Article Details

Abstract

Aiming at the problems of high labor costs, strong subjectivity in evaluation during enterprise recruitment, and job seekers' lack of immersive simulation training platforms, this paper designs and implements an intelligent interview system based on multimodal Large Language Model. Adopting a dual-backend architecture featuring decoupling between Java business middle platform and Python microservices, the system integrates large models such as Qwen and Gemini, and constructs three core functional modules: a practical programming sandbox, multi-role voice interview, and multimodal comprehensive evaluation. Test results show that the system runs stably: the programming sandbox can execute code safely and conduct code quality analysis; the voice interview module can simulate conversations in various workplace styles; finally, the system can generate structured evaluation reports integrating multi-dimensional information. This system provides a feasible solution for full-process intelligent talent assessment and training, and has reference value for promoting the engineering application of AI-enabled interviews.

Keywords

Large Language Model; intelligent interview system; Artificial Intelligence

References

1. [1] Li Chengwei Three stages and five steps to effectively manage the external recruitment process of human resources for small and medium-sized enterprises [J]. China Foreign Investment, 2020 (14): 27-28
2. [2] Yang Zhen, Chen Jian'an Research on the Framework and Modules of Artificial Intelligence System for Recruitment Interview [J]. Journal of Jiangsu University (Social Sciences Edition), 2017, 19 (6): 73-80, 92
3. [3] Ju Weigang, Wang Jia Research on the Application of stateless microservice architecture and continuous integration methods [J]. Wireless Internet Technology, 2025, 22 (3): 9-14, 24
4. [4] The Yellow Guards Optimization of Implementation Solutions for Microservice Architecture in Enterprise Application Development [C]//Forum on Humanities and Development at the 2025 Sociology Symposium, 2025:230-232
5. [5] He Ning, Bi Jiana, Xu Qiuxi, etc Refactoring and Practice of AI Empowering Python Programming Course Teaching System [J]. Electronic Components and Information Technology, 2025, 9 (9): 11-14
6. [6] Ling Dalian, Feng Shiying, Chen Sinan, etc A Comparative Study of Large Language Models and Students' Performance in Exams: A Case Study of Tongyi Qianwen [J]. Modern Information Technology, 2025, 9 (12): 50-57, 62
7. [7] Dong Lifeng The Application of Facial Recognition Technology in Information System Identity Authentication [D]. Chengdu: Sichuan University, 2004
8. [8] Zhu Shiling, Chen Lejun, Yuan Ziqian Design and Implementation of an Intelligent Examination System Integrating Multimodal Knowledge Analysis and Large Model Generation [J]. Modern Information Technology, 2025, 9 (20): 79-86, 91
9. [9] Kang Feng, Zhang Huiwei, Chen Liqiong Testing and Analysis of Chinese Text Editing Performance of Domestic Artificial Intelligence Large Models [J]. Publishing and Printing, 2025 (3): 58-69
10. [10] Guan Lingling, Li Changying Application Analysis of AI Technology in Automated Software Testing [J]. Software, 2025, 46 (9): 74-77

About the authors

Feng Bo (1987-), male, Han ethnicity, from Dezhou, Shandong, is a lecturer, engineer, and information system project manager with a master's degree. His research interests include software engineering, artificial intelligence, and higher vocational education.