Motion pattern recognition for device power policies
The present disclosure is directed to routine recognition for adjusting the power state of a device. Human activity recognition is performed to detect various activity states, and create a current sequence of activity states. In response to detecting a new activity state, routine comparison is performed in order to compare the current sequence to a past sequence that ended with the user starting to interact with the device. The device is preemptively turned on in response to finding a match.
1 . A device, comprising:
a motion sensor configured to generate motion measurements; and
a processor coupled to the motion sensor, the processor configured to:
detect a plurality of activity states based on the motion measurements, the detected plurality of activity states including a stationary state in which the device has a determined amount of movement, a walking state in which a user is walking with the device, and a transport state in which the user is traveling in a vehicle with the device;
generate a current sequence of activity states based on the detected plurality of activity states;
compare the current sequence of activity states to a database sequence of activity states stored in a database; and
set the device to an ON state in a case where the current sequence of activity states corresponds to the database sequence of activity states.
2 . The device of claim 1 wherein the database sequence of activity states is a sequence that terminates with the user interacting with the device.
3 . The device of claim 1 wherein
the database sequence of activity states is a sequence that starts upon detection of a transition from a super still state in which the device remains still to another activity state after the super still state has been detected consecutively for a determined amount of time, and
the database sequence of activity states is a sequence that terminates with the user interacting with the device.
4 . The device of claim 1 wherein the processor is configured to determine the current sequence of activity states corresponds to the database sequence of activity states based on a duration distance, a unique distance, or a histogram distance.
5 . The device of claim 1 wherein the processor is configured to determine the current sequence of activity states corresponds to the database sequence of activity states in a case where a duration distance is below a first threshold value, a unique distance is below a second threshold value, and a histogram distance is below a third threshold value.
6 . The device of claim 1 wherein
the detected plurality of activity states includes a super still state in which the device remains still, and
the current sequence of activity states is a sequence that starts upon detection of a transition from the super still state to another activity state after the super still state has been detected consecutively for a determined amount of time.
7 . The device of claim 1 wherein the processor is configured to:
store the current sequence of activity states in the database in a case where the user interacts with the device.
8 . The device of claim 1 wherein the current sequence of activity states are the detected plurality of activity states arranged in sequential order.
9 . A method, comprising:
generating motion measurements of a device;
detecting a plurality of activity states based on the motion measurements, the detected plurality of activity states including a stationary state in which the device has a determined amount of movement, a walking state in which a user is walking with the device, and a transport state in which the user is traveling in a vehicle with the device;
generating a current sequence of activity states based on the detected plurality of activity states;
comparing the current sequence of activity states to a database sequence of activity states stored in a database; and
setting the device to an ON state in a case where the current sequence of activity states corresponds to the database sequence of activity states.
10 . The method of claim 9 , further comprising:
detecting a transition from a super still state in which the device remains still;
starting generation of the database sequence of activity states in response to detecting the transition from the super still state after the super still state has been detected consecutively for a determined amount of time;
detecting the user interacting with the device;
terminating the generation of the database sequence of activity states in response to detecting the user interacting with the device; and
storing the database sequence of activity states in the database in response to terminating the generation of the database sequence of activity states.
11 . The method of claim 9 , further comprising:
determining the current sequence of activity states corresponds to the database sequence of activity states based on a duration distance, a unique distance, or a histogram distance.
12 . The method of claim 9 , further comprising:
determining the current sequence of activity states corresponds to the database sequence of activity states in a case where a duration distance is below a first threshold value, a unique distance is below a second threshold value, and a histogram distance is below a third threshold value.
13 . The method of claim 9 wherein
the detected plurality of activity states includes a super still state in which the device remains still, and
the method further includes generating the current sequence of activity states in response to detecting a transition from the super still state to another activity state after the super still state has been detected consecutively for a determined amount of time.
14 . The method of claim 9 , further comprising:
storing the current sequence of activity states in the database in case where the user interacts with the device.
15 . A method, comprising:
generating motion measurements of a device;
detecting a plurality of activity states of the device based on the motion measurements, the detected plurality of activity states including a super still state in which the device remains still, a stationary state in which the device has a determined amount of movement, a walking state in which a user is walking with the device, and a transport state in which the user is traveling in a vehicle with the device;
generating, in response to detecting a transition from the super still state to another activity state after the super still state has been detected consecutively for a determined amount of time, a current sequence of activity states that includes activity states of the detected plurality of activity states;
determining whether or not the current sequence of activity states corresponds to a database sequence of activity states that terminates with the user interacting with the device;
setting the device to an ON state in a case where the current sequence of activity states corresponds to the database sequence of activity states; and
determining whether or not the current sequence of activity states corresponds to another database sequence of activity states that terminated with the user interacting with the device in a case where the current sequence of activity states does not correspond to the database sequence of activity states.
16 . The method of claim 15 , further comprising:
storing the current sequence of activity states in a database in case where the user interacts with the device.