Abstract
In this paper, we propose a computational framework that models concept invention. The framework is based on conceptual blending, a cognitive theory that models human creativity and explains how new concepts are created. Apart from the blending mechanism modeling the creation of new concepts, the framework considers two extra dimensions such as origin and destination. For the former, we describe how a Rich Background supports the discovery of input concepts to be blended. For the latter, we show how arguments, promoting or demoting the values of an audience, to which the invention is headed, can be used to evaluate the candidate blends created. Throughout the paper, we exemplify the computational framework in the domain of computer icons.