In this paper, firstly, the complementary grouping method is realized through the complementary grouping of cooperative shared learning supported by cognitive diagnosis, the knowledge relationship dependency graph construction, expected response pattern construction, and dynamic stratification process, and then the complementary grouping method is realized. Then, a cognitive mapping embedded resource sharing platform based on memory network and graph attention is proposed, including test factors based on graph attention and student factors based on memory network. The results show that in the FrcSub dataset DINA model deviates from the other two models in the 1st, 3rd, 8th, 12th, and 14th question prediction effects, and the overall question prediction performance is stable with a deviation of ±0.05. The cognitive mapping embedded resource sharing platform is efficient and feasible and also provides a new way of thinking for the development of macro education in universities.