SLEEP STATE ESTIMATION DEVICE, METHOD AND STORAGE MEDIUM

1 . A sleep state estimation device attached to a user during sleep and used, comprising:

a first detector configured to detect a first signal to estimate a first state of the user;

a first estimation module configured to estimate the user's first state, based on the first signal;

a second detector configured to detect a second signal to estimate a second state of the user other than the user's first state; and

a second estimation module configured to estimate the user's second state by using the second signal, based on an estimation method determined in accordance with the first signal.

2 . The device of claim 1 , wherein

the first detector is further configured to detect an acceleration signal indicating acceleration acting the device, and

the first estimation module is further configured to estimate a body position of the user, based on the acceleration signal.

3 . The device of claim 2 , wherein

the first detector is further configured to detect first to third acceleration signals indicating accelerations in directions of first to third axes orthogonal to each other, respectively,

the second detector is further configured to detect alternating-current components of the first to third acceleration signals from the respective first to third acceleration signals, and

the second estimation module is further configured to weight the alternating-current components of the first to third acceleration signals in accordance with direct-current components of the first to third acceleration signals, respectively, and estimate a respiratory state of the user, based on the weighted alternating-current components of the first to third acceleration signals.

4 . The device of claim 3 , wherein

the second detector includes an amplifier configured to amplify each of the alternating-current components of the first to third acceleration signals.

5 . The device of claim 3 , further comprising

an electrically conductive material having elasticity which allows the device to be attached to the user.

6 . The device of claim 2 , wherein

the second detector is further configured to detect an electrocardiographic signal indicating electrocardiogram of the user, and

the second estimation module is further configured to estimate a heart rate of the user by executing a processing corresponding to the user's body position estimated based on the acceleration signal, of a plurality of processing for estimating the user's heart rate, based on the electrocardiographic signal.

7 . The device of claim 2 , wherein

the second detector is further configured to detect a sound signal produced in accordance with a respiratory state of the user, and

the second estimation module is further configured to estimate the user's respiratory state by executing a processing corresponding to the user's body position estimated based on the acceleration signal, of a plurality of processing for estimating the user's respiratory state, based on the sound signal.

8 . A sleep state estimation method executed by a sleep state estimation device attached to a user during sleep and used, the method comprising:

detecting a first signal to estimate a first state of the user;

estimating the user's first state, based on the first signal;

detecting a second signal to estimate a second state of the user other than the user's first state; and

estimating the user's second state by using the second signal, based on an estimation method determined in accordance with the first signal.

9 . A non-transitory computer-readable storage medium having stored thereon a computer program which is executable by a computer of a sleep state estimation device comprising a first detector configured to detect a first signal to estimate a first state of a user during sleep, and a second detector configured to detect a second signal to estimate a second state of the user other than the user's first state, the computer program comprising instructions capable of causing the computer to execute functions of:

estimating the user's first state, based on the first signal; and

estimating the user's second state by using the second signal, based on an estimation method determined in accordance with the first signal.