Study on extracting implicit patterns of patent data based on timeline

Patent documents are provide a significant source of knowledge about future technologies. Many attempts have been conducted to mine important knowledge from patents to analyze new technology trends. In this paper, we will to analyze implicit knowledge derived from the patents dataset of Big Data domain from KIPRIS. Keywords that occur in the title of patents are classified into three categories: Approach, Goal Object, and Goal Predicate, in order to create a model of relations of title patterns. The same keywords found on the timeline interval will be analyzed and illustrated in the patent pattern which are able to depict the relationship of goals and approaches of the patents occurred in different time interval. As a result, implicit trends and knowledge related to of specific keywords of technology reflect of each time gap can be obtained. Search result using ‘Goal object, Goal predicate and Approach’ pattern query is also found efficient and meet the user enquiry related technologies in timeline.

[2]  R. S. Campbell,et al.  Patent trends as a technological forecasting tool , 1983 .

[3]  Myung-Sun Lee,et al.  Analysis of Technology Trends from Words in Patent Titles , 2010 .

[4]  Juan Enrique Ramos,et al.  Using TF-IDF to Determine Word Relevance in Document Queries , 2003 .

[5]  Soumyo D. Moitra,et al.  Innovation assessment through patent analysis , 2001 .

[6]  Aviv Segev,et al.  Identification of trends from patents using self-organizing maps , 2012, Expert Syst. Appl..

[7]  Hiroshi Nakagawa,et al.  A Simple but Powerful Automatic Term Extraction Method , 2002, COLING 2002.

[8]  Hwan Lim,et al.  Study for Improving the Patent Management Scheme by Using Citation Index in Public-sector R&D Institutes : Case Study on K Institute , 2008 .

[9]  Jinpyo Lee,et al.  A Trend Analysis Method for IoT Technologies Using Patent Dataset with Goal and Approach Concepts , 2016, Wirel. Pers. Commun..

[10]  C. Haruechaiyasak,et al.  A comparative study on Thai word segmentation approaches , 2008, 2008 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[11]  Key-Sun Choi,et al.  Korean Treebank Transformation for Parser Training , 2012, SPMRL@ACL 2012.

[12]  Jean Pierre Courtial,et al.  The use of patent titles for identifying the topics of invention and forecasting trends , 1993, Scientometrics.

[13]  M. A. Siegler,et al.  Automatic Segmentation, Classification and Clustering of Broadcast News Audio , 1997 .

[14]  Tugrul U. Daim,et al.  Forecasting emerging technologies: Use of bibliometrics and patent analysis , 2006 .

[15]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.