PAI-NET: Retrieval-Augmented Generation Patent Network Using Prior Art Information

PAI-NET: патентная сеть с генерацией, дополненной поиском, на основе информации о предшествующем уровне техники
Juho Bai, Kyung Yul Lee
2025-04-07

patent document retrievalpatent document similarityprior art relationshipsretrieval-augmented generationsemantic distance evaluation
Similar patent document retrieval is an essential task that reduces the scope of patent claimants' searches, and numerous studies have attempted to provide automated patent search services. Recently, Retrieval-Augmented Generation (RAG) based on generative language models has emerged as an excellent method for accessing and utilizing patent knowledge environments. RAG-based patent search services offer high utility as AI search services by providing document knowledge similar to queries. However, achieving satisfactory quality in similarity search services remains a challenging task, as search methods based on document similarity do not carefully consider the characteristics of patent documents. Unlike general document retrieval, the similarity of patent documents must take into account prior art relationships. To address this issue, we propose PAI-NET, a deep neural network for computing patent document similarities by incorporating expert knowledge of prior art relationships. We demonstrate that our proposed method outperforms current state-of-the-art models in patent document classification tasks through semantic distance evaluation on USPD and KPRIS datasets. PAI-NET presents similar document candidates demonstrating a superior patent search performance improvement of 15\% over state-of-the-art methods.
1
PAI-NET computes patent-document similarity by incorporating expert knowledge of prior-art relationships, addressing limitations of generic document-similarity retrieval.
2
PAI-NET outperforms current state-of-the-art models in patent-document classification based on semantic-distance evaluation on the USPD and KPRIS datasets.
3
The method improves patent search performance by 15% over state-of-the-art approaches when presenting similar-document candidates.
4
The proposed deep neural network is designed for retrieval-augmented generation patent search services that provide documents relevant to user queries.

patent documents and their prior-art relationships

similarity relationships and retrieval performance of patent documents when prior-art relationships are incorporated

Publication Details
Publication Date
2025-04-07
Journal
Publisher
ISSN
Cited by
7
Access Type
Author Information
Authors
Juho Bai
Kyung Yul Lee
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%