{"id":195359,"updated":"2025-01-19T23:08:38.307744+00:00","links":{},"created":"2025-01-19T01:00:17.692905+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00195359","sets":["1164:3696:9666:9721"]},"path":["9721"],"owner":"44499","recid":"195359","title":["営業活動の意思決定プロセス強化における環境モデルに基づくアプローチ"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-03-11"},"_buckets":{"deposit":"b0ddec27-9fa8-4f9b-ab17-78487046aa69"},"_deposit":{"id":"195359","pid":{"type":"depid","value":"195359","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"営業活動の意思決定プロセス強化における環境モデルに基づくアプローチ","author_link":["464856","464858","464855","464854","464851","464860","464857","464853","464852","464859"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"営業活動の意思決定プロセス強化における環境モデルに基づくアプローチ"},{"subitem_title":"An approach based on environment model for strengthening the decision-making process of sales activity","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2019-03-11","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院工学系研究科／(株)NTTデータイントラマート"},{"subitem_text_value":"(株)NTTデータイントラマート"},{"subitem_text_value":"日本電信電話（株）"},{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"東京大学大学院工学系研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"School of engineering, The University of Tokyo / NTT DATA INTRAMART Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT DATA INTRAMART Corporation","subitem_text_language":"en"},{"subitem_text_value":"Nippon Telegraph and Telephone Corporation","subitem_text_language":"en"},{"subitem_text_value":"School of engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"School of engineering, The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/195359/files/IPSJ-GN19107007.pdf","label":"IPSJ-GN19107007.pdf"},"date":[{"dateType":"Available","dateValue":"2021-03-11"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GN19107007.pdf","filesize":[{"value":"796.7 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"29"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"65d6ae92-fb64-40c4-882a-c627a6370990","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中山, 義人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"森, 雅広"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"斎藤, 忍"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"成末, 義哲"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"森川, 博之"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoshihito, Nakayama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masahiro, Mori","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinobu, Saito","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshiaki, Naruse","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroyuki, Morikawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1155524X","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8744","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"営業活動における意思決定から，営業担当者個人の経験や直感といった属人的要素を取り除くことにより，営業活動を大幅に効率化するための手段が求められている．筆者らはこの課題に対し，機械学習モデルを用いた業務意思決定支援システムの構築を試みている．これまで，営業活動の意思決定プロセスに強化学習を適用することで，受注確率の高い営業プロセスの規則性を抽出することができた．その際，営業をエージェント，顧客を環境と位置づけ，その間のやり取りをシミュレータで自動実行する案件シミュレータを開発することで，学習に必要となる十分な案件データ量を確保することができた．しかしこの案件シミュレータのモデリングでは，シミュレータのパラメータ設定範囲が固定化されており，さらには営業エージェントが環境に依存して自由度が制限されるという課題がある．そこで本稿では，案件の背景，要件，顧客のパーソナリティといった環境自体を，シミュレータで作成された案件データを利用して深層学習し，最適な価値関数や方策をプランニングするための環境モデルを構築する．さらにこの構築された環境モデルを利用して，営業エージェントとの間のシミュレーションをセルフプレイで行うことで営業エージェントの学習モデルを強化する．これにより，営業活動場面でより現実に近い理想的なリコメンドが可能となることが想定される．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In the decision-making process of sales activities, the result depends greatly on the judgment of sales personnel. Therefore, the means for establishing the efficiency of sales activities throughout the organization are required by eliminating individuals' factors such as experience and intuition from the decision-making process. In order to solve this problem, we are developing the business decision support system using a machine learning model. Previous studies of applying reinforcement learning to the decision making process of sales activities have produced the extraction of regularity in sales processes with high order acceptance probability. In these studies, it was possible to secure sufficient amount of data to be required for learning by developing a simulator that positions sales as agents and customers as environment and automatically executing exchange between them. However, in modeling of the simulator, there are issues that the parameter setting range of the simulator is fixed and furthermore, the agent depends on the environment. In this paper, we construct an environmental model for planning optimal value functions and policies by deep learning of customer's environment such as background, requirements and customer's personalities. Furthermore, learning model is strengthened by performing self-play simulation with agent using this constructed environmental model. As a result, it is assumed that an ideal recommendation that is closer to reality is possible in the sales activity.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告グループウェアとネットワークサービス（GN）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-03-11","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"7","bibliographicVolumeNumber":"2019-GN-107"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}