Trainingsverfahren und -vorrichtung für ein lithografiemaskenerzeugungsmodell sowie vorrichtung und speichermedium

AT1924362TUndetermined Publication Date: 2026-06-15TENCENT TECHNOLOGY (SHENZHEN) CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
AT2023744348T
Authority / Receiving Office
AT · AT
Patent Type
Patents
Current Assignee / Owner
Priority Date
2022-06-14
Filing Date
2023-05-09
Publication Date
2026-06-15
Estimated Expiration
2043-05-09

AI Technical Summary

Technical Problem

The existing lithographic mask generation model training process is inefficient due to the complexity and slow generation speed of wafer patterns using lithographic physical models, which hinders the training efficiency of the model.

Method used

A training method and apparatus that utilize a neural network-based pre-trained wafer pattern generation model to generate predictive wafer patterns, determining training loss based on these patterns to update the lithographic mask generation model parameters, reducing computation requirements and improving efficiency.

Benefits of technology

This approach significantly reduces the time required to generate predictive wafer patterns, thereby enhancing the training efficiency of the lithographic mask generation model by leveraging neural networks over traditional physical models.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Embodiments of this disclosure provide a training method and apparatus for a lithographic mask generation model, a device and a storage medium, and relate to the field of chip and machine learning technologies. The method includes: generating a predictive mask map corresponding to a chip layout through a lithographic mask generation model (301); generating a predictive wafer pattern corresponding to the predictive mask map through a pre-trained wafer pattern generation model, the wafer pattern generation model being a neural network-based machine learning model (302); determining a model precision evaluation index according to the predictive mask map, and determining a mask quality evaluation index according to the predictive wafer pattern; determining a training loss according to the model precision evaluation index and the mask quality evaluation index (303); and adjusting at least one parameter of the lithographic mask generation model according to the training loss (304). The technical solutions provided in the embodiments of this disclosure improve the training efficiency of the lithographic mask generation model.
Need to check novelty before this filing date? Find Prior Art