Abstract
The technology described in this paper relates to an agentic AI method for the automated visual analysis of telemetry plots provided in image format. The method involves identifying time-series characteristics within an image, such as axes and trends, and utilizing dependency-awareness to prioritize relevant data. Significant events are detected by analyzing value changes relative to plot scales, with a specific focus on identifying correlated shifts across multiple time series. These events are subsequently categorized into types, such as sustained increases or slow degrades, and summarized in a structured format. This approach automates the interpretation of graphical patterns to accelerate event identification and improve debugging efficiency without requiring manually defined thresholds or algorithms.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
N/A and , "AI-Powered Visual Analysis of Telemetry Time Series Images for Event Identification", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/9839