When the manufacturing industry is dealing with information technology, it has to face a large number of parameters and frequent adjustments. This study proposed artificial intelligence models to find out the hidden rules behind a large number of customized labels, through data processing and model building. Model and parameter experiments are used to improve the effectiveness of artificial intelligence models, and the method of cyclic testing is adopted to increase the diversity of the test set. The results of this paper, we integrate each stage and an auxiliary decision-making is established. The contributions of this paper, can improve the problem with reducing production line shutdown and improve factory productivity. The accuracy rate of the artificial intelligence model can be increased to 95%. The number of stoppages is reduced from 4 times to 1 time per month. Under full capacity, this assist the decision-making system can reduce loss cost.