将论文转专利描述，用结构化图谱保证法律合规性
FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions
- 用有向图提取技术实体与功能关系，构建知识骨架
- 分阶段规划章节内容，确保符合专利标准结构
- 适合需要将科研成果转化为专利的团队使用
从科学论文生成专利描述面临根本性的修辞与结构差异挑战。现有方法仅视作表面重写，未能捕捉专利撰写中固有的层级推理与法定约束。本文提出FlowPlan-G2P，一种基于图结构的生成框架，分三步实现转化：(1) 概念图构建，将技术实体与功能依赖提取为有向图；(2) 章节级规划，将图分割为与标准专利章节对齐的子图；(3) 图条件生成，基于子图生成符合法律要求的段落。在专家验证基准上实验显示，通用NLG指标偏好非合规输出，因此我们采用领域专用评估。结果显示，使用开源模型的FlowPlan-G2P始终优于纯商业模型，证明结构化分解比模型规模更能决定质量。
原文摘要 · Abstract (English)
Generating patent descriptions from scientific papers is challenging due to fundamental rhetorical and structural disparities between the two genres. Existing approaches treat this as surface-level rewriting, failing to capture the hierarchical reasoning and statutory constraints inherent in patent drafting. We propose FlowPlan-G2P, a graph-mediated generation framework that decomposes this transformation into three stages: (1) Concept Graph Induction, extracting technical entities and functional dependencies into a directed graph; (2) Section-level Planning, partitioning the graph into coherent subgraphs aligned with canonical patent sections; and (3) Graph-Conditioned Generation, synthesizing legally compliant paragraphs conditioned on section-specific subgraphs. Experiments on expert-validated benchmarks reveal that standard NLG metrics systematically favor legally non-compliant outputs over valid patent descriptions, motivating our domain-specific evaluation. Under this evaluation, FlowPlan-G2P with an open-weight backbone consistently outperforms vanilla proprietary models, demonstrating that structured decomposition is a stronger determinant of quality than model scale.
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。