System and method for personalized and adaptive application management

Abstract

The present teaching relates to method, system, and medium for cross network communications. Information related to an application running on a user device is first received, which includes a state of the application and sensor data obtained with respect to a user interacting with the application on the user device. A request is sent to an application server for an instruction of a state transition of the application. A light weight model (LWM) for an object involved in the state transition is received and is personalized based on at least one of the sensor data and one or more preferences related to the user to generate a personalized model (PM) for the object, which is then sent to the user device.

We claim: 
     
         1 . A method implemented on at least one machine including at least one processor, memory, and a communication platform connected to a network for cross network communications, the method comprising:
 initiating, on a user device, an application associated with a current state and configured to interact with a user;   activating one or more sensors on the user device to acquire sensor data about the user and a surrounding scene of the user;   determining an updated state of the application based on an input from the user and the current state;   analyzing the sensor data to extract relevant features characterizing the user and the surrounding scene; and   sending the updated state and the relevant features to an application client for a first instruction to executing a state transition of the application, wherein   the updated state and the relevant features are used by the application client to generate the first instruction by personalizing a second instruction from an application server based on the preference of the user.   
     
     
         2 . The method of  claim 1 , wherein the application client resides on the user device and is configured to interface with the application server. 
     
     
         3 . The method of  claim 1 , further comprising:
 receiving, from the application client, the first instruction with a personalized model (PM) therein to be used to render an object in the application;   decoding the PM; and   rendering the object based on the decoded PM.   
     
     
         4 . The method of  claim 3 , wherein the object is one of
 a new object to be inserted in the application; and   an object currently existing in the application and to be modified based on the personalized model.   
     
     
         5 . The method of  claim 3 , wherein
 the second instruction from the application server provides a light weight (LW) model with respect to the object; and   the PM is generated based on the LW model to incorporate additional attributes of the object, wherein   the additional attributes are determined in accordance with at least one of a preference of the user and the surrounding scene.   
     
     
         6 . The method of  claim 5 , wherein the preference of the user is estimated based on at least one of
 a previously known preference of the user; and   the relevant features extracted from the sensor data.   
     
     
         7 . Machine readable and non-transitory medium having information recorded thereon for cross network communication, wherein the information, when read by the machine, causes the machine to perform the following steps:
 initiating, on a user device, an application associated with a current state and configured to interact with a user;   activating one or more sensors on the user device to acquire sensor data about the user and a surrounding scene of the user;   determining an updated state of the application based on an input from the user and the current state;   analyzing the sensor data to extract relevant features characterizing the user and the surrounding scene; and   sending the updated state and the relevant features to an application client for a first instruction to executing a state transition of the application, wherein   the updated state and the relevant features are used by the application client to generate the first instruction by personalizing a second instruction from an application server based on the preference of the user.   
     
     
         8 . The medium of  claim 7 , wherein the application client resides on the user device and is configured to interface with the application server. 
     
     
         9 . The medium of  claim 7 , wherein the information, when read by the machine, further causes the machine to perform the following steps:
 receiving, from the application client, the first instruction with a personalized model (PM) therein to be used to render an object in the application;   decoding the PM; and   rendering the object based on the decoded PM.   
     
     
         10 . The medium of  claim 9 , wherein the object is one of
 a new object to be inserted in the application; and   an object currently existing in the application and to be modified based on the personalized model.   
     
     
         11 . The medium of  claim 9 , wherein
 the second instruction from the application server provides a light weight (LW) model with respect to the object; and   the PM is generated based on the LW model to incorporate additional attributes of the object, wherein   the additional attributes are determined in accordance with at least one of a preference of the user and the surrounding scene.   
     
     
         12 . The medium of  claim 11 , wherein the preference of the user is estimated based on at least one of
 a previously known preference of the user; and   the relevant features extracted from the sensor data.   
     
     
         13 . A system for cross network communication, comprising:
 an application operating on a user device having an associated current state and configured to interact with the user;   an application controller configured for activating one or more sensors on the user device to acquire sensor data about the user and a surrounding scene of the user;   an application state updater configured for determining an updated state of the application based on an input from the user and the current state;   a sensor data processor configured for analyzing the sensor data to extract relevant features characterizing the user and the surrounding scene; and   an application client communication unit configured for sending the updated state and the relevant features to an application client for a first instruction to execute a state transition of the application, wherein   the updated state and the relevant features are used by the application client to generate the first instruction by personalizing a second instruction from an application server based on the preference of the user.   
     
     
         14 . The system of  claim 13 , wherein the application client resides on the user device and is configured to interface with the application server. 
     
     
         15 . The system of  claim 13 , wherein the application client communication unit is further configured for receiving, from the application client, the first instruction with a personalized model (PM) therein to be used to render an object in the application. 
     
     
         16 . The system of  claim 15 , further comprising:
 a PM decoder configured for decoding the PM received from the application client; and   a PM-based rendering unit configured for rendering the object based on the decoded PM.   
     
     
         17 . The system of  claim 15 , wherein the object is one of
 a new object to be inserted in the application; and   an object currently existing in the application and to be modified based on the personalized model.   
     
     
         18 . The system of  claim 15 , wherein
 the second instruction from the application server provides a light weight (LW) model with respect to the object; and   the PM is generated based on the LW model to incorporate additional attributes of the object, wherein   the additional attributes are determined in accordance with at least one of a preference of the user and the surrounding scene.   
     
     
         19 . The system of  claim 18 , wherein the preference of the user is estimated based on at least one of
 a previously known preference of the user; and   the relevant features extracted from the sensor data.