Mining Association Rules Based On The Extended Model Of Concept Lattice

Knowledge Discovery in Databases (KDD) is the hot subject that databases and artificial intelligence field are studied. Mining association rules is an important branch of KDD. There are problems about time and space and problems about show the results in the classical and other algorithms of mining association rules.Concept lattice represents knowledge with the relation between the intensions and the extensions of concepts, and the relation between the generalization and the specialization between concepts, thus it is an efficient tool for KDD. By introducing equivalent intension into Golois concept lattice, the Extending model of concept lattice is gotten which represent the knowledge more clearly and distinctly.The methods of how to mining association rules by Extended model concept is expatiated in this dissertation. The contents is as follow.(1) The method of extend and realization about concept lattice: Quantitative, and relative reduced are Introduced, more convenient discover rules. Quantitative is reduce the space of extents, relative reduced reduce the space of intents, those let it has better space performance. The algorithm of generate extended concept lattice is given in this dissertation.(2) The research and algorithm of mining association rules in extended concept lattice: The algorithm of mining association rules is given in the dissertation. Finally, the results of experiment of the algorithm about space and time performance is provided.