The K-means algorithm is a classical unsupervised learning method used to partition datasets into K clusters, where each data point belongs to the nearest cluster center. The main steps of the algorithm include initializing the clustering center, iterative updating, and reassigning the data points. First, K data points are randomly selected as the initial cluster center; then each data point is assigned to the class of the nearest cluster center of each class, usually the mean of all data points in the class; and finally, repeat iteration until the cluster center does not change significantly or reaches the preset number of iterations. With its simple, efficient and understandable features, K-means algorithm is widely used in data analysis and user clustering.MATLAB simulation shows that under the condition of certain evaluation criteria, the English learning platform based on K-means algorithm can informatize English learning The learning efficiency of feasibility and learning informatization is better than that of ordinary teaching mode.