic module technologies are discovered.
In this paper, we propose a new methodology to discover emerging technologies that lead the industry and market through patent analysis. The proposed methodology proceeds as follows. First, the patent documents including detailed descriptions on developed technologies are collected. Second, unstructured patent data such as title, abstract, and claims is converted into a structured data. Third, a topic modeling, latent Dirichelt allocation(LDA), is adopted to extract latent topics in the title, abstract, and claims of patent documents. Lastly, the emerging technologies are discovered by adopting Bass diffusion model. For experimental verification, the patent documents of photovoltaic power generation system technology are collected from the Korea Intellectual Property Office(KIPO). As a result, six emerging technologies such as organic solar cell and high concentrating photovoltaic module technologies are discovered.
M. L. Kent, A.J. Saffer, "A Delphi study of the future of new technology research in public relations," Public Relations Review, vol. 40, no. 3, pp.568-576, 2014.
S. Altuntas, T. Dereli, A. Kusiak, "Forecasting technology success basedc on patent data," Technological Forecasting & Social Change, vol. 96, pp.202-214, 2015.
J. Bae, "Technology and Korea's Competitiveness Analysis through UAV Patent Analysis," The Journal of The Korean Institute of Communication Sciences, Vol. 41, No. 12, pp.1868-1875, 2016.
Y. Zhou, X. Li, R. Lema, F. Urban, "Comparing the knowledge bases of wind turbine firms in Asia and Europe: patent trajectories, networks, and globalisation," Science and Public Policy, vol. 43, no. 4, pp.476-491, 2015.
J. Lee, J. Kim, J. Lee, S. Park, D. Jang, "A study on analysis of R&D intensity based on patent citation information: Case study on self-driving car of google," Journal of Korean Institute of Intelligent Systems, vol. 26, no. 4, pp.327-333, 2016.
S. Jun, "Technology forecasting of intelligent systems using patent analysis," Korean Institute of Intelligent Systems, vol. 21, no. 1, pp.100-105, 2011.
G. J. Kim, J. W. Bae, "A novel approach to forecast promising technology through patent analysis," Technological Forecasting & Social Change, vol. 117, pp.228-237, 2017.
H. Chen, G. Zhang, D. Zhu, J. Lu "Topic-based technological forecasting based on patent data: A case study of Australian patents from 2000 to 2014," Technological Forecasting & Social Change, vol. 119, pp.39-52, 2017.
C. Liu, J. Wang, "Forecasting the development of the biped robot walking technique in Japan through S-curve model analysis," Scientometrics, vol. 82 no. 1, pp.21-36, 2010.
J. A. Norton, F. M. Bass, "A diffusion theory model of adoption and substitution for successive generations of high-technology products," Management Science, vol. 33, no. 9, pp.1069-1086, 1987.
J. Yeon, D. Lee, J. Shim, S. Lee, "Product review data and sentiment analytical processing modeling," The Jounal of Society for e-Business Studies, vol. 16, no. 4, pp.125-137, 2011.
C. Kwak, S. Kim, S. Park, K. Y. Kim, "Topic expansion based on infinite vocabulary online LDA topic model using semantic correlation information," KIISE Transactions on Computing Practices, vol. 22, no. 9, pp.461-466, 2016.
K. D. Renuka, P. Visalakshi, "Latent semantic indexing based SVM model for email spam classification," Journal of Scientific and Industrial Research, vol. 73, no. 7, pp.437-442, 2014.
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.