In the paper <Tracking and forecasting milepost moments of the epidemic in the early-outbreak: framework and applications to the COVID-19> , we proposed a method to predict "turning points", whose main idea is using the change velocity of infection rate (InfectionRateVelocity) and the change velocity of completion rate(RemovedRateVelocity) to forcast newly diagnoses cases and number of cases treated in the hospital in the future. Here, we proposed one of the algorithms to calculate the change rate and then make the prediction, which is the method we used in our paper mentioned above. The original data collected from China CDC is also included.