Patent · US Active

Software navigation crash prediction system

US11521086B2 · kind B2 · utility

1Cited by
7References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 2, 2020
Grant dateDec 6, 2022
Priority date
Expiry dateMar 9, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A crash prediction computing system includes a machine learning module capable of analyzing data logs associated with each of a plurality of services or applications to identify and categorize every error, exception, and/or crash, such as those resulting from client system interactions based on crash type, customer profile type, customer screen navigation flow, time or crash. The machine learning algorithms continuously train the crash prediction models for each crash category with associated client computing system navigation flow. The crash prediction computing system applies each model before each screen/activity navigation to predict whether the next move will result in an error, exception or crash, and for each predicted error, exception, or crash, automatically implement alternate route functionality to arrive at a desired target.

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