# US 2024/0202549 A1 · Method and system for predicting a stability value for a determined fragrance in a determined fragrance base

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0202549 A1
- Document ID: US20240202549A1
- Status: Published application
- Kind: A1
- Application number: 18/540,727
- Filed: 2023-12-14
- Published: 2024-06-20
- Earliest claimed: 2022-12-16
- Applicants: Firmenich SA
- Inventors: Christine CHICHESTER; Addisalem SHIFERAW; Elena TVERDOKHLEBOVA
- Web page: https://patentgrep.com/patent/US20240202549A1

## CPC

- G16C 20/30: Prediction of properties of chemical compounds, compositions or mixtures
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G16C 20/70: Machine learning, data mining or chemometrics
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The method (100) for predicting a stability value for a determined fragrance in a determined fragrance base, comprises: a step (105) of inputting, upon a computer interface, at least two fragrance ingredient digital identifiers, representative of material fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients, a step (110) of inputting, upon a computer interface, a fragrance base digital identifier, representative of a material fragrance base, a step (115) of determination, by a computing device, of a stability value for the input composition in the input fragrance base, as a function of the input composition and the input fragrance base and a step (120) of providing, upon a computer interface, a value representative of the determined stability value.

## Claims

### Claim 1

Method for predicting a stability value for a determined fragrance in a determined fragrance base, comprising:
a step of inputting, upon a computer interface, at least two fragrance ingredient digital identifiers, representative of material fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients,
a step of inputting, upon a computer interface, a fragrance base digital identifier, representative of a material fragrance base,
a step of determination, by a computing device, of a stability value for the input composition in the input fragrance base, as a function of the input composition and the input fragrance base and
a step of providing, upon a computer interface, a value representative of the determined stability value.

### Claim 2 (depends on 1)

Method according to claim 1, which comprises a step of inputting, upon a computer interface, a fragrance application digital identifier, representative of the use the input fragrance and the input base.

### Claim 3 (depends on 1)

Method according to claim 1, in which the step of determination comprises a step of operating a trained classifier machine learning device, in which input composition and the input fragrance base are used as input of the classifier machine learning model and in which the output is a stability class identifier, representative of a stability of the input composition in the input fragrance base.

### Claim 4 (depends on 3)

Method according to claim 3, which comprises, upstream of the step of operating a trained classifier machine learning device, the steps of:
providing to a classifier machine learning device a set of exemplar data, comprising:
composition digital identifiers, each composition digital identifier being associated with fragrance ingredient digital identifiers,
for at least part of the exemplar composition digital identifiers, a fragrance base digital identifier, and
for at least one couple formed of the exemplar composition and base digital identifiers, a value representative of stability of the exemplar composition,
operating the classifier machine learning device based upon the set of exemplar data and
obtaining the trained classifier machine learning device.

### Claim 5 (depends on 4)

Method according to claim 4, in which the exemplar data further comprises, for at least one couple formed of exemplar composition and base digital identifiers, a value representative of duration from assembly of said couple.

### Claim 6 (depends on 4)

Method according to claim 4, in which the exemplar data further comprises for at least one couple formed of exemplar composition and base digital identifiers, a value representative of the concentration of the composition within the base of said couple.

### Claim 7 (depends on 4)

Method according to claim 4, in which the exemplar data further comprises for at least one couple formed of exemplar composition and base digital identifiers, a value representative of an application for said couple.

### Claim 8 (depends on 3)

Method according to claim 3, in which the trained classifier machine learning model is a classifier gradient boosting decision tree device.

### Claim 9 (depends on 3)

Method according to claim 3, comprising, downstream of the step of operating the trained gradient boosting decision tree device, a step of determining, by a computing device, a numerical value representative of a stability impact for at least one input fragrance ingredient digital identifier and a step of providing, upon a computer interface, the determined stability impact numerical value.

### Claim 10 (depends on 9)

Method according to claim 9, comprising, downstream of the step of determining a numerical value representative of a stability impact, a step of providing at least one alternative fragrance ingredient digital identifier for at least one fragrance ingredient digital identifier input to form the composition as function of the numerical value representative of a stability impacts of the said input and of said alternative fragrance ingredient digital identifiers.

### Claim 11 (depends on 10)

Method according to claim 10, in which the step of providing at least one alternative fragrance ingredient digital identifier is configured to further provide at least one value representative of a concentration of at least one said alternative fragrance ingredient digital identifier.

### Claim 12 (depends on 9)

Method according to claim 9, in which the step of providing at least one alternative fragrance ingredient digital identifier is configured to further provide a minimum and/or a maximum value representative of a concentration of at least one said alternative fragrance ingredient digital identifier.

### Claim 13 (depends on 1)

Method according to claim 1, comprising a step of physically assembling the input composition in the input fragrance base.

### Claim 14 (depends on 1)

Method according to claim 1, comprising at least one of:
a step of constituting a database of fragrance ingredient digital identifier, wherein a physical fragrance ingredient is associated with a fragrance ingredient digital identifier according to a one-to-one relationship, and/or
a step of constituting a database of fragrance base digital identifier, wherein a physical base ingredient is associated with a fragrance base digital identifier according to a one-to-one relationship,
wherein at least one of said databases is used during a step of inputting.

### Claim 15

System for predicting a stability value for a determined fragrance in a determined fragrance base, comprising:
one or more computer systems comprising one or more hardware processors and storage media; and
instructions stored in the storage media and which, when executed by the computing system, cause the computing system to perform:
a step of inputting, upon a computer interface, at least two fragrance ingredient digital identifiers, representative of material fragrance ingredients, the resulting input corresponding to a composition of fragrance ingredients,
a step of inputting, upon a computer interface, a fragrance base digital identifier, representative of a material fragrance base,
a step of determination, by a computing device, of a stability value for the input composition in the input fragrance base, as a function of the input composition and the input fragrance base and
a step of providing, upon a computer interface, a value representative of the determined stability value.
