IP Library › Granted Patent US 11,922,164
Granted Patent B2
US 11,922,164 · App. 18/107,294 · Granted Mar 5, 2024

System and method for sensory characterization

Inventors: Oliver Zahn (Berkeley, CA); Karthik Sekar (Berkeley, CA); Richard Gerkin (Berkeley, CA)
Assignee: Climax Foods Inc.
G06F9/06G01N33/0001G01N33/02G06N20/00G16C20/70
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,922,164
App. No.
18/107,294
Granted
Mar 5, 2024
Kind
B2
Abstract

In variants, a method for sensory characterization can include: determining attributes for a sample, collecting sensory data for the sample, determining a sensory characterization model, training the sensory characterization model based on the attributes and the sensory data, determining attributes for a test sample, and predicting a sensory characterization for the test sample using the sensory characterization model.

Claims (17)

1. A method, comprising:

training a flavor model using a panelist flavor ranking for a set of training samples collected using a set of sensory panelists;

determining attributes for a sample; and

determining a flavor characterization for the sample based on the attributes using the trained flavor model.

2. The method of claim 1 , wherein training the flavor model comprises:

predicting a flavor characterization for each of the set of training samples using the flavor model;

determining a predicted flavor ranking for the set of training samples based on the predicted flavor characterizations; and

training the flavor model based on a comparison between the predicted flavor ranking and the panelist flavor ranking.

3. The method of claim 2 , wherein the predicted flavor ranking comprises a probability of a flavor ranking.

4. The method of claim 1 , wherein the panelist flavor ranking comprises an intensity ranking for each of a set of flavor qualities for each of the set of training samples.

5. The method of claim 4 , wherein the intensity ranking for a training sample is: higher than another sample, lower than another sample, or similar to another sample.

6. The method of claim 1 , wherein the sample comprises a mixture of sample components, wherein determining the flavor characterization for the sample comprises:

determining a component flavor characterization for each sample component;

aggregating the component flavor characterizations to determine the flavor characterization for the sample.

7. The method of claim 6 , wherein the trained flavor model comprises a component model and a mixture model, wherein the component model is used to determine the component flavor characterization for each sample component, and wherein the mixture model is used to aggregate the component flavor characterizations.

8. The method of claim 1 , wherein the attributes comprise a context for the sample, wherein the context comprises at least one of a sensory panelist, a sample matrix, or environmental parameters.

9. The method of claim 1 , wherein the sample comprises a mixture of sample components, wherein the attributes comprise a molecular structure for each sample component.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 4, 2023
From: ZAHN, OLIVER; SEKAR, KARTHIK; GERKIN, RICHARD
To: CLIMAX FOODS INC.
Reel/Frame 065756/0277 →
Continuity (4)
Provisional Application 63320635 · Mar 16, 2022
Provisional Application 63311739 · Feb 18, 2022
Provisional Application 63308465 · Feb 9, 2022
Related Publication 20230259363A1 · Aug 17, 2023