Investigation on Knowledge Reduction and Rule Fusion Based on Probability Graph Model

Abstract

With the complexity of social things, the uncertainty of things is also increasing, the study of fuzziness and uncertainty can effectively promote social development. Knowledge reduction and rules in rough set can realize the research and analysis of uncertain things, but in the current situation, the separation of the two hinders the in-depth study of uncertain things. The probabilistic graph model has realized the effective combination of probability theory knowledge and graph theory knowledge, can realize the effective processing of various variables, and provides a new solution for the study of knowledge reduction and rule fusion. The purpose of this paper is to study the fusion of knowledge reduction and rules with the help of probability graph model, so as to promote the continuous expansion of their practical application. Based on the probabilistic graph model, this paper first discusses the concepts of probabilistic graph model, knowledge reduction and decision rules, then proposes a fusion algorithm based on the existing research data, and finally verifies and analyzes the algorithm through experiments, proving the correctness of the algorithm. The experimental results show that the proposed fusion algorithm based on the probabilistic graph model solves a series of problems in knowledge reduction and rule fusion, and promotes the efficient fusion of knowledge reduction and decision rules.