| Web挖掘中基于交集算法发现用户频繁访问模式 |
| |
| 引用本文： | 郭维,欧阳一鸣,郭骏. Web挖掘中基于交集算法发现用户频繁访问模式[J]. 合肥工业大学学报(自然科学版), 2006, 29(12): 1511-1515 |
| |
| 作者姓名： | 郭维 欧阳一鸣 郭骏 |
| |
| 作者单位： | 合肥工业大学,计算机与信息学院,安徽,合肥,230009;合肥工业大学,计算机与信息学院,安徽,合肥,230009;合肥工业大学,计算机与信息学院,安徽,合肥,230009 |
| |
| 基金项目： | 合肥工业大学校科研和教改项目 |
| |
| 摘 要： | 文章提出了一种基于交集关系原理的算法叫做交集算法,它与类Apriori算法本质上互补。这种算法的最大优势是不需要产生大量的候选频繁访问模式,就可以直接生成最大频繁访问模式,因此在挖掘过程中也就不需要反复扫描原始数据库来计算各个候选频繁访问模式的支持度计数;经理论分析和试验证明,交集算法具有一定的理论意义和应用价值。
|
| 关 键 词： | Web日志挖掘 类Apriori算法 交集算法 最大前向引用 频繁访问模式 |
| 文章编号： | 1003-5060(2006)12-1511-05 |
| 修稿时间： | 2005-12-05 |
Discovery of user frequent access patterns based on the intersection algorithm for Web mining |
| |
| GUO Wei,OUYANG Yi-ming,GUO Jun. Discovery of user frequent access patterns based on the intersection algorithm for Web mining[J]. Journal of Hefei University of Technology(Natural Science), 2006, 29(12): 1511-1515 |
| |
| Authors: | GUO Wei OUYANG Yi-ming GUO Jun |
| |
| Abstract: | In the paper,a sequential patterns discovering algorithm called the intersection algorithm is brought forward based on the principle of intersection relation.The presented algorithm is in fact supplements the algorithm similar to the Apriori.The most advantage of this algorithm is that it does not produce large amount of candidates of frequent access patterns but can directly creat the frequent access patterns,so it need not take count of the number of each candidate of frequent access patterns by scanning the original database.Theoretic analysis and experiment results show that the introduced intersection algorithm is valuable. |
| |
| Keywords: | Web log mining algorithm similar to the Apriori intersection algorithm maximal forward reference frequent access pattern |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
