ML-Based Vulnerability Evaluation Assignment for Resource Waste

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional software application evaluation systems are inefficient and costly, leading to high resource waste and potential data breaches due to insufficient evaluation and testing, lacking effective methods to identify and mitigate vulnerabilities.

Innovation Solution

A machine learning-based Software Application Vulnerability Evaluation Resource (SAVER) management system optimizes software application evaluation by automating the assignment of skilled professionals or systems to execute evaluation tasks, leveraging ML models to determine the most suitable SAVER based on strengths and weaknesses, ensuring thorough and efficient vulnerability detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional software application evaluation systems are used, then vulnerability detection can be performed, but resource waste and costs are high

Engineering Contradiction:

Improvevulnerability detection effectivenessVSAvoidresource waste

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system changes the parameters of SAVERS by dynamically adjusting their skill profiles, availability status, and performance metrics based on task requirements and historical performance data, enabling optimal matching between tasks and evaluators to reduce resource waste while maintaining detection effectiveness

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces manual, conventional evaluation assignment methods with an automated machine learning-based system that objectively matches tasks to SAVERS, eliminating inefficiencies and resource waste associated with traditional manual assignment processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If conventional evaluation methods are used, then some security assessment can be achieved, but the system lacks efficiency and effectiveness

Engineering Contradiction:

Improvesecurity assessment capabilityVSAvoidevaluation efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system enables self-service through automated task assignment where the ML model autonomously matches evaluation tasks to appropriate SAVERS without manual intervention, and SAVERS can independently view their assignments and update their availability status, significantly improving evaluation efficiency while maintaining security assessment quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where SAVER performance data, task completion status, and vulnerability detection results are continuously collected and fed back into the ML model to improve future assignment accuracy, creating a self-improving system that enhances both efficiency and effectiveness over time

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If manual assignment of evaluation tasks is performed, then flexibility can be maintained, but complexity and time consumption increase

Engineering Contradiction:

Improvetask assignment flexibilityVSAvoidassignment process complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The ML-based assignment system serves multiple functions simultaneously: it matches tasks to SAVERS based on skills, monitors SAVER availability, tracks task progress, and provides performance analytics, replacing multiple manual processes with a single universal system that reduces complexity while maintaining flexibility

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20260023860A1Systems and methods for software application vulnerability evaluation resource optimization

Publication Date: 2026.01.22 WELLS FARGO BANK NA

AI summary

Systems, apparatuses, methods, and computer program products are disclosed for providing software application vulnerability evaluation resource (SAVER) optimization. An example method includes receiving a software application and determining a first software application evaluation task for execution with respect to the software application. The example method also includes determining, based on a first set of evaluation task requirements, a first SAVER to execute the first software application evaluation task. The example method also includes providing an indication of the first SAVER to a computing device.