NFT Auto-Segmentation Using Machine Learning for Storage Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies face challenges in efficiently managing the storage and validation of non-fungible tokens (NFTs), particularly in terms of segmentation, risk management, and adapting to changes in value or ownership.

Innovation Solution

A computing platform with a machine learning-based auto-segmentation model that generates tier scores for NFTs, determining their storage location between cloud and local storage based on these scores, and an NFT validation model that assesses the validity of event processing requests by analyzing NFT information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all NFTs are stored in cloud computing platform, then security and accessibility are improved, but storage cost and processing time increase

Engineering Contradiction:

ImproveNFT storage securityVSAvoidNFT retrieval time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent segments NFTs into different storage categories (frequently accessed vs. infrequently accessed) and stores them in different locations (local device vs. cloud platform). This segmentation allows the system to optimize for both security and retrieval speed by placing only necessary NFTs locally while maintaining secure cloud storage for others.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by storing different types of NFTs in different locations based on their access patterns. Frequently accessed NFTs are stored locally with fast access, while infrequently accessed NFTs are stored in the cloud with enhanced security, creating optimized storage quality for each location.

Inventive Principle:

Principle #3Local quality

2Speed

If tier thresholds are adjusted to store more NFTs locally, then retrieval speed is improved, but storage device capacity is exceeded

Engineering Contradiction:

ImproveNFT retrieval speedVSAvoidLocal storage capacity

Core Design Contradiction:

SpeedVSQuantity of substance

Solution Approach 1:

The patent implements dynamic tier thresholds that automatically adjust based on available storage capacity, access frequency patterns, and NFT importance. This dynamic adjustment ensures optimal retrieval speed while preventing storage capacity exhaustion by flexibly adapting to changing conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of tier thresholds dynamically based on storage capacity, access patterns, and NFT priorities. By adjusting this parameter, the system optimizes the balance between local storage utilization and retrieval performance without exceeding capacity limits.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If manual segmentation of NFTs is performed, then storage organization is improved, but operational complexity and time consumption increase

Engineering Contradiction:

ImproveStorage organizationVSAvoidSegmentation process complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements self-service through automated machine learning models that perform NFT segmentation without user intervention. The system automatically analyzes access patterns, determines NFT priorities, and assigns appropriate storage locations, eliminating manual segmentation complexity while maintaining excellent organization.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical segmentation processes with automated machine learning algorithms. This substitution eliminates the need for user interaction in segmentation decisions, reducing operational complexity while improving consistency and accuracy of storage organization.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Device complexity

If static storage rules are used for NFTs, then system simplicity is maintained, but adaptability to value and ownership changes is reduced

Engineering Contradiction:

ImproveStorage rule complexityVSAvoidNFT storage adaptability

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic storage rules that automatically adapt to changes in NFT value, ownership, and access patterns. The system continuously monitors these parameters and adjusts storage locations and priorities accordingly, maintaining simplicity for users while providing high adaptability through automated dynamic rule adjustment.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20250028443A1Auto-segmentation of non-fungible tokens using machine learning

Publication Date: 2025.01.23 BANK OF AMERICA CORP

AI summary

Aspects of the disclosure relate to an NFT segmentation platform. The NFT segmentation platform may train an auto-segmentation model to generate tier scores corresponding to non-fungible tokens (NFTs). The NFT segmentation platform may compare the tier scores to tier thresholds defining threshold ranges. The NFT segmentation platform may automatically store the NFTs based on storage rules corresponding to the threshold ranges. The NFT segmentation platform may modify the storage location of the NFT based on changes in the tier score. The NFT segmentation platform may train an NFT validation model to generate NFT validation ratings for NFTs. The NFT segmentation platform may compare the NFT validation ratings to threshold values to determine whether or not to execute an event processing request. The NFT segmentation platform may create an iterative feedback loop to update the auto-segmentation model and the NFT validation model.