[Objective] Solve the application problem of LIME and its evolutionary algorithms in data storytelling, in order to better play the explanatory function of data stories. [Methods] Explore the principles, applications, and evolution strategies of the LIME algorithm, and based on this technical theory, construct a data storytelling process assisted by LIME related algorithms. Collect a partial dataset for identifying cats and dogs on the Kaggle platform, and utilize the data source to train interpretable models. Apply the data storytelling method fused with the LIME algorithm to the interpretation of image classification results. [Results] Taking the "Tabby Cat" image as the analysis object, based on the LIME interpretation results and the storytelling development curve, it can be determined that the important features that affect the prediction results are M-shaped stripes, black eyes, and pink nose, and the number of key superpixels is 2. [Limitations] The optimization of feature recognition and automated generation of data stories need to be solved. [Conclusions] The application of LIME related algorithms in the data storytelling process helps to transform model predictions and interpretation results into interpretable stories, thereby better conveying data analysis results.