Method and system for real-time shelf-life prediction of food items

Patent metadata

Field	Value
Publication number	US-11977608-B2
Application number	US-202117515834-A
Country	US
Kind code	B2
Filing date	Nov 1, 2021
Priority date	Nov 6, 2020
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

Traditional food quality monitoring systems fail to monitor the variation of food quality in real-time scenarios. Existing machine learning approaches require dedicated data models for different classes of food items due to differences in characteristics of different food items. Also, to generate such data models, a lot of annotated data is required per food item, which are expensive. The disclosure herein generally relates to monitoring and shelf-life prediction of food items, and, more particularly, to system and method for real-time monitoring and shelf-life prediction of food items. The system generates a data model using a knowledge graph indicative of a hierarchical taxonomy for a plurality of categories of the plurality of food items, which in turn contains metadata representing similarities in physio-chemical degradation pattern of different classes of the food items. This data model serves as a generic data model for real-time shelf-life prediction of different food items.

First claim

What is claimed is:

1. A processor implemented method of generating a data model for determining remaining shelf-life of a food item, comprising:
obtaining, via one or more hardware processors, training data comprising (i) a plurality of images of each food item from among a plurality of food items belonging to a plurality of food categories, and (ii) information on a trend of change of one or more physio-chemical parameters of each food item over a period of time;
determining, via the one or more hardware processors, a state of each of the plurality of food items as one of ‘unripe’, ‘ideally ripe’, and ‘overly ripe’, based on the trend of change of the one or more physio-chemical parameters;
mapping, via the one or more hardware processors, the determined state with a corresponding image from the plurality of images, of each of the plurality of food items;
generating, via the one or more hardware processors, a knowledge graph indicative of a hierarchical taxonomy for the plurality of food categories, wherein the knowledge graph captures a label corresponding to a determined state associated with each of the plurality of images; and
training, via the one or more hardware processors, the data model using the knowledge graph for determining the remaining shelf-life of each of the plurality of food items, the training comprising:
creating an inductive bias by establishing an aging pattern relationship based on similarity of physio-chemical degradation parameters associated with (i) an aging pattern of food items belonging to a food category from among the plurality of food categories and (ii) aging pattern of food items belonging to at least one other food category from among the plurality of food categories, wherein the aging pattern relationship is established using at least one of a zero-shot learning approach or a few-shot learning approach which captures metadata representing the physio-chemical degradation parameters of the food items; and
generating the data model based on the label associated with each of the plurality of images, and the established aging pattern relationship.

2. The method as claimed in claim 1 , wherein the trend of change represents one of an upward or a downward change or a constant value of the one or more physio-chemical degradation parameters over the period of time.

3. The method as claimed in claim 1 , wherein classification of each of the plurality of food items is modelled as a task in meta learning to capture the metadata.

4. The method as claimed in claim 1 , further comprises:
receiving, via the one or more hardware processes, an image of a new food item for determining the remaining shelf-life thereof;
performing, via the one or more hardware processors, one of the following, based on a match between the received image and at least one of the plurality of images in the training data for the generated data model:
determining a current state of the new food item using a corresponding label associated with a matching image in the plurality of images in the training data; or
determining the current state of the new food item using a label associated with an image of a food item belonging to a food category having similar physio-chemical degradation parameters with a food category of the new food item, based on the established aging pattern relationship; and

determining, via the one or more hardware processors, the remaining shelf-life of the new food item as a difference between an estimated total shelf-life of the food item and a consumed shelf-life based on the determined state of the new food item.

5. A system for generating a data model for determining remaining shelf-life of a food item, comprising:
one or more hardware processors;
a communication interface; and
a memory storing a plurality of instructions, wherein the plurality of instructions when executed, cause the one or more hardware processors to:
obtain training data comprising (i) a plurality of images of each food item from among a plurality of food items belonging to a plurality of food categories, and (ii) information on a trend of change of one or more physio-chemical parameters of each food item over a period of time;
determine a state of each of the plurality of food items as one of ‘unripe’, ‘ideally ripe’, and ‘overly ripe’, based on the trend of change of the one or more physio-chemical parameters;
map the determined state with a corresponding image from the plurality of images, of each of the plurality of food items;
generate a knowledge graph indicative of a hierarchical taxonomy for the plurality of food categories, wherein the knowledge graph captures a label corresponding to a determined state associated with each of the plurality of images; and
train the data model using the knowledge graph for determining the remaining shelf-life of each of the plurality of food items, the training comprising:
creating an inductive bias by establishing an aging pattern relationship based on similarity of physio-chemical degradation parameters associated with (i) an aging pattern of food items belonging to a food category from among the plurality of food categories and (ii) aging pattern of food items belonging to at least one other food category from among the plurality of food categories, wherein the aging pattern relationship is established using at least one of a zero-shot learning approach or a few-shot learning approach which captures metadata representing the physio-chemical degradation parameters of the food items; and
generating the data model based on the label associated with each of the plurality of images, and the established aging pattern relationship.

6. The system as claimed in claim 5 , wherein the trend of change represents one of an upward or a downward change or a constant value of the one or more physio-chemical degradation parameters over the period of time.

7. The system as claimed in claim 5 , wherein the one of more hardware processors are configured to model classification of each of the plurality of food items as a task in meta learning to capture the metadata.

8. The system as claimed in claim 5 , wherein the one of more hardware processors are configured to determine the remaining shelf-life of the food item by:
receiving an image of a new food item for determining the remaining shelf-life thereof;
performing one of the following, based on a match between the received image and at least one of the plurality of images in the training data for the generated data model:
determining a current state of the new food item using a corresponding label associated with a matching image in the plurality of images in the training data; or
determining the current state of the new food item using a label associated with an image of a food item belonging to a food category having similar physio-chemical degradation parameters with a food category of the new food item, based on the established aging pattern relationship; and

determining the remaining shelf-life of the new food item as a difference between an estimated total shelf-life of the food item and a consumed shelf-life based on the determined state of the new food item.

9. A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
obtain, via one or more hardware processors, training data comprising (i) a plurality of images of each food item from among a plurality of food items belonging to a plurality of food categories, and (ii) information on a trend of change of one or more physio-chemical parameters of each food item over a period of time;
determine, via the

Assignees

• Tata Consultancy Services Ltd

Inventors

• Dutta Jayita
• Deshpande Parijat
• Patwardhan Manasi Samarth
• Karande Shirish Subhash
• Kausley Shankar
• Kedia Priya
• Kapse Shrikant Arjunrao
• Rai Beena

Classifications

• G06N3/0985

  Hyperparameter optimisation; Meta-learning; Learning-to-learn · CPC title

• G06N3/096

  Transfer learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06F18/2413 Primary

  based on distances to training or reference patterns · CPC title