CAJ | 학술논문

介绍了Web日志挖掘的模型，分析了使用关联规则挖掘Web日志时遇到的规则数量大且存在冗余等问题，提出了基于频繁闭项集的挖掘办法来减少规则数量．同时引入最小关联规则的概念，从而避免了冗余规则的产生．最后用实验验证了算法的有效性，并以周口师范学院校园网为例，对该网站日志数据进行分析，得到了有价值的规则，并对该网站提出了相应的建议和意见．
개소료Web일지알굴적모형，분석료사용관련규칙알굴Web일지시우도적규칙수량대차존재용여등문제，제출료기우빈번폐항집적알굴판법래감소규칙수량．동시인입최소관련규칙적개념，종이피면료용여규칙적산생．최후용실험험증료산법적유효성，병이주구사범학원교완망위례，대해망참일지수거진행분석，득도료유개치적규칙，병대해망참제출료상응적건의화의견．
In this study, we introduced the model of Web log mining, and at the same item, a new method of Web log min ing is proposed. Firstly,we found that the traditional Web log mining approaches suffer from one major deficiency： a training data set often generates a huge set of rules,which is also redundancy. Secondly,we put forward the frequent closed itemsets based on the way to reduce the number of mining rules. The paper introduced the concept of minimum association rules, so as to avoid the generation of the redundancy rules. And then, our extensive experiments on learning database repository show that the algorithm is effective with higher quality and no redundancy. Finally, we take the campus web-log mining of zhouKou normal university for a ~tata source. We extracted valuahle rules and put forward recommendations and methods for improving the site.