US 12,147,155 B2
Mask correction method, mask correction device for double patterning and training method for layout machine learning model
Min-Cheng Yang, Tainan (TW); and Chung-Yi Chiu, Tainan (TW)
Assigned to UNITED MICROELECTRONICS CORP., Hsinchu (TW)
Filed by UNITED MICROELECTRONICS CORP., Hsinchu (TW)
Filed on Jun. 28, 2021, as Appl. No. 17/359,687.
Claims priority of application No. 202110557042.5 (CN), filed on May 21, 2021.
Prior Publication US 2022/0373877 A1, Nov. 24, 2022
Int. Cl. G03F 1/36 (2012.01); G03F 7/00 (2006.01); G06F 30/27 (2020.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06F 119/18 (2020.01); G06F 119/22 (2020.01)
CPC G03F 1/36 (2013.01) [G03F 7/705 (2013.01); G03F 7/70516 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06F 30/27 (2020.01); G06F 2119/18 (2020.01); G06F 2119/22 (2020.01)] 13 Claims
OG exemplary drawing
 
1. A mask correction method for double patterning, comprising:
obtaining a target layout;
decomposing the target layout into two sub-layouts, which overlap at a stitch region, wherein a size of the stitch region is analyzed by a layout machine learning model according to the target layout, and the layout machine learning model is established according to a three-dimensional information after etching; and
performing an optical proximity correction (OPC) procedure on the sub-layouts.