Patent · US Active

Self-evolved adjustment framework for cloud-based large system based on machine learning

US10949542B2 · kind B2 · utility

0Cited by
8References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 25, 2018
Grant dateMar 16, 2021
Priority date
Expiry dateSep 5, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/022
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An approach is provided that trains neural network by receiving data inputs to a cloud-based system from users, gathering a sets of responsive system data from the cloud-based system, and training the neural network by passing the received data inputs and corresponding sets of responsive data through the neural network. After the training is performed, the approach receives user actions from a user of the cloud-based system, inputs the user actions to the trained neural network and receives one or more predicted next user actions from the trained neural network. Based on the predicted next user actions, the approach then performs a proactive response at the cloud-based system.

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