Simulating Patent Knowledge Contexts

Abstract

Patent users such as government, inventors, and manufacturing organizations strive to identify the directions in which the new technology is advancing. The organization of patent knowledge in maps aims at outlining the boundaries of existing knowledge. This article demonstrates the methodology for simulating alternative knowledge contexts beyond the border of existing knowledge. The process starts with extracting knowledge from patents and applying self-organizing maps for presenting knowledge. The knowledge extraction model was tested earlier on patents from the United States Patent and Trademark Office. A demonstrator tool is then used to perform “what-if” type of analysis/simulation on the clusters in the dataset to see alternative knowledge contexts for the new knowledge “entity”. This may open up new directions and help to plan for the future. The demonstrator tool has been tested earlier on other datasets. The proposed knowledge context simulation shows promise for the future development and applications.