Patent · US Active

Learned model integration method, apparatus, program, IC chip, and system

US11475371B2 · kind B2 · utility

0Cited by
7References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 26, 2018
Grant dateOct 18, 2022
Priority date
Expiry dateFeb 1, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A learned model integration method for integrating multiple different learned models obtained by letting a learning model learn a predetermined data group, the learning model having a tree structure in which multiple nodes associated with respective hierarchically divided state spaces are hierarchically arranged, the method includes: a data reading step of reading data related to the multiple different learned models from a predetermined memory unit; and an integrating step in which, for each node constituting a tree structure related to the multiple different learned models, when a node exists in only one learned model, the node is duplicated, and when nodes exist in corresponding positions in the multiple learned models, the corresponding nodes are integrated, thereby integrating the multiple different learned models into a single learned model.

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