Data Modeling with Human-System Circulation via Abstract Conceptual Structure Representation

2022 Fiscal Year Final Research Report

• Project/Area Number: 17K06250
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent mechanics/Mechanical systems
• Research Institution: Hokkaido University (2022); The University of Tokyo (2017)
• Principal Investigator: Wakuda Yuki 北海道大学, 大学院教育推進機構, 特任准教授 (00377847)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Keywords: データサイエンス / 機械学習 / オントロジー / AI / DX

Outline of Final Research Achievements

In this study, we aimed to map the results obtained from data analysis to an abstracted conceptual structure, to interpret semantic relations as automatically as possible, and to present the analysis results in a written form. The data used in the study were text data containing a mixture of numerical values and character strings.The unique feature of this study is that it attempts to improve the analysis results by identifying semantic relationships among variables in tabular data and introducing them into the analysis as external knowledge data. In this study, a prototype of a conceptual structure (ontology) showing lexical relationships among infrastructure maintenance data was produced, and an attempt was made to generate explanatory text for the analysis results using this ontology. In addition, data analysis was conducted in the specific field of social infrastructure maintenance management.

Free Research Field

データサイエンス

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は，ビッグデータからモデリングを行った結果を抽象化した概念構造に紐づけ，文章表現迄行う事である．特に，インフラメンテナンス分野を対象として，データ分析結果を実務者への説明を日本語の文章表現によって行うことで，データサイエンスを広く様々な人に活用してもらえるよう努めた点で，社会的意義がある．このとき，データ分析により構築した「モデル」による出力結果と，この結果に対する人による解釈とを対比することを実現し，これにより， AIや機械学習の実務を通じた運用の実現を目指したものである．