Granted Patent B2

US 12,700,479 · App. 18/254,384 · Granted Aug 4, 2026

Inventor: Kyohei Hanaoka (Tokyo, JP)

G16C20/30G16C20/70G06N3/044G06N3/0464G06N3/08G06N20/00G16C60/00

Abstract

Claims (66)

1 . An information processing system comprising at least one processor,

wherein the at least one processor is configured to:

acquire a numerical representation and a combination ratio for each of a multiplicity of mutually different polymers or monomers, wherein the numerical representation represents attributes of the multiplicity of polymers or monomers, and wherein the combination ratio corresponds to a ratio among the multiplicity of polymers or monomers;

generate a first trained machine learning model by executing and repeating a first machine learning process comprising:

inputting a first input vector into a first untrained machine learning model to calculate a first output value;

calculating a first difference between the first output value and a first ground truth; and

updating a first parameter of the first untrained machine learning model based on the first difference;

input a plurality of numerical representations to the first trained machine learning model to calculate a plurality of feature vectors corresponding to the multiplicity of polymers or monomers;

generate a second trained machine learning model by executing and repeating a second machine learning process comprising:

inputting a second input vector into a second untrained machine learning model to calculate a second output value;

calculating a second difference between the second output value and a second ground truth; and

updating a second parameter of the second untrained machine learning model based on the second difference;

input the plurality of feature vectors to the second trained machine learning model to calculate a plurality of regression parameters corresponding to the multiplicity of polymers or monomers; and

apply a plurality of the combination ratios to a regression model defined by the plurality of regression parameters to calculate a predicted value indicating characteristics of a polymer alloy obtained by combining the multiplicity of polymers or monomers;

change values of the plurality of combination ratios;

recalculate the predicted value indicating the characteristics of the polymer alloy, by using the changed values of the plurality of combination ratios and the calculated plurality of regression parameters;

output the calculated predicted value and the recalculated predicted value;

execute processing for searching for the characteristics of the polymer alloy using the calculated predicted value and the recalculated predicted value; and

cause a display device to display a result of the processing for searching.

2 . The information processing system according to claim 1 ,

wherein the first machine learning model includes a machine learning model for an embedding function and a machine learning model for an interaction function, and

wherein the at least one processor is configured to:

input the plurality of numerical representations to the machine learning model for the embedding function to calculate a plurality of first feature vectors corresponding to the multiplicity of polymers or monomers;

input the plurality of first feature vectors into the machine learning model for the interaction function to calculate a plurality of second feature vectors corresponding to the multiplicity of polymers or monomers; and

input the plurality of second feature vectors to the second machine learning model to calculate the plurality of regression parameters.

3 . The information processing system according to claim 2 , wherein the machine learning model for the embedding function is a machine learning model that generates the first feature vector that is a fixed-length vector, from the numerical representation that is unstructured data.

4 . The information processing system according to claim 1 ,

wherein the regression model is a Scheffe polynomial, and

wherein the at least one processor is configured to calculate a plurality of regression coefficients of a first-order term of the Scheffe polynomial, as the plurality of regression parameters.

5 . The information processing system according to claim 4 , wherein the at least one processor is configured to further calculate a plurality of regression coefficients of a second-order term of the Scheffe polynomial, as the plurality of regression parameters.

6 . An information processing method executed by an information processing system comprising at least one processor, the method comprising:

acquiring a numerical representation and a combination ratio for each of a multiplicity of mutually different polymers or monomers, wherein the numerical representation represents attributes of the multiplicity of polymers or monomers, and wherein the combination ratio corresponds to a ratio among the multiplicity of polymers or monomers;

generating a first trained machine learning model by executing and repeating a first machine learning process comprising:

inputting a first input vector into a first untrained machine learning model to calculate a first output value;

calculating a first difference between the first output value and a first ground truth; and

updating a first parameter of the first untrained machine learning model based on the first difference;

inputting a plurality of numerical representations to the first trained machine learning model to calculate a plurality of feature vectors corresponding to the multiplicity of polymers or monomers;

generating a second trained machine learning model by executing and repeating a second machine learning process comprising:

inputting a second input vector into a second untrained machine learning model to calculate a second output value;

calculating a second difference between the second output value and a second ground truth; and

updating a second parameter of the second untrained machine learning model based on the second difference;

inputting the plurality of feature vectors to the second trained machine learning model to calculate a plurality of regression parameters corresponding to the multiplicity of polymers or monomers; and

applying a plurality of the combination ratios to a regression model defined by the plurality of regression parameters to calculate a predicted value indicating characteristics of a polymer alloy obtained by combining the multiplicity of polymers or monomers;

changing values of the plurality of combination ratios;

recalculating the predicted value indicating the characteristics of the polymer alloy, by using the changed values of the plurality of combination ratios and the calculated plurality of regression parameters;

outputting the calculated predicted value and the recalculated predicted value;

executing processing for searching for the characteristics of the polymer alloy using the calculated predicted value and the recalculated predicted value; and

cause a display device to display a result of the processing for searching.

7 . A non-transitory computer-readable storage medium storing an information processing program for causing a computer to execute:

acquiring a numerical representation and a combination ratio for each of a multiplicity of mutually different polymers or monomers, wherein the numerical representation represents attributes of the multiplicity of polymers or monomers, and wherein the combination ratio corresponds to a ratio among the multiplicity of polymers or monomers;

generating a first trained machine learning model by executing and repeating a first machine learning process comprising:

inputting a first input vector into a first untrained machine learning model to calculate a first output value;

calculating a first difference between the first output value and a first ground truth; and

updating a first parameter of the first untrained machine learning model based on the first difference;

inputting a plurality of numerical representations to the first trained machine learning model to calculate a plurality of feature vectors corresponding to the multiplicity of polymers or monomers;

generating a second trained machine learning model by executing and repeating a second machine learning process comprising:

inputting a second input vector into a second untrained machine learning model to calculate a second output value;

calculating a second difference between the second output value and a second ground truth; and

updating a second parameter of the second untrained machine learning model based on the second difference;

inputting the plurality of feature vectors to the second trained machine learning model to calculate a plurality of regression parameters corresponding to the multiplicity of polymers or monomers; and

applying a plurality of the combination ratios to a regression model defined by the plurality of regression parameters to calculate a predicted value indicating characteristics of a polymer alloy obtained by combining the multiplicity of polymers or monomers;

changing values of the plurality of combination ratios;

recalculating the predicted value indicating the characteristics of the polymer alloy, by using the changed values of the plurality of combination ratios and the calculated plurality of regression parameters;

outputting the calculated predicted value and the recalculated predicted value;

executing processing for searching for the characteristics of the polymer alloy using the calculated predicted value and the recalculated predicted value; and

cause a display device to display a result of the processing for searching.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (15)