The teaching of the course "Fundamentals of Concrete Structures their interests. This article deeply integrates machine learning with concrete teaching, and constructs a new teaching path of four-step fusion: predictive modeling-constructing a nonlinear mapping between input parameters and mechanical responses, breaking through the shackles of traditional formulas; interpretive analysis-quantifying the contribution of variables through interpretable machine learning models, transforming empirical coefficients into intuitive expressions of physical logic; discovery of laws-using symbolic regression to mine mathematical formulas that are both accurate and interpretable, and to restore the exploration process of scientific laws; intelligent design-generating multi-objective equilibrium solutions based on genetic algorithms, achieving a leap from manual trial and error to intelligent optimization. The new teaching path reshapes the knowledge learning model with data thinking, realizing the transformation from static standardized formulas to dynamic renewable models. Reconstruct the teaching methodology, and realize the transformation from one-way teaching to interactive exploration between teachers and students. Upgrading the ability evaluation system, from result assessment to process tracking, and ultimately promoting students to transform from "formula applicators" to "science discoverers", provides new ideas for the cultivation of interdisciplinary talents in the context of new engineering.