Search

Research on Big Data-Driven Precision Push of Personalized Learning Resources in Vocational Education

Author(s)

Kun Liu*, Xiaoxiao Gu, Wenjuan Shao

Affiliation(s)

College of Applied Science and Technology, Beijing Union University, Beijing, China *Corresponding Author

Abstract

To address the limitations of current personalized learning recommendation systems in vocational education—such as single-dimensional recommendation algorithms, the absence of vocational competency association mechanisms, and the difficulty in adapting to job-oriented talent cultivation requirements—this paper constructs a big-data precision recommendation model oriented toward vocational competency enhancement. The model employs data mining techniques to build a knowledge graph with bidirectional associations between knowledge points and vocational competencies. It integrates multi-source data, including learning behaviors, vocational competency assessments, and job requirements, to construct dynamic learner profiles. A hybrid recommendation engine is then developed by combining content-based filtering, collaborative filtering, and sequential pattern mining algorithms, enabling the dynamic matching of resources and learning paths. Furthermore, closed-loop iterative optimization of the model is achieved based on user learning feedback and competency growth data. Experiments conducted on the Vocational-Edu-Resource dataset demonstrate that the proposed model outperforms traditional baseline models in terms of recommendation precision (0.82) and NDCG (0.86). Additionally, the learners’ vocational competency attainment rate increased by 27.3%, resource utilization improved by 31.5%, and the learning completion rate reached 89.2%, thereby validating the model’s effectiveness. This research provides a novel technical solution for the digital and intelligent precision supply of resources in vocational education, and holds significant practical value for promoting the implementation of competency-oriented personalized smart teaching.

Keywords

Big Data; Precision Recommendation; Vocational Education; Deep Learning; Data Mining

References

[1] Liu H L, Ma J, Zhang G X. A Survey of Content Recommendation Algorithms Based on Deep Learning. Computer Engineering, 2021, 47(07): 1-12. [2] Liu J L, Li X G. Technological Advancements in Personalized Recommendation Systems. Computer Science, 2020, 47(07): 47-55. [3] Wu D. Application of Personalized Recommendation Function in the Big Data Environment. Electronic Technology and Software Engineering, 2021, (09): 174-175. [4] Guo D H, Zhang M K, Jia N, et al. A Survey on User POI Recommendation Incorporating Deep Learning Techniques. Journal of Wuhan University (Information Science Edition), 2020, 45(12): 1890-1902. [5] Xu X J, Lin C W. Collaborative Filtering Recommendation Algorithm Based on Knowledge Graph for Sparse Data. Science and Industry, 2025, 25(06): 30-35. [6] Zou C H, Li W J. Personalized Recommendation Model Integrating Knowledge Graph and Review Texts. Computer Engineering and Science, 2023, 45(01): 181-190. [7] Sungho K, Sunyong L, Debabrata B, et al. Personalization and recommendation systems: Leveraging machine learning algorithms to offer personalized product recommendations and content to customers based on their behavior, preferences and purchasing history. International Journal of Grid Computing & Applications, 2025, 16(2): 1-4. [8] He L, Long Y. Research and Implementation of Content Recommendation Algorithm Optimization Based on Multi-Source Information Fusion. Academic Journal of Mathematical Sciences, 2024, 5(2): 18-24. [9] Long H, Li N. Research on Personalized Learning Resource Recommendation System Based on Deep Learning. Computer Programming Skills and Maintenance, 2020, (02): 128-130. [10]Huang J G. Research on the Construction and Application of a Vocational Ability-Oriented Smart Learning Model in Higher Vocational Colleges. Northeast Normal University, 2023. [11]Movahedian H, Khayyambashi R M .Folksonomy-based user interest and disinterest profiling for improved recommendations: An ontological approach. Journal of Information Science, 2014, 40(5): 594-610. [12]Mallat S, Mdimagh A, Zrigui M .Personalized learning resource recommendations based on learning styles using the tabtransformer neural model. International Journal of Information Technology, 2025, (prepublish): 1-13. [13]Yang L N, Wei Y H, Xiao K X, et al. Research on Personalized Learning Service Mechanism Driven by Educational Big Data. Journal of Educational Technology Research, 2020, 41(09): 68-74. [14]Liu R J, Li P Z. Design of a Personalized Learning Resource Recommendation System Based on Big Data. China-Arab States Science and Technology Forum (Chinese and English), 2025, (01): 80-84. [15]Gu H B. Analysis of the Application of Personalized Teaching System Supported by Big Data Technology. Information System Engineering, 2025, (12): 24-27. [16]Wang P J. A Survey on User Privacy Protection in Personalized Recommendation Systems. Modern Computer, 2021, 27(24): 1-8+13.