Patent · US Active

Machine-learned model selection network planning

US11853657B2 · kind B2 · utility

0Cited by
7References
19Claims
0Family size

Assignee

Inventor

Key dates

Filing dateFeb 28, 2019
Grant dateDec 26, 2023
Priority date
Expiry dateAug 30, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06Q30/0202
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and systems for data modelling. One method includes receiving a plurality of data points representing training data, and generating a plurality of models based on the training data, each of the plurality of models using at least one a different modelling methodology or a different portion of the training data. The method also includes receiving an input representing a requested prediction, generating an output based on the input using each of the plurality of models, providing the output generated by each of the plurality of models and the training data to a machine learning algorithm, generating, with the machine learning algorithm, the requested prediction using the output generated by each of the plurality of models and the training data, and outputting the requested prediction for display to a user.

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