计算机科学 ›› 2026, Vol. 53 ›› Issue (5): 68-78.doi: 10.11896/jsjkx.250600157
刘美麟, 马乐
LIU Meilin, MA Le
摘要： 针对现有学习路径推荐方法在个性化适配性、动态适应性以及多目标优化方面的不足,提出一种基于超图神经网络与知识追踪的协同推荐模型。通过构建学习资源无向图编码资源关联关系,生成学习资源嵌入向量,并结合超图神经网络聚合学习者历史行为数据,捕获学习者-学习资源交互特征。设计多目标优化策略,利用非支配排序遗传算法(NSGA-II)生成帕累托前沿解集,同步优化学习路径推荐精准性、难度适配性、有效性与学习资源多样性,并结合权重分配与综合效用函数提升学习路径的质量。在MOOCCube与MOOPer数据集上对所提方法进行实验,其在MOOPer数据集上的HR@5与MRR@5分别达93.9%与90.7%,实现了学习路径的精准推荐。实验结果验证了所提模型在学习者历史交互建模与课程结构约束融合方面的有效性。
中图分类号:
| [1]HU F X,CHEN C Q,XIAO Y C.Research on the Mechanism and Path of Empowering Vocational Education with Artificial Intelligence[J].Journal of Changsha Social Work College,2024,31(4):91-95. [2]YUN Y,DAI H,ZHANG Y P,et al.State-of -the -art Survey on Personalized Learning Path Recommendation[J].Journal of Software,2022,33(12):4590-4615. [3]BANSAL S,BALIYAN N.A Study of Recent RecommenderSystem Techniques[J].International Journal of Knowledge and Systems Science,2019,10(2):13-41. [4]HE K K.Significant Influence of Emerging Information Technology on Deepening Reformation of Education in the 21st Century[J].Education Research,2019,40(3):5-12. [5]XIE D F,ZHOU A Z,LI J Q.Research on the construction and application of personalized model based on learner portrait[C]//Proceedings of the 2023 China Tao Xingzhi Research Association Life Education Academic Symposium(II).Hunan Industrial Vocational and Technical College,2024:551-556. [6]ZHANG H,HUANG T,LYU Z H,et al.MOOCRC:A Highly Accurate Resource Recommendation Model for Use in MOOC Environments[J].Mobile Networks and Applications,2019,24(1):34-46. [7]LI B F,LI G F,XU J X,et al.A personalized recommendation framework based on MOOC system integrating deep learning and big data[J].Computers and Electrical Engineering,2023,106:108571. [8]CHEN H Y.Research and Design of Personalized Learning Recommendation Model Based on User Learning Feature Collaborative Filtering Algorithm[J].Journal of Guangdong Polytechnic University,2022,21(5):7-11. [9]GAO J Q,LIU Q H,HUANG W B.Research on Automatic Generation of Learning Paths Based on Knowledge Graph[J].Modern Educational Technology,2021,31(7):88-96. [10]ALJOHANI T I,CRISTEA A I.Predicting Learners’ Demo-graphics Characteristics Deep Learning Ensemble Architecture for Learners’ Characteristics Prediction in MOOCs[C]//Proceedings of the 4th International Conference on Information and Education Innovations(ICIEI 2019).Department of Computer Science Durham University,2019:24-28. [11]FAN Y X,DU J H,ZHANG J,et al.Adaptive Learning Path Recommendation Model for Dynamic Learning Environments[J].e-Eduction Research,2024,45(6):89-96,105. [12]ZHOU Y T,CHU H,ZHU F F,et al.Survey on Deep Learning-based Personalized Learning Resource Recommendation[J].Computer Science,2024,51(10):17-32. [13]SHEN X L,WANG J H.User Interest Recommendation Based on Knowledge Graph[J].Computer Systems & Applications,2025,34(4):155-165. [14]WANG X,WANG D X,XU C R,et al.Explainable Reasoning over Knowledge Graphs for Recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019. [15]XIA X N,QI W X.Learning Behavior Interest PropagationStrategy of MOOCs Based on Multi Entity Knowledge Graph[J].Education and Information Technologies,2023,28(10):13349-13377. [16]CHEN P Y,FANG M Y,HOU X B,et al.Root Cause Analysis Based on Association Mining Between Accident Report and Indicator[J].Computer Systems & Applications,2025,34(2):272-280. [17]WANG X H,MA W Y,GUO L,et al.HGNN:Hyperedge-based graph neural network for MOOC Course Recommendation[J].Information Processing and Management,2022,59(3):102938. [18]ZHANG X M,LIU S,WANG H Y.Personalized learning path recommendation for e-learning based on knowledge graph and graph convolutional network[J].International Journal of Software Engineering and Knowledge Engineering,2023,33(1):109-131. [19]CAO Z.Research on Online Learning Resource Recommenda-tion Method Based on Deep Learning[J].Information Recording Materials,2024,25(11):62-64. [20]ZHANG Q,LI Y,ZHANG G Q,et al.A recurrent neural network-based recommender system framework and prototype for sequential E-learning[C]//15th Symposium of Intelligent Systems and Knowledge Engineering(ISKE) held jointly with 14th International FLINS Conference(FLINS).2020:488-495. [21]ZHOU Y W,HUANG C Q,HU Q T,et al.Personalized lear-ning full-path recommendation model based on LSTM neural networks[J].Information Sciences,2018,444:135-152. [22]ZHOU Y T,LI Q S,CHU H,et al.Knowledge Point Recommendation Method Based on Static and Dynamic Learning Demand Perception[J].Journal of Software,2024,35(9):4425-4447. [23]ZHU H P,WANG Z Y,ZHAO C C,et al.Learning ResourceRecommendation Method Based on Spatiotemporal Multi-granularity Interest Modeling[J].Journal of Computer Research and Development,2025,62(8):1884-1901. [24]SUN L,RAO Y,ZHANG X B,et al.MS-HGAT:Memory-Enhanced Sequential Hypergraph Attention Network for Information Diffusion Prediction[C]//36th AAAI Conference on Artificial Intelligence／34th Conference on Innovative Applications of Artificial Intelligence／12th Symposium on Educational Advances in Artificial Intelligence.2022:4156-4164. [25]ZHAO Y,TUO J K,SHAN K X,et al.Review of Knowledge Tracing Models in Intelligent Education Field[J].Computer System & Application,2025(6):1-11. [26]SU Y,LIU Q W,LIU Q,et al.Exercise-Enhanced Sequential Modeling for Student Performance Prediction[C]//32nd AAAI Conference on Artificial Intelligence／30th Innovative Applications of Artificial Intelligence Conference／8th AAAI Symposium on Educational Advances in Artificial Intelligence.2018:2435-2443. [27]NAKAGAWA H,IWASAWA Y,MATSUO Y.Graph-basedknowledge tracing:Modeling student proficiency using graph neural networks[J].Web Intelligence,2021,19(1/2):87-102. [28]SONG X Y,LI J X,TANG Y F,et al.JKT:a joint graph convolutional network based deep knowledge tracing[J].Information Sciences,2021,580:510-523. [29]PENG Y T,MENG X F,DU Z J.Survey on Diversified Recommendation[J].Journal of Computer Research and Development,2025,62(2):285-313. [30]NABIZADEH H A,JORGE M A,LEAL P J.Estimating time and score uncertainty in generating successful learning paths under time constraints[J].Expert Systems,2019,36(2):e12351. [31]HUANG Z Y,LIU Q,ZHAI C X,et al.Exploring Multi-Objective Exercise Recommendations in Online Education Systems[C]//28th ACM International Conference on Information and Knowledge Management(CIKM).2019:1261-1270. [32]ELSHANI L,NUCI K P.Constructing a personalized learningpath using genetic algorithms approach[J].arXiv:2104.11276,2021. [33]REN Y M,LIANG K,SHANG Y H,et al.MulOER-SAN:2-layer multi-objective framework for exercise recommendation with self-attention networks[J].Knowledge-Based Systems,2023,260:110117. [34]LIU Q,TONG S W,LIU C R,et al.Exploiting Cognitive Structure for Adaptive Learning[C]//25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining(KDD).2019:627-635. [35]YU J F,LUO G,XIAO T,et al.MOOCCube:A large-scale data repository for NLP applications in MOOCs[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:3135-3142. [36]LIU K J,ZHAO X,TANG J Y,et al.MOOPer:a large-scale dataset of practice-oriented online learning[C]//Proceedings of the 6th China Conference of Knowledge Graph and Semantic Computing:Knowledge Graph Empowers New Infrastructure Construction.2021:281-287. [37]GAO Y.MOOCs video recommendation using low-rank andsparse matrix factorization with inter-entity relations and intra-entity affinity information[J].Information Processing and Ma-nagement,2024,61(6):103861. [38]CHEN X,SUN Y H,ZHOU T,et al.A Method on OnlineLearning Video Recommendation Method Based on Knowledge Graph[C]//12th IFIP TC 12 International Conference on Intelligent Information Processing(IIP 2022).2022:419-430. [39]LYU J N,YANG B Y,GAO P,et al.Online course video recommendation based on weighted Heterogeneous Information Network fused with student characteristics[C]//2022 International Conference on Frontiers of Communications,Information System and Data Science(CISDS 2022).2022:54-59. [40]WEN J F,QIN Y H,SU X W,et al.Video recommendation method based on multi-attention mechanism and heterogeneous information network[C]//4th International Conference on Computer Engineering and Application(ICCEA 2023).2023:669-674. [41]GONG J B,WANG S,WANG J L,et al.Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View[C]//43rd International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR).2020:79-88. [42]SHENG D M,YUAN J L,XIE Q,et al.ACMF:An Attention Collaborative Extended Matrix Factorization Based Model for MOOC course service via a heterogeneous view[J].Future Gene-ration Computer Systems,2022,126:211-224. [43]CHEN X Y,SHEN J,XIA W,et al.Set-to-Sequence Ranking-Based Concept-Aware Learning Path Recommendation[C]//37th AAAI Conference on Artificial Intelligence(AAAI)／35th Conference on Innovative Applications of Artificial Intelligence／13th Symposium on Educational Advances in Artificial Intelligence.2023:5027-5035. [44]ZHANG H T,SHEN S H,XU B H,et al.Item-Difficulty-Aware Learning Path Recommendation:From a Real Walking Perspective[C]//30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2024:4167-4178. |
|
||
首页