AI Loan Decision Framework Automating Digital Asset Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing loan processing methods are inefficient and inaccurate, requiring manual analysis of user data by lending practitioners, which can lead to delays and errors in loan approval decisions.

Innovation Solution

A decision intelligence (DI)-based computerized framework that electronically collects user data for loan applications, using AI/ML and LLM technologies for real-time digital asset processing, to automate loan approval decisions and securely manage digital assets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual analysis of user data by lending practitioners is used, then flexibility in decision-making is maintained, but processing efficiency decreases and errors increase

Engineering Contradiction:
Improveloan processing efficiencyVSAvoidmanual analysis requirement
Core Design Contradiction:
ProductivityVSExtent of automation

Solution Approach 1:

The patent replaces manual mechanical analysis of digital assets with an AI-based automated system. The machine learning model automatically processes, analyzes, and evaluates digital assets (bank statements, tax returns, pay stubs) to make loan approval decisions, eliminating the need for manual practitioner analysis while maintaining decision-making flexibility through the intelligent system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If AI/ML technologies are used for automated decision-making, then processing speed and accuracy improve, but system complexity increases

Engineering Contradiction:
Improveloan approval accuracyVSAvoidframework complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a universal AI/ML framework that handles multiple functions within the loan processing system. The same machine learning model performs various tasks including digital asset processing, risk assessment, creditworthiness evaluation, and approval decisions, reducing overall system complexity by consolidating multiple specialized systems into one multi-functional platform.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Speed

If real-time digital asset processing is implemented, then loan approval speed increases, but data security risks increase

Engineering Contradiction:
Improveloan approval speedVSAvoiddata security risk
Core Design Contradiction:
SpeedVSObject-affected harmful factors

Solution Approach 1:

The patent introduces a secure data processing layer that acts as an intermediary between data collection and decision-making. The system securely stores digital assets, encrypts sensitive information, and uses controlled access protocols to handle data during real-time processing, thereby enabling fast loan approvals while mitigating security risks through structured data protection measures.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS20250156944A1Systems and methods for artificial intelligence (AI)-based real-time management and control of user electronic assets
Publication Date: 2025.05.15 IBUSINESS FUNDING LLC
  • US20250156944A1 patent drawing
  • US20250156944A1 patent drawing
  • US20250156944A1 patent drawing

AI summary

Disclosed are systems and methods for a decision intelligence (DI)-based, computerized framework that executes artificial intelligence/machine learning (AI/ML) and/or large language model (LLM) software for performing real-time digital asset processing related to the control, management and transfer of such digital assets. The disclosed framework operates by computationally analyzing data related to users respective to requests for a digital asset transfer, which is effectuated via the AI/ML and/or LLM software, such that remittance, denials and/or curated ownership transfers of such assets can be securely performed in real-time.