Digital tools for identifying work tasks in various occupations: A scoping review
这篇范围综述梳理了2014-2024年间49项研究，发现数字工具（主要是传感器和视觉工具）能自动或半自动识别工作任务的类型、时长、地点和人员，但样本小、代表性不足，需改进方法并推广到实际应用。
This scoping review aimed to map peer-reviewed studies applying digital tools for automatically or semi-automatically mapping work tasks, including their type, location, duration, or worker identification. Following Arksey and O'Malley's framework and PRISMA-ScR guidelines, systematic searches were conducted in PubMed, Web of Science, and Google Scholar (2014-2024). Forty-nine studies were included, most of which were of moderate quality, limited by small and unrepresentative samples and low user involvement. Studies covered diverse occupations, mainly construction (n = 20) and manufacturing (n = 16). The most common tools were sensor-based (n = 24), vision-based (n = 13), multimodal (hybrid) (n = 6), and localisation-based (n = 4). Audio- and interaction-based tools appeared in single studies. Many tools captured task duration, some also worker identity, and fewer captured task location. These findings highlight both the potential and the current limitations of digital tools for mapping work tasks, underscoring the need for methodological development and real-world application in occupational research and practice. The protocol was preregistered in the Open Science Framework (OSF): https://doi.org/10.17605/OSF.IO/U7PBT.