Information processing device, information processing method and non-transitory computer readable medium

Patent metadata

Field	Value
Publication number	US-2019204124-A1
Application number	US-201916238679-A
Country	US
Kind code	A1
Filing date	Jan 3, 2019
Priority date	Jan 4, 2018
Publication date	Jul 4, 2019
Grant date	—

Abstract

According to one embodiment, an information processing device includes an anomaly detector and an integration unit. The anomaly detector is configured to estimate a degree of drift anomaly based on measured values of a sensor during a sub-period which is a part of a monitored period. The integration unit is configured to estimate the degree of drift anomaly accumulated within the monitored period based on the estimated degrees of drift anomaly accumulated within the sub-periods. Symptoms of a drift anomaly include mismatches between the actual values and measured values.

First claim

1 . An information processing device comprising:
an anomaly detector configured to estimate a degree of drift anomaly based on measured values of a sensor during a sub-period which is a part of a monitored period; and an integration unit configured to estimate the degree of drift anomaly accumulated within the monitored period based on the degrees of drift anomaly accumulated within the sub-periods; wherein symptoms of a drift anomaly include mismatches between the actual values and measured values.

2 . The information processing device according to claim 1 , wherein
the integration unit is configured to determine whether the drift anomaly has occurred based on an estimated degree of drift anomaly accumulated within the monitored period.

3 . The information processing device according to claim 2 , further comprising a display device which is configured to display at least whether the drift anomaly has occurred or the degree of drift anomaly on the sensor.

4 . The information processing device according to claim 2 , wherein
the degree of drift anomaly is an amount of drift indicating a size of mismatch between the actual values and the measured values of the sensor, and the integration unit is configured to estimate the amount of drift accumulated within the monitored period.

5 . The information processing device according to claim 2 , further comprising a sub-period generator which is configured to generate the sub-period.

6 . The information processing device according to claim 5 , wherein
the sub-period generator is configured to generate a plurality of sub-periods, and the integration unit is configured to determine whether the drift anomaly has occurred within the monitored period by estimating the degree of drift anomaly accumulated within the monitored period based on the estimated degrees of drift anomaly accumulated within the sub-periods.

7 . The information processing device according to claim 6 , wherein
the anomaly detector is configured to concurrently estimate the degrees of drift anomaly based on the measured values of the sensors during the plurality of sub-periods.

8 . The information processing device according to claim 6 , wherein
the sub-period generator is configured to generate sub-periods with overlapping periods, and the integration unit is configured to use the estimated degree of drift anomaly for at least one of the sub-periods if the sub-periods include overlapping periods, when estimating the degree of drift anomaly accumulated within the monitored period.

9 . The information processing device according to claim 6 , wherein
the sub-period generator is configured to generate sub-periods by dividing the monitored period.

10 . The information processing device according to claim 5 , wherein
the sub-period generator is configured to generate a sub-period excluding a part of the monitored period, and the integration unit is configured to estimate the degree of drift anomaly accumulated within the excluded part of the monitored period, based on the degree of drift anomaly estimated for the sub-period, when estimating the degree of drift anomaly accumulated within the monitored period.

11 . The information processing device according to claim 5 , wherein
the anomaly detector is configured to calculate a degree of reliability of the degree of drift anomaly estimated for the sub-period, and the sub-period generator is configured to determine whether the sub-period is generated again or not, based on the degree of reliability.

12 . The information processing device according to claim 5 , wherein
the anomaly detector is configured to determine whether estimation of the degree of drift anomaly is successful for the sub-period, and the sub-period generator is configured to generate the sub-period again if the anomaly detector determines that the estimation of the degree of drift anomaly is failed.

13 . The information processing device according to claim 1 , wherein
the anomaly detector is configured to estimate the degree of drift anomaly multiple times for the sub-period, and the integration unit is configured to determine whether the drift anomaly has occurred in the sensor by selecting the degrees of drift anomaly and estimating the degree of drift anomaly accumulated within the monitored period, multiple times.

14 . An information processing method comprising the steps of:
generating sub-periods which are parts of a monitored period; estimating degrees of drift anomaly based on measured values of sensors during the sub-periods; estimating the degree of drift anomaly accumulated within the monitored period, based on the estimated degrees of drift anomaly for the sub-periods; determining whether a drift anomaly has occurred in a sensor based on the estimated degree of drift anomaly accumulated within the monitored period; and displaying whether the drift anomaly has occurred in the sensor,
wherein symptoms of drift anomaly include mismatches between the actual values and measured values.

15 . A non-transitory storage medium having a computer program stored therein which causes a computer to execute processes comprising:
generating sub-periods which are parts of a monitored period; estimating degrees of drift anomaly based on measured values of sensors during the sub-periods; estimating the degree of drift anomaly accumulated within the monitored period, based on the estimated degrees of drift anomaly for the sub-periods; determining whether a drift anomaly has occurred in a sensor based on the estimated degree of drift anomaly accumulated within the monitored period; and displaying whether the drift anomaly has occurred in the sensor, wherein symptoms of the drift anomaly include mismatches between the actual values and measured values.

Assignees

• Toshiba Kk
• Kabushiki Kaish·a Toshiba

Inventors

• Moriyama Takuro
• Ishii Gaku

Classifications

• G01D18/00 Primary

  Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00 · CPC title

• G01D3/032 Primary

  affecting incoming signal, e.g. by averaging; gating undesired signals · CPC title