In order to achieve the evaluation of human rehabilitation training movements, a human 3D pose estimation network integrating keyframe enhancement method (KFEM) and CTRAMM module is proposed, and a matching algorithm based on position and type (LTDTW) is developed to evaluate rehabilitation movements. KFEM determines keyframes and adjusts their weights by calculating the coordinate transformation of human keypoints. The CTRAMM module dynamically learns different topological structures, improving the feature representation ability of the model. LTDTW improves the accuracy of sequence matching through adaptive weight coefficients. The experimental results on different datasets have validated the effectiveness of the proposed method.