Methods and systems for automatic determination of a device-specific configuration for a software application operating on a user device

Abstract

A method and system for automatically determining a device-specific configuration for a software application operating on a user device. A configuration monitoring program monitors local user data stored on a user device and generates a device-specific prediction model using a machine learning algorithm applied to the monitored local data. The configuration monitoring program also receives a global prediction model generated remotely using global user data collected from a plurality of user devices. The configuration monitoring program generates a predicted device-specific configuration of the application operating on the user device using prediction data from both the device-specific prediction model and the global prediction model and updates the configuration of the given application using the predicted device-specific configuration.

1 - 28 . (canceled) 
     
     
         29 . A method for automatically determining a device-specific configuration for a given application operating on a user device, the user device having a processor and a non-transitory memory, the method comprising:
 operating a configuration monitoring program on the user device;   monitoring, by the configuration monitoring program, local user data stored in the non-transitory memory;   generating, by the configuration monitoring program, a local prediction of the device-specific configuration based on applying a machine learning algorithm to the monitored local data;   generating, by the configuration monitoring program, a global prediction of the device-specific configuration based on a remotely-generated global configuration prediction model;   defining, by the configuration monitoring program, a predicted device-specific configuration of the given application operating on the user device using the local prediction of the device-specific configuration and the global prediction of the device-specific configuration; and   updating the configuration of the given application using the predicted device-specific configuration.   
     
     
         30 . The method of  claim 29 , further comprising:
 monitoring, by the configuration monitoring program, device activity of the user device;   determining, by the configuration monitoring program, that configuration update criteria have been satisfied based on the device activity; and   in response to determining that the configuration update criteria have been satisfied, updating the configuration of the given application using the predicted device-specific configuration.   
     
     
         31 . The method of  claim 30 , further comprising:
 defining, by the configuration monitoring program, the predicted device-specific configuration in response to determining that the configuration update criteria have been satisfied.   
     
     
         32 . The method of  claim 29 , wherein generating the local prediction of the device-specific configuration comprises:
 generating a device-specific configuration prediction model by applying the machine learning algorithm to the monitored local data; and   generating the local prediction using the device-specific configuration prediction model.   
     
     
         33 . The method of  claim 32 , wherein the configuration monitoring program is configured to generate model weights for the device-specific configuration prediction model using aggregate local user data corresponding to a plurality of additional user devices. 
     
     
         34 . The method of  claim 32 , further comprising:
 monitoring, by the configuration monitoring program, a user feedback input corresponding to the configuration of the given application; and   updating the device-specific configuration prediction model using data corresponding to the user feedback input.   
     
     
         35 . The method of  claim 29 , further comprising:
 monitoring, by the configuration monitoring program, a user feedback input corresponding to the configuration of the given application;   determining, by the configuration monitoring program, a local prediction metric using the local prediction of the device-specific configuration and the user feedback input, wherein the local prediction metric is indicative of an accuracy of the local prediction of the device-specific configuration; and   defining the predicted device-specific configuration using the local prediction metric.   
     
     
         36 . The method of  claim 35 , wherein defining the predicted device-specific configuration of the given application comprises:
 determining whether the local prediction metric is above a predetermined performance threshold; and   when the local prediction metric is above the predetermined performance threshold, defining the predicted device-specific configuration of the given application entirely from the local prediction, otherwise defining the predicted device-specific configuration of the given application entirely from the global prediction.   
     
     
         37 . The method of  claim 35 , wherein generating the predicted device-specific configuration of the given application comprises:
 assigning a first bias weight to the local prediction, wherein the first bias weight is based on the local prediction metric;   assigning a second bias weight to the global prediction; and   defining the predicted device-specific configuration by combining the local prediction and the global prediction according to the first and second bias weights, respectively.   
     
     
         38 . The method of  claim 37 , further comprising:
 determining whether the local prediction metric is above a predetermined performance threshold; and   defining the predicted device-specific configuration using only the global prediction if the local prediction metric is below the predetermined performance threshold, otherwise defining the predicted device-specific configuration by combining the local prediction and the global prediction weighted according to the first and second bias weights respectively.   
     
     
         39 . A device configured to determine a device-specific configuration for a given application operating on the device, the device comprising:
 a non-transitory memory storing local user data; and   a processor configured to:
 monitor the local user data; 
 generate a local prediction of the device-specific configuration based on applying a machine learning algorithm to the monitored local data; 
 generate a global prediction of the device-specific configuration based on a remotely-generated global configuration prediction model; 
 define a predicted device-specific configuration of the given application operating on the user device using the local prediction of the device-specific configuration and the global prediction of the device-specific configuration; and 
 update the configuration of the given application using the predicted device-specific configuration. 
   
     
     
         40 . The device of  claim 39 , wherein the processor is configured to:
 monitor device activity of the device;   determine that configuration update criteria have been satisfied based on the device activity; and   in response to determining that the configuration update criteria have been satisfied, update the configuration of the given application using the predicted device-specific configuration.   
     
     
         41 . The device of  claim 40 , wherein the processor is configured to:
 define the predicted device-specific configuration in response to determining that the configuration update criteria have been satisfied.   
     
     
         42 . The device of  claim 39 , wherein the processor is configured to generate the local prediction of the device-specific configuration by:
 generating a device-specific configuration prediction model by applying the machine learning algorithm to the monitored local data; and   generating the local prediction using the device-specific configuration prediction model.   
     
     
         43 . The device of  claim 42 , wherein the processor is configured to generate model weights for the device-specific configuration prediction model using aggregate local user data corresponding to a plurality of additional user devices. 
     
     
         44 . The device of  claim 42 , wherein the processor is configured to:
 monitor a user feedback input corresponding to the configuration of the given application; and   update the device-specific configuration prediction model using data corresponding to the user feedback input.   
     
     
         45 . The device of  claim 39 , wherein the processor is configured to:
 monitor a user feedback input corresponding to the configuration of the given application;   determine a local prediction metric using the local prediction of the device-specific configuration and the user feedback input, wherein the local prediction metric is indicative of an accuracy of the local prediction of the device-specific configuration; and   define the predicted device-specific configuration using the local prediction metric.   
     
     
         46 . The device of  claim 45 , wherein the processor is configured to define the predicted device-specific configuration of the given application by:
 determining whether the local prediction metric is above a predetermined performance threshold; and   when the local prediction metric is above the predetermined performance threshold, defining the predicted device-specific configuration of the given application entirely from the local prediction, otherwise defining the predicted device-specific configuration of the given application entirely from the global prediction.   
     
     
         47 . The device of  claim 45 , wherein the processor is configured to define the predicted device-specific configuration of the given application by:
 assigning a first bias weight to the local prediction, wherein the first bias weight is based on the local prediction metric;   assigning a second bias weight to the global prediction; and   defining the predicted device-specific configuration by combining the local prediction and the global prediction according to the first and second bias weights, respectively.   
     
     
         48 . The device of  claim 47 , wherein the processor is configured to:
 determine whether the local prediction metric is above a predetermined performance threshold; and   define the predicted device-specific configuration using only the global prediction if the local prediction metric is below the predetermined performance threshold, otherwise define the predicted device-specific configuration by combining the local prediction and the global prediction weighted according to the first and second bias weights respectively.