A Three-Way Clustering Method Considering Structural Characteristics of Decision Objects

In order to deal with the problem of multi-attribute decision-making, from the perspective of the internal structural characteristics of the decision object based on the nature and characteristics of the structured data of the decision object, we construct a three-way clustering model considering the structural characteristics of the decision object, and then exploit grey structural incidence and a double-evaluation function three-way clustering model to design a three-way clustering threshold pair (3WCTP) algorithm to calculate the threshold pair. Finally, a case of development of R&D activities in various provinces is used to verify the effectiveness of the model. The results show that the proposed method fully considers the internal structural characteristics of the decision object, and it can measure the similarity of the internal structure of the decision objects and provide a new methodological support for the grey incidence analysis of the decision objects.