Automatic detection of user's periods of sleep and sleep stage

A method for automatically detecting periods of sleep of a user of a wearable electronic device, the wearable device comprising one or more processors, the method comprising:

• obtaining, using the one or more processors of the wearable device, motion data from one or more motion sensors in the wearable electronic device;
• defining, using the one or more processors of the wearable device, a plurality of time windows including a first time window and a second time window, the first and second time windows overlapping;
• obtaining, using the one or more processors of the wearable device, a set of feature values from the motion data including a first feature value corresponding to a first time interval and determined based on the motion data within the first time window and a second feature value corresponding to a second time interval and determine based on the motion data within the second time window, wherein the first time window comprising the first time interval and the second time interval, the second time interval being adjacent to the first time interval, and the second time window comprising the second time interval;
• classifying, using the one or more processors of the wearable device, each of the time intervals into one of a plurality of statuses of the user based on the corresponding feature value, wherein the statuses are indicative of relative degrees of movement of the user;
• consolidating, using the one or more processors of the wearable device, one or more consecutive time intervals into one or more blocks of time based at least in part on the statuses corresponding to the one or more consecutive time intervals, wherein each block of time is indicative of the user being in one of an awake state and an asleep state;
• and
• detecting, using the one or more processors of the wearable device, the periods of sleep of the user based on the consolidated blocks of time.

A computer readable storage device that includes instructions that are for automatically detecting periods of sleep of a user of a wearable electronic device and that, when executed by one or more processors, cause the one or more processors to:

• obtain motion data from one or more motion sensors in the wearable electronic device;
• define a plurality of time windows including a first time window and a second time window, the first and second time windows overlapping;
• obtain a set of feature values from the motion data including a first feature value corresponding to a first time interval and determined based on the motion data within the first time window and a second feature value corresponding to a second time interval and determine based on the motion data within the second time window, the first time window comprising the first time interval and the second time interval, the second time interval being adjacent to the first time interval, and the second time window comprising the second time interval;
• classify each of the time intervals into one of a plurality of statuses of the user based on the corresponding feature value, wherein the statuses are indicative of relative degrees of movement of the user;
• consolidate one or more consecutive time intervals into one or more blocks of time based at least in part on the statuses corresponding to the one or more consecutive time intervals, wherein each block of time is indicative of the user being in one of an awake state and an asleep state;
• and
• detect the periods of sleep of the user based on the consolidated blocks of time.