Abstract: Soil mechanical stratification based on cone penetration test data (such as soil classification index Ic) is widely applied. However, soil stratification based on soil classification index depends on engineering experience, and the subjective uncertainty is prominent. Soil mechanical stratification is not necessarily consistent with the stratification based on borehole sampling. Although Bayesian soil stratification method based on Ic data can reasonably consider the influence of uncertainty on soil mechanical stratification, it is inconvenient for engineering applications because of its complex calculation process and low calculation efficiency. In this paper, an efficient optimization identification method based on Ic data and the joint probability density function of soil mechanical profile parameters is proposed under the framework of Bayesian learning, the rationality and validity of the proposed method are illustrated by a set of CPT data obtained from a subway section in Hangzhou and simulation data, and the stratification principle and characteristics of the proposed method are illustrated with the soil profile identification results. Compared with the existing Bayesian soil stratification method, the calculation efficiency of the proposed method for identifying the soil mechanical stratification based on the Ic data is significantly improved, and it is suitable for analyzing CPT data with different sounding depths. The calculation procedure of the proposed approach is relatively simple and is convenient for engineering applications.