효율적인 특허정보 조사를 위한 분류 모형
A Novel Classification Model for Efficient Patent Information Research
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
A patent contains detailed information of the developed technology and is published to the public. Thus, patents can be used to overcome the limitations of traditional technology trend research and prediction techniques. Recently, due to the advantages of patented analytical methodology, IP R&D is carried out worldwide. The patent is big data and has a huge amount, various domains, and structured and unstructured data characteristics. For this reason, there are many difficulties in collecting and researching patent information. Patent research generally writes the Search formula to collect patent documents from DB. The collected patent documents contain some noise patents that are irrelevant to the purpose of analysis, so they are removed. However, eliminating noise patents is a manual task of reading and classifying technology, which is time consuming and expensive. In this study, we propose a model that automatically classifies The Noise patent for efficient patent information research. The proposed method performs Patent Embedding using Word2Vec and generates Noise seed label. In addition, noise patent classification is performed using the Random forest. The experimental data is published and registered with the USPTO among the patents related to Ocean Surveillance & Tracking Network technology. As a result of experimenting with the proposed model, it showed 73% accuracy with the label actually given by experts.
Abstract
A patent contains detailed information of the developed technology and is published to the public. Thus, patents can be used to overcome the limitations of traditional technology trend research and prediction techniques. Recently, due to the advantages of patented analytical methodology, IP R&D is carried out worldwide. The patent is big data and has a huge amount, various domains, and structured and unstructured data characteristics. For this reason, there are many difficulties in collecting and researching patent information. Patent research generally writes the Search formula to collect patent documents from DB. The collected patent documents contain some noise patents that are irrelevant to the purpose of analysis, so they are removed. However, eliminating noise patents is a manual task of reading and classifying technology, which is time consuming and expensive. In this study, we propose a model that automatically classifies The Noise patent for efficient patent information research. The proposed method performs Patent Embedding using Word2Vec and generates Noise seed label. In addition, noise patent classification is performed using the Random forest. The experimental data is published and registered with the USPTO among the patents related to Ocean Surveillance & Tracking Network technology. As a result of experimenting with the proposed model, it showed 73% accuracy with the label actually given by experts.
참고문헌 (17)
- D. Hunt, "Patent Searching Tools & Techniques" (2007), Wiley
- A. Abbas, "A literature review on the state-of-the-art in patent analysis", World Patent Information, 37, pp.3~13 (2014)
- 전성해, "특허분석을 위한 빅 데이터학습", 한국지능시스템학회 논문지, 23(5), pp.406~411 (2013), 한국지능시스템학회
- Patent and Information Analysis (for Researchers), "Korean Intellectual Property Office", KIPO, ~ (2006)
- Intellectual Property Research & Development, "Korean Intellectual Property Office", KIPO, ~ (2012)
- T. Mikolov, "Efficient Estimation of Word Representations in Vector Space", arXiv preprint arXiv:1301.3781, ~ (2013)
- X. Rong, "word2vec Parameter Learning Explained", arXiv preprint arXiv:1411.2738, ~ (2016)
- S. Goki, "Deep Learning from Scratch 2" (2019), O’Reilly
- 김우주, "Word2vec을 활용한 문서의 의미 확장 검색방법", 한국콘텐츠학회 논문지, 16(10), pp.687~692 (2016), 한국콘텐츠학회[DOI]
- 서덕성, "워드임베딩과 그래프 기반 준지도학습을 통한 한국어 어휘 감성 점수 산출", 대한산업공학회지, 43(5), pp.330~340 (2017), 대한산업공학회[DOI]
- 김기용, "Word2Vec과 2계층 양방향 장단기 기억 네트워크를 이용한 특허 문서의 자동 IPC 분류", 한국차세대컴퓨팅학회 논문지, 15(2), pp.50~60 (2019), 한국차세대컴퓨팅학회[DOI]
- 정재윤, "워드 임베딩과 단어 네트워크 분석을 활용한비지도학습 기반의 문서 다중 범주 가중치 산출 : 휴대폰 리뷰 사례를 중심으로", 대한산업공학회지, 44(6), pp.442~451 (2018), 대한산업공학회[DOI]
- A. Geron, "Hands-on Machine Learning with Scikit-learn & Tensorflow" (2017), O’Reilly
- C. Park, "R Data Mining" (2011), Kyowoosa
- V. Sventnik, "Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling", Journal of Chemical Information and Computer Science, 43(6), pp.1947~1958 (2003)
- W. T. Aung, "Random forest classifier for multi-category classification of web pages", Proceedings of 2009 IEEE Asia-Pacific Services Computing Conference, pp.372~376 (2009)
- A. Onan, "Ensemble of keyword extraction methods and classifier in text classification", Expert Systems with Applications, 57(15), pp.232~247 (2016)