DBAIOps：一种使用知识图谱的推理大语言模型增强数据库运维系统
DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs
AI总结：
DBAIOps结合推理大语言模型与知识图谱，构建混合数据库运维系统，通过异构图、800+异常模型和两阶段图演化实现DBA风格诊断，在四个主流数据库上显著提升根本原因和人工评估准确率。
摘要：
数据库系统的运维（O&M）对于确保系统可用性和性能至关重要，通常需要专家经验（例如，识别指标与异常之间的关系）来进行有效的诊断和恢复。然而，现有的自动数据库运维方法，包括商业产品，无法有效利用专家经验。一方面，基于规则的方法仅支持基本的运维任务（例如，基于指标的异常检测），这些方法大多是数值方程，无法有效整合文字形式的运维经验（例如，手册中的故障排除指南）。另一方面，基于大语言模型（LLM）的方法，检索碎片化信息（例如，标准文档+检索增强生成RAG），往往生成不准确或通用的结果。为解决这些局限性，我们提出了DBAIOps，一种新颖的混合数据库运维系统，将推理大语言模型与知识图谱相结合，以实现DBA风格的诊断。首先，DBAIOps引入了一种异构图模型来表示诊断经验，并提出了一种半自动图构建算法，从数千份文档中构建该图。其次，DBAIOps开发了一组（800多个）可复用的异常模型，这些模型既能识别直接告警的指标，也能识别隐含相关的经验和指标。第三，对于每个异常，DBAIOps提出了一种两阶段图演化机制，以自动探索相关的诊断路径并识别缺失的关系。然后，它利用推理大语言模型（例如，DeepSeek-R1）来推断根本原因，并为DBA和普通用户生成清晰的诊断报告。我们在四个主流数据库系统（Oracle、MySQL、PostgreSQL和DM8）上的评估表明，DBAIOps在根本原因准确率和人工评估准确率上分别比最先进的基线高出34.85%和47.22%。
英文摘要：
The operation and maintenance (O&M) of database systems is critical to ensuring system availability and performance, typically requiring expert experience (e.g., identifying metric-to-anomaly relations) for effective diagnosis and recovery. However, existing automatic database O&M methods, including commercial products, cannot effectively utilize expert experience. On the one hand, rule-based methods only support basic O&M tasks (e.g., metric-based anomaly detection), which are mostly numerical equations and cannot effectively incorporate literal O&M experience (e.g., troubleshooting guidance in manuals). On the other hand, LLM-based methods, which retrieve fragmented information (e.g., standard documents + RAG), often generate inaccurate or generic results. To address these limitations, we present DBAIOps, a novel hybrid database O&M system that combines reasoning LLMs with knowledge graphs to achieve DBA-style diagnosis. First, DBAIOps introduces a heterogeneous graph model for representing the diagnosis experience, and proposes a semi-automatic graph construction algorithm to build that graph from thousands of documents. Second, DBAIOps develops a collection of (800+) reusable anomaly models that identify both directly alerted metrics and implicitly correlated experience and metrics. Third, for each anomaly, DBAIOps proposes a two-stage graph evolution mechanism to explore relevant diagnosis paths and identify missing relations automatically. It then leverages a reasoning LLM (e.g., DeepSeek-R1) to infer root causes and generate clear diagnosis reports for both DBAs and common users. Our evaluation over four mainstream database systems (Oracle, MySQL, PostgreSQL, and DM8) demonstrates that DBAIOps outperforms state-of-the-art baselines, 34.85% and 47.22% higher in root cause and human evaluation accuracy, respectively.
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。
