基于大语言模型的组件化工业软件系统测试用例生成方法

罗嘉乐; 王涛; 程良伦; 陈翀

doi:10.12052/gdutxb.250017

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于大语言模型的组件化工业软件系统测试用例生成方法

计算机科学与技术 | 更新时间：2026-08-04

- 基于大语言模型的组件化工业软件系统测试用例生成方法
- A Method for Generating Test Cases for Component-based Industrial Software Systems Based on Large Language Models
- 广东工业大学学报 2026年43卷第4期页码：91-102
- 作者机构：
  
  1. 广东工业大学计算机学院,广东,广州,510006
  2. 广东工业大学自动化学院,广东,广州,510006
- 作者简介：
  
  罗嘉乐(1998–)，男，硕士研究生，主要研究方向为软件测试、人工智能与大模型，E-mail：2112205036@mail2.gdut.edu.cn
  王涛(1983–)，男，副教授，博士，主要研究方向为人工智能与大模型、工业大数据与知识自动化、智能工业机器人与具身智能，E-mail：wangtao_cps@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(U20A600004)
- DOI：10.12052/gdutxb.250017
  中图分类号： TP311.5;TP273
- 纸质出版：2026
- 稿件说明：
移动端阅览
罗嘉乐, 王涛, 程良伦, 等. 基于大语言模型的组件化工业软件系统测试用例生成方法[J]. 广东工业大学学报, 2026, 43(4): 91-102.
罗嘉乐, 王涛, 程良伦, 等. 基于大语言模型的组件化工业软件系统测试用例生成方法[J]. 广东工业大学学报, 2026, 43(4): 91-102. DOI： 10.12052/gdutxb.250017.

DOI： 10.12052/gdutxb.250017

摘要

近年来，随着软件复杂度的增加，传统手动和部分自动化的测试方法难以满足系统测试工作的效率需求，尤其在应对快速变化和高度定制的工业软件系统时，测试覆盖率和效率往往不足。为此，本文提出了一种基于大语言模型的组件化工业软件系统测试用例生成方法，旨在提高测试工作的灵活性和效率。该方法采用大语言模型将用户描述转化为测试用例，结合分步生成策略，涵盖测试用例生成、修正及生成测试代码3个步骤。首先，系统从用户输入开始，结合知识库生成初步测试用例数据。随后，利用Petri网模型对生成的测试用例路径进行修正，确保测试流程的准确性。最后，通过模块化生成核心业务代码，加速测试用例的部署。实验结果表明，该方法在组件化工业软件系统测试中展现了良好的自动化能力，显著提升了测试效率和覆盖率。

Abstract

In recent years

with the increasing complexity of software

traditional manual and partially automated testing methods have found it difficult to meet the efficiency requirements of system testing work

especially when dealing with rapidly changing and highly customized industrial software systems

where testing coverage and efficiency are often insufficient. Therefore

in this research

a component-based industrial software system test case generation method is proposed based on a large language model

aiming to improve the flexibility and efficiency of testing work. This method uses a large language model to convert user descriptions into test cases

combined with a step-by-step generation strategy

covering three stages: test case generation

correction

and test code generation. Firstly

the system starts from user input and generates preliminary test case data based on the knowledge base. Subsequently

the Petri net model is used to modify the generated test case paths to ensure the accuracy of the testing process. Finally

by modularizing the generation of core business code

the deployment of test cases can be accelerated. The experimental results show that this method demonstrates good automation capabilities in component-based industrial software system testing

significantly improving testing efficiency and coverage.

关键词

Keywords

references

WANG B, TAO F, FANG X, et al . Smart manufacturing and intelligent manufacturing: a comparative review[J ] . Engineering, 2021, 7(6): 738-757.

NODA K, NEMOTO Y, HOTTA K, et al . Experience report: how effective is automated program repair for industrial software?[C ] //2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER) . Piscataway: IEEE, 2020: 612-616.

EHSAN A, ABUHALIQA M A M E, CATAL C, et al . RESTful API testing methodologies: rationale, challenges, and solution directions[J ] . Applied Sciences, 2022, 12(9): 4369.

WANG L, MA C, FENG X, et al . A survey on large language model based autonomous agents[J ] . Frontiers of Computer Science, 2024, 18(6): 186345.

NARAYANAN D, SHOEYBI M, CASPER J, et al . Efficient large-scale language model training on gpu clusters using megatron-lm[C ] //Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. Saint Louis City: IEEE Computer Society, 2021: 1-15.

MARTIN-LOPEZ L, SEGURA S, RUIZ-CORTES C. RESTest: black-box constraint-based testing of RESTful web APIs[C]//International Conference on Service-Oriented Computing. Cham: Springer International Publishing, 2020: 459-475.

PRAYOGI A A, NISWAR M, RIJAl M. Design and implementation of REST API for academic information system[J]. IOP Conference Series: Materials Science and Engineering, 2020, 875(1): 012047.

KASNECI E, SEBLER K, KUCHEMANN S, et al . ChatGPT for good? on opportunities and challenges of large language models for education[J ] . Learning and Individual Differences, 2023, 103: 102274.

FORELL M, SCHULER S. Modeling meets large language models[C]//Modellierung 2024 Satellite Events. Bonn: Gesellschaft für Informatik e. V. , 2024: 10-18420.

RYAN G, JAIN S, SHANG M, et al . Code-aware prompting: a study of coverage-guided test generation in regression setting using LLM[J ] . Proceedings of the ACM on Software Engineering, 2024, 1: 951-971.

GU Q. LLM-based code generation method for Golang compiler testing[C]//Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York: ACM, 2023: 2201-2203.

DAFFLON B, MOALLA N, OUZROUT Y. The challenges, approaches, and used techniques of CPS for manufacturing in industry 4.0: a literature review[J]. The International Journal of Advanced Manufacturing Technology, 2021, 113: 2395-2412.

SANCHEZ M, EXPOSITO E, AGUILAR J. Autonomic computing in manufacturing process coordination in industry 4.0 context[J]. Journal of Industrial Information Integration, 2020, 19: 100159.

HAGHNEGAHDAR L, JOSHI S S, DAHITRE N B. From IoT-based cloud manufacturing approach to intelligent additive manufacturing: industrial internet of things-an overview[J]. The International Journal of Advanced Manufacturing Technology, 2022, 119(3): 1461-1478.

REYNOLDS L, MCDONELL K. Prompt programming for large language models: beyond the few-shot paradigm[C]//Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2021: 1-7.

KUBLIK S, SABOO S. GPT-3: the ultimate guide to building NLP products with OpenAI API[M]. Birmingham, UK: Packt Publishing Ltd, 2023.

ARURI A, CAMPOS J, FRASER G. Unit test generation during software development: evosuite plugins for maven, intelliJ and jenkins[C]//Proceedings of the 2016 IEEE International Conference on Software Testing, Verification and Validation (ICST) . Piscataway, NJ: IEEE, 2016: 401-408.

CHEN Y, HU Z, ZHI C, et al . ChatUniTest: a framework for LLM-based test generation[C ] //Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering. New York: ACM, 2024: 572-576.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多轮强化学习驱动的Web服务增强分类

金黄色葡萄球菌暴露对秀丽隐杆线虫的毒性机制研究

稀疏传感器动作捕捉物理约束的深度模型求解方法

“棘手问题”可拓策略生成研究——以社区协同问题为例

SMA接枝氨基化碳纳米管抗静电剂的制备及性能分析