Pet food recommendation devices and methods
AssigneeSociete des Produits Nestle S.A.
InventorsEverett Hullverson, Brian Michael Zanghi, Alison Beloshapka, Robert Leslie Hunt, Nathan Tippy
Life of this patent
Estimating the term…
Abstract
A system or method is provided that includes receiving a pet image. The pet image may depict a pet and may be received from a user device. The system or method may further analyze the pet image with a pet image recognition model to determine one or more pet characteristics of the pet. In certain embodiments, analyzing the pet image may further include identifying one or more image characteristics of the pet image. The system or method may further analyze the pet characteristics with a pet food recommendation model to generate a pet food recommendation for the pet.
Claims20
A method comprising:
- receiving, by a web interface server, a pet image depicting a pet;
- analyzing, by the web interface server using a pet image recognition model, the pet image to determine one or more pet characteristics of the pet, including:
- training the pet image recognition model to identify an image characteristic based on a percentage of pixels of the pet image occupied by the pet;
- and
- identifying the one or more pet characteristics of the pet using the trained pet image recognition model;
- receiving, by the web interface server, one or more pet-related data inputs;
- storing behavioral data of the pet in a historical database;
- training, by the web interface server, a pet food recommendation model based on the behavioral data stored in the historical database;
- and
- analyzing, by the web interface server using the pet food recommendation model, the pet characteristics and pet-related data inputs to generate a pet food recommendation and/or pet feeding recommendation for the pet.
A system comprising:
- a processor;
- and
- a memory storing instructions which, when executed by the processor, cause the processor to:
- receive a pet image depicting a pet;
- analyze, using a pet image recognition model, the pet image to determine one or more pet characteristics of the pet, including:
- training the pet image recognition model to identify an image characteristic based on a percentage of pixels of the pet image occupied by the pet;
- and
- identifying the one or more pet characteristics of the pet using the trained pet image recognition model;
- receive one or more pet-related data inputs;
- store behavioral data of the pet in a historical database;
- train a pet food recommendation model based on the behavioral data stored in the historical database;
- analyze, using the pet food recommendation model, the pet characteristics and pet related data inputs to generate a pet food recommendation and/or pet feeding recommendation for the pet.
A non-transitory, computer-readable medium storing instructions which, when executed by a processor, cause the processor to:
- receive a pet image depicting a pet;
- analyze, using a pet image recognition model, the pet image to determine one or more pet characteristics of the pet, including:
- training the pet image recognition model to identify an image characteristic based on a percentage of pixels of the pet image occupied by the pet;
- and
- identifying the one or more pet characteristics of the pet using the trained pet image recognition model;
- receive one or more pet-related data inputs;
- store behavioral data of the pet in a historical database;
- train a pet food recommendation model based on the behavioral data stored in the historical database;
- and
- analyze, using the pet food recommendation model, the pet characteristics and pet-related data inputs to generate a pet food recommendation for the pet.
Dependencies are inferred from the claim text.