Identification of trends from patents using self-organizing maps

: Segev A, Kantola J

Publisher: PERGAMON-ELSEVIER SCIENCE LTD

: 2012

: Expert Systems with Applications

: EXPERT SYSTEMS WITH APPLICATIONS

: EXPERT SYST APPL

: 39

: 18

: 13235

: 13242

: 8

: 0957-4174

DOI: https://doi.org/10.1016/j.eswa.2012.05.078

Patent users such as governments, inventors, and manufacturing organizations strive to identify the directions in which new technology is advancing, and their goal is to outline the boundaries of existing knowledge. The paper analyzes patent knowledge to identify research trends. A model based on knowledge extraction from patents and self-organizing maps for knowledge representation is presented. The model was tested on patents from the United States Patent and Trademark Office. The experiments show that the method provides both an overview of the directions of the trends and a drill-down perspective of current trends. (C) 2012 Elsevier Ltd. All rights reserved.