The Generalized Weng Model is one of the basic models for oil production forecasting. Professor Chen Yuanqian first proposed the linear iterative trial-and-error method to solve the generalized Weng Model, and scholar Zhao Lin proposed the method to solve the Weng model based on binary regression. In this paper, a new method for solving Weng Model is put forward. Taking Liaohe Oilfield in China as an example, the process and results of the three methods are compared, and the advantages and disadvantages of the three methods are analyzed. The results show that when the original linear iterative trial and error method solves the model, it needs to simulate the value of parameter b with computer software, and then select a judgment criterion to find the optimal b value. In this paper, a method based on binary regression is proposed which can directly calculate parameter<i> b</i>. The new method can directly calculate the parameter <i>b</i> better than the method based on binary regression. The method in this paper is to fit all the data at one time, avoiding the above two kinds of uncertainties, and the calculation workload is small and can be realized by EXCEL, which is convenient for technical personnel.