MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF

The present invention relates to a machine learning system based on a hybrid machine character that a method for utilizing multiple personality of human is applied to machine learning and an implementation method thereof. The implementation method comprises the steps of: distinguishing one artificia...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KOH, EUN JIN, BAEK, HA EUN, LEE, JU YOUNG
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 KOH, EUN JIN
BAEK, HA EUN
LEE, JU YOUNG
description The present invention relates to a machine learning system based on a hybrid machine character that a method for utilizing multiple personality of human is applied to machine learning and an implementation method thereof. The implementation method comprises the steps of: distinguishing one artificial intelligence into a plurality of machine characters to have classes and class characteristics different from each other based on learning data; applying test data to the plurality of distinguished machine characters to extract features for each state having a good classification success rate for each machine character; identifying a feature for each state consistent with a state of input data among the extracted features for each state when applying the input data to be recognized; and classifying classes of the input data by calling a machine character indicating a high recognition rate for the identified feature for each state of the machine characters. 본 발명은 인간의 다중인격 활용방법을 기계학습에 적용한 하이브리드 머신 캐릭터 기반의 기계학습 시스템 및 그 구현방법에 관한 것으로, 학습 데이타를 근거로 서로 상이한 클래스 및 클래스 특성을 갖도록 하나의 인공지능을 복수의 머신 캐릭터로 구분하는 단계; 상기 구분된 복수의 머신 캐릭터에 테스트 데이터를 인가하여 각 머신 캐릭터마다 우수한 분류 성공율을 갖는 상황별 특징을 추출하는 단계; 인식할 입력 데이타 인가시 상기 추출된 복수의 상황별 특징 중에서 상기 입력 데이터의 상황과 일치하는 상황별 특징을 식별하는 단계; 및 상기 복수의 머신 캐릭터 중에서 상기 식별된 상황별 특징에 높은 인식율을 나타내는 머신 캐릭터를 호출하여 입력 데이터의 클래스를 분류하는 단계;를 포한한다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20190022153A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20190022153A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20190022153A3</originalsourceid><addsrcrecordid>eNqNyrEKwjAQANAsDqL-w4GzkKY4OF6Tqwk2F0mC2KkUiZNoof4_Lro7veUtxdWjto4JOsLIjo-Q-pTJQ4OJDAQG2zfRGfg9bTGizhQB2YChC3Xh7IkzeMo2GMiWIoV2LRb38TGXzdeV2LaUtd2V6TWUeRpv5VnewykqWR2kVKra11j_tz6E0zG7</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF</title><source>esp@cenet</source><creator>KOH, EUN JIN ; BAEK, HA EUN ; LEE, JU YOUNG</creator><creatorcontrib>KOH, EUN JIN ; BAEK, HA EUN ; LEE, JU YOUNG</creatorcontrib><description>The present invention relates to a machine learning system based on a hybrid machine character that a method for utilizing multiple personality of human is applied to machine learning and an implementation method thereof. The implementation method comprises the steps of: distinguishing one artificial intelligence into a plurality of machine characters to have classes and class characteristics different from each other based on learning data; applying test data to the plurality of distinguished machine characters to extract features for each state having a good classification success rate for each machine character; identifying a feature for each state consistent with a state of input data among the extracted features for each state when applying the input data to be recognized; and classifying classes of the input data by calling a machine character indicating a high recognition rate for the identified feature for each state of the machine characters. 본 발명은 인간의 다중인격 활용방법을 기계학습에 적용한 하이브리드 머신 캐릭터 기반의 기계학습 시스템 및 그 구현방법에 관한 것으로, 학습 데이타를 근거로 서로 상이한 클래스 및 클래스 특성을 갖도록 하나의 인공지능을 복수의 머신 캐릭터로 구분하는 단계; 상기 구분된 복수의 머신 캐릭터에 테스트 데이터를 인가하여 각 머신 캐릭터마다 우수한 분류 성공율을 갖는 상황별 특징을 추출하는 단계; 인식할 입력 데이타 인가시 상기 추출된 복수의 상황별 특징 중에서 상기 입력 데이터의 상황과 일치하는 상황별 특징을 식별하는 단계; 및 상기 복수의 머신 캐릭터 중에서 상기 식별된 상황별 특징에 높은 인식율을 나타내는 머신 캐릭터를 호출하여 입력 데이터의 클래스를 분류하는 단계;를 포한한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2019</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&amp;date=20190306&amp;DB=EPODOC&amp;CC=KR&amp;NR=20190022153A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190306&amp;DB=EPODOC&amp;CC=KR&amp;NR=20190022153A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KOH, EUN JIN</creatorcontrib><creatorcontrib>BAEK, HA EUN</creatorcontrib><creatorcontrib>LEE, JU YOUNG</creatorcontrib><title>MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF</title><description>The present invention relates to a machine learning system based on a hybrid machine character that a method for utilizing multiple personality of human is applied to machine learning and an implementation method thereof. The implementation method comprises the steps of: distinguishing one artificial intelligence into a plurality of machine characters to have classes and class characteristics different from each other based on learning data; applying test data to the plurality of distinguished machine characters to extract features for each state having a good classification success rate for each machine character; identifying a feature for each state consistent with a state of input data among the extracted features for each state when applying the input data to be recognized; and classifying classes of the input data by calling a machine character indicating a high recognition rate for the identified feature for each state of the machine characters. 본 발명은 인간의 다중인격 활용방법을 기계학습에 적용한 하이브리드 머신 캐릭터 기반의 기계학습 시스템 및 그 구현방법에 관한 것으로, 학습 데이타를 근거로 서로 상이한 클래스 및 클래스 특성을 갖도록 하나의 인공지능을 복수의 머신 캐릭터로 구분하는 단계; 상기 구분된 복수의 머신 캐릭터에 테스트 데이터를 인가하여 각 머신 캐릭터마다 우수한 분류 성공율을 갖는 상황별 특징을 추출하는 단계; 인식할 입력 데이타 인가시 상기 추출된 복수의 상황별 특징 중에서 상기 입력 데이터의 상황과 일치하는 상황별 특징을 식별하는 단계; 및 상기 복수의 머신 캐릭터 중에서 상기 식별된 상황별 특징에 높은 인식율을 나타내는 머신 캐릭터를 호출하여 입력 데이터의 클래스를 분류하는 단계;를 포한한다.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyrEKwjAQANAsDqL-w4GzkKY4OF6Tqwk2F0mC2KkUiZNoof4_Lro7veUtxdWjto4JOsLIjo-Q-pTJQ4OJDAQG2zfRGfg9bTGizhQB2YChC3Xh7IkzeMo2GMiWIoV2LRb38TGXzdeV2LaUtd2V6TWUeRpv5VnewykqWR2kVKra11j_tz6E0zG7</recordid><startdate>20190306</startdate><enddate>20190306</enddate><creator>KOH, EUN JIN</creator><creator>BAEK, HA EUN</creator><creator>LEE, JU YOUNG</creator><scope>EVB</scope></search><sort><creationdate>20190306</creationdate><title>MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF</title><author>KOH, EUN JIN ; BAEK, HA EUN ; LEE, JU YOUNG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20190022153A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KOH, EUN JIN</creatorcontrib><creatorcontrib>BAEK, HA EUN</creatorcontrib><creatorcontrib>LEE, JU YOUNG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KOH, EUN JIN</au><au>BAEK, HA EUN</au><au>LEE, JU YOUNG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF</title><date>2019-03-06</date><risdate>2019</risdate><abstract>The present invention relates to a machine learning system based on a hybrid machine character that a method for utilizing multiple personality of human is applied to machine learning and an implementation method thereof. The implementation method comprises the steps of: distinguishing one artificial intelligence into a plurality of machine characters to have classes and class characteristics different from each other based on learning data; applying test data to the plurality of distinguished machine characters to extract features for each state having a good classification success rate for each machine character; identifying a feature for each state consistent with a state of input data among the extracted features for each state when applying the input data to be recognized; and classifying classes of the input data by calling a machine character indicating a high recognition rate for the identified feature for each state of the machine characters. 본 발명은 인간의 다중인격 활용방법을 기계학습에 적용한 하이브리드 머신 캐릭터 기반의 기계학습 시스템 및 그 구현방법에 관한 것으로, 학습 데이타를 근거로 서로 상이한 클래스 및 클래스 특성을 갖도록 하나의 인공지능을 복수의 머신 캐릭터로 구분하는 단계; 상기 구분된 복수의 머신 캐릭터에 테스트 데이터를 인가하여 각 머신 캐릭터마다 우수한 분류 성공율을 갖는 상황별 특징을 추출하는 단계; 인식할 입력 데이타 인가시 상기 추출된 복수의 상황별 특징 중에서 상기 입력 데이터의 상황과 일치하는 상황별 특징을 식별하는 단계; 및 상기 복수의 머신 캐릭터 중에서 상기 식별된 상황별 특징에 높은 인식율을 나타내는 머신 캐릭터를 호출하여 입력 데이터의 클래스를 분류하는 단계;를 포한한다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; kor
recordid cdi_epo_espacenet_KR20190022153A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title MACHINE LEARNING SYSTEM BASED ON HYBRID MACHINE CHARACTER AND DEVELOPMENT METHOD THEREOF
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T16%3A01%3A19IST&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=KOH,%20EUN%20JIN&rft.date=2019-03-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20190022153A%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