Title:
POLYMER GRAPH NEURAL NETWORK AND IMPLEMENTATION METHOD THEREFOR
Document Type and Number:
WIPO Patent Application WO/2024/085562
Kind Code:
A1
Abstract:
The present invention provides a computer implementation method for predicting, from the chemical structure of a polymer, characteristic information of the polymer. The present invention provides a method for graphically representing the chemical structure of a polymer, and provides a method and a system for calculating, from graph information of a polymer, on the basis of information defining interconnected relationships between respective atoms constituting repeating units of the polymer and connecting nodes in which repeating units are repeatedly connected, characteristic information of the polymer through machine learning of the chemical structure of the polymer.
Inventors:
MOON HEE YEON (KR)
BAE JAE SOON (KR)
LEE KYU HWANG (KR)
SHIN HYEON AH (KR)
BAE JAE SOON (KR)
LEE KYU HWANG (KR)
SHIN HYEON AH (KR)
Application Number:
PCT/KR2023/015926
Publication Date:
April 25, 2024
Filing Date:
October 16, 2023
Export Citation:
Assignee:
LG CHEMICAL LTD (KR)
International Classes:
G16C20/80; G06N3/08; G16C20/30; G16C20/70; G16C20/90
Attorney, Agent or Firm:
LEE, Kangmin (KR)
Download PDF: