Intelligent Exercise and Feedback System for Social Healthcare using LLMOps

TL;DR

This paper presents an LLMOps-based system that automates exercise analysis and provides personalized health feedback in social healthcare platforms, enhancing engagement and accuracy over manual methods.

Contribution

It introduces a scalable, reliable LLM-driven architecture for automated exercise analysis and personalized recommendations in large-scale healthcare communities.

Findings

Effective exercise classification and prediction accuracy

Improved user engagement through personalized feedback

Enhanced scalability and security of healthcare data processing

Abstract

This study addresses the growing demand for personalized feedback in healthcare platforms and social communities by introducing an LLMOps-based system for automated exercise analysis and personalized recommendations. Current healthcare platforms rely heavily on manual analysis and generic health advice, limiting user engagement and health promotion effectiveness. We developed a system that leverages Large Language Models (LLM) to automatically analyze user activity data from the "Ounwan" exercise recording community. The system integrates LLMOps with LLM APIs, containerized infrastructure, and CI/CD practices to efficiently process large-scale user activity data, identify patterns, and generate personalized recommendations. The architecture ensures scalability, reliability, and security for large-scale healthcare communities. Evaluation results demonstrate the system's effectiveness in three key metrics: exercise classification, duration prediction, and caloric expenditure estimation. This approach improves the efficiency of community management while providing more accurate and personalized feedback to users, addressing the limitations of traditional manual analysis methods.