From Requirements to Test Cases: An NLP-Based Approach for High-Performance ECU Test Case Automation

2025-05-01

AI Summary

In high-performance, production-grade electronic control unit (ECU) software testing, the automatic transformation of natural-language requirements into structured test-case specifications suffers from low efficiency and insufficient accuracy. Method: This paper proposes a hybrid NLP approach combining rule-based parsing as the primary strategy with named entity recognition (NER) as a complementary technique. It presents the first systematic performance comparison between rule-based and machine learning–based (SVM) methods for ECU signal-level requirement parsing. Results: The rule-based method achieves 95% accuracy on single-signal requirements and accelerates test-case authoring by 3.2× over manual writing; NER attains 77.3% accuracy. The integrated approach significantly reduces human effort in test-case generation. Deployed within the Polarion requirements management platform, the solution demonstrates robust engineering feasibility and industrial applicability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Automating test case specification generation is vital for improving the efficiency and accuracy of software testing, particularly in complex systems like high-performance Electronic Control Units (ECUs). This study investigates the use of Natural Language Processing (NLP) techniques, including Rule-Based Information Extraction and Named Entity Recognition (NER), to transform natural language requirements into structured test case specifications. A dataset of 400 feature element documents from the Polarion tool was used to evaluate both approaches for extracting key elements such as signal names and values. The results reveal that the Rule-Based method outperforms the NER method, achieving 95% accuracy for more straightforward requirements with single signals, while the NER method, leveraging SVM and other machine learning algorithms, achieved 77.3% accuracy but struggled with complex scenarios. Statistical analysis confirmed that the Rule-Based approach significantly enhances efficiency and accuracy compared to manual methods. This research highlights the potential of NLP-driven automation in improving quality assurance, reducing manual effort, and expediting test case generation, with future work focused on refining NER and hybrid models to handle greater complexity.

Problem

• Automate test case generation from natural language requirements
• Compare Rule-Based and NER methods for requirement extraction
• Improve accuracy and efficiency in ECU testing processes

Innovation

• Uses NLP for test case automation
• Compares Rule-Based and NER methods
• Achieves 95% accuracy with Rule-Based