智能电网问答系统通过迭代检索优化，提升响应准确性和实时性。
Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid
- 结合稀疏与稠密检索，动态扩展查询覆盖多源电网数据。
- 问答准确率、相关性等指标优于现有方法2.37%至3.58%。
- 适合需要高可靠性的电网运维与智能客服场景。
随着人工智能快速发展，问答（Q&A）系统在智能搜索引擎、虚拟助手和客服平台中日益重要。然而，在智能电网等动态领域，传统检索增强生成（RAG）系统面临检索质量不足、回答无关及处理大规模实时数据流效率低等问题。本文提出面向智能电网环境的迭代检索优化框架Chats-Grid。预检索阶段，通过高级查询扩展确保对传感器读数、电表记录和控制系统参数等多源数据的全面覆盖。检索阶段，融合BM25稀疏检索与BAAI通用嵌入（BGE）稠密检索，高效处理异构大数据集。后检索阶段，微调的大语言模型利用提示工程评估相关性，过滤无关结果并按上下文准确性重排文档，进一步生成精准、上下文感知的答案，并采用自检机制提升可靠性。实验表明，该框架在保真度、上下文召回率、相关性和准确率上分别优于现有最优方法2.37%、2.19%和3.58%。该方案显著提升电网管理决策与用户交互能力，推动韧性、自适应电网基础设施发展。
原文摘要 · Abstract (English)
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.
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。