Computer-readable recording medium storing determination program, determination method, and information processing device

Patent metadata

Field	Value
Publication number	US-2024119258-A1
Application number	US-202318363431-A
Country	US
Kind code	A1
Filing date	Aug 1, 2023
Priority date	Oct 11, 2022
Publication date	Apr 11, 2024
Grant date	—

Abstract

A computer-readable recording medium storing a program for causing a computer to execute processing including: acquiring a first determination result of first graph data by performing determination processing on the first graph data; acquiring one or more first scores regarding a feature of the first graph data by using a trained model, the one or more first scores representing a basis of the first determination result of the first graph data, the trained model being a model configured to output, in response to obtaining graph data, one or more scores regarding the feature of the graph data; in a case where all of the one or more first scores are less than a threshold, specifying second graph data being a second determination result different from the first determination result; and outputting, in association with the first determination result, information regarding the feature of the second graph data.

First claim

What is claimed is:

1 . A non-transitory computer-readable recording medium storing a determination program for causing a computer to execute processing comprising:
acquiring a first determination result of first graph data by performing predetermined determination processing on the first graph data; acquiring one or more first scores regarding a predetermined feature of the first graph data by using a trained machine learning model, the one or more first scores including one or more scores representing a basis of the first determination result of the first graph data, the trained machine learning model being a trained model configured to output, in response to obtaining graph data, one or more scores regarding the predetermined feature of the graph data; in a case where all the first scores of the acquired one or more first scores are less than a threshold, referring to a storage device, to specify among one or more pieces of graph data, second graph data that is a second determination result different from the acquired first determination result, the storage device being a device that stores, for each piece of graph data of the one or more pieces of graph data, a determination result obtained by performing the predetermined determination processing on the piece of graph data; and outputting, in association with the acquired first determination result, information regarding the predetermined feature of the specified second graph data.

2 . The non-transitory computer-readable recording medium according to claim 1 , the processing further comprising:
calculating one or more second scores regarding the predetermined feature of the specified second graph data by using the trained machine learning model, wherein, in the processing of outputting, the second determination result stored in the storage unit, the specified second graph data, and the calculated one or more second scores are output in association with the acquired first determination result.

3 . The non-transitory computer-readable recording medium according to claim 2 , wherein the outputting includes
outputting, in association with the acquired first determination result, the second determination result stored in the storage device, the specified second graph data, the calculated one or more second scores, the first graph data, and the acquired one or more first scores.

4 . The non-transitory computer-readable recording medium according to claim 1 , wherein the outputting includes
in a case where at least any one first score of the acquired one or more first scores is equal to or greater than the threshold, outputting, in association with the acquired first determination result, the first graph data and the acquired one or more first scores are output.

5 . The non-transitory computer-readable recording medium according to claim 1 , wherein the trained machine learning model calculates, in response to obtaining the graph data, a score that corresponds to each element of an adjacency matrix with respect to the graph data, the calculated score being a score regarding a predetermined feature of the graph data and representing a basis of a determination result of the graph data by the predetermined determination processing.

6 . The non-transitory computer-readable recording medium according to claim 1 , the processing further including:
calculating, for each piece of graph data of the one or more pieces of graph data, an index value that indicates magnitude of a difference between the graph data and the first graph data, wherein the specifying includes in a case where all the first scores of the acquired one or more first scores are less than the threshold, referring to the storage device, to specify, among the one or more pieces of graph data, the second graph data that is a second determination result different from the acquired first determination result and that has the calculated index value less than a reference value.

7 . A determination method implemented by a computer, the determination method comprising:
acquiring, in a hardware processor of the computer, a first determination result of first graph data by performing predetermined determination processing on the first graph data; acquiring, in the hardware processor of the computer, one or more first scores regarding a predetermined feature of the first graph data by using a trained machine learning model, the one or more first scores including one or more scores representing a basis of the first determination result of the first graph data, the trained machine learning model being a trained model configured to output, in response to obtaining graph data, one or more scores regarding the predetermined feature of the graph data; in a case where all the first scores of the acquired one or more first scores are less than a threshold, referring to a storage device, to specify among one or more pieces of graph data, second graph data that is a second determination result different from the acquired first determination result, the storage device being a device that stores, for each piece of graph data of the one or more pieces of graph data, a determination result obtained by performing the predetermined determination processing on the piece of graph data; and outputting, in association with the acquired first determination result, information regarding the predetermined feature of the specified second graph data.

8 . An information processing apparatus comprising a hardware processor configured to perform determination processing including:
acquiring a first determination result of first graph data by performing predetermined determination processing on the first graph data; acquiring one or more first scores regarding a predetermined feature of the first graph data by using a trained machine learning model, the one or more first scores including one or more scores representing a basis of the first determination result of the first graph data, the trained machine learning model being a trained model configured to output, in response to obtaining graph data, one or more scores regarding the predetermined feature of the graph data; in a case where all the first scores of the acquired one or more first scores are less than a threshold, referring to a storage device, to specify among one or more pieces of graph data, second graph data that is a second determination result different from the acquired first determination result, the storage device being a device that stores, for each piece of graph data of the one or more pieces of graph data, a determination result obtained by performing the predetermined determination processing on the piece of graph data; and outputting, in association with the acquired first determination result, information regarding the predetermined feature of the specified second graph data.

Assignees

• Fujitsu Ltd

Inventors

• Komikado Tao
• Maruhashi Koji

Classifications

• G06N3/042 Primary

  Knowledge-based neural networks; Logical representations of neural networks · CPC title

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06N5/045

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title