Fuzzy comprehensive evaluation method for knowledge graph recommendation system

The invention discloses a fuzzy comprehensive evaluation method for a knowledge graph recommendation system, and the method comprises the following steps: selecting an evaluation index of the knowledge graph recommendation system, and constructing an evaluation index system of the knowledge graph recommendation system; calculating a weight relationship among the indexes; constructing a fuzzy evaluation matrix according to the evaluation index system of the knowledge graph recommendation system; and performing multi-level fuzzy comprehensive evaluation on the knowledge graph recommendation system through combination of the fuzzy evaluation matrix and the weight relationship between the indexes to obtain an evaluation result. A set of multi-level knowledge graph recommendation system evaluation index system is established on the basis of reliability, functionality, efficiency and economy, four first-level indexes, eight second-level indexes and fifteen quantitative indexes are included, classification is clear,