Article Details

Abstract

To address the limitations of traditional data structure experiment teaching, such as monotonous experiment tasks, delayed evaluation feedback, and difficulty in quantifying learning processes. This paper designs and implements an AI-assisted experimental teaching platform based on Large Language Models (LLMs). The platform adopts a four-layer architecture consisting of the frontend interaction layer, teaching service layer, intelligent engine layer, and data analysis layer, and integrates four major functional modules: intelligent tutoring, automatic evaluation, behavior analysis, and teacher management. By connecting to LLM APIs such as DeepSeek, the system enables code semantic understanding, experimental guidance, and personalized feedback. Furthermore, by utilizing learning behavior data, it constructs student learning profiles to achieve refined analysis of the learning process. The platform is applied in the Data Structures course, and experimental results show that it reduced teachers' grading time by an average of 45%, achieved 94.3% accuracy in code evaluation, maintained an average response delay within 1.8 seconds, and attained a student satisfaction rate above 90%. The study demonstrates the platform's effectiveness in improving teaching efficiency, promoting personalized learning, and optimizing teaching management, providing a scalable technical approach for the construction of intelligent teaching platforms in computer science education.

Keywords

Artificial Intelligence; Large Language Model; data structure; intelligent teaching; auto-grading

References

1. [1] Zavakchi Richter, Vimalin, Bond, etc A review of research on the application of artificial intelligence in higher education: What is the role of educators? [J] China Distance Education, 2020 (6): 1-21, 76
2. [2] Zhang Biying, Lv Youbo, Zhang Yanrong, etc Construction of Java Programming Teaching Mode under the Background of ChatGPT [J]. Microcomputer, 2025 (1): 244-246
3. [3] Chen Kaiquan, Hu Xiaosong, Han Xiaoli, etc The Mechanism, Scenarios, Challenges, and Countermeasures of Dialogue based General Artificial Intelligence Education Applications [J]. Distance Education Journal, 2023, 41 (3): 36-42
4. [4] Peng Gang, Chen Qiang Research on the Teaching Reform of "Data Structures" Course Based on the Integration of Science and Education [J]. Science and Education Guide, 2023 (31): 118-121
5. [5] Xiong Hao, Yan Haihua, Guo Tao, etc Code Similarity Detection Techniques: A Research Review [J]. Computer Science, 2010, 37 (8): 9-14, 76
6. [6] Wu Zhengyang, Tang Yong, bangs A review of personalized learning recommendation research [J]. Computer Science and Exploration, 2022, 16 (1): 21-40
7. [7] WU Y T， YE X H， WANG L J. Preliminary Evaluation of an Automated Feedback Scaffold for Collaborative Scientific Inquiry Integrating Generative AI [J]. Journal of Education & Psychology， 2024（12）：31-67.
8. [8] Wang Qijun, Hang Bo Teaching Reform and Practice of "Data Structures and Algorithms" in Artificial Intelligence Major Based on "Teaching Competition Integration" - Taking the School of Artificial Intelligence at Anhui University as an Example [J]. Journal of Hubei University of Arts and Sciences, 2024, 45 (7): 84-88
9. [9] Xu Zhiwei, Li Hailong, Li Bo, etc Overview of AIGC Large Model Evaluation: Enabling Technologies, Security Hazards, and Responses [J]. Computer Science and Exploration, 2024, 18 (9): 2293-2325
10. [10] Gu Guangbing Research and Implementation of University Teaching Inspection Platform Based on SaaS Model [J]. Modern Information Technology, 2025, 9 (17): 156-160

Funding

Beijing Printing School Campus Project (Eb202404); Project approved by Beijing Higher Education Association in 2022

About the authors

Yang Yanhong (1985-), female, Han ethnicity, from Xinzhou, Shanxi Province, associate professor, PhD, research direction: big data, artificial intelligence education; Dong Zhihong (1979-), female, Han ethnicity, from Zhengzhou, Henan Province, associate professor, PhD, research direction: image recognition, data structure; Wang Jia (1978-), female, Han ethnicity, from Luoyang, Henan Province, associate professor, PhD, research direction: image recognition, machine vision.