PatentVision: A multimodal method for drafting patent applications
This work addresses the complex task of patent drafting for legal and innovation professionals, offering a scalable tool to reduce manual workloads, though it is incremental as it applies existing LVLM techniques to a new domain.
The paper tackles the problem of automating patent drafting by developing PatentVision, a multimodal framework that integrates textual and visual inputs to generate patent specifications, resulting in outputs that surpass text-only methods with greater fidelity and alignment to human standards.
Patent drafting is complex due to its need for detailed technical descriptions, legal compliance, and visual elements. Although Large Vision Language Models (LVLMs) show promise across various tasks, their application in automating patent writing remains underexplored. In this paper, we present PatentVision, a multimodal framework that integrates textual and visual inputs such as patent claims and drawings to generate complete patent specifications. Built on advanced LVLMs, PatentVision enhances accuracy by combining fine tuned vision language models with domain specific training tailored to patents. Experiments reveal it surpasses text only methods, producing outputs with greater fidelity and alignment with human written standards. Its incorporation of visual data allows it to better represent intricate design features and functional connections, leading to richer and more precise results. This study underscores the value of multimodal techniques in patent automation, providing a scalable tool to reduce manual workloads and improve consistency. PatentVision not only advances patent drafting but also lays the groundwork for broader use of LVLMs in specialized areas, potentially transforming intellectual property management and innovation processes.