Can you imagine... a language for combinatorial creativity?


 

Combinatorial creativity combines existing concepts in a novel way in order to produce new concepts. For example, we can imagine jewelry that measures blood pressure. For this, we would combine the concept of jewelry with the capabilities of medical devices. Combinatorial creativity can be used to develop new business ideas, to find plots for books or movies, or simply to disrupt conventional thinking. In this paper, we propose a formal language for combinatorial creativity, based on description logics. We show that our language can be used to model existing inventions and (to a limited degree) to generate new concepts.

Publications

Software

We provide a Java tool that implements our language, as well as a concept generator. Just download and double-click. If the tool does not run, make sure that you have Java installed, and that you have the latest version (at least 1.8). You can also download the source code.

The software was written by Fabian M. Suchanek (https://suchanek.name) and is available under a Creative Commons Attribution-ShareAlike license. This work includes data from ConceptNet 5, which was compiled by the Commonsense Computing Initiative. ConceptNet 5 is freely available under the Creative Commons Attribution-ShareAlike license (CC BY SA 3.0) from http://conceptnet5.media.mit.edu. The included data was created by contributors to Commonsense Computing projects, contributors to Wikimedia projects, Games with a Purpose, Princeton University's WordNet, DBPedia, OpenCyc, and Umbel.

Descriptive Experiments

We provide all hand-drawn concepts of the descriptive experiments, as well as all transitions. The hand-drawn concepts are stored in files of the form number.extension, where number runs from 01 to 25, and extension is either png, or jpg, or pdf (depending on how the drawing was scanned). The transitions are stored in the accompanying files number.txt.

Generative experiments

We also provide our generated concepts with the user evaluations. While the first concepts in the list are unfortunately not particularly insightful, the overall quality is better than we expected.