A Framework for Graph-Conditioned Hierarchical Shapley Attribution in Patent Valuation
Researchers have developed PatentXAI, a novel framework designed to tackle the complex problem of valuing individual patents within large product portfolios. This framework leverages graph-conditioned hierarchical Shapley attribution, treating patent valuation as an explainable AI task. By focusing on a patent's Markov Blanket within a knowledge graph, PatentXAI significantly improves computational tractability and efficiency, achieving rapid execution times even with a large number of patents. AI
IMPACT Provides a more efficient and accurate method for valuing intellectual property within complex product ecosystems.