FML-based type-2 fuzzy ontology for computer go knowledge representation

In this paper, an Fuzzy Markup Language (FML)-based type-2 fuzzy ontology is proposed to represent the computer Go knowledge, including an FML transformation mechanism, a type-2 fuzzy set construction, and a type-2 fuzzy set inference mechanism. The FML transformation mechanism transforms the generated smart game format (SGF) files into an FML-based document to describe the computer Go ontology. The type-2 set construction is responsible for building the type-2 fuzzy sets. Based on the built FML-based document and type-2 fuzzy sets, the type-2 fuzzy set inference mechanism infers the possibility of the game´s winning rate. It is hoped that the proposed idea are feasible for inferring the winning rate of the games in the future.