The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jan. 07, 2025

Filed:

Jun. 27, 2022
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Sudipto Mukherjee, Seattle, WA (US);

Liang Du, Redmond, WA (US);

Ke Jiang, Bellevue, WA (US);

Robin Abraham, Redmond, WA (US);

Assignee:
Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G16C 20/70 (2019.01); G06N 3/04 (2023.01); G16C 20/10 (2019.01);
U.S. Cl.
CPC ...
G16C 20/70 (2019.02); G06N 3/04 (2013.01); G16C 20/10 (2019.02);
Abstract

This disclosure describes a machine learning system that includes a contrastive learning based two-tower model for retrieval of relevant chemical reaction procedures given a query chemical reaction. The two-tower model uses attention-based transformers and neural networks to convert tokenized representations of chemical reactions and chemical reaction procedures to embeddings in a shared embedding space. Each tower can include a transformer network, a pooling layer, a normalization layer, and a neural network. The model is trained with labeled data pairs that include a chemical reaction and the text of a chemical reaction procedure for that chemical reaction. New queries can locate chemical reaction procedures for performing a given chemical reaction as well as procedures for similar chemical reactions. The architecture and training of the model make it possible to perform semantic matching based on chemical structures. The model is highly accurate providing an average recall at K=5 of 95.9%.


Find Patent Forward Citations

Loading…