In this talk, we will provide a concise introduction to the Cucker-Smale model and the Random Batch Method (RBM), a computational technique designed to reduce complexity from $\mathcal{O}(N^2)$ to $\mathcal{O}(N)$. It is notable that for large-scale interacting particle systems, the mean-field limit is a well-known approximation describing complex systems from the perspective of distributions. A natural question arises: Does the numerical scheme maintain a consistent structure as the number of particles $N\to\infty$? Building on this, we explore the mean-field limit of the Random Batch Cucker-Smale model. Different from the classical mean-field limit analysis, the chaos in this model is imposed at discrete time and is propagated to discrete time flux. By leveraging the flocking property of the Cucker-Smale model and insights from combinatorics, we separately examine the limits as the number of particles $N\to\infty$ and the discrete time interval $\tau\to 0$. The Wasserstein distance is used to quantify the discrepancy between the approximation limit and the original mean-field limit. Additionally, we propose the RBM-gPC method, which integrates RBM with generalized Polynomial Chaos (gPC) expansion to approximate stochastic mean-field equations while preserving the positivity and momentum of the mean-field limit with random inputs.