Method and system for unique, procedurally generated digital objects via few-shot model
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.
1. A method of employing a few-shot model to generate a unique set of image data comprising:
training a few shot convolutional neural network model with a set of training data configured to extract visual features from a plurality of a input types and parameters associated therewith, wherein the input types include:
visual representations of cryptographic tokens as indicated by smart contracts;
image data; and
multimedia data;
receiving user specific parameters associated with a first user and conforming to the set of input types, wherein the user specific parameters are implemented as a few-shot;
extracting visual features from the few-shot via the few shot convolutional neural network model;
identifying, via a machine learning model, a set of elements from the extracted visual features that meet a threshold model confidence for amalgamation;
encoding the set of elements to a cryptographic token ID stored in a smart contract associated with the cryptographic token;
generating a unique image that corresponds to the first user based on the user specific parameters and a salt element, wherein the unique image that incorporates the set of elements of the user specific input; and
minting the unique image as a cryptographic token.
2. The method of claim 1 , wherein the user specific parameters associated with the first user are a set of cryptographic tokens that each have a visual representation indicated by associated smart contracts.
3. A method comprising:
establishing a set of input types and parameters handled by a digital object generator, wherein the types of input include any combination of:
cryptographic protocols;
image data; or
multimedia data;
receiving user specific parameters associated with a first user and conforming to the set of input types;
training an artificial intelligence model to identify contextual rarity in a cryptographic object as a function of adherence to predetermined categories as opposed to object uniqueness; and
generating a unique digital object that corresponds to the first user based on the user specific parameters and a salt element, wherein the unique digital object includes a visual representation, and the visual representation incorporates elements of the user specific input.
4. The method of claim 3 , wherein the set of input types includes cryptographic protocols and the user specific parameters are contents of a cryptographic wallet associated with the first user.
5. The method of claim 3 , wherein the visual representation does not include elements of the salt element.
6. The method of claim 3 , wherein the visual representation of the unique digital object is unique to the digital object generator.
7. The method of claim 3 , wherein said generating implements the artificial intelligence model to generate the visual representation, and the visual representation incorporates elements of the contextual rarity of the user specific parameters.
8. The method of claim 3 , wherein the artificial intelligence model is any of:
a few-shot model;
a hidden Markov model;
a neural network; or
a heuristic model.
9. A system comprising:
a processor; and
a memory including instructions that when executed cause the processor to:
establish a set of input types and parameters handled by a digital object generator, wherein the types of input include cryptographic protocols;
receive user specific parameters associated with a first user and the user specific parameters are contents of a cryptographic wallet associated with the first user; and
generate a unique digital object that corresponds to the first user based on the user specific parameters and a salt element, wherein the unique digital object includes a visual representation, and the visual representation incorporates elements of the user specific input.
10. The system of claim 9 , wherein the visual representation does not include elements of the salt element.
11. The system of claim 9 , wherein the visual representation of the unique digital object is unique to the digital object generator.
12. The system of claim 9 , the instructions further comprising:
training an artificial intelligence model to identify contextual rarity in a cryptographic object as a function of adherence to predetermined categories as opposed to object uniqueness.
13. The system of claim 12 , wherein said generating implements the artificial intelligence model to generate the visual representation, and the visual representation incorporates elements of the contextual rarity of the user specific parameters.
14. The system of claim 12 , wherein the artificial intelligence model is any of:
a few-shot model;
a hidden Markov model;
a neural network; or
a heuristic model.
15. A non-transitory computer-readable medium contains a plurality of instructions that when executed by a processor cause the processor to:
establish a set of input types and parameters handled by a digital object generator, wherein the types of input includes cryptographic protocols;
receive user specific parameters associated with a first user and the user specific parameters are contents of a cryptographic wallet associated with the first user; and
generate a unique digital object that corresponds to the first user based on the user specific parameters and a salt element, wherein the unique digital object includes a visual representation, and the visual representation incorporates elements of the user specific input.
16. The non-transitory computer-readable medium of claim 15 , wherein the visual representation does not include elements of the salt element.
17. The non-transitory computer-readable medium of claim 15 , wherein the visual representation of the unique digital object is unique to the digital object generator.
18. The non-transitory computer-readable medium of claim 15 , the instructions further comprising:
training an artificial intelligence model to identify contextual rarity in a cryptographic object as a function of adherence to predetermined categories as opposed to object uniqueness.
19. The non-transitory computer-readable medium of claim 18 , wherein said generating implements the artificial intelligence model to generate the visual representation, and the visual representation incorporates elements of the contextual rarity of the user specific parameters.
20. The non-transitory computer-readable medium of claim 18 , wherein the artificial intelligence model is any of:
a few-shot model;
a hidden Markov model;
a neural network; or
a heuristic model.