Title:
MODEL GENERATION DEVICE, PREDICTION DEVICE, MODEL GENERATION METHOD, PREDICTION METHOD, AND RESIN COMPOSITION MANUFACTURING SYSTEM
Document Type and Number:
WIPO Patent Application WO/2023/002804
Kind Code:
A1
Abstract:
According to the present invention, a condition under which required characteristics of a resin composition are satisfied is identified more efficiently than in the past. In this model generation device (100), a first machine learning unit (21) generates, on the basis of first input data (110) and second input data (120) forming a pair with the first input data (110), a first prediction model (MODEL1) for predicting unknown resin composition characteristic data from one or more of (i) arbitrary inorganic filler characteristic data, (ii) arbitrary resin characteristic data, (iii) arbitrary inorganic filler compounding data, and (iv) arbitrary resin compounding data. A second machine learning unit (22) generates, on the basis of the first prediction model (MODEL1), a second prediction model (MODEL2) for predicting one or more of (i) predicted inorganic filler characteristic data, (ii) predicted resin characteristic data, (iii) predicted inorganic filler compounding data, and (iv) predicted resin compounding data satisfying arbitrary resin composition characteristic data.
More Like This:
Inventors:
TAI MINAMI (JP)
IMAI SHUNSUKE (JP)
HAMASAKA GO (JP)
IMAI SHUNSUKE (JP)
HAMASAKA GO (JP)
Application Number:
PCT/JP2022/025344
Publication Date:
January 26, 2023
Filing Date:
June 24, 2022
Export Citation:
Assignee:
TOKUYAMA CORP (JP)
International Classes:
G16C20/30; C08K3/013; C08L101/00; G06Q10/04; G16C20/70
Domestic Patent References:
WO2021079985A1 | 2021-04-29 |
Foreign References:
CN112182979A | 2021-01-05 | |||
JP2004053440A | 2004-02-19 |
Attorney, Agent or Firm:
HARAKENZO WORLD PATENT & TRADEMARK (JP)
Download PDF:
Previous Patent: ACCELERATION DETECTION DEVICE AND ATTACHMENT ANGLE DETECTION METHOD
Next Patent: PRIZE ACQUISITION GAME DEVICE
Next Patent: PRIZE ACQUISITION GAME DEVICE