IP Library › Granted Patent US 12,517,779
Granted Patent B2
US 12,517,779 · App. 18/444,056 · Granted Jan 6, 2026

Method, program, system, and device for estimating cause of problem

Inventor: Shuichi Kurabayashi (Tokyo, JP)
Assignee: CYGAMES, INC.
G06F11/079A63F13/40G06F11/3476
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,517,779
App. No.
18/444,056
Granted
Jan 6, 2026
Kind
B2
Abstract

One or more embodiments of the invention is a method for estimating the cause of a problem from game log data in a game that proceeds in accordance with actions selected by users, whereby a game state is updated, the method including a step of determining, for a combination of an action preceding the occurrence of the problem and a prescribed game state element included in a game state relating to that action, the action and the game state element being included in one irregular-log-data array among irregular-log-data arrays, whether or not the combination is a cause of the occurrence of the problem on the basis of the degree of presence of the combination in the irregular-log-data arrays included in the game log data and the degree of presence of the same combination in regular-log-data arrays included in the game log data.

Claims (39)

1 . A method comprising:

generating, by a computer, a virtual environment for executing a game service of a computer game,

wherein the virtual environment employs a virtual game server, a virtual terminal device, and a virtual database server to produce an end-to-end virtualization of the computer game, and

wherein the game service is provided by the virtual game server to the virtual terminal device via a network;

executing, by the computer, a plurality of auto-plays of the game service using the virtual environment to produce a plurality of game logs;

detecting, by the computer and during a respective auto-play among the plurality of auto-plays, a game error in a respective game log among the plurality of game logs;

assigning, by the computer, an irregular label to a first game log among the plurality of game logs in response to detecting the game error to produce a plurality of irregular-log-data arrays;

assigning, by the computer, a regular label to a second game log among the plurality of game logs in response to detecting no error occurred to produce a plurality of regular-log-data arrays;

determining, by the computer, an action preceding an occurrence of the game error in the respective auto-play and a game state element relating to the action using a respective irregular-log-data array among the plurality of irregular-log-data arrays; and

determining, by the computer, whether a combination of the action and the game state element is a cause of the occurrence of the game error based on a degree of presence of the combination in the plurality of irregular- log-data arrays and a degree of presence of the combination in the plurality of regular-log-data arrays.

2 . The method according to claim 1 , wherein determining the combination of the action and the game state element is the cause of the occurrence of the game error is further based on a ratio of a first value based on the degree of presence of the combination in the plurality of irregular-log-data arrays to a second value based on the degree of presence of the combination in the plurality of regular-log-data arrays being greater than or equal to a prescribed value.

3 . The method according to claim 1 , the method comprising:

extracting the game state element from a plurality of game state elements in the respective auto-play.

4 . The method according to claim 1 , wherein determining the cause of the occurrence of the game error is based on one action immediately preceding the occurrence of the game error in the respective auto-play.

5 . The method according to claim 1 , wherein determining the cause of the occurrence of the game error is based on two or more actions immediately preceding the occurrence of the game error in the respective auto-play.

6 . A non-transitory computer readable medium storing a program for causing the computer to execute the method according to claim 1 .

7 . An estimating system comprising:

a processor; and

a memory connected to the processor, wherein the memory comprises a program configured to perform a method comprising:

generating a virtual environment for executing a game service of a computer game,

wherein the virtual environment employs a virtual game server, a virtual terminal device, and a virtual database server to produce an end-to-end virtualization of the computer game, and

wherein the game service is provided by the virtual game server to the virtual terminal device via a network;

executing a plurality of auto-plays of the game service using the virtual environment to produce a plurality of game logs;

detecting, during a respective auto-play among the plurality of auto-plays, a game error in a respective game log among the plurality of game logs;

assigning an irregular label to a first game log among the plurality of game logs in response to detecting the game error to produce a plurality of irregular-log-data arrays;

assigning a regular label to a second game log among the plurality of game logs in response to detecting no error occurred to produce a plurality of regular-log-data arrays;

determining an action preceding an occurrence of the game error in the respective auto-play and a game state element relating to the action using a respective irregular-log-data array among the plurality of irregular-log-data arrays; and

determining whether a combination of the action and the game state element is a cause of the occurrence of the game error based on a degree of presence of the combination in the plurality of irregular-log-data arrays and a degree of presence of the combination in the plurality of regular-log-data arrays.

8 . An estimating device comprising:

a processor; and

a memory connected to the processor, wherein the memory comprises a program configured to perform a method comprising:

generating a virtual environment for executing a game service of a computer game,

wherein the virtual environment employs a virtual game server, a virtual terminal device, and a virtual database server to produce an end-to-end virtualization of the computer game, and

wherein the game service is provided by the virtual game server to the virtual terminal device via a network;

executing a plurality of auto-plays of the game service using the virtual environment to produce a plurality of game logs;

wherein the plurality of game logs comprise a plurality of irregular-log-data arrays that are assigned an irregular label in response to detecting at least one game error, and

wherein the plurality of game logs comprise a plurality of regular-log-data arrays that are assigned an irregular label in response to detecting no game errors;

determining an action preceding an occurrence of the at least one game error in a respective auto-play among the plurality of auto-plays and a game state element relating to the action using a respective irregular-log-data array among the plurality of irregular-log-data arrays; and

determining whether a combination of the action and the game state element is a cause of the occurrence of the at least one game error based on a degree of presence of the combination in the plurality of irregular-log-data arrays and a degree of presence of the combination in the plurality of regular-log-data arrays.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2025
From: KURABAYASHI, SHUICHI
To: CYGAMES, INC.
Reel/Frame 073129/0814 →
Priority Claims (1)
JP 2021-132934 · Aug 17, 2021 · national
Continuity (2)
Continuation PCTJP2022030951 · Aug 16, 2022
Related Publication 20240184660A1 · Jun 6, 2024
References Cited (19)
US 10282280B1 · Gouskova · 2019 [cited by examiner]
US 10891219B1 · Dimitropoulos · 2021 [cited by examiner]
US 11331580B2 · Kurabayashi · 2022 [cited by applicant]
US 11874764B2 · Jang · 2024 [cited by examiner]
US 20050288103A1 · Konuma · 2005 [cited by examiner]
US 20100190551A1 · Iwakiri · 2010 [cited by examiner]
US 20120209571A1 · Peterson · 2012 [cited by examiner]
US 20160310850A1 · Covington · 2016 [cited by examiner]
US 20200192788A1 · Seo · 2020 [cited by examiner]
US 20210001231A1 · Kurabayashi · 2021 [cited by applicant]
US 20220032199A1 · Rudi · 2022 [cited by examiner]
US 20220197784A1 · Jang · 2022 [cited by examiner]
US 20230014321A1 · Nair · 2023 [cited by examiner]
US 20230121618A1 · Rudi · 2023 [cited by examiner]
US 20240050858A1 · Sestini · 2024 [cited by examiner]
US 20240184660A1 · Kurabayashi · 2024 [cited by examiner]
US 20250041734A1 · Takashima · 2025 [cited by examiner]
JP 6438612B1 · 2018 [cited by applicant]
“Cygames is developing AI system for automating game debugging”, Retrieved from the Internet on Jul. 27, 2021; Retrieved from the Internet: URL:https://www.nikkan.co.jp/articles/view/00591096 (7 pages). [cited by applicant]