Electronic sensing systems and methods thereof

Patent metadata

Field	Value
Publication number	US-11250310-B2
Application number	US-201715646827-A
Country	US
Kind code	B2
Filing date	Jul 11, 2017
Priority date	Mar 9, 2017
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.

First claim

What is claimed is:

1. A processor implemented method, comprising:
receiving, by an electronic sensing system ( 100 ), a olfactory product ( 302 );
detecting and extracting, using a sensing module ( 202 ) of the electronic sensing system ( 100 ), one or more smell characteristics of the olfactory product by identifying a headspace of the olfactory product ( 304 );
performing, by using a comparison module ( 204 ), a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database ( 306 ), wherein the database is dynamically updated with attributes associated with the one or more smell characteristics of the olfactory product;
generating based on the comparison, by one or more neural network models, by using a report generation module ( 206 ), a report for the olfactory product comprising type of the olfactory product, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index ( 308 ), wherein the decaying index is computed based on a rate of decay of the olfactory product over a time period, wherein at least one of freshness characteristic and stale characteristic of the olfactory product is determined based on the decaying index, wherein an output of one or more neural network models is calculated with an expression of:

labelling
=

activation
⁢

⁢

e

x
i

∑

i
=
1

n

⁢

e
x_i

;

x
i

=

w
i

⁢
t

+
b

where ‘w’ is a weight and ‘b’ is bias towards each of the classes, and ‘e’ is exponential wherein total exponential is a calculation of probability,
wherein the report is generated based on a minimum distance between the one or more extracted smell characteristics of the olfactory product and the smell characteristics associated with the historic training data stored in the database,
wherein the step of receiving an olfactory product is preceded by:
training the electronic sensing system based on the historic training data comprising:
receiving one or more olfactory products, extracting one or more smell characteristics of the one or more olfactory products, generating one or more reports pertaining to the one or more olfactory products and classifying the one or more olfactory products into one or more categories.

2. The processor implemented method of claim 1 , wherein the step of performing a comparison of the one or more extracted smell characteristics of the olfactory product with smell characteristics associated with a historic training data stored in a database comprises:
analyzing the extracted smell characteristics of the olfactory product to obtain a set of normalized values and intensity values;
performing a comparison of the set of normalized values and the intensity values with values associated with the historic training data stored in the database; and
determining, using one or more neural network models, a match between the at least some of values from the set of normalized values and intensity values with the values with the historic training data stored in the database.

3. The processor implemented method of claim 1 , further comprising classifying, using a classification module ( 208 ), the olfactory product into the one or more categories based on at least one of the generated report and the historic training data.

4. The processor implemented method of claim 1 , wherein the step of receiving an olfactory product is preceded by: training the electronic sensing system based on the historic training data comprising:
receiving one or more olfactory products;
extracting one or more smell characteristics of the one or more olfactory products;
generating one or more reports pertaining to the one or more olfactory products; and
classifying the one or more olfactory products into the one or more categories.

5. The processor implemented method of claim 1 , wherein the status of the olfactory product comprises at least one of consumable, and non-consumable.

6. An electronic sensing system comprising:
one or more processors ( 104 ); and
one or more internal data storage devices ( 102 ) operatively coupled to the one or more processors ( 104 ) and storing instructions configured for execution by the one or more processors ( 104 ), the instructions comprises:
a sensing module ( 202 ) that is configured to receive an olfactory product, and detect and extract one or more smell characteristics of the olfactory product by identifying a headspace of the olfactory product;
a comparison module ( 204 ) configured to perform a comparison of the one or more extracted smell characteristics of the olfactory product with one or more smell characteristics associated with a historic training data stored in a database, wherein the database is dynamically updated with attributes associated with the one or more smell characteristics of the olfactory product;
a report generation module ( 206 ) configured to generate, based on the comparison, using the one or more neural network models, a report for the olfactory product comprising at type of the olfactory product, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, wherein the decaying index is computed based on a rate of decay of the olfactory product over a time period, wherein at least one of freshness characteristic and stale characteristic of the olfactory product is determined based on the decaying index, wherein an output of one or more neural network models is calculated with an expression of:

labelling
=

activation
⁢

⁢

e

x
i

∑

i
=
1

n

⁢

e
x_i

Assignees

• Tata Consultancy Services Ltd

Inventors

• TOMMY Robin
• Vardekar Rohan Chandrakant
• Raj Rishin

Classifications

• G06N3/042 Primary

  Knowledge-based neural networks; Logical representations of neural networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G01N33/0001 Primary

  by organoleptic means · CPC title

• G06N3/0427 Primary

  Physics · mapped topic

• G06N3/08

  Learning methods · CPC title