Finding your MUSE: Mining Unexpected Solutions Engine

2025-09-05

AI Summary

Innovators often suffer from cognitive fixation, hindering breakthrough solutions beyond existing paradigms. Method: This paper proposes the Functional Concept Graph (FCG) construction framework and the MUSE creative generation framework. First, leveraging 500,000 patent texts, we integrate natural language processing and knowledge graph techniques to automatically construct, for the first time, a large-scale, interpretable FCG that explicitly models abstract functional relationships. Second, we design MUSE—a graph neural network algorithm—that generates highly diverse and novel solutions via problem reformulation and cross-domain analogical reasoning. Contribution/Results: The constructed FCG is publicly released. Experiments demonstrate that MUSE significantly outperforms baseline methods across creativity quality, solution coverage, and interpretability—establishing new state-of-the-art performance in data-driven inventive problem solving.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Overcoming cognitive fixation on existing solutions
• Generating creative inspirations for given problems
• Constructing large-scale Functional Concept Graphs from patents

Innovation

• Constructs Functional Concept Graphs for abstraction
• Leverages FCGs to generate creative inspirations
• Computes large-scale FCGs on patent datasets