DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care

TL;DR

DEMENTIA-PLAN is an innovative framework that uses multiple knowledge graphs and a self-reflection agent to improve conversational support and emotional stability in dementia patients through enhanced retrieval-augmented generation.

Contribution

It introduces a multi-knowledge graph architecture with a self-reflection planning agent for dynamic knowledge retrieval in dementia care.

Findings

Effective integration of daily routine and memory graphs

Improved emotional support and memory assistance

Dynamic retrieval weight adjustment enhances response quality

Abstract

Mild-stage dementia patients primarily experience two critical symptoms: severe memory loss and emotional instability. To address these challenges, we propose DEMENTIA-PLAN, an innovative retrieval-augmented generation framework that leverages large language models to enhance conversational support. Our model employs a multiple knowledge graph architecture, integrating various dimensional knowledge representations including daily routine graphs and life memory graphs. Through this multi-graph architecture, DEMENTIA-PLAN comprehensively addresses both immediate care needs and facilitates deeper emotional resonance through personal memories, helping stabilize patient mood while providing reliable memory support. Our notable innovation is the self-reflection planning agent, which systematically coordinates knowledge retrieval and semantic integration across multiple knowledge graphs, while scoring retrieved content from daily routine and life memory graphs to dynamically adjust their retrieval weights for optimized response generation. DEMENTIA-PLAN represents a significant advancement in the clinical application of large language models for dementia care, bridging the gap between AI tools and caregivers interventions.