口袋RAG:面向离线移动环境的设备端RAG用于急救指导
Pocket RAG: On-Device RAG for First Aid Guidance in Offline Mobile Environment
AI总结:
本研究提出了一种轻量级移动RAG系统,用于在无网络环境下提供可靠的急救指导,实现了高准确率和快速响应。
摘要:
在灾害场景或偏远地区,提供急救时第一响应者常常会失去网络连接。在这种情况下,基于服务器的AI系统无法提供关键指导。为了解决这一问题,我们提出了一种轻量级、基于移动设备的检索增强生成系统,适用于小型语言模型(SLMs),可直接在Android设备上运行。我们的系统集成了一个移动友好的优化流程,包含混合RAG、选择性压缩、批量提示解码和量化缓存。尽管模型体积较小,我们的RAG系统在物理急救方面达到94.5%的准确率,在心理急救方面达到97.0%的准确率。此外,我们还将响应时间从14.2秒减少到3.7秒,实现了近4倍的速度提升。这些结果证明了我们的系统是实用的,能够在没有互联网连接的情况下提供可靠的急救指导。
英文摘要:
In disaster scenarios or remote areas, first responders often lose network connectivity when providing first aid. In such situations, server-based AI systems fail to provide critical guidance. To address this issue, we present a lightweight, mobile-based retrieval-augmented generation system for small language models (SLMs) that can run directly on Android devices. Our system integrates a mobile-friendly optimized pipeline featuring Hybrid RAG, selective compression, batched prompt decoding, and quantization caching. Despite the model's small size, our RAG-based system achieves 94.5\% accuracy for physical first aid and 97.0\% for psychological first aid. Additionally, we reduce response time from 14.2s to 3.7s, achieving a nearly 4x speedup. These results prove that our system is practical and can deliver reliable first aid guidance even without internet connectivity.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。