数字图书馆下的文献阅读智能推荐
Intelligent Recommendation for Literature Reading in Digital Library
DOI: 10.12677/SEA.2018.75030, PDF,    科研立项经费支持
作者: 朱辉生, 陈琳, 张禹, 陆宇：泰州学院计算机科学与技术学院，江苏 泰州
关键词: 数字图书馆；智能推荐；频繁情节；深度优先搜索；共享前缀树；Digital Library； Intelligent Recommendation； Frequent Episode； Depth-First-Search； Shared Prefix Tree
摘要: 数字图书馆以其信息容量大、传输速度快、时空限制少等优势，已成为读者阅读文献的主流平台。如何向读者提供导向性强、个性化好的服务，是数字图书馆向智慧图书馆转变的关键。鉴于此，提出一种文献阅读智能推荐算法。该算法只需单遍扫描文献阅读流，以深度优先搜索策略来挖掘频繁情节，以共享前缀树来存储频繁情节，以情节单调性来压缩搜索空间。实验表明，与经典算法相比，所提算法具有较好的时空性能和较高的挖掘质量，挖掘结果能够揭示读者的阅读习惯和预测读者的阅读倾向，从而有助于数字图书馆提高文献资源的利用率并向读者提供更好的个性化服务。
Abstract: Digital library has become a mainstream platform for readers to read literatures with its ad-vantages of large information capacity, fast transmission speed, and less spatio-temporal re-strictions. How to provide readers with high guidance quality and good personalized services is a key to transform digital library into smart library. In this paper, an intelligent recommendation algorithm for literature reading in digital library is proposed. After scanning the given literature reading stream only one pass, the algorithm mines frequent episodes by depth-first-search, stores frequent episodes by a shared prefix tree, and compresses the search space by episode monoton-ically. Experiments show that the proposed algorithm has better spatio-temporal performance and higher mining quality than the classical algorithms. The mining results can reveal the reading habits of readers and predict the reading tendency of readers, which helps the digital library to improve the utilization rate of literature resources and provide readers with better personalized services.
文章引用：朱辉生, 陈琳, 张禹, 陆宇. 数字图书馆下的文献阅读智能推荐[J]. 软件工程与应用, 2018, 7(5): 261-272. https://doi.org/10.12677/SEA.2018.75030

参考文献

[1] Mannila, H., Toivonen, H. and Verkamo, A.I. (1997) Discovering Frequent Episodes in Event Sequences. Data Mining and Knowledge Discovery, 1, 259-289. [Google Scholar] [CrossRef] 
[2] Méger, N. and Rigotti, C. (2004) Constraint-Based Mining of Episode Rules and Optimal Window Sizes. Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases, Springer, Pisa, 313-324.
[3] Lin, Y.-F., Huang, C.-F. and Tseng, V.S. (2017) A Novel Methodology for Stock Investment Using High Utility Episode Mining and Genetic Algorithm. Applied Soft Computing, 59, 303-315. [Google Scholar] [CrossRef] 
[4] Ma, X., Pang, H.H. and Tan, K.L. (2004) Finding Constrained Frequent Episodes Using Minimal Occurrences. Proceedings of the 4th IEEE International Conference on Data Mining, Brighton, 1-4 November 2004, 471-474.
[5] Zhou, W.Z., Liu, H.Y. and Cheng, H. (2010) Mining Closed Episodes from Event Sequences Efficiently. Proceedings of the 15th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Springer, Hyderabad, 310-318. [Google Scholar] [CrossRef] 
[6] Wu, J.J., Wan, L. and Xu, Z.R. (2011) Algorithms to Discover Complete Frequent Episodes in Sequences. Proceedings of the 15th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Shenzhen, 24-27 May 2011, 267-278.
[7] Wu, C.W., Lin, Y.F., Yu, P.S., et al. (2013) Mining High Utility Episodes in Complex Event Sequences. Proceedings of the 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM Press, Chicago, 536-544.
[8] 林树宽, 乔建忠. 一种基于情节矩阵和频繁情节树的情节挖掘方法[J]. 控制与决策, 2013, 28(3): 339-344.
[9] Ao, X., Luo, P., Li, C.K., et al. (2014) Discovering and Learning Sensational Episodes of News Events. Proceedings of the 23rd International World Wide Web Conferences, ACM Press, Seoul, 217-218.
[10] Laxman, S. (2006) Discovering Frequent Episodes: Fast Algorithms, Connections with HMMs and Generalizations. Indian Institute of Science, Bangalore.
[11] Laxman, S., Sastry, P.S. and Unnikrishnan, K. (2005) Discovering Frequent Episodes and Learning Hidden Markov Models: A Formal Connection. IEEE Transactions on Knowledge and Data Engineering, 17, 1505-1517.
[12] Laxman, S., Sastry, P.S. and Unnikrishnan, K.P. (2007) A Fast Algorithm for Finding Frequent Episodes in Event Streams. Proceedings of the 13th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM Press, San Jose, 410-419.

为你推荐