PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation

2025-06-12

AI Summary

Addressing the dual challenges of joint segmentation across multiple temporal granularities—from system-level behavior to event-level details—and poor dynamic adaptability in multivariate time series, this paper proposes the first prompt-based unified time-series segmentation framework. The framework integrates prompt learning, boundary-aware supervision, and hierarchical state modeling to enable collaborative representation of coarse- and fine-grained states and zero-shot pattern generalization. Evaluated on heterogeneous data from manufacturing systems and wearable devices, it achieves a 24.49% improvement in multi-granularity segmentation accuracy, a 17.88% gain in single-granularity accuracy, and a 599.24% enhancement in cross-domain transfer performance. Its core innovation lies in pioneering the integration of prompt mechanisms into time-series segmentation—enabling cross-granularity joint modeling and adaptive transfer under dynamic environmental conditions.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Prompt Engineering / Prompting
• Computer Vision: Segmentation

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Multivariate time series data, collected across various fields such as manufacturing and wearable technology, exhibit states at multiple levels of granularity, from coarse-grained system behaviors to fine-grained, detailed events. Effectively segmenting and integrating states across these different granularities is crucial for tasks like predictive maintenance and performance optimization. However, existing time series segmentation methods face two key challenges: (1) the inability to handle multiple levels of granularity within a unified model, and (2) limited adaptability to new, evolving patterns in dynamic environments. To address these challenges, we propose PromptTSS, a novel framework for time series segmentation with multi-granularity states. PromptTSS uses a unified model with a prompting mechanism that leverages label and boundary information to guide segmentation, capturing both coarse- and fine-grained patterns while adapting dynamically to unseen patterns. Experiments show PromptTSS improves accuracy by 24.49% in multi-granularity segmentation, 17.88% in single-granularity segmentation, and up to 599.24% in transfer learning, demonstrating its adaptability to hierarchical states and evolving time series dynamics.

Problem

• Segments multi-granularity time series data
• Handles evolving patterns in dynamic environments
• Unifies coarse- and fine-grained state segmentation

Innovation

• Unified model with prompting mechanism
• Leverages label and boundary information
• Adapts dynamically to unseen patterns