Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sweed, Nir, Hakim, Hanit, Wolfson, Ben, Lifshitz, Hila, Shahaf, Dafna
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.05072
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908521298132992
author Sweed, Nir
Hakim, Hanit
Wolfson, Ben
Lifshitz, Hila
Shahaf, Dafna
author_facet Sweed, Nir
Hakim, Hanit
Wolfson, Ben
Lifshitz, Hila
Shahaf, Dafna
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05072
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finding your MUSE: Mining Unexpected Solutions Engine
Sweed, Nir
Hakim, Hanit
Wolfson, Ben
Lifshitz, Hila
Shahaf, Dafna
Artificial Intelligence
Computation and Language
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.
title Finding your MUSE: Mining Unexpected Solutions Engine
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2509.05072