| 摘要 |
<p>The present technique relates to an information processing device, an information processing method, and a program, whereby the value of a target variable can be set with high accuracy. A log acquisition part acquires target time series data corresponding to a target variable that it is desired to estimate, and a plurality of series of explanatory time series data which is time series data that corresponds to a plurality of explanatory variables that explain a target variable. Using the acquired target time series data and plurality of series of description time series data, a model parameter updating part learns parameters of a probability model. On the basis of a parameter of the probability model obtained through learning, a log selection part selects an explanatory variable corresponding to the description time series data acquired by the log acquisition part. On the basis of the results of selection by the selection part, an estimation part, using the plurality of series of description time series data acquired by the log acquisition part, estimates a value of the target variable. The present technique can be applied, for example, to an information processing device for estimating power consumption by a machine.</p> |
