模糊ID3算法是模糊决策树归纳中比较普遍和有效的启发式算法.以模糊ID3算法为例,分析了属性之间的冗余信息对构建模糊决策树的影响,并提出一个扩展算法,要求所选择的测试属性不仅和类的交互信息较大,而且和祖先节点上用过的属性之间的交互信息较小.实验结果表明:扩展算法优于模糊ID3算法. The fuzzy ID3 algorithm is a more general and effective heuristic in the induction of fuzzy decision trees.With the fuzzy ID3 algorithm as an example, the influence of redundant information between attributes on the construction of fuzzy decision tree is analyzed and an extended algorithm is proposed, The selected test attribute not only has more interaction information with the class but also has less interaction information with the attributes used by the ancestor nodes.The experimental results show that the extended algorithm is better than the fuzzy ID3 algorithm.