Defect-Triggered ML Test Generation for Faster QA Coverage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The manual process of generating and coding test scenarios for IT assets is time-consuming and requires specialized knowledge, creating bottlenecks in quality assurance teams and delaying test coverage and code quality.

Innovation Solution

Utilizing large language models (LLMs) to automatically generate and execute test scenarios based on defect data from support tickets, reducing the need for manual coding by QA engineers and enabling rapid adaptation to detected defects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual process is used to generate and code test scenarios, then test scenarios can be customized and verified by QA engineers, but the process is time-consuming and creates bottlenecks in quality assurance teams

Engineering Contradiction:

Improvetest scenario qualityVSAvoidtest scenario generation speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of writing and coding test scenarios with an automated AI-based system. The AI model automatically generates test scenarios from defect data and maps them to executable test codes, eliminating the time-consuming manual coding process while maintaining test quality through automated validation and execution frameworks.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the AI model to autonomously generate, validate, and execute test scenarios without requiring specialized QA engineer intervention for each step. The automated framework handles test code generation, mapping to execution frameworks, and result analysis, making the system self-sufficient while reducing dependency on skilled personnel.

Inventive Principle:

Principle #25Self-service

2Manufacturing precision

If specialized knowledge is required for test scenario generation, then test scenarios can be accurately designed, but it creates dependency on skilled personnel and limits scalability

Engineering Contradiction:

Improvetest scenario accuracyVSAvoidsystem scalability

Core Design Contradiction:

Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces the expertise-dependent manual process with an AI-based automated system. The AI model is trained on defect data and testing frameworks, enabling it to generate accurate test scenarios without requiring specialized knowledge from personnel. This substitution maintains test accuracy while eliminating the bottleneck of skilled personnel availability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system achieves universality by creating a scalable AI-based platform that can handle diverse test scenarios across different IT assets without requiring specialized knowledge for each case. The AI model generalizes defect patterns and testing approaches, making the system adaptable to various defect types and platforms while maintaining high accuracy through learned patterns from training data.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Reliability

If manual coding of test scenarios is performed, then test scenarios can be thoroughly tested and validated, but it delays test coverage and code quality improvement

Engineering Contradiction:

Improvetest scenario validationVSAvoidtest coverage time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual coding and validation processes with automated AI-generated test scenarios that are directly mapped to executable test codes. The system automatically validates generated scenarios through integration with execution frameworks, eliminating the time delay associated with manual coding while maintaining thorough validation through automated testing pipelines.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary actions by pre-training the AI model on defect data and testing frameworks, enabling rapid generation of validated test scenarios without time-consuming manual preparation. The automated framework pre-configures test mappings and execution parameters, allowing immediate execution once scenarios are generated, thus reducing overall test coverage time.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20260023678A1Defect-triggered machine learning-based test generation and control

Publication Date: 2026.01.22 DELL PROD LP

AI summary

An apparatus comprises at least one processing device configured to generate a first data structure by parsing a support ticket comprising information characterizing defects encountered while operating an information technology asset. The at least one processing device is also configured to process the first data structure utilizing a machine learning model to generate a second data structure specifying a given sequence of test steps for a given test scenario configured for testing of the defects. The at least one processing device is further configured to map the given sequence of test steps in the second data structure to respective application programming interface calls of a test automation framework, each of the application programming interface calls being associated with a functional code test unit of a test code database of the test automation framework, and to execute the given test scenario utilizing the mapped application programming interface calls.