一种网站个性化系统的设计
|
摘要
新信息、新产品、新服务大都在不断被推上web,同时,用户的种类、数量和关注点也在增加。一方面,用户己经疲于以“人海扮针”的方式搜寻信息,另一方面web网上的服务商也在不断设法获取用户的兴趣爱好,以填补用户和网站之间的信息鸿沟。个性化技术就是基于这种需要产生的。传统个性化技术(如CF技术、基于内容过滤技术)中存在着一些限制,如处理大数据量的能力差、依赖于用户的登记信息,不能获取web对象之间丰富的语义联系等。为解决传统技术中出现的这些问题,将web使用日志的挖掘应用到个性化技术中。
本文提出了一个基于序列模式挖掘的个性化技术,它使用概念格(concept lattice)作为存储频繁序列的数据结构。序列模式挖掘就是发现序列数据库中的频繁子序列作为用户感兴趣的模式。概念格适用于挖掘包括序列模式在内的各种知识。依据序列模式发现的特点,频繁概念格可以改善模式发现的时空性能。
Every day, new information, products and services are being offered by providers onthe World Wide Web. At the same time, the number of consumers and the diversity of their interests increase. As a result, providers are seeking ways to infer the customers'interests and to adapt their web sites to make the content of interest more easily accessible. Proposal have suggested Web usage mining as an enabling mechanism to overcome the problem associated with more traditional Web personalization technique such as Collaborative or Content-based filtering.These problems include lack of scalability ,reliance on Subjective user ratings ,and the inability to capture a richer set of semantic relationships among objects.
In this paper we present an sequential-pattern-based recommendation System,which extract usage patterns from web log file and use the concept lattice as its data structure storing frequent sequences. Sequential pattern mining, which discovers frequent subsequences as interesting patterns in a sequence database. The Concept Lattice is suitable to discover various knowledge including sequential patterns. Considering the characters of the sequential patterns mining, Fequent Concept Lattice can improve the mining efficiency.
本文提出了一个基于序列模式挖掘的个性化技术,它使用概念格(concept lattice)作为存储频繁序列的数据结构。序列模式挖掘就是发现序列数据库中的频繁子序列作为用户感兴趣的模式。概念格适用于挖掘包括序列模式在内的各种知识。依据序列模式发现的特点,频繁概念格可以改善模式发现的时空性能。
Every day, new information, products and services are being offered by providers onthe World Wide Web. At the same time, the number of consumers and the diversity of their interests increase. As a result, providers are seeking ways to infer the customers'interests and to adapt their web sites to make the content of interest more easily accessible. Proposal have suggested Web usage mining as an enabling mechanism to overcome the problem associated with more traditional Web personalization technique such as Collaborative or Content-based filtering.These problems include lack of scalability ,reliance on Subjective user ratings ,and the inability to capture a richer set of semantic relationships among objects.
In this paper we present an sequential-pattern-based recommendation System,which extract usage patterns from web log file and use the concept lattice as its data structure storing frequent sequences. Sequential pattern mining, which discovers frequent subsequences as interesting patterns in a sequence database. The Concept Lattice is suitable to discover various knowledge including sequential patterns. Considering the characters of the sequential patterns mining, Fequent Concept Lattice can improve the mining efficiency.
引文
[1] Jiawei Han, Micheline Kamber. 数据挖掘概念与技术(第一版). 范明,孟小峰译. 北京:机械工业出版社, 2001.p290～297
[2] David Hand等著,张银奎,廖丽等译.数据挖掘原理〔M].北京:机械工业出版社.2003.全书
[3] R Agrawal , R Srikant1. Mining sequential patterns.In : Proc of the 11t h Int’l Conf on Data Engineering ,Taipei , Taiwan : IEEE Society Press ,.1995.p3～14
[4] S. Krajci. The basic theorem on generalized concept lattice. CLA 2004, Ostrava, proceedings of the 2nd international workshop, eds. V. Snel, R. Blohlvek.2004. ISBN 80-248-0597-9, p25–33
[5](美)索沃(John F. Sowa).知识表示(英文版,书名原文:Knowledge Representation: Logical, Philosophical, and Computational Foundation).北京: 机 械工业出版社, 2003 .全书
[6] Langsdorf R, Skorsky M, Wille R, Wolf A. An approach to automated drawing drawing of concept lattices. General algebra and applications in discrete mathematics. Shaker Verlag:Aachen.1997. pp. 125-136.
[1] Godin,r,Chau,T-t.lncremental concept formation algorithms based on Galois Lattice .Compulational Intelligence. 1998,l 1,n 2.p246-267
[2] Wille,R.Concept Lattices and conceptual Knowledge Sysgems. Computers&Mathematics Applications,1992,11,23,pp.493-515,
[3] Godin,R.,Missaoui,R.&Alaoui,H.lncremental Concept Formation Algorithms Based on Galois (Concept)Latices. Computational Intelligence.1995,11,11(2),246-267.
[4] Fald M, Missaoui R, Godin R. Knowledge discovery in complex objects. Computational Intelligence, 1999,7, 15( i):28-49 [5] 欧阳为民,蔡庆生.在大型数据库中多层序贯模式的发现.软件学报. 1998,10,10(35). p916-920.
[6] 张娥, 冯秋红,宣慧玉等. Web 使用模式研究中的数据挖掘. 计算机应用研究.2001, 3,18(3). p80～83
[7] 杨红菊等.一种有效的关联规则的挖掘方法.计算机应用.2004,3, Vo1.24, No.3. pp.88-89.
[8] 陆楠,王喆，周春光.基于 FP-tree 频繁模式的 FP-tree 算法对关联规则挖掘的影 响.吉林大学自然科学学报(理学版).2003,2,2003 年第 2 期.第 180 ~ 185 页。
[9] 谢志鹏,刘宗田. 概念格与关联规则发现.计算机研究与发展. 2000 , 12, 37(12) . p1415～1421
[10] 王志海,胡可云,胡学钢等.概念格上规则提取的一般渐进式算法.计算机学报.1999 ,1,22 (1) .p66～70
[11] Kuznetsov, S.O.A Fast Algorithm for Computing All Intersections of Objects in a Finite Semi-lattice,.Automatic Documentation and Mathematical Linguistics.1993,5, vol. 27, no. 5 . p11–21.
[12] Carpineto, C., Romano, G.A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval,.Machine Learning.1996,12, no. 24.p95–122.
[13] Ganter, B. and Reuter, K.Finding All Closed Sets: A General Approach. Order,.1991,8, vol. 8.p 283-290.
[14] 谢志鹏, 刘宗田. 概念格快速渐进式构造算法. 计算机学报.2002 , 5 , 25(5) p1-7.
[15] Yan X, Han J, and Afshar R. CloSpan: Mining Closed Sequential. Journal of Experimental and Theoretical Artificial Intelligence. 2003,7, 14. p143– 156
[16]孙莹,胡学刚.基于频繁概念格的序列模式发现研究.计算机科学.2004,10,31.p168-171
[2] David Hand等著,张银奎,廖丽等译.数据挖掘原理〔M].北京:机械工业出版社.2003.全书
[3] R Agrawal , R Srikant1. Mining sequential patterns.In : Proc of the 11t h Int’l Conf on Data Engineering ,Taipei , Taiwan : IEEE Society Press ,.1995.p3～14
[4] S. Krajci. The basic theorem on generalized concept lattice. CLA 2004, Ostrava, proceedings of the 2nd international workshop, eds. V. Snel, R. Blohlvek.2004. ISBN 80-248-0597-9, p25–33
[5](美)索沃(John F. Sowa).知识表示(英文版,书名原文:Knowledge Representation: Logical, Philosophical, and Computational Foundation).北京: 机 械工业出版社, 2003 .全书
[6] Langsdorf R, Skorsky M, Wille R, Wolf A. An approach to automated drawing drawing of concept lattices. General algebra and applications in discrete mathematics. Shaker Verlag:Aachen.1997. pp. 125-136.
[1] Godin,r,Chau,T-t.lncremental concept formation algorithms based on Galois Lattice .Compulational Intelligence. 1998,l 1,n 2.p246-267
[2] Wille,R.Concept Lattices and conceptual Knowledge Sysgems. Computers&Mathematics Applications,1992,11,23,pp.493-515,
[3] Godin,R.,Missaoui,R.&Alaoui,H.lncremental Concept Formation Algorithms Based on Galois (Concept)Latices. Computational Intelligence.1995,11,11(2),246-267.
[4] Fald M, Missaoui R, Godin R. Knowledge discovery in complex objects. Computational Intelligence, 1999,7, 15( i):28-49 [5] 欧阳为民,蔡庆生.在大型数据库中多层序贯模式的发现.软件学报. 1998,10,10(35). p916-920.
[6] 张娥, 冯秋红,宣慧玉等. Web 使用模式研究中的数据挖掘. 计算机应用研究.2001, 3,18(3). p80～83
[7] 杨红菊等.一种有效的关联规则的挖掘方法.计算机应用.2004,3, Vo1.24, No.3. pp.88-89.
[8] 陆楠,王喆，周春光.基于 FP-tree 频繁模式的 FP-tree 算法对关联规则挖掘的影 响.吉林大学自然科学学报(理学版).2003,2,2003 年第 2 期.第 180 ~ 185 页。
[9] 谢志鹏,刘宗田. 概念格与关联规则发现.计算机研究与发展. 2000 , 12, 37(12) . p1415～1421
[10] 王志海,胡可云,胡学钢等.概念格上规则提取的一般渐进式算法.计算机学报.1999 ,1,22 (1) .p66～70
[11] Kuznetsov, S.O.A Fast Algorithm for Computing All Intersections of Objects in a Finite Semi-lattice,.Automatic Documentation and Mathematical Linguistics.1993,5, vol. 27, no. 5 . p11–21.
[12] Carpineto, C., Romano, G.A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval,.Machine Learning.1996,12, no. 24.p95–122.
[13] Ganter, B. and Reuter, K.Finding All Closed Sets: A General Approach. Order,.1991,8, vol. 8.p 283-290.
[14] 谢志鹏, 刘宗田. 概念格快速渐进式构造算法. 计算机学报.2002 , 5 , 25(5) p1-7.
[15] Yan X, Han J, and Afshar R. CloSpan: Mining Closed Sequential. Journal of Experimental and Theoretical Artificial Intelligence. 2003,7, 14. p143– 156
[16]孙莹,胡学刚.基于频繁概念格的序列模式发现研究.计算机科学.2004,10,31.p168-171