A probabilistic coverage decision-theoretic rough set (PCDTRS) model is proposed in this study to deal with the two main issues in rule acquisition from decision table, i.e., contradiction of extracted rules and redundancy of override sample. Firstly, the basic theories of the decision-theoretic rough set (DTRS) model including the attribute and value reduction algorithms are presented. Subsequently, the probabilistic coverage model is raised based on the DTRS model, and three levels covered matrixes meeting the needs of value reduction are proposed to resolve the aforementioned problems. Finally, the results of a series of experiments on Chinese cookbook nutrition illustrate the feasibility and effectiveness of the PCDTRS model. Compared with other models, the reduction strength and the number of conflicting rules using the PCDTRS model are higher and fewer respectively.