混合AI框架提升对话系统响应速度与准确率，适配企业级多轮对话。
Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation
- 融合预设回复与RAG动态路由，复杂问题自动转至知识检索
- 多轮对话保持连贯性，95%准确率，180ms低延迟
- 支持反馈迭代优化，适合需要快速更新的场景
检索增强生成（RAG）系统与大语言模型驱动的聊天机器人显著推动了对话人工智能的发展，结合生成能力与外部知识检索。尽管取得成功，企业级部署仍面临用户查询多样、高延迟、幻觉及频繁更新领域知识的挑战。本文提出一种新型混合框架，将RAG与基于意图的预设回复相结合，利用高置信度预设回复提升效率，同时动态将复杂或模糊查询路由至RAG管道。框架采用对话上下文管理器确保多轮交互连贯性，并引入反馈回路以优化意图识别、动态调整置信阈值并逐步扩展响应覆盖范围。实验表明，该框架在多种查询类型下实现95%准确率与180ms延迟，优于传统RAG与意图系统，具备可扩展性和自适应能力，适用于企业级对话AI应用。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems and large language model (LLM)-powered chatbots have significantly advanced conversational AI by combining generative capabilities with external knowledge retrieval. Despite their success, enterprise-scale deployments face critical challenges, including diverse user queries, high latency, hallucinations, and difficulty integrating frequently updated domain-specific knowledge. This paper introduces a novel hybrid framework that integrates RAG with intent-based canned responses, leveraging predefined high-confidence responses for efficiency while dynamically routing complex or ambiguous queries to the RAG pipeline. Our framework employs a dialogue context manager to ensure coherence in multi-turn interactions and incorporates a feedback loop to refine intents, dynamically adjust confidence thresholds, and expand response coverage over time. Experimental results demonstrate that the proposed framework achieves a balance of high accuracy (95\%) and low latency (180ms), outperforming RAG and intent-based systems across diverse query types, positioning it as a scalable and adaptive solution for enterprise conversational AI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。