ML Defect Prediction Mapping for IT Asset Components

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software development processes face challenges in early detection of defect-prone components, leading to increased costs and delays due to late identification of defects, especially in continuous integration/continuous deployment (CI/CD) environments, and manual inspection methods are unreliable and inefficient.

Innovation Solution

Implementing machine-learning based models to associate historical defects and specifications, generating patterns to identify vulnerable areas in IT assets, enabling early detection and corrective measures during development stages.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection methods are used to detect defects, then development processes can be maintained with simple tools, but defect detection reliability is low and detection timing is late

Engineering Contradiction:

Improvedefect detection accuracyVSAvoiddefect detection reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces manual inspection methods (mechanical/systematic human review) with machine learning-based automated analysis. The system uses trained models to automatically analyze code, requirements, and historical defect data, substituting human judgment with algorithmic prediction to improve both accuracy and reliability of defect detection.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs defect prediction during early development stages by analyzing requirements and design documents before actual coding begins. By using machine learning models to predict potential defects in advance based on historical data and current project characteristics, the system enables preventive actions rather than reactive debugging.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If defects are detected late in the development cycle, then development can proceed without interruptions, but development costs and cycle time increase

Engineering Contradiction:

Improvedevelopment speedVSAvoiddevelopment cycle time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system establishes continuous feedback loops where defect predictions from the machine learning model are fed back to developers during the development process. This allows real-time adjustments and corrections to be made while the project is still in progress, preventing minor issues from escalating into major problems that would require extensive rework later.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If machine learning models are implemented for defect prediction, then defect detection accuracy improves, but system complexity increases

Engineering Contradiction:

Improvedefect prediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a multi-functional system where the machine learning model serves multiple purposes: analyzing requirements documents, reviewing design specifications, predicting defect-prone areas, and providing recommendations. This single integrated system replaces multiple separate tools (manual review processes, separate testing phases, retrospective analysis), thereby managing complexity through consolidation rather than proliferation of separate components.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system is designed to be self-training and self-improving by automatically learning from historical project data and actual defect patterns. The machine learning models continuously refine their predictions based on feedback from real project outcomes, reducing the need for manual configuration and tuning by experts, thereby managing operational complexity while maintaining high accuracy.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12487913B2Machine-learning based prediction of defect-prone components of information technology assets

Publication Date: 2025.12.02 DELL PROD LP

AI summary

An apparatus comprises a processing device configured to determine specifications for an information technology asset to be developed, and to identify, utilizing at least one machine learning model, whether at least one of the specifications for the information technology asset is defect-prone, wherein a given specification is identified as defect-prone responsive to at least one output of the at least one machine learning model indicating that the given specification has at least a threshold likelihood of resulting in one or more defects during development of the information technology asset. The processing device is also configured to establish a mapping between the one or more identified defect-prone specifications for the information technology asset and one or more components of the information technology asset, and to modify one or more development processes for the information technology asset based at least in part on the established mapping.