Back to results
US 11,885,720 B2Granted
Time series data processing method
AssigneeNEC Corporation
InventorNaoki Yoshinaga
Life of this patent
Estimating the term…
Abstract
A time series data processing apparatus according to the present invention includes an extracting unit configured to extract, from normal period time series data that is time series data of a period during which a measurement target is determined to be in a normal state of time series data including a plurality of parameters based on data measured from the measurement target, a combination of the plurality of parameters in which a value of another parameter with respect to a value of a predetermined parameter is maximum among combinations of the plurality of parameters, as a normal period maximum value.
Claims10
A time series data processing method comprising:
- determining, by a processor, a plurality of first periods during which a measurement target is in a normal state, based on data measured from the measurement target;
- determining, by the processor, a second period during which the measurement target is in an anomalous state, based on the data measured from the measurement target and a threshold;
- for each first period, extracting, by the processor and from first time series data of the each first period, a first combination of a plurality of parameters in which a first value of a first parameter is maximum for a first given value of a second parameter, as a normal period maximum value;
- extracting, by the processor and from second time series data of the second period, a second combination of the plurality of parameters in which a second value of the first parameter is maximum for a second given value of the second parameter, as an anomalous period maximum value;
- updating, by the processor, the threshold used to determine whether the measurement target is in the anomalous state, as the normal period maximum value of one of the first periods, based on the normal period maximum value of each first period and based on the anomalous period maximum value;
- and
- determining, by the processor, that the measurement target is in the anomalous state based on the updated threshold.
4 more elements
An information processing apparatus comprising:
- at least one memory configured to store instructions;
- and
- at least one processor configured to execute the instructions to:
- determine a plurality of first periods during which a measurement target is in a normal state, based on data measured from the measurement target;
- determine a second period during which the measurement target is in an anomalous state, based on the data measured from the measurement target and a threshold;
- for each first period, extract, from first time series data of the each first period, a first combination of a plurality of parameters in which a first value of a first parameter is maximum for a first given value of a second, as a normal period maximum value;
- extract, from second time series data of the second period, a second combination of the plurality of parameters in which a second value of the first parameter is maximum for a second given value of the second parameter, as an anomalous period maximum value;
- update the threshold used to determine whether the measurement target is in the anomalous state, as the normal period maximum value of one of the first periods, based on the normal period maximum value of each first period and based on the anomalous period maximum value;
- and
- determine that the measurement target is in the anomalous state based on the updated threshold.
7 more elements
A non-transitory computer-readable medium storing a program executable by an information processing apparatus to:
- determine a plurality of first periods during which a measurement target is in a normal state, based on data measured from the measurement target;
- determine a second period during which the measurement target is in an anomalous state, based on the data measured from the measurement target and a threshold;
- for each first period, extract, from first time series data of the each first period, a first combination of a plurality of parameters in which a first value of a first parameter is maximum for a first given value of a second parameter, as a normal period maximum value;
- extract, from second time series data of the second period, a second combination of the plurality of parameters in which a second value of the first parameter is maximum for a second given value of the second parameter, as an anomalous period maximum value;
- update the threshold used to determine whether the measurement target is in the anomalous state, as the normal period maximum value of one of the first periods, based on the normal period maximum value of each first period and based on the anomalous period maximum value;
- and
- determine that the measurement target is in the anomalous state based on the updated threshold.
4 more elements
Dependencies are inferred from the claim text.