AIGC-Empowered Efficient Personalized Lesson Preparation System

Chenxi Nan

doi:10.58244/joerai.263700

Research Article

AIGC-Empowered Efficient Personalized Lesson Preparation System

By: Chenxi Nan^*

School of Computer Science and Engineering, Xi'an Technological University, Xi’an, Shaanxi, China.

^*Corresponding author

Received: 2025-08-13Revised: 2025-10-16Accepted: 2025-11-13Published: 2026-02-20

JOERAI 2026, 4(1), 34-42; https://doi.org/10.58244/joerai.263700

Funding: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.

Abstract
To address the increasing demand for personalized instruction in education and ameliorate the time-consuming and inflexible nature of traditional lesson planning, this paper presents the development and evaluation of an intelligent, AI-based lesson preparation tool. The system integrates Large Language Models (LLMs), including the Langchain-Chatchat framework, ChatGLM3, and ERNIE-3.5-8K, with the objective of significantly enhancing both the efficiency of teacher preparation and the quality of instruction. The tool implements four core functionalities: rapid question-answering based on a local knowledge base, one-click intelligent generation of instructional images and PowerPoint presentations (PPTs), and automated assignment generation and grading. Results from functional testing and user feedback evaluations indicate that the tool operates stably, effectively reduces educators' preparation time, enriches the dimensions of teaching content, and increases student engagement. The successful implementation of this research provides a valid paradigm for the deep application of artificial intelligence technology in the education sector, demonstrating its substantial potential in advancing personalized learning and automating pedagogical tasks.
Keywords: Educational Technology; Artificial Intelligence; Intelligent Teaching Resources; Teaching Efficiency

Full Text
Download the full text PDF for viewing and using it according to the license of this paper.

References

Liu, Yuehan; Huo, Haobin; Jin, Canguo. Practice and Exploration of Building an Enterprise-Level Private Large Language Model Assistant Based on ChatGLM3 and RPA Technologies. Architectural Design Management, 2023, 40(12): 33-40.
Yin, Xian; Feng, Yanhong; Ye, Shigen. Optimization Study of an Intelligent Conversational System for Aquatic Animal Disease Diagnosis Based on ChatGLM. Modern Electronic Technology [Online], 2024: 1-7 [Accessed Apr. 18, 2024]. http://kns.cnki.net/kcms/detail/61.1224.TN.20240409.1451.002.html
Zhao, Juecheng. AI-Generated Art: Surprise Accompanied by Controversy. Global Times, Mar. 24, 2023 (008). DOI: 10.28378/n.cnki.nhqsb.2023.002496.
Niu, Li; Han, Xiaoting. Research on the Integration and Service Models of Archival Information Resources in Cloud Computing Environments. Archives Science Study, 2013(05): 26-29. DOI: 10.16065/j.cnki.issn1002-1620.2013.05.007.
Huang, Jian; Liu, Jingyi; Li, Zhe. An Analysis of the Integrated Co-Construction Model of Enterprise Document Knowledge Bases and AI Resource Pools. Zhejiang Archives, 2021(09): 53-55. DOI: 10.16033/j.cnki.33-1055/g2.2021.09.020.
Bo, Junge; Qiao, Yanan; Qi, Qi; et al. Exploring the Potential and Challenges of AIGC Technologies in University Programming Courses. Computer Technology and Development [Online], 2024: 1-8 [Accessed May 28, 2024]. Available: http://kns.cnki.net/kcms/detail/61.1450.tp.20240514.1711.029.html
Guo, Jianan; Zhao, Shan. Education in the Era of Generative Artificial Intelligence: Opportunities, Challenges, and Responses of ChatGPT in Promoting University Course Innovation. Educational Science Exploration, 2023, 41(06): 89-97.