基于图注意力网络的专利诉讼预测中权利要求依赖结构建模

中文摘要 AI 辅助

专利诉讼会给企业带来巨额成本并扭曲研发激励，因此早期风险识别是一项具有重要实际意义的任务。尽管已有研究将基于BERT的模型应用于专利权利要求文本，但仍存在两个根本性局限：平面序列编码会丢失独立权利要求与从属权利要求之间的依赖结构，而这种结构在法律上决定了专利保护范围；将全部权利要求集输入单个编码器会丢弃法律上关键的文本信息。对134万件美国专利商标局（USPTO）实用专利进行的六模型 ablation 实验证实，每件权利要求的编码、图连通性、注意力机制及Attentional Aggregation均能提供独立的、可叠加的预测价值。我们提出了ClaimGAT，这是一种图注意力网络，它对每件权利要求进行独立编码，构建有向权利要求依赖图，通过GATConv层处理该图，并通过Attentional Aggregation聚合独立权利要求，以生成诉讼风险评分和权利要求级别的门控权重，从而支持事后结构分析。ClaimGAT仅使用专利授权时可观测的信息，就达到了0.818的AUC-ROC值和Top 10%时4.89倍的提升率（lift）。它还揭示了高风险专利存在结构选择与内容敏感性偏离的趋势，这一模式与防御性权利要求撰写方式一致。

英文摘要

Patent litigation imposes substantial costs on firms and distorts R&D incentives, making early risk identification a practically important task. While prior work has applied BERT-based models to patent claim text, two fundamental limitations remain: flat sequence encoding loses the dependency structure between independent and dependent claims that legally determines patent scope, and feeding the entire claim set to a single encoder discards legally critical text. A six-model ablation on 1.34 million USPTO utility patents confirms that per-claim encoding, graph connectivity, attention, and Attentional Aggregation each provide independent, additive predictive value. We propose ClaimGAT, a Graph Attention Network that encodes each claim independently, constructs a directed claim dependency graph, processes it with GATConv layers, and aggregates independent claims via Attentional Aggregation to yield both a litigation risk score and claim-level gate weights that enable post-hoc structural analysis. ClaimGAT achieves an AUC-ROC of 0.818 and a lift of 4.89x at the top 10%, using only information observable at the time of patent grant. It reveals a tendency in high-risk patents for structural selection and content sensitivity to diverge, a pattern consistent with defensive claim drafting.

发表机构

• Graduate School of Information Science（信息科学研究生院）
• University of Hyogo（兵库县立大学）
• Center for Computational Science, RIKEN（理化学研究所计算科学中心）

机构由 AI 辅助整理，请以论文原文为准。