An automatic patent literature retrieval system based on LLM-RAG

TL;DR

This paper introduces an automated patent retrieval system that combines Large Language Models with Retrieval-Augmented Generation to improve semantic accuracy and relevance in patent literature searches.

Contribution

It presents a novel integrated framework leveraging LLMs and RAG technology for efficient, accurate patent retrieval and classification, outperforming traditional methods.

Findings

Achieved 80.5% semantic matching accuracy

Surpassed baseline LLM methods by 28 percentage points

Demonstrated strong generalization in cross-domain tasks

Abstract

With the acceleration of technological innovation efficient retrieval and classification of patent literature have become essential for intellectual property management and enterprise RD Traditional keyword and rulebased retrieval methods often fail to address complex query intents or capture semantic associations across technical domains resulting in incomplete and lowrelevance results This study presents an automated patent retrieval framework integrating Large Language Models LLMs with RetrievalAugmented Generation RAG technology The system comprises three components: 1) a preprocessing module for patent data standardization, 2) a highefficiency vector retrieval engine leveraging LLMgenerated embeddings, and 3) a RAGenhanced query module that combines external document retrieval with contextaware response generation Evaluations were conducted on the Google Patents dataset 20062024 containing millions of global patent records with metadata such as filing date domain and status The proposed gpt35turbo0125RAG configuration achieved 805 semantic matching accuracy and 92.1% recall surpassing baseline LLM methods by 28 percentage points The framework also demonstrated strong generalization in crossdomain classification and semantic clustering tasks These results validate the effectiveness of LLMRAG integration for intelligent patent retrieval providing a foundation for nextgeneration AIdriven intellectual property analysis platforms