During the assembly process, there are occasional human errors that can lead to products with screws not fully tightened or with gaps in the accessories. For such repetitive assembly defect detection, the introduction of automation will quickly improve product omission problems and further improve the efficiency of manpower allocation.By applying Solomon SolVision's Segmentation technology, the image of screws and other assembly positions is located, and the preliminary identification and classification of the assembly dovetail degree is performed. The AI model is trained to quickly identify the completeness of the assembly of electronic components. With the increase in the number of image samples learned, its detection efficiency can also be continuously optimized, effectively improving the product quality yield.