Design of the Intelligent Interview System

DOI: https://doi.org/10.62517/jbdc.202601119

Author(s)

Bolin Chen1, Ruian Yan2

Affiliation(s)

1School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou, Henan, China 2iFLYTEK Co., Ltd., Hefei, Anhui, China

Abstract

Intelligent interview systems have attracted increasing attention as an effective solution for improving the efficiency and objectivity of interview evaluation. This study presents the design and implementation of an intelligent interview system that integrates natural language processing, computer vision, and large language models to support automated interview interaction and assessment. The proposed system adopts a modular architecture and enables multimodal data acquisition, including text, speech, and facial video information. A large language model is utilized to generate interview questions and conduct interactive dialogue, while visual and speech features are extracted to analyze interviewee behavior and emotional states. By jointly analyzing multimodal information, the system provides objective feedback on interview performance. Experimental results indicate that the system supports stable real-time interaction and effective feature extraction, demonstrating its applicability to intelligent interview simulation scenarios.

Keywords

Intelligent Interview System; Large Language Model; Multimodal Interaction; Computer Vision

References

[1] Ni Ying, Wang Shihan, Sun Jian, et al. Simulation and modeling of complex interactive behaviors at intersections based on multi-agent imitation learning. Journal of Tongji University (Natural Science Edition), 2025, 53(9): 1391–1402. [2] Li Ming, Wang Hua, Zhao Qiang. Research progress on interview evaluation systems based on deep learning. Chinese Journal of Computers, 2023, 46(10): 2145–2158. [3] Zhang Yu, Liu Hang, Wang Jun. A survey of artificial intelligence applications in recruitment and interview assessment. Journal of Software, 2023, 34(8): 3721–3736. [4] Zhou Chen, Li Tao, Chen Si. Research on interview behavior analysis methods based on multimodal data fusion. Computer Engineering and Applications, 2024, 60(12): 45–52. [5] Wang Lei, Zhao Xin, Sun Kai. Intelligent interview evaluation model integrating speech and visual features. Pattern Recognition and Artificial Intelligence, 2024, 37(6): 561–570. [6] Liu Yang, Chen Jie, Huang Rui. Research on multimodal emotion recognition methods for human–computer interaction. Computer Research and Development, 2025, 62(3): 589–601. [7] Brown T, Mann B, Ryder N. Language Models are Few-Shot Learners//Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver: NeurIPS, 2020: 1877-1901. [8] He K, Zhang X, Ren S. Deep Residual Learning for Image Recognition//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 770-778. [9] RISC-V Foundation. The RISC-V Instruction Set Manual. San Jose: RISC-V International, 2022. [10]Bradski G, Kaehler A, Pisarevsky V. OpenCV 4.8 Computer Vision Library Reference Manual. Beijing: OpenCV Organization, 2023.