State estimation device, method and program

Abstract

In an embodiment of this invention, in a learning phase, a state estimation device acquires activity state data and biometric data at that time from user terminals of a plurality of users, generates a regression formula representing the relationship between the biometric data and the activity state data using a regression analysis method on the basis of these pieces of measurement data, and calculates a difference between the coefficients of the regression formula of all users and each user to generate a coefficient correction regression formula representing a relationship between the difference of the coefficient and an average value of the biometric data. In an estimation phase, the state estimation device acquires biometric data of a new user, corrects a coefficient value of an activity state estimation regression formula to a coefficient value for the new user on the basis of the average value of the biometric data and the coefficient correction regression formula, and estimates the activity state of the new user using the regression formula having the corrected coefficient.

Dependencies are inferred from the claim text.