English(EN) From Rules to Neural Graphs: Scalable Structured Prediction for Patent Prior Art Search

新型神经网络解析器为专利检索生成发明图谱

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 12:20

研究人员开发了一种新颖的神经网络解析器，该解析器采用双仿射注意力机制，可直接从专利文本预测发明图谱，克服了传统基于规则的解析器的局限性。该方法在一个百万份规则解析文档的蒸馏数据上进行训练，降低了复杂性，并允许处理超过40,000个 token 的文档而无需重新训练。该系统生成的神经网络图谱在下游检索任务中将引用召回率提高了多达1.1%，同时降低了推理成本。 AI

影响这种生成发明图谱的新方法可以提高专利现有技术检索的准确性和效率。

排序理由这是一篇研究论文，详细介绍了一种用于信息检索的新型结构化预测方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇研究论文，详细介绍了一种用于信息检索的新型结构化预测方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 7 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Sebastian Björkqvist · 2026-10-01 12:20

从规则到神经网络图：可扩展的结构化预测用于专利现有技术检索

Patent search requires processing documents routinely exceeding tens of thousands of tokens. Most neural retrieval approaches operate on truncated inputs, limiting their effectiveness. Graph-based retrieval addresses this by representing each patent as a structured invention grap…

本文如何被排名

报道来源 [1]

从规则到神经网络图：可扩展的结构化预测用于专利现有技术检索

相关实体

相关话题