GenAI Test Case Generation for Software Vulnerability Repair
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Software testing requires significant manual effort from developers to create and execute tests, which can be time-consuming and prone to errors.
Innovation Solution
An apparatus and method utilizing a generative artificial intelligence (GenAI) model to automatically generate testing elements and test cases based on software program requirements, reducing the need for manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual testing is used to ensure high quality software tests, then testing quality is improved, but testing time and developer effort increase significantly
Solution Approach 1:
The system enables self-service testing by automatically generating test cases from requirements documents using AI models. The testing system serves itself by extracting test scenarios, test steps, and expected results directly from requirement specifications without requiring manual developer intervention for each test case creation, thus maintaining quality while reducing time loss.
Solution Approach 2:
The patent replaces the mechanical manual process of test case creation with an automated AI-based system. The generative AI model processes requirements documents and automatically produces structured test cases, substituting the manual mechanical effort of developers with an automated intelligent system that maintains high testing quality while significantly reducing the time required.
2Measurement precision
If manual test case creation is performed to ensure accuracy, then testing precision is improved, but developer effort and complexity increase
Solution Approach 1:
The patent introduces an intermediary AI-based test generation system that sits between the requirements documentation and the test execution phase. This intermediary automatically extracts test scenarios, generates test steps, and defines expected results from requirements documents, maintaining testing precision while reducing the complexity of manual test case creation processes.
Solution Approach 2:
The test generation system performs multiple functions universally: it parses requirements documents, identifies test scenarios, generates test steps, defines expected results, and creates structured test cases all through a single automated process. This multi-functional approach maintains testing precision while reducing the overall process complexity compared to manual methods.
3Productivity
If automated test generation is implemented to reduce manual effort, then productivity is improved, but test design complexity increases
Solution Approach 1:
The patent segments the test generation process into distinct modular components: requirements parsing module, test scenario identification module, test step generation module, and expected result definition module. Each module handles a specific aspect of test case creation, improving productivity through automation while managing design complexity through modular architecture that can be independently configured and maintained.
Data Source
AI summary
An example operation may include one or more of receiving, via a user interface, a request to test a software program, reading source code of the software program and identifying a vulnerability in the source code based on the reading, generating repair code for fixing the identified vulnerability based on execution of a generative artificial intelligence (GenAI) model on the source code and a repository of repair code used to repair previous vulnerabilities, and displaying information about the repair code via the user interface.