To optimize the extraction process of black pepper by Box-Benhnken response surface method combined with BP neural network based on traditional Chinese medicine fingerprint technology.The comprehensive evaluation indexes were obtained by weighting the total peak area standardization value of HPLC fingerprint of black pepper,the peak area normalization value of piperine and the similarity of fingerprint.On the basis of single factor experiment,the extraction process of black pepper was optimized by Box-Benhnken response surface methodology.The optimal extraction process was as follows:ethanol concentration was 90%,solid-liquid ratio was 1∶40 (g/mL) and ultrasonic time was 40 min.BP neural network was trained,verified and predicted by selecting the comprehensive evaluation indexes obtained by Box-Benhnken response surface method.The optimal extraction process was as follows:ethanol concentration was 100%,solid-liquid ratio was 1∶30 (g/mL) and ultrasonic time was 40 min.The validation results of three groups of optimal extraction process of black pepper showed that the comprehensive evaluation index of BP neural network was 0.895,which was better than that of Box-Benhnken response surface method,i.e.0.885.Based on the fingerprint technology of traditional Chinese medicine,the Box-Benhnken response surface method combined with BP neural network can provide a new idea for the optimization of black pepper extraction process and obtain the best extraction scheme.