Simulation method and information processing apparatus

Patent metadata

Field	Value
Publication number	US-2026073094-A1
Application number	US-202519387730-A
Country	US
Kind code	A1
Filing date	Nov 13, 2025
Priority date	May 18, 2023
Publication date	Mar 12, 2026
Grant date	—

Abstract

A computer obtains simulation result data including a plurality of records corresponding to a plurality of agents that act within a designated space, each of the plurality of records including attribute values of a plurality of attributes concerning an action result of one agent among the plurality of agents. Based on the simulation result data, the computer detects one or more causal relationships among the plurality of attributes, each causal relationship indicating that one attribute is a cause of another attribute. Based on the one or more causal relationships, the computer determines, among the plurality of attributes, a cause attribute that indicates a cause for a target attribute indicating an evaluation of the space. The computer outputs information corresponding to the cause attribute.

First claim

What is claimed is:

1 . A non-transitory computer-readable storage medium storing a computer program that causes a computer to perform a process comprising:
obtaining simulation result data including a plurality of records corresponding to a plurality of agents that act within a designated space, each of the plurality of records including attribute values of a plurality of attributes concerning an action result of one agent among the plurality of agents; detecting, based on the simulation result data, one or more causal relationships among the plurality of attributes, each indicating that one of the plurality of attributes is a cause of another of the plurality of attributes; determining, based on the one or more causal relationships, a cause attribute among the plurality of attributes that indicates a cause for a target attribute that indicates an evaluation of the space; and outputting information corresponding to the cause attribute.

2 . The non-transitory computer-readable storage medium according to claim 1 , wherein the information corresponding to the cause attribute includes modification proposal information that indicates a method for modifying the space in order to change an attribute value of the cause attribute.

3 . The non-transitory computer-readable storage medium according to claim 1 , wherein
the process further includes extracting, from the plurality of attributes, two or more attributes of a type selected from the group consisting of a goal attribute that indicates a goal of the one agent, an action attribute that indicates an action executed by the one agent, an environment attribute that indicates an interaction between the one agent and the space, an external factor attribute that indicates a constraint imposed on the one agent by the space, and the target attribute, and the detecting of the one or more causal relationships includes detecting the one or more causal relationships among the two or more attributes.

4 . The non-transitory computer-readable storage medium according to claim 1 , wherein
the process further includes calculating a causal effect between the target attribute and another attribute among the plurality of attributes based on the simulation result data, and the determining of the cause attribute includes determining the cause attribute based on the one or more causal relationships and the causal effect.

5 . The non-transitory computer-readable storage medium according to claim 4 , wherein
the plurality of records includes records having different attribute values of an external factor attribute among the plurality of attributes, the external factor attribute indicating a constraint imposed on the one agent by the space, and the calculating of the causal effect includes calculating the causal effect for each group of records having the same attribute value of the external factor attribute.

6 . The non-transitory computer-readable storage medium according to claim 1 , wherein the process further includes:
accepting, after the outputting of the information corresponding to the cause attribute, spatial information indicating a modified space; and simulating actions of the plurality of agents within the modified space.

7 . A simulation method comprising:
obtaining, by a processor, simulation result data including a plurality of records corresponding to a plurality of agents that act within a designated space, each of the plurality of records including attribute values of a plurality of attributes concerning an action result of one agent among the plurality of agents; detecting, by the processor, based on the simulation result data, one or more causal relationships among the plurality of attributes, each indicating that one of the plurality of attributes is a cause of another of the plurality of attributes; determining, by the processor, based on the one or more causal relationships, a cause attribute among the plurality of attributes that indicates a cause for a target attribute that indicates an evaluation of the space; and outputting, by the processor, information corresponding to the cause attribute.

8 . An information processing apparatus comprising:
a memory configured to store simulation result data including a plurality of records corresponding to a plurality of agents that act within a designated space, each of the plurality of records including attribute values of a plurality of attributes concerning an action result of one agent among the plurality of agents; and a processor coupled to the memory and the processor configured to:
detect, based on the simulation result data, one or more causal relationships among the plurality of attributes, each indicating that one of the plurality of attributes is a cause of another of the plurality of attributes;
determine, based on the one or more causal relationships, a cause attribute among the plurality of attributes that indicates a cause for a target attribute that indicates an evaluation of the space; and
output information corresponding to the cause attribute.

Assignees

• Fujitsu Ltd

Inventors

• Chang Shuang
• Maruhashi Koji

Classifications

• G06N5/04

  Inference or reasoning models · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title