Back to results
US 12,769,297 B2Granted
Information processing apparatus, information processing method, and computer-readable recording medium
AssigneeYokogawa Electric Corporation
InventorShinichi Miyazono
Life of this patent
Estimating the term…
Abstract
An information processing apparatus acquires pieces of normal data belonging to a plurality of intervals of measurement data measured by a device, combines the acquired pieces of normal data to generate combined data, and performs machine learning using the combined data to train a machine learning model that outputs a score indicating a normal condition of a system in which the device is installed, in response to an input of measurement data.
Claims10
An information processing apparatus comprising a processor configured to:
- acquire pieces of normal data belonging to a plurality of intervals of first measurement data previously measured by a device, for each of the intervals;
- acquire predicted normal data that is normal data among pieces of predicted data including predicted values of the first measurement data;
- combine the acquired pieces of normal data and the predicted normal data by concatenating the acquired pieces of normal data and the predicted normal data to generate combined predicted data;
- train a machine learning model by performing machine learning using the combined predicted data, wherein the machine learning model outputs a first score indicating a normal condition of a system in which the device is installed, in response to an input of the first measurement data;
- input second measurement data transmitted by the device to the trained machine learning model to output a second score indicating a normal condition of the system in which the device is installed;
- and
- detect an abnormal condition or a normal condition of the system based on the output second score.
4 more elements
An information processing method comprising:
- acquiring pieces of normal data belonging to a plurality of intervals of first measurement data previously measured by a device, for each of the intervals;
- acquiring predicted normal data that is normal data among pieces of predicted data including predicted values of the first measurement data;
- combining the acquired pieces of normal data and the predicted normal data by concatenating the acquired pieces of normal data and the predicted normal data to generate combined predicted data;
- training a machine learning model by performing machine learning using the combined predicted data, wherein the machine learning model outputs a first score indicating a normal condition of a system in which the device is installed, in response to an input of the first measurement data;
- inputting second measurement data transmitted by the device to the trained machine learning model to output a second score indicating a normal condition of the system in which the device is installed;
- and
- detecting an abnormal condition or a normal condition of the system based on the output second score.
4 more elements
An information processing apparatus comprising a processor configured to:
- acquire pieces of normal data belonging to a plurality of intervals of first measurement data previously measured by a device, for each of the intervals;
- combine the acquired pieces of normal data by concatenating the acquired pieces of normal data and re-assigning timestamps to the concatenated data to generate combined data as a single continuous time-series dataset;
- train a machine learning model by performing machine learning using the combined data, wherein the machine learning model outputs a score indicating a normal condition of a system in which the device is installed, in response to an input of the first measurement data;
- input second measurement data transmitted by the device to the trained machine learning model to output a second score indicating a normal condition of the system in which the device is installed;
- and
- detect an abnormal condition or a normal condition of the system based on the output second score.
3 more elements
Dependencies are inferred from the claim text.