Overcharge is recognized as a significant factor contributing to the degradation and potential thermal runaway of Li-ion cells. In this study, a novel approach is proposed to estimate the extent of overcharge-induced degradation in 18,650-type Li-ion cells with NCA cathodes and graphite anodes. Experimental results reveal abnormal heat generation and capacity loss due to overcharge-induced degradation. Using Differential Thermal Voltammetry (DTV) and Distribution of Relaxation Times (DRT) methods, ten degradation factors (DFs) that reflect the extent of degradation are identified. Through Pearson correlation analysis, the height of peak P1 in DTV and S2 in DRT are identified as the most indictive parameters to estimate degradation. Next, a predictive model based on Kriging deep learning method is developed using these parameters, which enables precise estimation. Validation results for the model demonstrate outstanding predictive accuracy, with a mean absolute percentage error (MAPE) of 3.25 % and a root mean square error (RMPE) of 3.62 %. The proposed methodology not only offers a robust approach to estimate overcharge-induced degradation of Li-ion cells, but also provides valuable insights for enhancing the monitoring and management capabilities of battery system.