Modeling Patent Quality: A System for Large-scale Patentability Analysis using Text Mining

• Item type: JInfP(1)
• 公開日: 2012-07-15
• タイトル: Modeling Patent Quality: A System for Large-scale Patentability Analysis using Text Mining
• タイトル / 言語: en
• タイトル: Modeling Patent Quality: A System for Large-scale Patentability Analysis using Text Mining
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [Special Issue on Theory and Application of Intelligent Information Technology] patent quality index, patentability, document classification
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo／Presently with Preferred Infrastructure, Inc.
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo
• 著者所属: IP Law Department, IBM Japan
• 著者所属: IP Law Department, IBM Japan
• 著者所属: IP Law Department, IBM Japan
• 著者所属: Analytics & Intelligence, IBM Research - Tokyo／Presently with Yahoo! Japan
• 著者所属: Research Center for Advanced Science and Technology, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo / Presently with Preferred Infrastructure, Inc.
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo
• 著者所属(英): en
• 著者所属(英): IP Law Department, IBM Japan
• 著者所属(英): en
• 著者所属(英): IP Law Department, IBM Japan
• 著者所属(英): en
• 著者所属(英): IP Law Department, IBM Japan
• 著者所属(英): en
• 著者所属(英): Analytics & Intelligence, IBM Research - Tokyo / Presently with Yahoo! Japan
• 著者所属(英): en
• 著者所属(英): Research Center for Advanced Science and Technology, The University of Tokyo
• 著者名: Shohei, Hido; Shoko, Suzuki; Risa, Nishiyama; Takashi, Imamichi; Rikiya, Takahashi; Tetsuya, Nasukawa; Tsuyoshi, Ide; Yusuke, Kanehira; Rinju, Yohda; Takeshi, Ueno; Akira, Tajima; Toshiya, Watanabe
• 著者名(英): Shohei, Hido; Shoko, Suzuki; Risa, Nishiyama; Takashi, Imamichi; Rikiya, Takahashi; Tetsuya, Nasukawa; Tsuyoshi, Ide; Yusuke, Kanehira; Rinju, Yohda; Takeshi, Ueno; Akira, Tajima; Toshiya, Watanabe
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Current patent systems face a serious problem of declining quality of patents as the larger number of applications make it difficult for patent officers to spend enough time for evaluating each application. For building a better patent system, it is necessary to define a public consensus on the quality of patent applications in a quantitative way. In this article, we tackle the problem of assessing the quality of patent applications based on machine learning and text mining techniques. For each patent application, our tool automatically computes a score called patentability, which indicates how likely it is that the application will be approved by the patent office. We employ a new statistical prediction model to estimate examination results (approval or rejection) based on a large data set including 0.3 million patent applications. The model computes the patentability score based on a set of feature variables including the text contents of the specification documents. Experimental results showed that our model outperforms a conventional method which uses only the structural properties of the documents. Since users can access the estimated result through a Web-browser-based GUI, this system allows both patent examiners and applicants to quickly detect weak applications and to find their specific flaws.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Current patent systems face a serious problem of declining quality of patents as the larger number of applications make it difficult for patent officers to spend enough time for evaluating each application. For building a better patent system, it is necessary to define a public consensus on the quality of patent applications in a quantitative way. In this article, we tackle the problem of assessing the quality of patent applications based on machine learning and text mining techniques. For each patent application, our tool automatically computes a score called patentability, which indicates how likely it is that the application will be approved by the patent office. We employ a new statistical prediction model to estimate examination results (approval or rejection) based on a large data set including 0.3 million patent applications. The model computes the patentability score based on a set of feature variables including the text contents of the specification documents. Experimental results showed that our model outperforms a conventional method which uses only the structural properties of the documents. Since users can access the estimated result through a Web-browser-based GUI, this system allows both patent examiners and applicants to quickly detect weak applications and to find their specific flaws.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA00700121
• 書誌情報: Journal of information processing; 巻 20, 号 3, p. 655-666, 発行日 2012-07-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-6652
• 出版者 / 言語: ja
• 出版者: 情報処理学会