朴素贝叶斯分类是一种简单而高效的分类模型，然而条件独立性假设在现实中很少出，致使其性能有所下降。通过引入关联规则，从两方面来改善朴素贝叶斯分类的性能。一方面，通过对关联规则的挖掘，发现条件属性之间的关联关系，并且利用这种关联关系弱化朴素贝叶斯的独立性假设；另一方面，通过关联规则的置信度，给朴素贝叶斯加权。 -Naive Bayesian classifier is a simple and efficient classification model, the conditional independence assumption, however, rarely in the real world, resulting in decreased performance. Through the introduction of association rules, two ways to improve the performance of naive Bayesian classifier. On the one hand, by association rule mining, found the association between condition attributes and use this association weakened Bayesian independence assumption　the other hand, by association rule confidence, to the simple Bayesian Alaska right.