Correct answer data generation apparatus, correct answer data generation method and correct answer data generation program

Patent metadata

Field	Value
Publication number	US-12388706-B2
Application number	US-202118567312-A
Country	US
Kind code	B2
Filing date	Jun 7, 2021
Priority date	Jun 7, 2021
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

A correct data generation device 1 includes: an acquisition unit 11 that acquires alarm information output from a plurality of devices; a correlation unit 13 that associates, from the alarm information, alarms whose occurrence times are within a first time width and recovery times are within a second time width, as a group of alarms that have occurred by the same event; and a generation unit 14 that generates correct data in which identification information of the event is set for each alarm of the group of alarms that has been associated.

First claim

The invention claimed is:

1. A correct data generation device comprising:
an acquisition unit, including one or more processors, configured to acquire alarm information output from a plurality of devices;
a correlation unit, including one or more processors, configured to associate, from the alarm information, a group of alarms that have occurred by a same event, the associating comprises:
determining if two or more alarms have occurrence times within a first time width;
determining if the two or more alarms have recovery times within a second time width;
determining if the two or more alarms occurred at a same location; and
in response to determining that (i) the two or more alarms have the occurrence times within the first time width, (ii) the two or more alarms have the recovery times within the second time width, and (iii) the two or more alarms occurred at the same location, associating the two or more alarms as the group of alarms that have occurred by the same event; and
a generation unit, including one or more processors, configured to generate correct data in which identification information of the event is set for each alarm of the group of alarms that has been associated, and use the correct data to perform machine learning of an alarm correlation model configured to perform association of an alarm.

2. The correct data generation device according to claim 1 ,
wherein the alarm includes location information of a device that has issued the alarm.

3. The correct data generation device according to claim 1 ,
further comprising a configuration information storage unit in which location information of each device is stored.

4. A correct data generation method performed by a correct data generation device, the method comprising steps of:
acquiring alarm information output from a plurality of devices;
associating, from the alarm information, a group of alarms that have occurred by a same event, the associating comprises:
determining if two or more alarms have occurrence times within a first time width;
determining if the two or more alarms have recovery times within a second time width;
determining if the two or more alarms occurred at a same location; and
in response to determining that (i) the two or more alarms have the occurrence times within the first time width, (ii) the two or more alarms have the recovery times within the second time width, and (iii) the two or more alarms occurred at the same location, associating the two or more alarms as the group of alarms that have occurred by the same event; and

generating correct data in which identification information of the event is set for each alarm of the group of alarms that has been associated; and
using the correct data to perform machine learning of an alarm correlation model configured to perform association of an alarm.

5. A non-transitory computer-readable storage medium storing a program for causing a computer perform operations comprising:
acquiring alarm information output from a plurality of devices;
associating, from the alarm information, a group of alarms that have occurred by a same event, the associating comprises:
determining if two or more alarms have occurrence times within a first time width;
determining if the two or more alarms have recovery times within a second time width;
determining if the two or more alarms occurred at a same location; and
in response to determining that (i) the two or more alarms have the occurrence times within the first time width, (ii) the two or more alarms have the recovery times within the second time width, and (iii) the two or more alarms occurred at the same location, associating the two or more alarms as the group of identified alarms that have occurred by the same event; and

generating correct data in which identification information of the event is set for each alarm of the group of alarms that has been associated; and
using the correct data to perform machine learning of an alarm correlation model configured to perform association of an alarm.

6. The correct data generation method according to claim 4 , wherein the alarm includes location information of a device that has issued the alarm.

7. The correct data generation method according to claim 4 , further comprising:
storing location information of each device in a configuration information storage unit.

8. The non-transitory computer-readable storage medium according to claim 5 ,
wherein the alarm includes location information of a device that has issued the alarm.

9. The non-transitory computer-readable storage medium according to claim 5 , wherein the operations further comprise:
storing location information of each device in a configuration information storage unit.

Assignees

• Nippon Telegraph & Telephone

Inventors

• Takada Atsushi
• Hayashi Naoki
• Sato Ryosuke
• Seki Toshihiko
• Yamagoe Kyoko

Classifications

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• H04L41/0677

  Localisation of faults · CPC title

• H04L41/064 Primary

  involving time analysis · CPC title