To optimize the extraction process of the tail of Angelica sinensis by BP neural network (BP-ANN) combined with orthogonal experiment.The extraction frequency,the solid-liquid ratio and the extraction time were taken as factors.CRITIC (criteria importance though intercrieria correlation) was used to calculate the comprehensive scores of the multi-indicators of the content and four active components of chlorogenic acid,ferulic acid,imperatorin and butenyl phthalide.Using comprehe-nsive score as an evaluation indicator,the BP neural network model was established by orthogonal experiment design,and the optimal extraction process of the tail of A. sinensis was predicted through network training.The optimized extraction process of the tail of  A. sinensis was carried out by adding 9.6 times of water,extracting 3 times and 67 minute each times.The relative error between the network predicted value and the actual measured value of the test sample was less than 1%.The established mathematical model can analyze and predict the extraction process of the tail of A. sinensis. The obtained process is stable and feasible,and can effectively extract the active ingredients in the tail of A. sinensis.