·1124· 智能系统学报 第16卷 习风格特征和静态兴趣偏好特征，动态特征包括 al.Enhancing e-learning systems with personalized re- 认知水平特征和动态兴趣偏好特征。采用协同过 commendation based on collaborative tagging 滤作为在线学习资源的基础方法，将学习者静态 techniques[J].Applied intelligence,2018,48(6): 特征和动态特征分别融入协同过滤的推荐方法 1519-1535. 中，通过实验得到的数据证实，本文构建的学习 [11]BAKER R S J D,CORBETT A T.ALEVEN V.More ac- 者模型，以及基于该模型构建的学习资源推荐方 curate student modeling through contextual estimation of 法提高了在线学习资源协同过滤推荐的性能。该 slip and guess probabilities in Bayesian knowledge tra- 方法对于满足个性化学习的需求、提高在线学习 cing[C]//Proceedings of the 9th International Conference 的学习效果具有重要意义。 on Intelligent Tutoring Systems.Montreal,Canada,2008. [12]SALEHI M.Application of implicit and explicit attribute 参考文献： based collaborative filtering and BIDE for learning re- source recommendation[J].Data knowledge engineer- [1]中国互联网络信息中心(CNNIC).第45次中国互联网 ing,2013,87:130-145. 络发展状况统计报告R].北京：中国互联网络信息中 [13]KURILOVAS E,SERIKOVIENE S.VUORIKARI R. 心(CNNIC),2020:4 Expert centred vs learner centred approach for evaluating [2]AL-SHAMRI M Y H.Power coefficient as a similarity quality and reusability of learning objects[J].Computers measure for memory-based collaborative recommender in human behavior,2014,30:526-534 systems[J].Expert systems with applications,2014,41(13): [14]现代远程教育技术标准化委员会.CELTS-11,学习者模 5680-5688 型规范[S].现代远程教育技术标准化委员会，2000：11. [3]NAJAFABADI MK,MOHAMED A,ONN C W.Anim- [15]COSTA R D,SOUZA G F,VALENTIM R A M,et al. pact of time and item influencer in collaborative filtering The theory of learning styles applied to distance recommendations using graph-based model[J].Informa- learning[J].Cognitive systems research,2020,64: tion processing management,2019,56(3):526-540. 134145. [4]WANG Yong,DENG Jiangzhou,GAO J,et al.A hybrid [16]ARIEVITCH I M.Reprint of:the vision of Development- user similarity model for collaborative filtering[]].Inform- al Teaching and Learning and Bloom's Taxonomy of edu- ation sciences,2017,418-419:102-118. cational objectives[J].Learning,culture and social inter- [5]JIANG Shan,FANG S C,AN Qi,et al.A sub-one quasi- action,2020,27:100473. norm-based similarity measure for collaborative filtering in [17]ZLATKOVIC D,DENIC N,PETROVIC M,et al.Ana- recommender systems[J].Information sciences,2019,487: lysis of adaptive e-learning systems with adjustment of 142-155 Felder-Silverman model in a Moodle DLS[J].Computer [6]MU Yi.XIAO Nianhao,TANG Ruichun,et al.An effi- applications in engineering education,2020,28(4): cient similarity measure for collaborative filtering[J.Pro- 803-813. cedia computer science,2019,147:416-421. [18]DASCALU MI,BODEA C N.MOLDOVEANU A,et al. [7]WANG T I.TSAI K H.LEE M C.et al.Personalized A recommender agent based on learning styles for better learning objects recommendation based on the semantic- virtual collaborative learning experiences[].Computers aware discovery and the learner preference pattern[J].Edu- in human behavior,2015,45:243-253. cational technology society,2007,10(3):84-105. [19]GONZALEZ G.LOPEZ B.DE LA ROSA J L.A multi- [8]SEGAL A.KATZIR Z.GAL Y.et al.EduRank:a collab- agent smart user model for cross-domain recommender orative filtering approach to personalization in E- systems[C]//Proceedings of Beyond Personalization 2005: learning[C]//Proceedings of the 7th International Confer- The Next Stage of Recommender Systems Research,In- ence on Educational Data Mining.London,UK,2014: ternational Conference on Intelligent User Interfaces IUI 68-74 2005.San Diego,USA,2005. [9]ZHANG Fuzheng,YUAN N J,LIAN Defu,et al.Collabor- [20]谢修娟，陈永，李香菊，等.融人信任的变权重相似度模 ative knowledge base embedding for recommender sys- 型在线学习协同推荐算法「刀.小型微型计算机系统」 tems[C]//Proceedings of the 22nd ACM SIGKDD Interna- 2018,39(3):525-528 tional Conference on Knowledge Discovery and Data Min- XIE Xiujuan,CHEN Yong,LI Xiangju,et al.Collaborat- ing.San Francisco,USA,2016:353-362. ive recommendation algorithm of online learning based [10]KLASNJA-MILICEVIC A.IVANOVIC M,VESIN B,et on trust-combined simi-larity model with variable习风格特征和静态兴趣偏好特征，动态特征包括 认知水平特征和动态兴趣偏好特征。采用协同过 滤作为在线学习资源的基础方法，将学习者静态 特征和动态特征分别融入协同过滤的推荐方法 中，通过实验得到的数据证实，本文构建的学习 者模型，以及基于该模型构建的学习资源推荐方 法提高了在线学习资源协同过滤推荐的性能。该 方法对于满足个性化学习的需求、提高在线学习 的学习效果具有重要意义。 参考文献： 中国互联网络信息中心 (CNNIC). 第 45 次中国互联网 络发展状况统计报告 [R]. 北京: 中国互联网络信息中 心 (CNNIC), 2020: 4. [1] AL-SHAMRI M Y H. Power coefficient as a similarity measure for memory-based collaborative recommender systems[J]. Expert systems with applications, 2014, 41(13): 5680–5688. [2] NAJAFABADI M K, MOHAMED A, ONN C W. Anim￾pact of time and item influencer in collaborative filtering recommendations using graph-based model[J]. Informa￾tion processing & management, 2019, 56(3): 526–540. [3] WANG Yong, DENG Jiangzhou, GAO J, et al. A hybrid user similarity model for collaborative filtering[J]. Inform￾ation sciences, 2017, 418−419: 102–118. [4] JIANG Shan, FANG S C, AN Qi, et al. A sub-one quasi￾norm-based similarity measure for collaborative filtering in recommender systems[J]. Information sciences, 2019, 487: 142–155. [5] MU Yi, XIAO Nianhao, TANG Ruichun, et al. An effi￾cient similarity measure for collaborative filtering[J]. Pro￾cedia computer science, 2019, 147: 416–421. [6] WANG T I, TSAI K H, LEE M C, et al. Personalized learning objects recommendation based on the semantic￾aware discovery and the learner preference pattern[J]. Edu￾cational technology & society, 2007, 10(3): 84–105. [7] SEGAL A, KATZIR Z, GAL Y, et al. EduRank: a collab￾orative filtering approach to personalization in E￾learning[C]//Proceedings of the 7th International Confer￾ence on Educational Data Mining. London, UK, 2014: 68−74. [8] ZHANG Fuzheng, YUAN N J, LIAN Defu, et al. Collabor￾ative knowledge base embedding for recommender sys￾tems[C]//Proceedings of the 22nd ACM SIGKDD Interna￾tional Conference on Knowledge Discovery and Data Min￾ing. San Francisco, USA, 2016: 353−362. [9] [10] KLAŠNJA-MILIĆEVIĆ A, IVANOVIĆ M, VESIN B, et al. Enhancing e-learning systems with personalized re￾commendation based on collaborative tagging techniques[J]. Applied intelligence, 2018, 48(6): 1519–1535. BAKER R S J D, CORBETT A T, ALEVEN V. More ac￾curate student modeling through contextual estimation of slip and guess probabilities in Bayesian knowledge tra￾cing[C]//Proceedings of the 9th International Conference on Intelligent Tutoring Systems. Montreal, Canada, 2008. [11] SALEHI M. Application of implicit and explicit attribute based collaborative filtering and BIDE for learning re￾source recommendation[J]. Data & knowledge engineer￾ing, 2013, 87: 130–145. [12] KURILOVAS E, SERIKOVIENE S, VUORIKARI R. Expert centred vs learner centred approach for evaluating quality and reusability of learning objects[J]. Computers in human behavior, 2014, 30: 526–534. [13] 现代远程教育技术标准化委员会. CELTS-11, 学习者模 型规范 [S]. 现代远程教育技术标准化委员会, 2000: 11. [14] COSTA R D, SOUZA G F, VALENTIM R A M, et al. The theory of learning styles applied to distance learning[J]. Cognitive systems research, 2020, 64: 134–145. [15] ARIEVITCH I M. Reprint of: the vision of Development￾al Teaching and Learning and Bloom's Taxonomy of edu￾cational objectives[J]. Learning, culture and social inter￾action, 2020, 27: 100473. [16] ZLATKOVIC D, DENIC N, PETROVIC M, et al. Ana￾lysis of adaptive e-learning systems with adjustment of Felder-Silverman model in a Moodle DLS[J]. Computer applications in engineering education, 2020, 28(4): 803–813. [17] DASCALU M I, BODEA C N, MOLDOVEANU A, et al. A recommender agent based on learning styles for better virtual collaborative learning experiences[J]. Computers in human behavior, 2015, 45: 243–253. [18] GONZÁLEZ G, LÓPEZ B, DE LA ROSA J L. A multi￾agent smart user model for cross-domain recommender systems[C]//Proceedings of Beyond Personalization 2005: The Next Stage of Recommender Systems Research, In￾ternational Conference on Intelligent User Interfaces IUI 2005. San Diego, USA, 2005. [19] 谢修娟, 陈永, 李香菊, 等. 融入信任的变权重相似度模 型在线学习协同推荐算法 [J]. 小型微型计算机系统, 2018, 39(3): 525–528. XIE Xiujuan, CHEN Yong, LI Xiangju, et al. Collaborat￾ive recommendation algorithm of online learning based on trust-combined simi-larity model with variable [20] ·1124· 智 能 系 统 学 报 第 16 卷