AI 中文总结
本文提出具备时序记忆、安全护栏与语音评估功能的本地可部署智能体式健康助手ECHO，其核心聊天机器人、安全层、语音评估模块均达特定性能指标，且可在消费级硬件运行，符合数据保护法规。
AI 中文摘要
本文提出了ECHO（Enhanced Care & Health Observer，增强型护理与健康观测器），一款用于长期慢性病护理管理的本地可部署对话式健康助手。ECHO整合了在统一监督下开发的三个互补软件模块，构成一个统一系统。核心模块是基于LangGraph编排的ReAct循环构建的智能体式聊天机器人，配备17种临床工具和用于跨会话持久记忆的时序知识图谱；在包含59个场景的基准测试中，使用GPT-5 Mini时其工具执行通过率达到94.9%。两层混合安全层拦截所有传入查询：基于规则的层处理明确的危机信号和越狱尝试，耗时不足1毫秒；带有APPNP式传播的符号图神经网络（GNN）根据临床意图对边界案例进行分类，在包含2537条查询的标注土耳其健康数据集上达到88.8%的准确率和90.6%的不安全召回率，同时优于包括Llama 3.3 70B在内的零样本大语言模型基线。多模态语音评估模块结合Whisper声学编码与BERT文本编码，并采用交叉注意力融合，用于评估情绪、抑郁和疼痛，平均宏F1值达到0.652。整个系统实现为可完全在消费级硬件上运行的网页应用，无需将患者数据传输至外部服务，支持符合GDPR和KVKK法规。
英文摘要
This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management. ECHO integrates three complementary software modules developed under shared supervision as a unified system. The core module is an agentic chatbot built on a ReAct loop orchestrated via LangGraph, equipped with 17 clinical tools and a temporal knowledge graph for persistent cross-session memory; it achieves a 94.9% tool-execution pass rate across a 59-scenario benchmark with GPT-5 Mini. A two-stage hybrid safety layer intercepts all incoming queries: a rule-based layer handles explicit crisis signals and jailbreak attempts in under 1ms, while a signed graph neural network (GNN) with APPNP-style propagation classifies boundary cases by clinical intent, achieving 88.8% accuracy and 90.6% unsafe recall on a 2,537-query annotated Turkish health dataset while outperforming zero-shot LLM baselines including Llama 3.3 70B. A multimodal speech assessment module combining Whisper acoustic encoding and BERT text encoding with cross-attention fusion estimates emotion, depression, and pain, reaching a mean macro F1 of 0.652. The full system is implemented as a web application that can run entirely on consumer hardware, with no patient data transmitted to external services, supporting compliance with GDPR and KVKK.
Comments5 pages
