To ensure the video QoS(quality of service) of the Web

DiffServ(differentiated service) methods are always used at the edge of network. Current label system of DiffServ is static and not so intelligent. In order to solve this problem and improve the Subject QoS

knowledge-system-based video quality guarantee model is provided and a system is built. In this system

the video adaptation is guided intelligently with the knowledge acquired at different phases of knowledge creation processes and (m

k) model is applied in label design so as to mapping to knowledge. Testing results have shown this model can satisfy the user preference and ensure video quality effectively. So it is proved that knowledge plays an important role and brings more intelligence to our system.