In order to further improve the efficiency of sorting robots, an algorithm based on artificial intelligence design is evaluated. On the basis of determining the design requirements of belt conveyor and motor selection, the reverse device and return device and camera bracket sorting car are redesigned, and the sorting car is further analyzed by finite element method. All programs are written based on PLC. The results show that the recognition and sorting rate of 100 express surface orders with the same specifications reaches 100% and the sorting rate reaches 94% by analyzing the data recorded in the database, and the average time consumed in each recognition process is 0.0493097 s and 0.047133 s, respectively, in basic and simulated recognition. The difference did not exceed 0.01 s, and the time was basically the same. Therefore, the scheme verifies the rationality of mechanical structure design, visual scheme design, and control system design.