Lithography model generating method based on deep learning, and mask manufacturing method including the lithography model generating method
AssigneeSamsung Electronics Co., Ltd.
InventorsSangchul Yeo, Jaewon Yang, Hyeok Lee
Life of this patent
Estimating the term…
Abstract
A reliable lithography model generating method reflecting a mask bias variation and a mask manufacturing method including the lithography model generating method are provided. The lithography model generating method includes preparing basic image data for learning, preparing transform image data that indicates a mask bias variation, generating a lithography model by performing deep learning by combining the basic image data and the transform image data, and verifying the lithography model.
Claims19
A lithography model generating method based on deep learning, the lithography model generating method comprising:
- preparing basic image data for learning;
- preparing transform image data that indicates a mask bias variation;
- generating a lithography model by performing deep learning by combining the basic image data and the transform image data;
- and
- verifying the lithography model,
- wherein the transform image data is image data transformed from the basic image data such that the transform image data indicates a process variation.
A lithography model generating method based on deep learning, the lithography model generating method comprising:
- preparing basic image data for learning;
- preparing transform image data that indicates a mask bias variation;
- generating a lithography model by performing deep learning by combining the basic image data and the transform image data;
- verifying the lithography model;
- and
- adjusting a recipe with respect to the lithography model,
- wherein the transform image data is generated through an image augmentation method from the basic image data such that the transform image data indicates a process variation.
A mask manufacturing method comprising:
- generating a lithography model based on deep learning;
- generating an optical proximity correction (OPC) ed layout by performing OPC on a mask layout by using an OPC model obtained based on the lithography model;
- transferring the OPCed layout as mask tape-out (MTO) design data;
- preparing mask data based on the MTO design data;
- and
- exposing a substrate for a mask based on the mask data,
- wherein the generating of the lithography model comprises:
- preparing basic image data for learning;
- preparing transform image data that indicates a mask bias variation;
- generating the lithography model by performing deep learning by combining the basic image data and the transform image data;
- verifying the lithography model;
- and
- adjusting a recipe with respect to the lithography model,
- wherein the lithography model comprises an optical proximity correction (OPC) model or a process proximity correction (PPC) model, and
- wherein the transform image data is image data transformed from the basic image data such that the transform image data indicates a process variation.
Dependencies are inferred from the claim text.