US Patent Application 18165420. COMPUTER-READABLE RECORDING MEDIUM STORING DETERMINATION PROGRAM, DETERMINATION APPARATUS, AND METHOD OF DETERMINING simplified abstract

From WikiPatents
Jump to navigation Jump to search

COMPUTER-READABLE RECORDING MEDIUM STORING DETERMINATION PROGRAM, DETERMINATION APPARATUS, AND METHOD OF DETERMINING

Organization Name

Fujitsu Limited

Inventor(s)

Kenichiroh Narita of Kawasaki (JP)

COMPUTER-READABLE RECORDING MEDIUM STORING DETERMINATION PROGRAM, DETERMINATION APPARATUS, AND METHOD OF DETERMINING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18165420 titled 'COMPUTER-READABLE RECORDING MEDIUM STORING DETERMINATION PROGRAM, DETERMINATION APPARATUS, AND METHOD OF DETERMINING

Simplified Explanation

The patent application describes a program that determines how a computer processes data based on certain attributes.

  • The program identifies differences between two sets of data and analyzes the nonuniformity of the first set of data with respect to a specific attribute.
  • It then identifies a second attribute that has been processed with a significant amount of processing power.
  • The program determines the contribution of the second attribute to the results obtained from a machine learning model when data is input and inference is performed.
  • Based on the magnitude of this contribution, the program determines the degree of influence when training the machine learning model using the second set of data.


Original Abstract Submitted

A determination program for causing a computer to execute processing including: identifying, based on a difference between a first plurality of pieces of data and a second plurality of pieces of data obtained by processing the first plurality of pieces of data based on nonuniformity of the first plurality of pieces of data with reference to a first attribute out of a plurality of attributes, at least one second attribute processed with a processing amount larger than or equal to a predetermined threshold out of the plurality of attributes; identifying a magnitude of contribution of the at least one second attribute to an inference result in a case where data is input and a machine learning model performs inference; and determining, based on the magnitude of the contribution, an influence degree in a case where the machine learning model is trained by using the second plurality of pieces of data.