Patent · US Active

Machine learning technique to diagnose software crashes

US12045124B2 · kind B2 · utility

0Cited by
0References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 25, 2021
Grant dateJul 23, 2024
Priority date
Expiry dateOct 13, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2201/83
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method includes receiving a crash signature and a crash configuration. The crash signature is generated in response to a software crash in a software application caused by the crash configuration. The method also includes applying a first machine learning model to determine a reference of a plurality of references that is closest to the crash signature and the crash configuration. The reference includes a reference crash signature and a reference configuration. The reference crash signature and the reference configuration are generated by a proxy crash to the software crash. The proxy crash was generated prior to the software crash by executing a modified test case against the software application.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.