Accurate evaluation of rock strength, especially real-time strength prediction during tunnel construction, is a key basis for ensuring engineering safety and optimal design. With the development of intelligent construction technology, machine learning prediction methods based on drilling parameters have shown great potential in the field of rock strength assessment. However, the black box characteristics of traditional machine learning models limit their credibility and application value in engineering practice. To this end, this study proposes a rock strength prediction method based on interpretable artificial intelligence for the first time. The decision-making mechanism of the XGBoost model is analyzed by SHAP analysis technology to achieve transparency and interpretability of the prediction process. The results show that the XGBoost model has achieved good results in rock strength prediction, and the prediction accuracy of the test set reaches 75.71 %. More importantly, the SHAP value analysis quantitatively reveals the contribution mechanism of each input parameter to the prediction results. It is found that the average drilling speed is dominated by the contribution of 25.67 %, while the total contribution of the parameter variability index ( standard deviation class ) is as high as 49.70 %. This finding breaks through the limitation of traditional cognition that only the mean of parameters is concerned. This study reveals the general law of drilling parameters changing with drilling depth, realizes the prediction of rock strength while drilling, and is of great significance to promote the interpretability and engineering application of underground engineering parameter prediction.