Multimodal Deep Learning for Patent Classification

Juhyun Lee, Junseok Lee, Jiho Kang, Youngho Kim, Dongsik Jang, Sangsung Park

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Citations (Scopus)

    Abstract

    The global technology market is changing rapidly. Organizations need strategies to increase their competitiveness. Technology transfer is an effective tool for them to plan for intellectual property research and development. Prediction of technology transfer leads to efficient results. For this, we propose multimodal learning. The model utilizes the quantitative information and text of the patent. Unlike the previous studies, it uses the architecture of deep learning. The model was tested for practical applicability through patent data. As a result, it showed higher performance than other models.

    Original languageEnglish
    Title of host publicationProceedings of 6th International Congress on Information and Communication Technology, ICICT 2021
    EditorsXin-She Yang, Simon Sherratt, Nilanjan Dey, Amit Joshi
    PublisherSpringer Science and Business Media Deutschland GmbH
    Pages281-289
    Number of pages9
    ISBN (Print)9789811621017
    DOIs
    Publication statusPublished - 2022
    Event6th International Congress on Information and Communication Technology, ICICT 2021 - Virtual, Online
    Duration: 2021 Feb 252021 Feb 26

    Publication series

    NameLecture Notes in Networks and Systems
    Volume217
    ISSN (Print)2367-3370
    ISSN (Electronic)2367-3389

    Conference

    Conference6th International Congress on Information and Communication Technology, ICICT 2021
    CityVirtual, Online
    Period21/2/2521/2/26

    Bibliographical note

    Publisher Copyright:
    © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

    Keywords

    • Multimodal learning
    • Patent classification
    • Technology transfer

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Signal Processing
    • Computer Networks and Communications

    Fingerprint

    Dive into the research topics of 'Multimodal Deep Learning for Patent Classification'. Together they form a unique fingerprint.

    Cite this