Aligning Human and Computational Evaluations of Functional Design Similarity

Abstract

Function drives many early design considerations in product development. Therefore, finding functionally similar examples is important when searching for sources of inspiration or evaluating designs against existing technology. However, it is difficult to capture what people consider to be functionally similar and therefore, if measures that compare function directly from the products themselves are meaningful. In this work, we compare human evaluations of similarity to computationally determined values, shedding light on how quantitative measures align with human perceptions of functional similarity. Human perception of functional similarity is considered at two levels of abstraction: (1) the high-level purpose of a product, and (2) a detailed view of how the product works. Human evaluations of similarity are quantified by crowdsourcing 1360 triplet ratings at each functional abstraction, and then compared to similarity that is computed between functional models. We demonstrate how different levels of abstraction and the fuzzy line between what is considered “similar” and “similar enough” may impact how these similarity measures are utilized, finding that different measures better align with human evaluations along each dimension. The results inform how product similarity can be leveraged by designers. Therefore, applications lie in creativity support tools, such as those used for design-by-analogy, or future computational methods in design that incorporate product function in addition to form.