用结构化方式解释两段时间序列的差异，无需专家经验。
DiffNator: Generating Structured Explanations of Time-Series Differences
- 设计JSON schema定义时序差异的核心特征。
- 在TORI数据集上训练模型，准确生成差异解释。
- 适合物联网异常检测与自动化诊断场景。
在众多物联网应用中，关注重点并非单个传感器信号，而是信号间的差异，但理解这些差异需依赖专业知识。本文提出DiffNator框架，用于生成两个时间序列差异的结构化解释。首先设计一种JSON模式，捕捉差异的关键属性；基于真实物联网时间序列数据集TORI，构建成对序列并训练模型，该模型结合时间序列编码器与冻结的大型语言模型，输出格式化的JSON解释。实验表明，DiffNator能生成高精度的差异解释，在性能上显著优于视觉问答基线和使用预训练时序编码器的检索方法。
原文摘要 · Abstract (English)
In many IoT applications, the central interest lies not in individual sensor signals but in their differences, yet interpreting such differences requires expert knowledge. We propose DiffNator, a framework for structured explanations of differences between two time series. We first design a JSON schema that captures the essential properties of such differences. Using the Time-series Observations of Real-world IoT (TORI) dataset, we generate paired sequences and train a model that combine a time-series encoder with a frozen LLM to output JSON-formatted explanations. Experimental results show that DiffNator generates accurate difference explanations and substantially outperforms both a visual question answering (VQA) baseline and a retrieval method using a pre-trained time-series encoder.
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。