Method and system for unique, procedurally generated digital objects via few-shot model

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.

1 . (canceled) 
     
     
         2 . A method of employing an artificial intelligence model to generate a set of image data comprising:
 training a machine learning model with a set of training data configured to extract visual features associated with a set of images;   receiving user specific parameters associated with a first user including a prompt;   extracting visual features from the set of images consistent with the prompt;   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 an output image that corresponds to the user specific parameters and based on the set of elements.   
     
     
         3 . The method of  claim 2 , further comprising:
 minting the output image as a cryptographic token.   
     
     
         4 . The method of  claim 3 , further comprising:
 encoding the output image to a cryptographic token ID stored in a smart contract associated with the cryptographic token.   
     
     
         5 . The method of  claim 2 , wherein the machine learning model is further trained to extract cryptographic elements from the user specific parameters including a generation of token for each cryptographic token, and wherein said generating the output image further corresponds to the cryptographic elements. 
     
     
         6 . The method of  claim 2 , wherein said extracting is performed by a few-shot model architecture that performs feature identification via a support set that includes a set of graphic features indicated by the prompt. 
     
     
         7 . The method of  claim 2 , further comprising:
 training the machine learning model to identify contextual rarity in a cryptographic token as a function of adherence to predetermined categories as opposed to object uniqueness.   
     
     
         8 . The method of  claim 7 , wherein the output image incorporates elements of the contextual rarity of the user specific parameters. 
     
     
         9 . The method of  claim 2 , wherein said generating the output image generates a model-unique image. 
     
     
         10 . A system of employing an artificial intelligence model to generate a 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 a set of images;   receive user specific parameters associated with a first user including a prompt;   extract visual features from the set of images consistent with the prompt;   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 an output image that corresponds to the user specific parameters and based on the set of elements.   
     
     
         11 . The system of  claim 10 , the instructions further comprising:
 minting the output image as a cryptographic token.   
     
     
         12 . The system of  claim 11 , the instructions further comprising:
 encoding the output image to a cryptographic token ID stored in a smart contract associated with the cryptographic token.   
     
     
         13 . The system of  claim 10 , wherein the machine learning model is further trained to extract cryptographic elements from the user specific parameters including a generation of token for each cryptographic token, and wherein said generating the output image further corresponds to the cryptographic elements. 
     
     
         14 . The system of  claim 10 , wherein said extracting is performed by a few-shot model architecture that performs feature identification via a support set that includes a set of graphic features indicated by the prompt. 
     
     
         15 . The system of  claim 10 , the instructions further comprising:
 training the machine learning model to identify contextual rarity in a cryptographic token as a function of adherence to predetermined categories as opposed to object uniqueness.   
     
     
         16 . The system of  claim 15 , wherein the output image incorporates elements of the contextual rarity of the user specific parameters. 
     
     
         17 . The system of  claim 10 , wherein the generation of the output image generates a model-unique image. 
     
     
         18 . A non-transitory computer-readable medium that contains a plurality of instructions that employ an artificial intelligence model to generate a model-unique set of image data and when executed by a processor cause the processor to:
 train a machine learning model with a set of training data configured to extract visual features associated with a set of images;   receive user specific parameters associated with a first user including a prompt;   extract visual features from the set of images consistent with the prompt;   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 an output image that corresponds to the user specific parameters and based on the set of elements, wherein the output image is a model-unique image.   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , the instructions further comprising:
 minting the output image as a cryptographic token.   
     
     
         20 . The non-transitory computer-readable medium of  claim 19 , the instructions further comprising:
 encoding the output image to a cryptographic token ID stored in a smart contract associated with the cryptographic token.   
     
     
         21 . The non-transitory computer-readable medium of  claim 18 , wherein the machine learning model is further trained to extract cryptographic elements from the user specific parameters including a generation of token for each cryptographic token, and wherein said generating the output image further corresponds to the cryptographic elements. 
     
     
         22 . The non-transitory computer-readable medium of  claim 18 , wherein said extracting is performed by a few-shot model architecture that performs feature identification via a support set that includes a set of graphic features indicated by the prompt.