US 12,223,530 B2
Method, system, and computer program product for representational machine learning for product formulation
Petar Ristoski, San Jose, CA (US); Richard T. Goodwin, Dobbs Ferry, NY (US); Jing Fu, Yorktown Heights, NY (US); Richard B. Segal, Chappaqua, NY (US); Robin Lougee, Yorktown Heights, NY (US); Kimberly C. Lang, Yorktown Heights, NY (US); Christian Harris, Port Chester, NY (US); and Tenzin Yeshi, New York, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Sep. 24, 2020, as Appl. No. 17/030,509.
Prior Publication US 2022/0092659 A1, Mar. 24, 2022
Int. Cl. G06Q 30/06 (2023.01); G06N 5/022 (2023.01); G06N 5/025 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0621 (2013.01) [G06N 5/022 (2013.01); G06N 5/025 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
accessing a set of product formulas, each product formula including a set of ingredient tuples;
generating a directed graph from the set of product formulas, the directed graph including a node for each ingredient of the sets of ingredient tuples of the set of product formulas;
generating a weighted graph from the directed graph, the weighted graph having a weight assigned to each edge in the directed graph;
modifying random walk models by incorporating the weight assigned to each edge into the random walk model;
vectorizing the set of product formulas based on ingredients within the product formulas;
feeding the random walks from the random walk models into a deep learning approach to determine a set of embeddings comprising ingredient embeddings and a set of ingredient vectors from the vectorizing, wherein the deep learning approach is run on data including ingredient recommendations; and substitute ingredient recommendation;
generating, based on the weighted graph, an embedding module;
deploying the random walk models on the weighted graph;
building neural models for two or more positive formulas in the weighted graph by: extracting, using the random walk models, a subgraph with depth d; extracting n biased walks in the subgraph; and building a neural model for each entity in the weighted graph, wherein positive formulas are used to generate a weight of edges to provide the bias for the biased walks on the weighted graph, wherein positive examples are formulas that have a threshold level of market success;
training, using a bias of the biased walks from the weight of the edges, a sequence-to-sequence neural network generated using a pairwise ranking loss functions derived from the neural models;
augmenting the sequence-to-sequence neural network with the set of embeddings for the weighted graph as a sigmoid layer in the sequence-to-sequence neural network,
wherein each node is represented with low-dimensional numerical formula vectors;
deploying the embedding module to generate a new product formula by passing the set of ingredient embeddings through the sequence-to-sequence neural network using one or more of the neural models; and
identifying, using the sequence-to-sequence neural network, a new ingredient tuple for the new product formula.