In order to solve the problems such as too many nodes and low compressibility in the tree structure constructed by CANonical-order tree (CAN-tree) algorithm, an improved CAN-tree algorithm based on restructure was proposed. Firstly, a tree structure was constructed directly with canonical-order, which scans the database only once in the frequent itemset mining algorithm. Then, in order to get a tree structure with high compressibility, a pruning operation was used with support in desending order to restructure the tree. Finally, frequent itemsets were mined out for the reconstructed tree structure. The experimental results show that compared with original CAN-tree algorithm, the number of nodes constructed by the improved CAN-tree algorithm is reduced to less than 20%,and the execution efficiency is improved by 4 to 6 times. The proposed algorithm shortens the execution time of the frequent itemset mining algorithm and effectively compresses the tree structure in it.

Concerning the problem of lacking completeness and accuracy in the individuals inference information and scientificity in the overall integration results, which exists in the process of inferring Conditional Probability Table (CPT) in Bayesian network according to expert knowledge, this paper presented a method based on the Dempster-Shafer/Analytic Hierarchy Process (DS/AHP) to derive optimal conditional probability from the expert inference information. Firstly, the inferred information extraction mechanism was proposed to make judgment objects more intuitive and judgment modes more perfect by introducing the knowledge matrix of the DS/AHP method. Then, the construction process of Bayesian network was proposed following an inference sequence of "anterior to later". Finally, the traditional method and the presented method were applied to infer the missing conditional probability table in the same Bayesian network. The numerical comparison analyses show that the calculation efficiency can be improved and the accumulative total deviation can be decreased by 41% through the proposed method. Meanwhile, the proposed method is illustrated to be scientific, applicable and feasible.