用多维度图结构评估专利相似性，更贴近专家判断。
PatentMind: A Multi-Aspect Reasoning Graph for Patent Similarity Evaluation
- 构建多方面推理图，分解专利的技术、应用、权利范围三维度
- 生成评分与专家标注相关性达0.938，显著优于现有方法
- 适合专利分析、侵权风险评估等实际决策场景
专利相似性评估在知识产权分析中至关重要。现有方法常忽视专利文档内在的复杂结构，该结构包含技术细节、法律边界和应用场景。本文提出PatentMind框架，基于多方面推理图（MARG）实现专利相似性评估。PatentMind将专利分解为技术特征、应用领域和权利要求范围三个维度，在MARG上分别计算维度内相似度，并通过上下文感知推理过程动态加权，模拟专家判断。为支持评估，构建了人工标注基准PatentSimBench，包含500对专利。实验表明，PatentMind生成的相似度评分与专家标注的相关系数高达$r=0.938$，显著优于基于嵌入的模型、专利专用模型及先进提示工程方法。该框架不仅推动计算语言学发展，更为侵权风险评估等现实决策任务提供结构化、语义可解释的基础，具有广泛的应用价值。
原文摘要 · Abstract (English)
Patent similarity evaluation plays a critical role in intellectual property analysis. However, existing methods often overlook the intricate structure of patent documents, which integrate technical specifications, legal boundaries, and application contexts. We introduce PatentMind, a novel framework for patent similarity assessment based on a Multi-Aspect Reasoning Graph (MARG). PatentMind decomposes patents into their three dimensions of technical features, application domains, and claim scopes, then dimension-specific similarity scores are calculated over the MARG. These scores are dynamically weighted through a context-aware reasoning process, which integrates contextual signals to emulate expert-level judgment. To support evaluation, we construct a human-annotated benchmark PatentSimBench, comprising 500 patent pairs. Experimental results demonstrate that the PatentMind-generated scores show a strong correlation ($r=0.938$) with expert annotations, significantly outperforming embedding-based models, patent-specific models, and advanced prompt engineering methods. Beyond computational linguistics, our framework provides a structured and semantically grounded foundation for real-world decision-making, particularly for tasks such as infringement risk assessment, underscoring its broader impact on both patent analytics and evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。