To address the parameter optimization problem in the three-bench excavation method for tunnels in shallow-buried soft surrounding rock (Class V), the following influencing factors were selected: the ratio of bench advance to half-span R, cohesion, internal friction angle, elastic modulus of the surrounding rock, and Poisson's ratio. Through multi-level orthogonal finite element analysis and design, the crown settlement values corresponding to different parameter combinations were obtained. An adaptive particle swarm optimization (APSO algorithm) was applied to optimize the surrounding rock parameters, ultimately establishing an optimized relationship between surrounding rock settlement and the advance length per stage in the three-bench excavation method. Using Poisson's ratio as an influencing factor, multi-level orthogonal finite element analysis was employed to determine the crown settlement values under various parameter combinations. An APSO-optimized support vector regression (SVR) model was developed to construct a prediction model for crown settlement during three-bench excavation. A comparative analysis was conducted using a conventional SVR model. Furthermore, an APSO-SVR model was established with crown settlement as the input and the strength ratio R, cohesion, internal friction angle, elastic modulus, and Poisson's ratio as outputs, enabling the inversion of ratio R. Based on an actual engineering case, multi-level orthogonal finite element analysis was applied for inversion analysis. Using the same project, Midas software was utilized to validate the accuracy of the limiting advance distance parameters in the sequential excavation process. The results show: the APSO-SVR model has lower error and higher accuracy than the SVR model, validating its optimization. Midas inversion shows a 0.72% difference between the simulated and specified arch top settlement values, confirming the optimized parameter scheme's accuracy. The inversion optimization model based on APSO-SVR for three-bench excavation has high accuracy and can guide similar project safety construction.