ML-Based Software Application Importance Ranking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to determine the importance of a given software application within the ecosystem of interrelated applications and computer systems, due to the lack of a taxonomy or methodology for training machine learning models to assess importance, and the requirement for large amounts of high-quality data.

Innovation Solution

The use of machine learning to identify patterns in the many-to-many relationships between system needs and software applications, generating an importance metric for each software application based on recovery time estimates, and ranking applications accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If machine learning models are used to determine software application importance, then the ability to process data and find patterns improves, but the requirement for large amounts of high-quality data and specialized knowledge increases complexity

Engineering Contradiction:

Improveautomated importance determinationVSAvoiddata collection and model training complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The patent performs preliminary actions by automatically collecting operational data, dependency information, and performance metrics before the importance determination is needed. This pre-collection and preprocessing of data eliminates the need for complex manual data gathering and ensures high-quality input data is readily available when the machine learning model needs to be applied.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service by automatically gathering, cleaning, and preparing the necessary data without human intervention. The machine learning model trains and executes autonomously, determining application importance rankings without requiring specialized human expertise for model training and data curation, thus reducing operational complexity.

Inventive Principle:

Principle #25Self-service

2Ease of manufacture

If manual methods are used to assess application importance, then data collection is simpler, but the process is time-consuming and cannot provide real-time notifications

Engineering Contradiction:

Improveease of implementationVSAvoidspeed of importance assessment

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces manual mechanical assessment processes with an automated machine learning-based system. Instead of human experts manually evaluating and ranking applications, the system uses automated data collection, machine learning inference, and algorithmic processing to rapidly determine importance rankings and provide real-time notifications, dramatically increasing productivity while maintaining ease of implementation through automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If existing systems are used to manage software applications, then basic functionality is maintained, but the ability to identify critical applications and optimize resource allocation is insufficient

Engineering Contradiction:

Improvesystem operationVSAvoidimportance metric information

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent introduces an intermediary machine learning-based importance determination system that bridges existing software application management infrastructure and resource allocation decisions. This intermediary layer analyzes operational data, dependencies, and performance metrics to generate importance rankings, providing previously unavailable information about which applications are critical and should receive prioritized resource allocation and protection.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12267202B2Systems and methods for a framework for algorithmically identifying critical software systems and applications within an organization

Publication Date: 2025.04.01 CAPITAL ONE SERVICES LLC

AI summary

Methods and systems generating real-time notifications of software application importance based on current processing requirements. The method includes receiving a first dataset, wherein the first dataset comprises recovery time estimates for processing requirements. The method includes receiving a second dataset, wherein the second dataset comprises second recovery time estimates for applications. The method includes receiving a third dataset, wherein the third dataset comprises dependencies between processing requirements and applications. The method determines many-to-many relationships between the processing requirements and applications based on the dependencies. The method inputs the many-to-many relationships into a machine learning model to identify importance metrics for each application. The method generates, for display on a user interface, a ranking of the applications in order of importance metric.