This paper introduced concepts of Meta Services and Meta Process, which can largely simplify the complexity of travel services composition. And corresponding to these concepts, a dynamic generation algorithm for meta process is presented instead of predefining a rigorous workflow model, which used Markov Decision Processes (MDP) referring to transition probability of meta service and the tourists? preference represented by preference reward function. And differently with some AI planning method, this approach more adept to the stochastic and dynamic environment and deals with the various requirements of tourists more effectively and flexibly. Additional this approach also can resolve similar problems in other services computing domain.