Bayesian network's parameter update method based on maximum likelihood estimates

A probability parameter updating method for Bayesain network with fixed structure and initial probability parameters is discussed, when new data set is available. It should reserve the original probability parameters as much as possible and also reflect the probability distribution contained in data set furthest. Principle of parameters updating based on MLE is discussed, algorithms for complete data set and incomplete data set are put forward. A case study is carried out to show how the algorithm works.