公开(公告)号：US11699227B2

公开(公告)日：2023-07-11

申请号：US17384366

申请日：2021-07-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Heungsuk Oh ,  Mincheol Kang ,  Sangwook Park

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/50 ,  G06T7/60 ,  G03F1/36 ,  G06V10/30 ,  G06V10/42 ,  G06V10/88 ,  G06F18/22 ,  G06F18/214

CPC classification number: G06T7/0006 ,  G03F1/36 ,  G06F18/2148 ,  G06F18/22 ,  G06T7/50 ,  G06T7/60 ,  G06V10/30 ,  G06V10/42 ,  G06V10/88 ,  G06T2207/10061 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148

Abstract: A method of fabricating a semiconductor device includes generating a mask based on second layout data obtained by applying an OPC model to first layout data and performing a semiconductor process using the mask on a substrate, obtaining a plurality of pattern images by selecting a plurality of sample patterns from the substrate, selecting sample images corresponding to the sample patterns from each of the first layout data, the second layout data, and simulation data obtained by performing a simulation based on the second layout data, generating a plurality of input images corresponding to the sample patterns by blending the sample images corresponding to the sample patterns, respectively, and generating an error prediction model for the OPC model by training a machine learning model using a data set including the input images and the pattern images.

公开(公告)号：US11150551B2

公开(公告)日：2021-10-19

申请号：US16855083

申请日：2020-04-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Heungsuk Oh ,  Joobyoung Kim ,  Sanghun Kim ,  Guk Hyun Kim

IPC: G06F30/392 ,  G03F1/36

Abstract: A computer-readable medium includes a program code that, when executed by a processing circuitry, causes the processing circuitry to divide a layout of a semiconductor chip into a plurality of patches, generate a plurality of segments from a layout of each of the plurality of patches, wherein a first patch of the plurality of patches includes first segments and a second patch of the plurality of patches includes second segments, calculate hash values respectively corresponding to the first segments and the second segments by using a hash function, calculate bias values of segments having a first hash value from among the first segments, calculate a representative value based on the bias values, and apply the representative value to the segments having the first hash value from among the first segments.

公开(公告)号：US20250004361A1

公开(公告)日：2025-01-02

申请号：US18437779

申请日：2024-02-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Woo-Yong Cho ,  Hun Kang ,  Sangwook Kim ,  Useong Kim ,  Heungsuk Oh ,  Hee-Jun Lee ,  Jeeeun Jung

IPC: G03F1/36

Abstract: Disclosed are semiconductor fabrication methods and optical proximity correction (OPC) methods. The semiconductor fabrication method comprises performing OPC on a design pattern of a layout to generate a corrected layout, and forming a photoresist pattern on a substrate by using a photomask manufactured with the corrected layout. Performing the OPC includes generating shape points on a contour of the design pattern, producing a hash value of the shape point, selecting a first unique shape point that represents first shape points, determining a first correction bias of the first unique shape point, and creating a correction pattern by applying the first correction bias in common to the first shape points. Producing the hash value includes generating a query range around a target shape point and, based on geometry analysis in the query range, producing the hash value.

公开(公告)号：US20220180503A1

公开(公告)日：2022-06-09

申请号：US17384366

申请日：2021-07-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Heungsuk Oh ,  Mincheol Kang ,  Sangwook Park

IPC: G06T7/00 ,  G06K9/62 ,  G06T7/50 ,  G06T7/60 ,  G06K9/82 ,  G06K9/52 ,  G06K9/40 ,  G03F1/36

Abstract: A method of fabricating a semiconductor device includes generating a mask based on second layout data obtained by applying an OPC model to first layout data and performing a semiconductor process using the mask on a substrate, obtaining a plurality of pattern images by selecting a plurality of sample patterns from the substrate, selecting sample images corresponding to the sample patterns from each of the first layout data, the second layout data, and simulation data obtained by performing a simulation based on the second layout data, generating a plurality of input images corresponding to the sample patterns by blending the sample images corresponding to the sample patterns, respectively, and generating an error prediction model for the OPC model by training a machine learning model using a data set including the input images and the pattern images.