发表机构
University of Technology Sydney; University of Sydney（悉尼科技大学; 悉尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一个端到端框架，通过两阶段语义抽象（LLM推理与RAG流程）从原始遥测数据自动构建业务语义层，显著提升语义质量并降低维护成本。
AI 中文摘要
现代应用生成海量的原始遥测数据，但将这些嘈杂、异构的事件流转化为可操作的业务洞察仍是一个根本性挑战。数据工程师和分析师花费大量精力来调和语义差异、手工编写解析逻辑，并维护原始数据与业务KPI之间的脆弱映射。在本文中，我们提出了一个端到端框架，可从应用原始日志中全自动构建业务语义层。我们的方法引入了一种两阶段语义抽象：首先，通过结合领域特定行业知识的LLM推理识别高层业务特征；其次，通过一个包含数据精炼、混合检索、多阶段过滤、语义聚类和规范命名的结构化流程推导细粒度业务节点。在生产规模遥测数据上的评估表明，我们的系统将人工评估的语义质量从50分提高到80分以上（满分100分），将维护工作量减少80%，过滤掉74%的噪声，并通过集成的LLM-as-Judge评估实现了0.87的Cohen's kappa系数，从而实现持续、可扩展的质量保证。总体而言，我们的工作与先前工作的不同之处在于，它解决了从原始遥测数据归纳业务语义层这一新问题，且无需标记训练数据或手动规则工程。
英文摘要
Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business insights remains a fundamental challenge. Data engineers and analysts expend substantial effort reconciling semantic discrepancies, hand-crafting parsing logics, and maintaining fragile mappings between raw data and business KPIs. In this paper, we present an end-to-end framework that fully automates the construction of a business semantic layer from application raw logs. Our approach introduces a two-stage semantic abstraction: first, high-level business features are identified via LLM inference augmented with domain-specific industry knowledge; second, fine-grained business nodes are derived through a structured pipeline comprising data refinement, hybrid retrieval, multi-stage filtering, semantic clustering, and canonical naming. Evaluation on production-scale telemetry demonstrates that our system improves human-assessed semantic quality from 50 to 80+ on a 100-point scale, reduces maintenance effort by 80%, filters out 74% of noise, and achieves 0.87 Cohen's kappa via an integrated LLM-as-Judge evaluation, enabling continuous, scalable quality assurance. Overall, our work distinguishes itself from prior work by addressing the novel problem of business semantic layer induction from raw telemetry, operating without labeled training data or manual rule engineering.
