Adjusting mobile device state based on user intentions and/or identity

Abstract

In one embodiment, a method includes receiving data associated with multiple first client devices, the data corresponding to a first set of sensor values and physical-state indicators of the first client devices; receiving data associated with a second client device corresponding to a second set of sensor values, the second client device including a first and a second set of sensors; generating functions that each determine a probability that the second client device is in a particular physical state, wherein the determination includes correlating the second set of sensor values with a corresponding physical state of the second client device based on the data associated with the multiple first client devices, and wherein a first function is based on values of the first set of sensors and a second function is based on values of the second set of sensors; and sending the generated functions to the second client device.

What is claimed is: 
     
         1 . A method comprising:
 by a computing device, receiving data associated with a plurality of first client devices, the data associated with each of the first client devices corresponding to a first set of sensor values and one or more indicators that each correspond to one of a plurality of physical states of the each of the first client devices;   by the computing device, receiving data associated with a second client device corresponding to a second set of sensor values, the second client device comprising a first and a second set of sensors;   by the computing device, generating a plurality of functions that each determine a probability that the second client device is in a respective one of the physical states, wherein the determination comprises correlating the second set of sensor values with a corresponding physical state of the second client device based on the data associated with the plurality of first client devices, and wherein a first function of the plurality of functions is based on sensor values of the first set of sensors and a second function of the plurality of functions is based on sensor values of the second set of sensors; and   by the computing device, sending the plurality of functions to the second client device.   
     
     
         2 . The method of  claim 1 , further comprising segregating the data based on a sensor type. 
     
     
         3 . The method of  claim 1 , further comprising:
 representing the sensor values as a vector; and   arranging the data in a data structure.   
     
     
         4 . The method of  claim 3 , wherein the first function comprises a plurality of weights that are multiplied to each value of the vector. 
     
     
         5 . The method of  claim 1 , wherein the plurality of functions are generated at pre-determined intervals. 
     
     
         6 . The method of  claim 1 , wherein the first function comprises one or more logical operators. 
     
     
         7 . The method of  claim 1 , wherein the second function is computationally more complex than the first function. 
     
     
         8 . The method of  claim 1 , wherein the first function is configured to output a value for each physical state of the second client device. 
     
     
         9 . The method of  claim 1 , wherein the second function is configured to adjust the probability the second client device is in one of the particular physical states based on a time of day. 
     
     
         10 . The method of  claim 1 , wherein the first set of sensor values comprises training data for a neural network. 
     
     
         11 . The method of  claim 10 , wherein the neural network generates first or second function using backpropagation training. 
     
     
         12 . The method of  claim 10 , wherein the neural network comprises a Hopfield, Elman, Jordan, Echo state, long short-term memory, bidirectional, or continuous time recurrent neural network. 
     
     
         13 . The method of  claim 10 , wherein the neural network comprises one or more adaptive linear elements. 
     
     
         14 . The method of  claim 1 , wherein the first set of sensors comprise low-power sensors. 
     
     
         15 . The method of  claim 14 , wherein the first set of sensors are one or more capacitive touch sensors. 
     
     
         16 . The method of  claim 1 , wherein the second set of sensors comprise sensors that are inactive in a locked or sleep mode of the second client device. 
     
     
         17 . The method of  claim 16 , wherein the second set of sensors are an accelerometer, gyrometer, proximity sensor, or light sensor. 
     
     
         18 . The method of  claim 1 , wherein the plurality of physical states each correspond to a particular use of a respective first or second client device. 
     
     
         19 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 receive data associated with a plurality of first client devices, the data associated with each of the first client devices corresponding to a first set of sensor values and one or more indicators that each correspond to one of a plurality of physical states of the each of the first client devices;   receive data associated with a second client device corresponding to a second set of sensor values, the second client device comprising a first and a second set of sensors;   generate a plurality of functions that each determine a probability that the second client device is in a respective one of the physical states, wherein the determination comprises correlating the second set of sensor values with a corresponding physical state of the second client device based on the data associated with the plurality of first client devices, and wherein a first function of the plurality of functions is based on sensor values of the first set of sensors and a second function of the plurality of functions is based on sensor values of the second set of sensors; and   send the plurality of functions to the second client device.   
     
     
         20 . A system comprising:
 one or more processors; and   a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
 receive data associated with a plurality of first client devices, the data associated with each of the first client devices corresponding to a first set of sensor values and one or more indicators that each correspond to one of a plurality of physical states of the each of the first client devices; 
 receive data associated with a second client device corresponding to a second set of sensor values, the second client device comprising a first and a second set of sensors; 
 generate a plurality of functions that each determine a probability that the second client device is in a respective one of the physical states, wherein the determination comprises correlating the second set of sensor values with a corresponding physical state of the second client device based on the data associated with the plurality of first client devices, and wherein a first function of the plurality of functions is based on sensor values of the first set of sensors and a second function of the plurality of functions is based on sensor values of the second set of sensors; and 
 send the plurality of functions to the second client device.