AI-Based Prior Art Search in Patent Examination
Explore how AI is revolutionizing the patent examination process by creating semantic clusters of patent documents to enhance prior art search efficiency. Rospatent, under the leadership of Alexander Gorbunov, is at the forefront of this innovation. Discover the infrastructure, datasets, and research findings shaping the future of intellectual property examination.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Rospatent Federal Service for Intellectual Property Data sets for training AI-based prior art search Speaker: Alexander Gorbunov Head of the Center for the Development of the Scientific Direction Artificial Intelligence
USING AI IN THE EXAMINATION : INVENTIONS The most important issue of the examination of an application for the patent is to search for a variety of documents characterizing the state of the art for this application. We suggest to name this set of documents a semantic cluster of patent documents. A unique feature of the published patent information is, in accordance with the WIPO standard, the list of documents characterized the state of the art for this patent application according to the examiner s contains a Semantic cluster of patent documents). opinion (thus published patent 2
PLATFORM FUNCTIONALITY : INFRASTRUCTURE for AI-based PATENT RETRIEVAL SERVICE REATING DATASETS FOR MACHINE LEARNING DATASETS BASED ON SEMANTIC CLUSTERS The semantic cluster of patent documents is a set of patent documents, including: an application for the patent, a description of the invention; patent documents of the patent family, which includes this application for the patent; patent documents referred to by examiners in publications of search reports for the the application and in the field entitled INID code (56); patent documents of patent families, which include documents examination; patent documents indicated by the applicant as prototypes in the submitted application; patent documents of patent families, which include documents referred to by references given by the applicant referred to by the 3
USING AI IN THE EXAMINATION : INVENTIONS ALREADY AVAILABLE TODAY: Dataset of semantic clusters of Russian-language patent documents(1.5 million clusters) Dataset generator of semantic clusters of English- language patent documents (8.5 million clusters) THE FIRST RESULTS ARE PUBLISHED: GORBUNOV A.V., GENIN B.L., ZOLKIN D.S., Prior art search as a problem of determining the elements of the semantic cluster of patent documents - , 1, 2023, 8 B.L.Genin, D.S.Zolkin, Similarity search in patents databases. The evaluations of the search quality , World Patent Information, Volume 64, March 2021, https://doi.org/10.1016/j.wpi.2021.102022 4
Rospatent Federal Service for Intellectual Property Thank you! Speaker: Alexander Gorbunov Head of the Center for the Development of the Scientific Direction Artificial Intelligence
