In this paper, a structure-adaptive piece-wise linear segments representation of time series is proposed. The algorithm can automatically produce the K piece-wise segments of time series, which can approximate the original time series. The time series prediction method based on support vector machine is proposed to predict coal price. The experiment results show that each error index of our proposed algorithm is less than that of any other model. The predictive accuracy is improved greatly, which can provide reference for pricing mechanism of coal enterprises.