Samsung electronics co., ltd. (20240160827). METHODS OF TRAINING DEEP LEARNING MODELS FOR OPTICAL PROXIMITY CORRECTION, OPTICAL PROXIMITY CORRECTION METHODS, AND METHODS OF MANUFACTURING SEMICONDUCTOR DEVICES USING THE SAME simplified abstract

METHODS OF TRAINING DEEP LEARNING MODELS FOR OPTICAL PROXIMITY CORRECTION, OPTICAL PROXIMITY CORRECTION METHODS, AND METHODS OF MANUFACTURING SEMICONDUCTOR DEVICES USING THE SAME

Organization Name

samsung electronics co., ltd.

Inventor(s)

Sangchul Yeo of Suwon-si (KR)

METHODS OF TRAINING DEEP LEARNING MODELS FOR OPTICAL PROXIMITY CORRECTION, OPTICAL PROXIMITY CORRECTION METHODS, AND METHODS OF MANUFACTURING SEMICONDUCTOR DEVICES USING THE SAME - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240160827 titled 'METHODS OF TRAINING DEEP LEARNING MODELS FOR OPTICAL PROXIMITY CORRECTION, OPTICAL PROXIMITY CORRECTION METHODS, AND METHODS OF MANUFACTURING SEMICONDUCTOR DEVICES USING THE SAME

Simplified Explanation

The abstract describes a method of training a deep learning model for optical proximity correction, where sample input images associated with sample layouts are obtained, and sample reference images are extracted from sample masks fabricated through the optical proximity correction process. The deep learning model is trained using the sample input images and sample reference images to perform corner rounding operations on semiconductor device layout patterns.

• Explanation of the patent:
• Obtaining sample input images associated with sample layouts targeted for optical proximity correction.
• Extracting sample reference images from sample masks fabricated through the optical proximity correction process.
• Training a deep learning model using the sample input images and sample reference images to perform corner rounding operations on semiconductor device layout patterns.

1. 1. 1. Potential Applications

This technology can be applied in the semiconductor industry for improving the accuracy and efficiency of optical proximity correction processes.

1. 1. 1. Problems Solved

1. Enhances the precision of corner rounding operations in semiconductor device layout patterns. 2. Streamlines the optical proximity correction process by utilizing deep learning models.

1. 1. 1. Benefits

1. Increased accuracy in optical proximity correction. 2. Reduction in manual intervention for corner rounding operations. 3. Improved overall efficiency in semiconductor manufacturing processes.

1. 1. 1. Potential Commercial Applications
         1. Improving Semiconductor Manufacturing Efficiency with Deep Learning Models

1. 1. 1. Possible Prior Art

There may be prior art related to using deep learning models for image processing tasks in the semiconductor industry, but specific examples are not provided in the abstract.

1. 1. 1. 1. Unanswered Questions

1. 1. 1. How does the deep learning model handle variations in sample layouts for optical proximity correction?

The abstract does not specify how the deep learning model adapts to different sample layouts and their corresponding input images.

1. 1. 1. What is the computational efficiency of the training operation on the deep learning model?

The abstract does not mention the computational resources required for training the deep learning model for optical proximity correction.

Original Abstract Submitted

in a method of training a deep learning model for optical proximity correction, sample input images associated with sample layouts may be obtained, where the sample layouts are targets of the optical proximity correction. sample reference images that correspond to the sample input images may be extracted from sample masks that are fabricated by performing the optical proximity correction on the sample layouts. a training operation may be performed on the deep learning model used in the optical proximity correction based on the sample input images and the sample reference images. the sample layouts may include sample layout patterns to form process patterns of a semiconductor device. the sample input images may include images of corner portions of the sample layout patterns. the deep learning model may be used to perform a corner rounding operation on the corner portions of the sample layout patterns.