Knowledge extraction from patent: Achievements and open problems. A multidisciplinary approach to find functions

Abstract

Patents are an increasingly important source of technological intelligence that companies can use to gain strategic advantage. Public databases, such as Espacenet, offer for free, available over the internet, some millions of documents with constant format and always updated. So, the answer to most of our technical questions depends on how we are able to extract crucial information from patent corpus and translate them into knowledge. A general overview on universal tools for knowledge management (bibliometric, text mining, semantic) is proposed, with the aim to highlight what problems have already been overcome and what still needs to be done, especially for TRIZ users who want to identify technical features in a text. © Springer-Verlag Berlin Heidelberg 2011.