{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00239026","sets":["1164:3500:11474:11710"]},"path":["11710"],"owner":"44499","recid":"239026","title":["RAGによる資金運用アドバイス生成手法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-09-04"},"_buckets":{"deposit":"701def40-1628-44c1-bfbf-4575efa4f6ba"},"_deposit":{"id":"239026","pid":{"type":"depid","value":"239026","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"RAGによる資金運用アドバイス生成手法の提案","author_link":["654790","654791","654789","654788"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"RAGによる資金運用アドバイス生成手法の提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"6B ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-09-04","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都産業大学"},{"subitem_text_value":"福岡大学"},{"subitem_text_value":"千葉工業大学"},{"subitem_text_value":"京都産業大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kyoto Sangyo University","subitem_text_language":"en"},{"subitem_text_value":"Fukuoka University","subitem_text_language":"en"},{"subitem_text_value":"Chiba Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Kyoto Sangyo University","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/239026/files/IPSJ-IFAT24156037.pdf","label":"IPSJ-IFAT24156037.pdf"},"date":[{"dateType":"Available","dateValue":"2026-09-04"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-IFAT24156037.pdf","filesize":[{"value":"4.7 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"39"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"13bf9f32-10c8-4a5c-8858-616935c00b21","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"三輪, 樹理音"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"栗, 達"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"熊本, 忠彦"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河合, 由起子"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10114171","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":"2188-8884","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，家計の改善をアドバイスする専門家の文章と家計簿の収支表データから Retrieval-Augmented Generation (RAG) を構築することで，大規模言語モデル（LLM）に基づく資産運用アドバイスの自動生成をより高精度に行うことを目的とする．RAG の構築は，Web 上のファイナンシャルプランナー（FP）への相談記事をスクレイピングし，相談文だけでなく，相談者の性別や家族構成といった基本情報，家計簿の表画像，および FP によるアドバイス文章を取得する．次に，家計簿の表画像から収支表データを抽出し，これら相談内容と表データから Pinecone よりベクトルデータを生成する．構築したベクトルデータベースにより質問の相談内容を拡張し LLM に投入することで，より高精度な資金運用のアドバイスを生成する．本稿では，提案手法により構築した RAG による資金運用アドバイス生成を OpenAI 上に実装し検証することで，RAG による文章と関連する表やグラフに基づく資産運用支援の応用可能性について考察する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This study aims to develop an automated asset management advisory system based on a large language model (LLM) using Retrieval-Augmented Generation (RAG). By leveraging expert advice texts and table data from household balance sheets, we seek to generate financial management advice. To build the RAG, we scrape web-based consultation articles from financial planners (FPs), acquiring not only the consultation text but also basic information such as the consultant's gender and family composition, balance sheet table images, and the FP's advice text. We then extract numerical data from the balance sheet images, convert these texts and table data into vector data using Pinecone, and generate new financial management advice using extended prompts based on these generated vectors and the consultation content. This paper implements and verifies the generation of financial management advice using OpenAI based on the proposed RAG method and discusses the potential applications of RAG in supporting asset management through related texts, tables, and graphs.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告情報基礎とアクセス技術（IFAT）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-09-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"37","bibliographicVolumeNumber":"2024-IFAT-156"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:42:26.185249+00:00","updated":"2025-01-19T08:25:06.212206+00:00","id":239026}