Adjusting Mobile Device State Based on User Intentions and/or Identity

• US 20140025973A1
• Filed: 07/20/2012
• Published: 01/23/2014
• Est. Priority Date: 07/20/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Schillings, Benoit M., Garcia, David Harry
• Granted Patent: US 9,052,896 B2
• Time in Patent Office: Days
• US Class Current: 713/323
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04Q 2209/10 using a centralized architecture
• CPC Class Codes: H04Q 2209/43 using wireless personal area networks [WPAN], e.g. 802.15, 802.15.1, 802.15.4, Bluetooth or ZigBee
• CPC Class Codes: H04Q 2209/47 using RFID associated with sensors
• CPC Class Codes: H04Q 2209/50 using a mobile data collecting device, e.g. walk by or drive by
• CPC Class Codes: H04Q 2209/823 where the data is sent when the measured values exceed a threshold, e.g. sending an alarm
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
• CPC Class Codes: H04W 52/0212 managed by the network, e.g. network or access point is master and terminal is slave
• CPC Class Codes: H04W 52/0254 detecting a user operation or a tactile contact or a motion of the device
• CPC Class Codes: H04W 8/22 Processing or transfer of terminal data, e.g. status or physical capabilities
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

In one embodiment, when a computing system is in a first state, a first set of inputs from one or more first sensors is detected. A first sensor value array is generated, and the first value array is fed as input to a first function generated by a first neural network. One or more first output values are calculated based on the first function, and a determination is made based on these first output values if a first action has occurred. If a first action has occurred, a second sensor value array is generated from a second set of inputs from one or more second sensors. The second sensor value array is fed as input to a second function generated by a second neural network. One or more second output values are calculated based on the second function, and the first state is exited based on these second output values.

Claims

1. A method comprising, by one or more computing systems:

detecting, while the one or more computing systems is in a first state, a first set of inputs from a plurality of first sensors;

generating a first sensor value array, each of the sensor values in the first sensor value array corresponding to one of the first set of inputs;

feeding the first sensor value array as input to a first function generated by a first neural network;

calculating one or more first output values based at least in part on the first function;

determining, based at least in part on the one or more first output values, if a first action has occurred; and

in response to a determination that a first action has occurred;

polling one or more second sensors for a second set of sensor inputs;

generating a second sensor value array including a second set of sensor values, each of the second set of sensor values corresponding to one of the second set of sensor inputs;

feeding the second sensor value array as input to a second function generated by a second neural network;

calculating one or more second output values based at least in part on the second function; and

based at least in part on the one or more second output values returned by the second function, exiting the first state.

2. The method of claim 1, wherein the one or more first output values are calculated by a low-power microcontroller;

and in response to a determination that a first action has occurred, the micro-controller wakes up a processor from a sleep mode for calculation of the one or more second output values.

3. The method of claim 1, wherein the first sensors comprise touch sensors.

4. The method of claim 3, wherein the touch sensors are capacitive.

5. The method of claim 1, wherein the one or more second sensors comprise:

an accelerometer;

a light sensor;

or

a multi-touch display surface.

6. The method of claim 1, wherein the first state is a locked state.

7. The method of claim 1, wherein the first action is a grab action.

8. The method of claim 1, wherein the first and second functions are received from a server.

9. A method comprising, by one or more computing systems:

transmitting a neural network training application to a plurality of client devices;

receiving a set of sensor values and a state from one or more of the plurality of client devices;

generating, via a neural network, one or more functions for estimating whether each of the plurality of client devices have been grabbed;

transmitting the one or more functions to the plurality of client devices.

10. The method of claim 9, wherein the neural network generates the one or more functions via backpropagation training.

11. The method of claim 9, generating the one or more functions comprising:

generating a primary function and a secondary function, wherein the primary function accepts a first set of sensor values as inputs and the secondary function accepts a second set of sensor values as inputs.

12. The method of claim 11, wherein the first set of sensor values corresponds to the output of one or more capacitive touch sensors.

13. The method of claim 12, wherein the second set of sensor values corresponds to the output of an accelerometer, gyrometer, proximity sensor, or light sensor.

14. One or more computer-readable non-transitory storage media in one or more computing systems, the media embodying logic that is operable when executed to:

detect, while the one or more computing systems is in a first state, a first set of inputs from a plurality of first sensors;

generate a first sensor value array, each of the sensor values in the first sensor value array corresponding to one of the first set of inputs;

feed the first sensor value array as input to a first function generated by a first neural network;

calculate one or more first output values based at least in part on the first function;

determine, based at least in part on the one or more first output values, if a first action has occurred; and

in response to a determination that a first action has occurred;

poll one or more second sensors for a second set of sensor inputs;

generate a second sensor value array including a second set of sensor values, each of the second set of sensor values corresponding to one of the second set of sensor inputs;

feed the second sensor value array as input to a second function generated by a second neural network;

calculate one or more second output values based at least in part on the second function; and

based at least in part on the one or more second output values returned by the second function, exit the first state.

15. The media of claim 14, wherein the one or more first output values are calculated by a low-power microcontroller;

and in response to a determination that a first action has occurred, the micro-controller wakes up a processor from a sleep mode for calculation of the one or more second output values.

16. The media of claim 14, wherein the first sensors comprise capacitive touch sensors.

17. The media of claim 14, wherein the one or more second sensors comprise:

an accelerometer;

a light sensor;

or

a multi-touch display surface.

18. The media of claim 14, wherein the first state is a locked state.

19. The media of claim 14, wherein the first action is a grab action.

20. The media of claim 14, wherein the first and second functions are received from a server.