Research on Case Knowledge Matching Based on K-means Cluster and Random Forest

Knowledge, as a core resource for value creation in enterprises, is growing in volume, increasing the complexity of knowledge application. Knowledge matching can be implemented for case knowledge base to improve the utility of case base knowledge application. In this paper, a case knowledge matching method is proposed, which adopts the information gain method to simplify the set of case attributes, and compresses the computational space based on K-means clustering horizontally; and then implements the matching of the problem to be solved through the vector similarity computation, and combines with the random forest algorithm to determine the final solution. The experimental results show that the matching efficiency and effectiveness of the method is progressive.