Diagnosing and remediating errors using visual error signatures
US11314609B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Oct 24, 2019 |
| Grant date | Apr 26, 2022 |
| Priority date | — |
| Expiry date | Sep 25, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F2201/88
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes detecting an error that has occurred in one or more assets of an enterprise system and generating a visual error signature of the detected error, the visual error signature comprising at least a portion of a graph-based visualization of operation of the assets. The method also includes providing the generated visual error signature for the detected error as input to a machine learning model and utilizing the machine learning model to classify the visual error signature for the detected error as belonging to at least a given one of a plurality of error classes, the machine learning model being trained using historical visual error signatures for previously-detected errors. The method further includes identifying at least one action taken to remediate each of one or more previously-detected errors of the given error class and remediating the detected error utilizing one or more of the identified actions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.