CC BY 4.0Kraft, DimitriDimitriKraftSchmidt, AngelinaAngelinaSchmidtOschinsky, Frederike MarieFrederike MarieOschinskyBüttner, LeaLeaBüttnerLambusch, FabienneFabienneLambuschLaerhoven, Kristof vanKristof vanLaerhovenBieber, GeraldGeraldBieberFellmann, MichaelMichaelFellmann2022-12-012022-12-012022https://publica.fraunhofer.de/handle/publica/429474https://doi.org/10.24406/publica-57910.24406/publica-579Health assistant tools at the workplace may contribute to preventing work-related absenteeism, increasing overall employee satisfaction, and reducing the costs of sickness or presenteeism in the long term. The tools may be integrated into a digital corporate health management strategy. Despite their huge potential, a major drawback of common tools (e.g., wearables, dedicated cameras) are that they require direct interaction, skin contact, or come with a high acquisition cost. A concept for unobtrusive and software-based monitoring to increase long-term health, improve working conditions or show the necessary adjustments to the new work situation can help to solve these problems. This paper presents a concept that shows how a simple webcam can be utilized to record vital signs, posture, and behavior during working hours. It offers individual and intelligent interven-tions and recommendations based on these data to reduce psychological and physical stress. Our approach demonstrates that the required parameters can be used to offer user-tailored interventions based on simple rules. We present a pro-totypical implementation of an intelligent health companion and show avenues for future research.enLead Topic: Individual HealthResearch Line: Computer vision (CV)Machine learningMental healthStressconference paper