English

Finding your MUSE: Mining Unexpected Solutions Engine

Artificial Intelligence 2025-09-08 v1 Computation and Language

Abstract

Innovators often exhibit cognitive fixation on existing solutions or nascent ideas, hindering the exploration of novel alternatives. This paper introduces a methodology for constructing Functional Concept Graphs (FCGs), interconnected representations of functional elements that support abstraction, problem reframing, and analogical inspiration. Our approach yields large-scale, high-quality FCGs with explicit abstraction relations, overcoming limitations of prior work. We further present MUSE, an algorithm leveraging FCGs to generate creative inspirations for a given problem. We demonstrate our method by computing an FCG on 500K patents, which we release for further research.

Keywords

Cite

@article{arxiv.2509.05072,
  title  = {Finding your MUSE: Mining Unexpected Solutions Engine},
  author = {Nir Sweed and Hanit Hakim and Ben Wolfson and Hila Lifshitz and Dafna Shahaf},
  journal= {arXiv preprint arXiv:2509.05072},
  year   = {2025}
}
R2 v1 2026-07-01T05:23:04.390Z