A good teacher-student relationship is an important part of the educational community and a symbol of spiritual civilization. Effective teaching in the classroom requires even better communication and interactive actions between teachers and students, and measures to improve teacher-student relationships are proposed for the sake of classroom teaching. In this paper, an adaptive learning system based on cognitive diagnosis is constructed, which utilizes the DINA cognitive diagnosis model to obtain the learner’s cognitive structure, perceive the changes in the student’s cognitive structure in real time, and allow the learning task to make adaptive adjustments. The K-means clustering algorithm randomly selects the number of K objects as the center of mass for the initial clustering, and after the output of clustering and layering results, the students will be classified according to the categorization of the student’s learning needs. The students are divided into three groups that are similar within the group. By doing this, the learning task becomes adaptive, and appropriate learning tasks are adjusted for different levels of learners. Most of them believe that the adaptive learning system can help learners improve their learning efficiency and are very satisfied with the effectiveness of the system. The proportion of teachers who were satisfied with overall perception reached 89.1%, and the proportion of students who were satisfied was also high. The overall perceived effect of the improved teacher-student relationship is excellent, suggesting that the adaptive learning system can effectively improve the teacher-student relationship.