Chats-Grid：智能电网中利用大模型与检索增强生成的迭代检索问答优化方案
Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid
AI总结：
针对智能电网领域传统RAG问答系统的检索质量差、响应无关等问题，提出Chats-Grid迭代检索框架，通过多阶段优化提升问答效果，助力智能电网管理升级。
摘要：
随着人工智能的快速发展，问答（Q&A）系统已成为智能搜索引擎、虚拟助手和客服平台中不可或缺的组成部分。然而，在智能电网这类动态领域中，传统的检索增强生成（RAG）问答系统面临着检索质量不足、响应无关以及处理大规模实时数据流效率低下等挑战。本文提出了一种专为智能电网环境定制的优化型迭代检索问答框架，名为Chats-Grid。在预检索阶段，Chats-Grid的高级查询扩展机制确保全面覆盖各类数据源，包括传感器读数、电表记录和控制系统参数。检索过程中，Chats-Grid结合最佳匹配25（BM25）稀疏检索与BAAI通用嵌入（BGE）稠密检索，有效处理海量异构数据集。检索后，经过微调的大语言模型利用提示工程评估相关性、过滤无关结果，并根据上下文准确性对文档重排序。该模型还会生成精准的、具备上下文感知能力的答案，遵循质量标准并采用自检机制以提升可靠性。实验结果表明，Chats-Grid在保真度、上下文召回率、相关性和准确性方面分别优于现有最优方法2.37%、2.19%和3.58%。该框架通过改善决策制定与用户交互推动智能电网管理进步，助力构建具备韧性与适应性的智能电网基础设施。
英文摘要：
With rapid advancements in artificial intelligence, question-answering (Q&A) systems have become essential in intelligent search engines, virtual assistants, and customer service platforms. However, in dynamic domains like smart grids, conventional retrieval-augmented generation(RAG) Q&A systems face challenges such as inadequate retrieval quality, irrelevant responses, and inefficiencies in handling large-scale, real-time data streams. This paper proposes an optimized iterative retrieval-based Q&A framework called Chats-Grid tailored for smart grid environments. In the pre-retrieval phase, Chats-Grid advanced query expansion ensures comprehensive coverage of diverse data sources, including sensor readings, meter records, and control system parameters. During retrieval, Best Matching 25(BM25) sparse retrieval and BAAI General Embedding(BGE) dense retrieval in Chats-Grid are combined to process vast, heterogeneous datasets effectively. Post-retrieval, a fine-tuned large language model uses prompt engineering to assess relevance, filter irrelevant results, and reorder documents based on contextual accuracy. The model further generates precise, context-aware answers, adhering to quality criteria and employing a self-checking mechanism for enhanced reliability. Experimental results demonstrate Chats-Grid's superiority over state-of-the-art methods in fidelity, contextual recall, relevance, and accuracy by 2.37%, 2.19%, and 3.58% respectively. This framework advances smart grid management by improving decision-making and user interactions, fostering resilient and adaptive smart grid infrastructures.
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。
