Development of a digital AI language companion for older people

Context

More and more older people are living alone and the risk of social isolation and cognitive impairment increases significantly with age. Loneliness in old age can be as detrimental to health as smoking or lack of exercise, and the risk of dementia, depression and physical illness is significantly increased. At the same time, there is a growing need for support systems because family and care resources are often not sufficient to ensure regular social interaction.

Digital voice assistance systems offer a promising approach here. They can stimulate conversations, train memory and attention, accompany everyday situations and provide emotional support by being empathetic, individual and available at all times.

In your thesis, you will develop the basis for such a digital companion: an AI-supported language system that not only provides functional support for older people, but also actively contributes to social participation, emotional well-being and mental activity. The aim is to use modern language models and dialog strategies in such a way that they enable empathic, motivating and everyday interactions. In doing so, you will create an innovative approach to digital support for the elderly and contribute to a future in which digital assistance systems are used in a way that is close to everyday life, supportive and effective for older people.

Tasks

• You will carry out structured market and literature research on voice assistance systems in the context of senior citizens and healthcare as well as on approaches to combat loneliness and cognitive decline in old age.
• You will analyze existing solutions (e.g. Alexa skills, companion apps, social assistance systems) and examine their potential and limitations.
• You derive requirements and usage scenarios for older users (e.g. accessibility, dialog guidance, data protection).
• You will develop dialog and interaction concepts that promote social activity and cognitive stimuli.
• You will design and implement a prototype system approach.
• You will assess technical feasibility and make recommendations for future implementation steps and possible user studies.

Requirements

• You are studying electrical engineering, computer science, data science, mechanical engineering or a related course of study or have the relevant knowledge.
• You are interested in audio analysis, AI, signal processing and/or human-machine interaction
• You have good programming skills (Python) and experience with AI frameworks (PyTorch, TensorFlow or similar).
• You like to work independently, are structured and show initiative.
• You have very good written and spoken German and English skills.