Large Language Model Informed Patent Image Retrieval

arXiv:2404.19360v1 Announce Type: new
Abstract: In patent prosecution, image-based retrieval systems for identifying similarities between current patent images and prior art are pivotal to ensure the novelty and non-obviousness of patent applications. Despite their growing popularity in recent years, existing attempts, while effective at recognizing images within the same patent, fail to deliver practical value due to their limited generalizability in retrieving relevant prior art. Moreover, this task inherently involves the challenges posed by the abstract visual features of patent …

abstract applications art arxiv cs.cl cs.cv cs.ir current image images language language model large language large language model patent pivotal prior retrieval systems type while