2024 Vol.7 Jun.N03

• Title: Research on personalized push of multimedia educational materials in colleges and universities based on deep reinforcement learn
• Name: Xiaoyu Zhang
• Company: Liaoning University of Techunology , School of Electronics &Information Engineering ,Jinzhou , 121001, China.
• Abstract:

  Conventional educational resource push methods usually use label and resource matching, combined with mapping relationships to push resources for users, which is superior to the lack of effective analysis of user interest, resulting in poor push results. In this regard, the research on personalized push of multimedia educational materials in colleges and universities based on deep reinforcement learning is proposed. Firstly, the neural network (BILSTM+CRF) based method is used to recognize the knowledge point entity, and word2vec is used to calculate the similarity to eliminate the expression ambiguity of the knowledge point. Then the similarity of the text is calculated using word vectors as the similarity between the user interest and the resource and the knowledge connectivity is calculated and fused with linear weighting to get the similarity between the learner and the resource. Finally, personalized push is given to the user in the order of connectivity degree. In the experiments, the proposed method is validated for actual push performance. By comparing the experimental results, it is clear that the algorithm has a high hit rate when using this paper's method to push educational materials, and has a more ideal pushing effect.

  
  

• Keyword: deep reinforcement learning; educational materials; personalized push methods;
• DOI: 10.12250/jpciams2024090605
• Citation form: Xiaoyu Zhang.Research on personalized push of multimedia educational materials in colleges and universities based on deep reinforcement learning[J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.20-24

bibliography

[1] Ohtomo K , Harakawa R , Ogawa T ,et al. [Paper] Personalized Recommendation of Tumblr Posts Using Graph Convolutional Networks with Preference-aware Multimodal Features[J].ITE Transactions on Media Technology and Applications, 2021, 9(1):54-61.

[2] Zhang X , Zhang J , Yang J .Personalized recommendation algorithm in social networks based on representation learning[J].Journal of Intelligent and Fuzzy Systems, 2021:1-9.

[3] Zhang X , Liu X , Guo J ,et al.Matrix Factorization Based Recommendation Algorithm for Sharing Patent Resource[J].IEICE Transactions on Information and Systems, 2021, E104.D(8):1250-1257.

[4] Gu T , Liang H , Bin C ,et al. Combining user-end and item-end knowledge graph learning for personalized recommendation[J].Journal of Intelligent and Fuzzy Systems, 2021(12):1-13

[5] Lv Y E , Yang Y , Zeng J X .An interpretable mechanism for personalized recommendation based on cross feature[J].Journal of Intelligent and Fuzzy Systems, 2021, 40(2):1-12.

[6] Cai D , Qian S , Fang Q ,et al. Heterogeneous Hierarchical Feature Aggregation Network for Personalized Micro-video Recommendation[J].IEEE Transactions on Multimedia, 2021, PP(99):1-1.

[7] Karacan H , Karacan H , Yenice Y E ,et al. A Novel Overlapping Method to Alleviate the Cold-Start Problem in Recommendation Systems[J].International Journal of Software Engineering and Knowledge Engineering, 2021, 31(09):1277-1297.

[8] Bao T , Xu L , Zhu L ,et al. Successive Point-of-Interest Recommendation with Personalized Local Differential Privacy[J].IEEE Transactions on Vehicular Technology, 2021, PP(99):1-1.

[9] Yang B , Li L , Wang X ,et al. A Novel Crowdsourcing Task Recommendation Method Considering Workers' Fuzzy Expectations: a Case of ZBJ.COM[J]. International Journal of Information Technology & Decision Making, 2024, 23(01):413-446.

[10] Tugiyati T , Wiyanto W , Lisdiana L .Ethnopedagogic Based Teaching Materials Analysis For Senior High School Students: a Literature Riview[J]. Journal of Innovative Science Education, 2021, 9:56-64.

[11] Zhang X , Liu S , Wang H .Personalized Learning Path Recommendation for E-Learning Based on Knowledge Graph and Graph Convolutional Network[J].Int. J. Softw. Eng. Knowl. Eng. 2022, 33:109-131.

[12] Peng Z , Wan D , Wang A ,et al. Deep learning-based recommendation method for top-K tasks in software crowdsourcing systems[J]. and Management Optimization, 2023, 19(9):6478-6499.

[13] Improved collaborative filtering personalized recommendation algorithm based on k-means clustering and weighted similarity on the reduced item space[J].Mathematical Modelling and Control, 2023, 3(1):39-49.

[14] Sun J , Zhu M , Jiang Y ,et al. Hierarchical attention model for personalized tag recommendation[J]. Science and Technology, 2021, 72(2):173-189.

[15] Zhao Y , Cao L . Simulation of Massive Sparse Big Data Mixed Feature Personalized Recommendation Algorithm[J]. Computer Simulation,2023(5)563-567.