A Study on the Construction of a Local Layered Knowledge Base for the Big Data Professional Curriculum System

DOI: https://doi.org/10.62517/jhet.202515624

Author(s)

Ying Li1, Xiaodong Li2,*, Wenjie Xiao1, Lanping Zhang1, Lilin Yang1, Wenlin Zou1, Yihan Shen1

Affiliation(s)

1School of Information Engineering, NanJing XiaoZhuang University, Nanjing, China 2Machining Teaching and Research Section, Benxi Mechanical and Electrical Engineering School, Benxi, China *Corresponding Author

Abstract

To address the challenges posed by the rapid technological advancements, vast and complex knowledge structures, and heterogeneous data sources that hinder efficient information retrieval within the big data professional curriculum system, this study proposes an innovative approach to constructing a local layered knowledge base. Utilizing a hybrid retrieval weighted fusion algorithm, the method effectively normalizes and integrates disparate data. Experimental comparisons against a benchmark retrieval service based on a standardized general corpus demonstrate the superior effectiveness of the proposed method. Additionally, this approach offers robust data support aimed at enhancing employment-oriented course recommendations and facilitating personalized learning pathways for students.

Keywords

Local Layered Knowledge Base; Employment-Oriented; Vectorization; Knowledge Graph

References

[1]Yang Bo, Li Yuanbiao. Complex Network Analysis on Curriculum System of Data Science and Big Data Technology. Computer Science, 2022, 49(S1): 680-685+807. [2]Yu Chengcheng, Shi Linxiang, Chen Lin, et al. Construction and Exploration of "Big Data Technology" AI Course Based on Knowledge Graph. Computer Era, 2025(10): 95-99. [3]Patrick Lewis, Ethan Perez, Aleksandara Piktus, et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems, 2020,33, 9459-9474. [4]Liu Zhenyi. Research on Construction and Application of Computer Course Knowledge Base Based on RAG. Computer Knowledge and Technology, 2025, 21(08): 26-28. [5]Yu Songwei, Liu Wei, Xia Xiujiang, et al. Constructing a Retrieval-Augmented Generation Knowledge Base for Urban Rail Transit Large Language Models: A Knowledge Graph-Based Approach. Urban Rapid Rail Transit, 2025, 38(02): 19-25. [6]Hou Pengliang, Zhang Fulong, Xiao Haining, et al. An Exploration of Teaching Reform to Promote Learning by Competitions and Promote Teaching by Competitions. Journal of Educational Institute of Jilin Province, 2024, 40(1): 121-126. [7]Shang Xueru, Chen Han. Optimal Conceptual Semantic Template Self Retrieval Based on Structured Corpus. Computer Simulation, 2025, 42(01): 550-554. [8]Wang Xiaoling, Yue Wenjing, Wang Haofen, et al. Teaching Exploration of Integrating Large Language Model Technology into Database Courses. Computer Education, 2024(9): 28-32. [9]Zhao Yubo, Zhang Liping, Yan Sheng, Hou Min, Gao Mao. Construction and Application of Discipline Knowledge Graph in Personalized Learning. Computer Engineering and Applications, 2023, 59(10): 1-21. [10]Huang Qiaojuan, Cao Cungen, Wang Ya, et al. Method for Expanding Event Commonsense Knowledge Graph Based on Large Language Models. Journal of Software, 2025, 36(09): 4153-4186. [11]Song Meixia, Zhang Shuaishuai. The Essence, Reality and Optimization Path of ChatGPT-Enabled Personalized Learning. Journal of Continuing Higher Education, 2023, 36(5): 73-80.