Computer-readable recording medium storing information processing program, method for processing information, and information processing apparatus

Patent metadata

Field	Value
Publication number	US-2024161891-A1
Application number	US-202318461454-A
Country	US
Kind code	A1
Filing date	Sep 5, 2023
Priority date	Nov 16, 2022
Publication date	May 16, 2024
Grant date	—

Abstract

A medium storing a program for causing a computer to execute processing including: obtaining pieces of combination data each including attribute information indicating attributes of a person and information indicating which choice is selected from choices; generating, for each choice, converted data obtained by converting the information into information indicating whether the choice is selected; identifying, for each choice, based on the converted data, an attribute, from the attributes, that has a correlation greater than a criterion with the selection of the choice and a condition; identifying a common condition among conditions of different choices based on the condition; and determining a plan for improving a selection result of the choice for a target who matches one of the different choices and who matches the common condition based on a result of an analysis between the attributes and the choice by using the converted data matching the common condition.

First claim

What is claimed is:

1 . A non-transitory computer-readable recording medium storing an information processing program for causing a computer to execute processing comprising:
obtaining a plurality of pieces of combination data, the plurality of pieces of combination data each including attribute information indicative of one or more attributes of a target person and information indicative of which choice is selected by the target person from among a plurality of choices; generating, for each of the plurality of choices, converted data obtained by converting the information into information indicative of whether the choice is selected; identifying, for each of the plurality of choices, based on the converted data, an attribute, out of the one or more attributes, that has a correlation greater than or equal to a predetermined criterion with the selection of the choice and an attribute condition that is a condition of a value of the attribute; identifying an attribute condition common to attribute conditions of two or more different choices based on the attribute condition for each of the plurality of choices; and determining an improvement plan for improving a selection result of the choice for a target person who matches one of the two or more different choices and who matches the common attribute condition based on a result of a causality analysis between the one or more attributes and the choice by using the converted data that matches the common attribute condition.

2 . The non-transitory computer-readable recording medium according to claim 1 , wherein
the identifying of the attribute condition executes a classification of the converted data, thereby identifying the attribute, out of the one or more attributes, that has the correlation greater than or equal to the predetermined criterion with the selection of the choice and the attribute condition that is the condition of the value of the attribute.

3 . The non-transitory computer-readable recording medium according to claim 1 , wherein
the plurality of pieces of combination data are generated by a simulation based on the information indicative of the one or more attributes for each of a plurality of the target persons, and wherein the process further includes outputting a result of the simulation based on the information indicative of the one or more attributes for each of the plurality of target persons for whom a data value has been changed based on the improvement plan, and performing, in a case where a quality determination on the result of the simulation is received and a determination result of the received quality determination indicates that the result of the simulation is not good, based on the plurality of pieces of combination data generated by the simulation which corresponds to the determination result, the generating of the converted data, the identifying of the attribute condition, the identifying of the common attribute condition, and the generating of the improvement plan.

4 . The non-transitory computer-readable recording medium according to claim 1 , wherein
the determining includes identifying an attribute, from among the one or more attributes, that has a causal relationship with a specific choice included in the plurality of choices based on the result of the causality analysis, and determining an improvement plan that improves the identified attribute that has the causal relationship.

5 . The non-transitory computer-readable recording medium according to claim 4 , wherein
the causality analysis is executed by using a plurality of causality analysis algorithms, and the attribute that is determined to have the causal relationship with the specific choice in a causality analysis in which two or more causality analysis algorithms a number of which has been predetermined out of the plurality of causality analysis algorithms are used is identified as the attribute that has the causal relationship with the specific choice.

6 . An information processing method implemented by a computer, the information processing method comprising:
obtaining a plurality of pieces of combination data, the plurality of pieces of combination data each including attribute information indicative of one or more attributes of a target person and information indicative of which choice is selected by the target person from among a plurality of choices; generating, for each of the plurality of choices, converted data obtained by converting the information into information indicative of whether the choice is selected; identifying, for each of the plurality of choices, based on the converted data, an attribute, out of the one or more attributes, that has a correlation greater than or equal to a predetermined criterion with the selection of the choice and an attribute condition that is a condition of a value of the attribute; identifying an attribute condition common to attribute conditions of two or more different choices based on the attribute condition for each of the plurality of choices; and determining an improvement plan for improving a selection result of the choice for a target person who matches one of the two or more different choices and who matches the common attribute condition based on a result of a causality analysis between the one or more attributes and the choice by using the converted data that matches the common attribute condition.

7 . An information processing apparatus comprising:
a memory; and a processor circuit coupled to the memory, the processor circuit being configured to perform processing including: obtaining a plurality of pieces of combination data, the plurality of pieces of combination data each including attribute information indicative of one or more attributes of a target person and information indicative of which choice is selected by the target person from among a plurality of choices; generating, for each of the plurality of choices, converted data obtained by converting the information into information indicative of whether the choice is selected; identifying, for each of the plurality of choices, based on the converted data, an attribute, out of the one or more attributes, that has a correlation greater than or equal to a predetermined criterion with the selection of the choice and an attribute condition that is a condition of a value of the attribute; identifying an attribute condition common to attribute conditions of two or more different choices based on the attribute condition for each of the plurality of choices; and determining an improvement plan for improving a selection result of the choice for a target person who matches one of the two or more different choices and who matches the common attribute condition based on a result of a causality analysis between the one or more attributes and the choice by using the converted data that matches the common attribute condition.

Assignees

• Fujitsu Ltd

Inventors

• Chang Shuang
• Asai Tatsuya
• Maruhashi Koji

Classifications

• G06F16/9035

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06F18/213

  Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods · CPC title

• G06Q50/26 Primary

  Government or public services (business processes related to the transportation industry G06Q50/40) · CPC title

• G16H20/00 Primary

  ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance · CPC title