Context-Aware Intelligent Chatbot Framework Leveraging Mobile Sensing

TL;DR

This paper introduces a context-aware chatbot framework that uses mobile sensing data to enhance user understanding and generate personalized, relevant conversations, advancing intelligent assistant capabilities.

Contribution

It presents a novel integration of mobile sensing data with large language models to improve contextual understanding in conversational agents.

Findings

Enhanced contextual understanding through mobile sensing data

Personalized dialogue generation based on user behavior and environment

Potential applications in digital health and personalized interaction

Abstract

With the rapid advancement of large language models (LLMs), intelligent conversational assistants have demonstrated remarkable capabilities across various domains. However, they still mainly rely on explicit textual input and do not know the real world behaviors of users. This paper proposes a context-sensitive conversational assistant framework grounded in mobile sensing data. By collecting user behavior and environmental data through smartphones, we abstract these signals into 16 contextual scenarios and translate them into natural language prompts, thus improving the model's understanding of the user's state. We design a structured prompting system to guide the LLM in generating a more personalized and contextually relevant dialogue. This approach integrates mobile sensing with large language models, demonstrating the potential of passive behavioral data in intelligent conversation and offering a viable path toward digital health and personalized interaction.