Method and system for unique, procedurally generated digital objects via few-shot model
AssigneeEmoji Id, LLC
InventorsNaveen Kumar Jain, Riccardo Paolo Spagni
Life of this patent
Estimating the term…
Abstract
Disclosed herein is digital object generator that makes uses a one-way function to generate unique digital objects based on the user specific input. Features of the input are first extracted via a few-shot convolutional neural network model, then evaluated weight and integrated fit. The resulting digital object includes a user decipherable output such as a visual representation, an audio representation, or a multimedia representation that includes recognizable elements from the user specific input.
Claims24
A method of employing an artificial intelligence model to generate a unique set of image data comprising:
- training a machine learning model with a set of training data configured to extract visual features associated with cryptographic tokens connected to a plurality of smart contracts;
- receiving user specific parameters associated with a first user and including a plurality of cryptographic tokens;
- extracting visual features from the user specific parameters via the machine learning model;
- identifying, via the machine learning model, a set of elements from the extracted visual features that meet a threshold model confidence for amalgamation;
- and
- generating a model-unique image that corresponds to the user specific parameters, wherein the model-unique image that incorporates the visual features of the user specific parameters.
A system of employing an artificial intelligence to generate a unique set of image data comprising:
- a processor;
- and
- a memory including instructions that when executed cause the processor to:
- train a machine learning model with a set of training data configured to extract visual features associated with cryptographic tokens connected to a plurality of smart contracts;
- receive user specific parameters associated with a first user and including a plurality of cryptographic tokens;
- extract visual features from the user specific parameters via the machine learning model;
- identify, via the machine learning model, a set of elements from the extracted visual features that meet a threshold model confidence for amalgamation;
- and
- generate a model-unique image that corresponds to the user specific parameters, wherein the model-unique image that incorporates the visual features of the user specific parameters.
A non-transitory computer-readable medium contains a plurality of instructions that when executed by a processor cause the processor to employ an artificial intelligence model to generate a unique set of image data comprising:
- train a machine learning model with a set of training data configured to extract visual features associated with cryptographic tokens connected to a plurality of smart contracts;
- receive user specific parameters associated with a first user and including a plurality of cryptographic tokens;
- extract visual features from the user specific parameters via the machine learning model;
- identify, via the machine learning model, a set of elements from the extracted visual features that meet a threshold model confidence for amalgamation;
- and
- generate a model-unique image that corresponds to the user specific parameters, wherein the model-unique image that incorporates the visual features of the user specific parameters.
Dependencies are inferred from the claim text.