$\texttt{PatentAgent}$: Intelligent Agent for Automated Pharmaceutical Patent Analysis

TL;DR

PatentAgent is a pioneering AI system that automates pharmaceutical patent analysis through modules for question-answering, chemical structure conversion, and core chemical identification, significantly improving accuracy over existing methods.

Contribution

The paper introduces the first unified intelligent agent for pharmaceutical patent analysis leveraging LLMs, with three modules that enhance various aspects of patent understanding and identification.

Findings

PA-Img2Mol outperforms existing methods with 2.46%-8.37% accuracy gain.

PA-CoreId improves accuracy by 7.15%-7.62% on PatentNetML.

The framework demonstrates significant effectiveness across multiple patent benchmarks.

Abstract

Pharmaceutical patents play a vital role in biochemical industries, especially in drug discovery, providing researchers with unique early access to data, experimental results, and research insights. With the advancement of machine learning, patent analysis has evolved from manual labor to tasks assisted by automatic tools. However, there still lacks an unified agent that assists every aspect of patent analysis, from patent reading to core chemical identification. Leveraging the capabilities of Large Language Models (LLMs) to understand requests and follow instructions, we introduce the $\textbf{first}$ intelligent agent in this domain, $\texttt{PatentAgent}$, poised to advance and potentially revolutionize the landscape of pharmaceutical research. $\texttt{PatentAgent}$ comprises three key end-to-end modules -- $\textit{PA-QA}$, $\textit{PA-Img2Mol}$, and $\textit{PA-CoreId}$ -- that respectively perform (1) patent question-answering, (2) image-to-molecular-structure conversion, and (3) core chemical structure identification, addressing the essential needs of scientists and practitioners in pharmaceutical patent analysis. Each module of $\texttt{PatentAgent}$ demonstrates significant effectiveness with the updated algorithm and the synergistic design of $\texttt{PatentAgent}$ framework. $\textit{PA-Img2Mol}$ outperforms existing methods across CLEF, JPO, UOB, and USPTO patent benchmarks with an accuracy gain between 2.46% and 8.37% while $\textit{PA-CoreId}$ realizes accuracy improvement ranging from 7.15% to 7.62% on PatentNetML benchmark. Our code and dataset will be publicly available.