Lithium-ion batteries have become a research hotspot in the field of battery life prediction due to their small size, light weight, high capacity and long life. In this study, a hybrid strategy combining Random Forest (RF) and Support Vector Machine (SVM) algorithms is proposed to predict the Remaining Useful Life (RUL) of lithium-ion batteries. The strategy exploits the integration properties and feature importance assessment capabilities of Random Forest, while combining the advantages of SVM in dealing with high-dimensional data and nonlinear problems. In addition, Random Forest features are used to reduce the risk of overfitting and improve the robustness of the model to outliers and noise. Through experimental validation using datasets provided by Toyota Motor Corporation and Stanford University, the results show that the hybrid strategy proposed in this study exhibits superior performance compared to the Random Forest SVM alone prediction method.