US 12,322,087 B1
Multi-scale autoencoders for semiconductor workpiece understanding
Matthew David Conrad, Cary, NC (US); and Edward Robert Van Brunt, Cary, NC (US)
Assigned to WOLFSPEED, INC., Durham, NC (US)
Filed by Wolfspeed, Inc., Durham, NC (US)
Filed on May 24, 2024, as Appl. No. 18/674,427.
Int. Cl. G06T 3/40 (2024.01); G06T 7/00 (2017.01); H01L 21/66 (2006.01)
CPC G06T 7/001 (2013.01) [G06T 3/40 (2013.01); H01L 22/12 (2013.01); G06T 2207/20016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/20224 (2013.01); G06T 2207/30164 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method for inspecting semiconductor workpieces, the method comprising:
obtaining a workpiece image of a semiconductor workpiece;
providing the workpiece image as input to a machine-learned encoding model;
obtaining an output from the machine-learned encoding model, the output comprising an encoding corresponding to the semiconductor workpiece; and
determining one or more characteristics of the semiconductor workpiece based at least in part on the encoding, the one or more characteristics associated with a crystalline material feature; and
modifying a semiconductor manufacturing process based at least in part on the encoding.