A study of route recommendation for longtail users based on features of urban and crowd

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K12240
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 62020:Web informatics and service informatics-related
• Research Institution: Kyoto Sangyo University
• Principal Investigator: Kawai Yukiko 京都産業大学, 情報理工学部, 教授 (90399543)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: SNSデータ分析 / 地理情報分析 / 経路推薦 / Webマイニング

Outline of Final Research Achievements

There is a serious issue that constantly staring at route guidance on a mobile phone screen while moving is dangerous and uncomfortable. In this research, we extract the atmosphere of places and streets that are not clearly visible to the public using big data such as images from SNS, GSV, geographic information, Wi-Fi sensors, etc., and the latest deep learning techniques, and then, we have achieved a certain level of research results by carrying out research and development to solve safe and secure route guidance for long-tail users with a comprehensive approach.

Free Research Field

データ工学

Academic Significance and Societal Importance of the Research Achievements

既存の経路案内では、利用者の多様性が増すと地物や通りの街の特性に対するユーザの認識率も多様化するため、認識率が異なるにも関わらず同一のランドマークによる経路案内の利用では、全てのユーザに対して安心で快適な案内が困難という本質的な課題があった。すなわち、店舗や通りなどのランドマークに対して多様なユーザの認知率を向上させる手法を確立する本研究の学術的価値は高く、記憶に残りやすい経路を推薦でき、その実用性の高さは社会的に大きな意義がある。