{"updated":"2025-01-19T23:05:57.594690+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00195452","sets":["6394:9652:9763"]},"path":["9763"],"owner":"33195","recid":"195452","title":["ビッグデータを活用した歩留解析支援システム“歩留新聞”による解析作業時間の短縮"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-04-15"},"_buckets":{"deposit":"44a10f4f-a269-4711-b151-df13bdebe1c8"},"_deposit":{"id":"195452","pid":{"type":"depid","value":"195452","revision_id":0},"owners":[33195],"status":"published","created_by":33195},"item_title":"ビッグデータを活用した歩留解析支援システム“歩留新聞”による解析作業時間の短縮","author_link":["465584","465583","465585"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ビッグデータを活用した歩留解析支援システム“歩留新聞”による解析作業時間の短縮"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"特集：ディープラーニングのプラクティス","subitem_subject_scheme":"Other"}]},"item_type_id":"21","publish_date":"2019-04-15","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_21_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"（株）東芝"},{"subitem_text_value":"（株）東芝"},{"subitem_text_value":"（株）東芝"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/195452/files/IPSJ-DP1002004.pdf","label":"IPSJ-DP1002004.pdf"},"date":[{"dateType":"Available","dateValue":"2019-04-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DP1002004.pdf","filesize":[{"value":"1.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2cef529f-29a7-4dfa-bb11-b3a1aadc632f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_21_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中田, 康太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高木, 健太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"陶, 亜玲"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_21_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1245124X","subitem_source_identifier_type":"NCID"}]},"item_21_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-4390","subitem_source_identifier_type":"ISSN"}]},"item_21_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"半導体製造における歩留解析では，製品の品質検査結果と各工程の処理履歴から不良の原因を特定し，対策に繋げることで生産性を向上している．半導体の製造プロセスから得られるデータは大量かつ複雑であるため，人手による歩留解析では作業に時間がかかることが問題となっている．本稿では，機械学習・データマイニングの技術を用いて不良の発生状況の可視化と不良原因装置の推定を網羅的に行う歩留解析支援システム「歩留新聞」について紹介する．歩留新聞はウェハ上の特徴的な不良の出現パターン（不良マップ）を自動で分類し，それぞれの原因装置候補を抽出する．不良マップの分類結果と原因装置候補を技術者に提示することで，不良1件あたりの解析時間を平均6時間から2時間に短縮した．ここでは，歩留新聞の概要とともに，コア技術となる深層学習技術について紹介し，製造現場における機械学習技術適用の課題とその解決方法について議論する． ","subitem_description_type":"Other"}]},"item_21_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"321","bibliographic_titles":[{"bibliographic_title":"デジタルプラクティス"}],"bibliographicPageStart":"304","bibliographicIssueDates":{"bibliographicIssueDate":"2019-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"10"}]},"relation_version_is_last":true,"item_21_alternative_title_2":{"attribute_name":"その他タイトル","attribute_value_mlt":[{"subitem_alternative_title":"招待論文"}]},"weko_creator_id":"33195"},"created":"2025-01-19T01:00:22.948565+00:00","id":195452,"links":{}}