PIA：将健康对话转化为记录并将记录转化为理解的个人智能体
PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding
- KAIST（韩国科学技术院）
- NAVER Corp.（NAVER公司）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对通用记忆机制无法处理健康数据时间与因果语义的问题，提出PIA个人智能体，通过四模块记忆框架将对话转为临床记录并生成多维度用户理解，实验验证了其有效性并总结运行经验。
中文摘要 AI 辅助
通用智能体的记忆机制通过总结对话来工作：它提取关键片段，将其嵌入向量，并检索最相关的top-k项放入提示中。然而，健康智能体无法仅依赖总结运行：一次剂量变成一句话，“自上周以来”这一时间信息由模型自行判断，而三个月的血糖趋势无法通过文本相似性来回答。我们提出了PIA，一个与消费级健康智能体并行部署的个人智能体。PIA接收智能体的自然语言请求，自行决定是否以及如何写入或读取，将对话转化为类型化的临床记录，并将记录转化为对用户的综合理解。其记忆框架由四个控制模块组成——提取、记忆、检索和理解——每个都是领域无关的机制，配有可插拔的健康模块：模式、医学别名词典、知识图谱和时间规则。我们展示了同一查询如何随着注入响应上下文的记忆从一维回忆、到二维健康快照、再到带因果关系的三维轨迹而得到不同答案，并报告了运行中的经验教训：自我报告的健康数据并非随机缺失，问题的措辞决定了综合理解的质量，而近三分之一的候选因果联系是仅靠规则即可消除的结构性噪声。
英文摘要
General-purpose agent memory summarizes conversations: it extracts salient snippets, embeds them, and retrieves the top-k into the prompt. A health agent cannot run on summaries: a dose becomes a sentence, "since last week" is resolved at the model's discretion, and a three-month glucose trend cannot be answered by text similarity. We present PIA, a personal intelligence agent deployed alongside a consumer health agent. PIA receives the agent's natural-language requests, decides for itself whether and how to write or read, and turns conversations into typed clinical records and records into a synthesized understanding of the user. Its memory harness consists of four controls -- extraction, memory, retrieval, and understanding -- each a domain-agnostic mechanism with a pluggable health module: schema, medical alias dictionary, knowledge graph, and temporal rules. We show how the same query receives a different answer as the memory injected into the response context deepens from one-dimensional recall, to a two-dimensional health snapshot, to a three-dimensional trajectory with causality, and report lessons from operation: self-reported health data are missing not at random, question phrasing governs the quality of synthesized understanding, and nearly a third of candidate causal links are structural noise that rules alone remove.
