让非专家用自然语言查询时间序列数据，精准定位异常和模式。
Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
- 先搜索后验证：用SQL快速筛选候选区间，再用程序验证信号特征。
- 在超长历史数据上表现优异，准确率显著高于传统方法。
- 首次构建大规模评测基准，适合时序数据分析与工具研发者。
面向时间序列数据库的自然语言查询（NLQ4TSDB）旨在帮助非专业用户从海量时序记录中检索有意义的事件、时间段和摘要。现有文本转SQL方法难以处理形状或异常等连续形态意图，而时序模型又无法有效应对超长历史数据。为此，我们提出Sonar-TS，一种神经符号框架，采用“搜索-验证”流程解决该问题。类比主动声呐，它利用特征索引通过SQL快速探测候选窗口，再由生成的Python程序对原始信号进行精确定位与验证。为支持有效评估，我们构建了NLQTSBench——首个针对时序数据库规模历史数据设计的大规模基准。实验揭示了该领域特有的挑战，并证明Sonar-TS在复杂时序查询中优于传统方法。本工作首次系统研究了NLQ4TSDB，提供通用框架与评估标准，推动后续研究发展。
原文摘要 · Abstract (English)
Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records. However, existing Text-to-SQL methods are not designed for continuous morphological intents such as shapes or anomalies, while time series models struggle to handle ultra-long histories. To address these challenges, we propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline. Analogous to active sonar, it utilizes a feature index to ping candidate windows via SQL, followed by generated Python programs to lock on and verify candidates against raw signals. To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories. Our experiments highlight the unique challenges within this domain and demonstrate that Sonar-TS effectively navigates complex temporal queries where traditional methods fail. This work presents the first systematic study of NLQ4TSDB, offering a general framework and evaluation standard to facilitate future research.
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。