公开(公告)号：WO2022136180A1

公开(公告)日：2022-06-30

申请号：PCT/EP2021/086591

申请日：2021-12-17

Applicant: FIRMENICH SA

Inventor： GODIN, Guillaume ,  VAN DEURSEN, Ruud ,  NOUCHI, Vincent ,  CAPELA, Fabio André ,  RAMET, Gaétan ,  CALVAYRAC, Thibault ,  CHICHESTER, Christine

IPC: G16C60/00 ,  G16C20/30 ,  G16C20/70 ,  G06N3/04

Abstract: The computer-implemented method (100) for training an autoencoder neural network or generative adversarial network device to generate indeterministic and realistic digital representations of new fragrance or flavor ingredient compositions to be compounded, comprises the steps of: - providing (105) an original set of exemplar fragrance or flavor composition digital identifiers, said exemplar fragrance or flavor composition digital identifiers being representative of materialized fragrance or flavor compositions comprising at least two distinct ingredients and - training (110) an autoencoder device or generative adversarial network device using the original set of exemplar fragrance or flavor composition digital identifiers to generate a fragrance or flavor composition generative model trained to generate new fragrance or flavor ingredient compositions, comprising at least two distinct ingredients, to be compounded. The trained autoencoder device or generative adversarial network device can be used to generate new fragrance or flavor ingredient compositions.