Affiliations: [a] LGECO/INSA Strasbourg, Strasbourg Cedex, France | [b] ICUBE/BFO Team, Illkirch Cedex, France | [c] Rousselot, Illkirch, France | Computational Intelligence Group, University of the Basque Country, UPV/EHU, Spain
Correspondence:
[*]
Corresponding author: Wei Yan, LGECO/INSA Strasbourg, 24 Boulevard de la Victoire, Strasbourg Cedex 67084, France. E-mail: wei.yan@insa-strasbourg.fr
Abstract: The theory of inventive problem solving (TRIZ) was developed to solve inventive problems in different industrial fields. In recent decades, modern innovation theories and methods proposed several different knowledge sources. These knowledge sources are all built independently of the specific application and their different levels of abstraction make it quite difficult to use them without extensive knowledge about different engineering domains. Considering that all the TRIZ knowledge sources are described in short-text, the missing links among the TRIZ knowledge sources are defined based on short-text semantic similarity, which also makes it possible to ease the use of TRIZ. Meanwhile, the ontology reasoning mechanism deployed on Protégé and JESS, is used to provide heuristic solutions dynamically for TRIZ users. Firstly, TRIZ users start solving the inventive problem with the TRIZ knowledge source of their choice. Then other similar knowledge sources are obtained according to a calculation of semantic relatedness. Finally, with the help of the heuristic abstract solutions and pointers to physical-chemical-geometrical effects, specific solutions are obtained through ontology reasoning. A particular case of a "Diving Fin" is studied to show the heuristic processes of searching abstract solutions and pointers to physical-chemical-geometrical effects in detail.
