View source for 18106091. LITHOGRAPHY MODEL GENERATING METHOD BASED ON DEEP LEARNING, AND MASK MANUFACTURING METHOD INCLUDING THE LITHOGRAPHY MODEL GENERATING METHOD simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

=LITHOGRAPHY MODEL GENERATING METHOD BASED ON DEEP LEARNING, AND MASK MANUFACTURING METHOD INCLUDING THE LITHOGRAPHY MODEL GENERATING METHOD=


==Organization Name==

[[:Category:SAMSUNG ELECTRONICS CO., LTD.|SAMSUNG ELECTRONICS CO., LTD.]]


[[Category:SAMSUNG ELECTRONICS CO., LTD.]]

==Inventor(s)==

[[:Category:Sangchul Yeo of Suwon-si (KR)|Sangchul Yeo of Suwon-si (KR)]][[Category:Sangchul Yeo of Suwon-si (KR)]]

[[:Category:Jaewon Yang of Suwon-si (KR)|Jaewon Yang of Suwon-si (KR)]][[Category:Jaewon Yang of Suwon-si (KR)]]

[[:Category:Hyeok Lee of Suwon-si (KR)|Hyeok Lee of Suwon-si (KR)]][[Category:Hyeok Lee of Suwon-si (KR)]]

==LITHOGRAPHY MODEL GENERATING METHOD BASED ON DEEP LEARNING, AND MASK MANUFACTURING METHOD INCLUDING THE LITHOGRAPHY MODEL GENERATING METHOD - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18106091 titled 'LITHOGRAPHY MODEL GENERATING METHOD BASED ON DEEP LEARNING, AND MASK MANUFACTURING METHOD INCLUDING THE LITHOGRAPHY MODEL GENERATING METHOD

==Simplified Explanation==

The patent application describes a method for generating a reliable lithography model that takes into account variations in mask bias during manufacturing. The method involves using deep learning techniques to combine basic image data and transform image data to create the lithography model. The model is then verified for accuracy.

* The method involves preparing basic image data for learning.
* Transform image data is prepared to indicate mask bias variation.
* Deep learning is performed to generate a lithography model by combining the basic image data and transform image data.
* The lithography model is verified for accuracy.

==Potential Applications==
This technology can be applied in various industries that rely on lithography processes, such as semiconductor manufacturing, printed circuit board production, and microelectronics fabrication.

==Problems Solved==
1. Mask bias variation during lithography manufacturing can lead to inaccuracies in the final product.
2. Existing lithography models may not adequately account for mask bias variations, resulting in suboptimal performance and yield.

==Benefits==
1. Improved accuracy: The generated lithography model takes into account mask bias variations, leading to more accurate predictions and better quality control.
2. Enhanced yield: By accurately modeling mask bias variations, the manufacturing process can be optimized, resulting in higher yield and reduced waste.
3. Time and cost savings: The use of deep learning techniques allows for efficient and automated generation of the lithography model, saving time and resources compared to manual methods.


==Original Abstract Submitted==

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.



[[Category:G05B19/4099]]
[[Category:G05B13/02]]