US 12,277,370 B2
Systems and methods for machine learning based product design automation and optimization
Amit Kumar, Sugar Land, TX (US); Nishant Mehta, Delhi (IN); Piyush Manocha, New Delhi (IN); Anshul Gupta, Delhi (IN); Anshul Anand, Lucknow (IN); and Naveen Sankaran, Chennai (IN)
Assigned to Accenture Global Solutions Limited, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Jun. 11, 2021, as Appl. No. 17/346,098.
Prior Publication US 2022/0398365 A1, Dec. 15, 2022
Int. Cl. G06F 30/27 (2020.01); G06F 18/211 (2023.01); G06F 18/40 (2023.01); G06F 111/20 (2020.01); G06N 20/00 (2019.01)
CPC G06F 30/27 (2020.01) [G06F 18/211 (2023.01); G06F 18/40 (2023.01); G06N 20/00 (2019.01); G06F 2111/20 (2020.01)] 16 Claims
OG exemplary drawing
 
1. A method for machine learning based product design, the method comprising:
receiving, by one or more processors, information that identifies a set of features for a product design;
executing, by the one or more processors, machine learning logic against the set of features to identify a set of components, wherein the set of components comprises components corresponding to each feature of the set of features, wherein the machine learning logic is configured to output correlation coefficients representative of a correlation between the set of components and the set of features;
determining, by the one or more processors, characteristics associated with each component of the set of components based on the correlation coefficients;
identifying, by the one or more processors, one or more candidate components as alternatives to one or more components of set of components based on the characteristics;
determining, by the one or more processors, one or more modifications to optimize the set of components based on at least one design metric and the one or more candidate components, wherein the at least one design metric comprises an attribute variance metric and a cost metric;
outputting, by the one or more processors, a final set of components for the product design based on the one or more modifications, wherein the final set of components includes at least one candidate component selected from the one or more candidate components, and wherein the at least one candidate component optimizes the final set of components with respect to the at least one design metric;
identifying, by a rationalization engine, at least one 3D printable component from the final set of components for the product design based on the machine learning logic;
determining, by the rationalization engine, whether the identified at least one 3D printable component is within an attribute variance of the product design;
providing 3D printable component data to the attribute variance metric if the at least one 3D printable component is inside the attribute variance;
selecting, by the rationalization engine, a next 3D printable component if the at least one 3D printable component is outside the attribute variance;
providing an updated 3D printable component data associated with the next 3D printable component to the attribute variance metric; and
producing, by a 3D printing module, the at least one 3D printable component of a newly designed product based on attribute variance metric and the cost metric.