基于事例的自适应关联规则挖掘模型的研究

认为传统的关联规则挖掘模型主要是针对结构化数据 ,其可信度和支持度不能随环境的变化自适应调节 ,即缺乏自适应性 ,而现实中还存在大量非结构化的数据 .针对传统发现模型的不足提出了一个基于事例的自适应关联规则发现模型 ,它不仅可以处理对非结构化数据的数据挖掘 ,而且还可以随着环境的变化自适应调节支持度和可信度 .

Study on Mining Model of Case-based Adaptive Association Rules

In data mining, the efficiency of traditional association rules mining model is lower in the stage of data preparation, especially when there are a lot of data information and non-structured data. The support and confidence of the traditional model can't adjust adaptively with the variation of environment, and namely, it lacks adaptability. In order to overcome the deficiency, a case-based discovering model of adaptive association rules is put forward, and its structure and characteristics are presented. It not only raises the efficiency in the stage of data preparing by using the past cases and expert experience, but also adjusts support and confidence with the variation of environment.