Predicting Patent Licensing Using Graph Convolutional Networks (GCN)

Date

2025-01-07

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

5119

Ending Page

Alternative Title

Abstract

Numerous scholars have delved into the primary factors influencing patent licensing, yet the relationships between licensors, licensees, and licensed patents require further exploration. This study proposes using Graph Convolutional Networks (GCN) to analyze these relationships and predict future patent licensing. Utilizing data from the United States Patent and Trademark Office (USPTO) assignment dataset, we extract features such as company technological capabilities, domains, licensed patents, International Patent Classifications (IPCs), and network similarity. Our proposed GCN model aims to enhance strategic planning for companies and provide insights into future technological trends. Experimental results demonstrate that the GCN model outperforms traditional machine learning methods, offering improved accuracy in predicting patent licensing and valuable guidance for corporate strategy development.

Description

Keywords

Knowledge Flows, Transfer, Sharing, and Exchange, graph convolutional network (gcn), link prediction, patent licensing

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 58th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.