This paper attempts to classify tennis games into 58 winning patterns for training purpose. It bases on tracking ball movement from broadcasting tennis video. Trajectory and landing position are used as the basic features for classification. We use an improved Bayesian networks to classify the landing position of different patterns. Intelligent agents are used to combine trajectories and landing positions as two features are in different dimensions. Semantic labels are granted after classification. The aim of the analysis is to provide a browsing tool for coachers or other personnel to retrieve tennis video clips.