A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE
The present invention relates to a deep learning model learning method for predicting pattern characteristics and a semiconductor device manufacturing method. According to exemplary embodiments for achieving an above technical problem, provided is the semiconductor device manufacturing method compri...
Gespeichert in:
Hauptverfasser: | , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | eng ; kor |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | KIM KWANG RAK BYOUN SEUNG GUN SONG GIL WOO LEE CHI YOUNG JO TAE YONG BAE YOON SUNG GWAK SEUNG HO YUN KYUNG WON SHIN YOUNG HOON |
description | The present invention relates to a deep learning model learning method for predicting pattern characteristics and a semiconductor device manufacturing method. According to exemplary embodiments for achieving an above technical problem, provided is the semiconductor device manufacturing method comprising the following steps of: forming a pattern on a wafer; measuring a spectrum of the patterned wafer with a spectroscopic optical system; analyzing the spectrum through a deep learning model for predicting the trained pattern characteristics based on domain knowledge; and evaluating the pattern on the wafer based on analysis of the spectrum. The domain knowledge may include factors causing a noise of the spectroscopic optical system. An objective of the present invention is to provide the deep learning model learning method for predicting the pattern characteristics with improved reliability, and the semiconductor device manufacturing method.
상기 기술적 과제를 달성하기 위한 예시적인 실시예들에 따르면, 반도체 소자 제조 방법이 제공된다. 상기 방법은, 웨이퍼 상에 패턴을 형성하는 단계; 상기 패턴이 형성된(Patterned) 웨이퍼의 스펙트럼을 분광 광학계로 측정하는 단계; 도메인 지식에 기초하여 학습된(trained) 패턴 특성의 예측을 위한 딥 러닝 모델을 통해 상기 스펙트럼을 분석하는 단계; 및 상기 스펙트럼의 분석에 기초하여 상기 웨이퍼 상의 패턴을 평가하는 단계를 포함하되, 상기 도메인 지식은 상기 분광 광학계의 노이즈 유발 인자를 포함할 수 있다. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20220050664A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20220050664A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20220050664A3</originalsourceid><addsrcrecordid>eNqNjL0KwjAURrs4iPoOF5yFUH_2S3JjLzZJSW9dS5E4iRbqO_jatuLg6PSdDw5nnr0QHEkRDAQLEpE9-yMYogpKwvh5LhgqwYYIVSTDWjj4Sa9QhKIHXWBEPSLXwroG9AZ-sw59Y0ehiVMNoSbHOnjTaBmbhs6saZnNrt1tSKvvLrK1JdHFJvWPNg19d0n39GxPMVd5rtReHQ473P5nvQGp8T5n</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE</title><source>esp@cenet</source><creator>KIM KWANG RAK ; BYOUN SEUNG GUN ; SONG GIL WOO ; LEE CHI YOUNG ; JO TAE YONG ; BAE YOON SUNG ; GWAK SEUNG HO ; YUN KYUNG WON ; SHIN YOUNG HOON</creator><creatorcontrib>KIM KWANG RAK ; BYOUN SEUNG GUN ; SONG GIL WOO ; LEE CHI YOUNG ; JO TAE YONG ; BAE YOON SUNG ; GWAK SEUNG HO ; YUN KYUNG WON ; SHIN YOUNG HOON</creatorcontrib><description>The present invention relates to a deep learning model learning method for predicting pattern characteristics and a semiconductor device manufacturing method. According to exemplary embodiments for achieving an above technical problem, provided is the semiconductor device manufacturing method comprising the following steps of: forming a pattern on a wafer; measuring a spectrum of the patterned wafer with a spectroscopic optical system; analyzing the spectrum through a deep learning model for predicting the trained pattern characteristics based on domain knowledge; and evaluating the pattern on the wafer based on analysis of the spectrum. The domain knowledge may include factors causing a noise of the spectroscopic optical system. An objective of the present invention is to provide the deep learning model learning method for predicting the pattern characteristics with improved reliability, and the semiconductor device manufacturing method.
상기 기술적 과제를 달성하기 위한 예시적인 실시예들에 따르면, 반도체 소자 제조 방법이 제공된다. 상기 방법은, 웨이퍼 상에 패턴을 형성하는 단계; 상기 패턴이 형성된(Patterned) 웨이퍼의 스펙트럼을 분광 광학계로 측정하는 단계; 도메인 지식에 기초하여 학습된(trained) 패턴 특성의 예측을 위한 딥 러닝 모델을 통해 상기 스펙트럼을 분석하는 단계; 및 상기 스펙트럼의 분석에 기초하여 상기 웨이퍼 상의 패턴을 평가하는 단계를 포함하되, 상기 도메인 지식은 상기 분광 광학계의 노이즈 유발 인자를 포함할 수 있다.</description><language>eng ; kor</language><subject>CALCULATING ; COLORIMETRY ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES ; MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT,POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRA-RED,VISIBLE OR ULTRA-VIOLET LIGHT ; MEASURING ; PHYSICS ; RADIATION PYROMETRY ; TESTING</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220425&DB=EPODOC&CC=KR&NR=20220050664A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220425&DB=EPODOC&CC=KR&NR=20220050664A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KIM KWANG RAK</creatorcontrib><creatorcontrib>BYOUN SEUNG GUN</creatorcontrib><creatorcontrib>SONG GIL WOO</creatorcontrib><creatorcontrib>LEE CHI YOUNG</creatorcontrib><creatorcontrib>JO TAE YONG</creatorcontrib><creatorcontrib>BAE YOON SUNG</creatorcontrib><creatorcontrib>GWAK SEUNG HO</creatorcontrib><creatorcontrib>YUN KYUNG WON</creatorcontrib><creatorcontrib>SHIN YOUNG HOON</creatorcontrib><title>A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE</title><description>The present invention relates to a deep learning model learning method for predicting pattern characteristics and a semiconductor device manufacturing method. According to exemplary embodiments for achieving an above technical problem, provided is the semiconductor device manufacturing method comprising the following steps of: forming a pattern on a wafer; measuring a spectrum of the patterned wafer with a spectroscopic optical system; analyzing the spectrum through a deep learning model for predicting the trained pattern characteristics based on domain knowledge; and evaluating the pattern on the wafer based on analysis of the spectrum. The domain knowledge may include factors causing a noise of the spectroscopic optical system. An objective of the present invention is to provide the deep learning model learning method for predicting the pattern characteristics with improved reliability, and the semiconductor device manufacturing method.
상기 기술적 과제를 달성하기 위한 예시적인 실시예들에 따르면, 반도체 소자 제조 방법이 제공된다. 상기 방법은, 웨이퍼 상에 패턴을 형성하는 단계; 상기 패턴이 형성된(Patterned) 웨이퍼의 스펙트럼을 분광 광학계로 측정하는 단계; 도메인 지식에 기초하여 학습된(trained) 패턴 특성의 예측을 위한 딥 러닝 모델을 통해 상기 스펙트럼을 분석하는 단계; 및 상기 스펙트럼의 분석에 기초하여 상기 웨이퍼 상의 패턴을 평가하는 단계를 포함하되, 상기 도메인 지식은 상기 분광 광학계의 노이즈 유발 인자를 포함할 수 있다.</description><subject>CALCULATING</subject><subject>COLORIMETRY</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES</subject><subject>MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT,POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRA-RED,VISIBLE OR ULTRA-VIOLET LIGHT</subject><subject>MEASURING</subject><subject>PHYSICS</subject><subject>RADIATION PYROMETRY</subject><subject>TESTING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjL0KwjAURrs4iPoOF5yFUH_2S3JjLzZJSW9dS5E4iRbqO_jatuLg6PSdDw5nnr0QHEkRDAQLEpE9-yMYogpKwvh5LhgqwYYIVSTDWjj4Sa9QhKIHXWBEPSLXwroG9AZ-sw59Y0ehiVMNoSbHOnjTaBmbhs6saZnNrt1tSKvvLrK1JdHFJvWPNg19d0n39GxPMVd5rtReHQ473P5nvQGp8T5n</recordid><startdate>20220425</startdate><enddate>20220425</enddate><creator>KIM KWANG RAK</creator><creator>BYOUN SEUNG GUN</creator><creator>SONG GIL WOO</creator><creator>LEE CHI YOUNG</creator><creator>JO TAE YONG</creator><creator>BAE YOON SUNG</creator><creator>GWAK SEUNG HO</creator><creator>YUN KYUNG WON</creator><creator>SHIN YOUNG HOON</creator><scope>EVB</scope></search><sort><creationdate>20220425</creationdate><title>A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE</title><author>KIM KWANG RAK ; BYOUN SEUNG GUN ; SONG GIL WOO ; LEE CHI YOUNG ; JO TAE YONG ; BAE YOON SUNG ; GWAK SEUNG HO ; YUN KYUNG WON ; SHIN YOUNG HOON</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20220050664A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COLORIMETRY</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES</topic><topic>MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT,POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRA-RED,VISIBLE OR ULTRA-VIOLET LIGHT</topic><topic>MEASURING</topic><topic>PHYSICS</topic><topic>RADIATION PYROMETRY</topic><topic>TESTING</topic><toplevel>online_resources</toplevel><creatorcontrib>KIM KWANG RAK</creatorcontrib><creatorcontrib>BYOUN SEUNG GUN</creatorcontrib><creatorcontrib>SONG GIL WOO</creatorcontrib><creatorcontrib>LEE CHI YOUNG</creatorcontrib><creatorcontrib>JO TAE YONG</creatorcontrib><creatorcontrib>BAE YOON SUNG</creatorcontrib><creatorcontrib>GWAK SEUNG HO</creatorcontrib><creatorcontrib>YUN KYUNG WON</creatorcontrib><creatorcontrib>SHIN YOUNG HOON</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KIM KWANG RAK</au><au>BYOUN SEUNG GUN</au><au>SONG GIL WOO</au><au>LEE CHI YOUNG</au><au>JO TAE YONG</au><au>BAE YOON SUNG</au><au>GWAK SEUNG HO</au><au>YUN KYUNG WON</au><au>SHIN YOUNG HOON</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE</title><date>2022-04-25</date><risdate>2022</risdate><abstract>The present invention relates to a deep learning model learning method for predicting pattern characteristics and a semiconductor device manufacturing method. According to exemplary embodiments for achieving an above technical problem, provided is the semiconductor device manufacturing method comprising the following steps of: forming a pattern on a wafer; measuring a spectrum of the patterned wafer with a spectroscopic optical system; analyzing the spectrum through a deep learning model for predicting the trained pattern characteristics based on domain knowledge; and evaluating the pattern on the wafer based on analysis of the spectrum. The domain knowledge may include factors causing a noise of the spectroscopic optical system. An objective of the present invention is to provide the deep learning model learning method for predicting the pattern characteristics with improved reliability, and the semiconductor device manufacturing method.
상기 기술적 과제를 달성하기 위한 예시적인 실시예들에 따르면, 반도체 소자 제조 방법이 제공된다. 상기 방법은, 웨이퍼 상에 패턴을 형성하는 단계; 상기 패턴이 형성된(Patterned) 웨이퍼의 스펙트럼을 분광 광학계로 측정하는 단계; 도메인 지식에 기초하여 학습된(trained) 패턴 특성의 예측을 위한 딥 러닝 모델을 통해 상기 스펙트럼을 분석하는 단계; 및 상기 스펙트럼의 분석에 기초하여 상기 웨이퍼 상의 패턴을 평가하는 단계를 포함하되, 상기 도메인 지식은 상기 분광 광학계의 노이즈 유발 인자를 포함할 수 있다.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng ; kor |
recordid | cdi_epo_espacenet_KR20220050664A |
source | esp@cenet |
subjects | CALCULATING COLORIMETRY COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT,POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRA-RED,VISIBLE OR ULTRA-VIOLET LIGHT MEASURING PHYSICS RADIATION PYROMETRY TESTING |
title | A METHOD OF TRAINING DEEP LEARNING MODEL FOR PREDICTION OF PATTERN CHARACTERISTICS AND A METHOD OF MANUFACTURING A SEMICONDUCTOR DEVICE |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T22%3A00%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=KIM%20KWANG%20RAK&rft.date=2022-04-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20220050664A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |