Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Finding new technological ideas and inventions with text mining and technique philosophy

: Thorleuchter, D.

Postprint urn:nbn:de:0011-n-748815 (246 KByte PDF)
MD5 Fingerprint: 694cda0faded5129f90e40507e1275ae
The original publication is available at
Erstellt am: 17.6.2011

Preisach, C. ; Gesellschaft für Klassifikation:
Data analysis, machine learning and applications : Proceedings of the 31st Annual Conference of the Gesellschaft für Klassifikation e.V., Albert-Ludwigs-Universität Freiburg, March 7-9, 2007
Berlin: Springer, 2008 (Studies in classification, data analysis, and knowledge organization)
ISBN: 978-3-540-78239-1
ISBN: 3-540-78239-7
Gesellschaft für Klassifikation (Annual Conference) <31, 2007, Freiburg>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer INT ()
text mining

Text mining refers generally to the process of deriving high quality information from unstructured texts. Unstructured texts come in many shapes and sizes. It may be stored in research papers, articles in technical periodicals, reports, documents, web pages etc. Here we introduce a new approach for finding textual patterns representing new technological ideas and inventions in unstructured technological texts.
This text mining approach follows the statements of technique philosophy. Therefore a technological idea or invention represents not only a new mean, but a new purpose and mean combination. By systematic identification of the purposes, means and purpose-mean combinations in unstructured technological texts compared to specialized reference collections, a (semi-) automatic finding of ideas and inventions can be realized. Characteristics that are used to measure the quality of these patterns found in technological texts are comprehensibility and novelty to humans and usefulness for an application.