Programmable customization of a user interface of an electronic equipment

Abstract

Provided is an electronic equipment offering a plurality of controllable functionalities and that receives information designating a functionality selected amongst this plurality of controllable functionalities. The electronic equipment also receives a plurality of recordings of a same group of at least one user input for this selected functionality. The electronic equipment also applies a trained neural network model on this received plurality of recordings to recognize an input pattern. The electronic equipment also associates this recognized input pattern with this selected functionality, and stores this association in a memory. The electronic equipment also controls this selected functionality based on this stored association.

1 . An electronic equipment, comprising:
 circuitry configured to:
 receive information designating a functionality selected among a plurality of controllable functionalities; 
 receive a plurality of first recordings of a same group of at least one user input for said selected functionality; 
 apply a trained neural network model on said received plurality of first recordings to recognize a first input pattern corresponding to said same group of said at least one user input; 
 control said trained neural network model to:
 determine a complexity level of said first input pattern under recognition based on a set of criteria; and 
 associate said recognized first input pattern with said selected functionality in a case where said determined complexity level of said first input pattern is greater than a first threshold complexity, wherein said trained neural network model is trained based on said set of criteria and said first threshold complexity; 
 
 store said association in a memory; and 
 control said selected functionality based on said stored association. 
   
     
     
         2 . The electronic equipment according to  claim 1 , wherein
 said circuitry is further configured to control said trained neural network model to reject said first input pattern in a case where said determined complexity level is greater than a second threshold complexity, and   said second threshold complexity is greater than said first threshold complexity.   
     
     
         3 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to:
 generate a distribution of said at least one user input of said first input pattern based on said received plurality of first recordings; and   determine a variability of said at least one user input of said first input pattern in said plurality of first recordings based on said generated distribution.   
     
     
         4 . The electronic equipment according to  claim 3 , wherein said circuitry is further configured to recognize said first input pattern in a case where said determined variability of said at least one user input is smaller than a threshold value. 
     
     
         5 . The electronic equipment according to  claim 4 , wherein said circuitry is further configured to:
 set said first input pattern as a password for authentication of a user of said electronic equipment in a case where said determined variability is smaller than said threshold value; and   associate said user with said first input pattern.   
     
     
         6 . The electronic equipment according to  claim 4 , wherein said circuitry is further configured to request for additional recordings of said at least one user input for said first input pattern in a case where said determined variability associated with said at least one user input of previously received recordings is larger than said threshold value. 
     
     
         7 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to:
 receive a plurality of second recordings for said selected functionality;   apply said trained neural network model on said received plurality of second recordings to recognize a second input pattern;   associate said recognized first input pattern and said second input pattern with said selected functionality; and   control said selected functionality based on said first input pattern or said second input pattern.   
     
     
         8 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to update an association of said selected functionality with a default input pattern with said recognized first input pattern. 
     
     
         9 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to:
 execute an input pattern recognition process on a user input of said first input pattern subsequent to said association; and   control one of execution of said selected functionality or authentication of a user associated with said first input pattern, based on said execution of said input pattern recognition process.   
     
     
         10 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to:
 receive a user input of said recognized first input pattern to control said selected functionality after said association of said selected functionality with said recognized first input pattern; and   train said trained neural network model based on said received user input as a learning input to said trained neural network model.   
     
     
         11 . The electronic equipment according to  claim 1 , wherein said first input pattern includes at least one of a user action on said electronic equipment, a user gesture associated with said electronic equipment, or a sequence of user actions or user gestures performed on said electronic equipment, and
 said set of criteria includes at least a minimum number of user actions or user gestures required in said sequence of user actions or user gestures of said first input pattern.   
     
     
         12 . The electronic equipment according to  claim 1 , further comprising at least one sensor, wherein said circuitry is further configured to control said at least one sensor to capture said plurality of first recordings of said same group of said at least one user input. 
     
     
         13 . The electronic equipment according to  claim 1 , wherein
 said circuitry is further configured to receive said plurality of first recordings of said first input pattern from an external device communicatively coupled with said electronic equipment, and   said electronic equipment further comprises at least one sensor configured to capture said plurality of first recordings.   
     
     
         14 . The electronic equipment according to  claim 1 , wherein each controllable functionality of said plurality of controllable functionalities is selected from one of a locking of said electronic equipment, unlocking of said electronic equipment, a start of use of said electronic equipment, a stop of use of said electronic equipment, a communication of said electronic equipment with an external device, a control of a heating element of said electronic equipment, one of an opening or closing of a shutter controlling access to a chamber of said electronic equipment, or a cleaning of said heating element. 
     
     
         15 . The electronic equipment according to  claim 1 , wherein said circuitry is further configured to trigger transmission of information defining said association between said recognized first input pattern and said selected functionality to a communication equipment for backup storage of said transmitted information. 
     
     
         16 . The electronic equipment according to  claim 1 , wherein said electronic equipment is one of a vaping device, an aerosol generation device, an electronic cigarette, a tobacco delivery device, or a nicotine delivery device. 
     
     
         17 . A device, comprising:
 circuitry configured to:
 receive information designating a selected functionality of a controlled electronic equipment, wherein said controlled electronic equipment has a plurality of controllable functionalities; 
 receive a plurality of first recordings of at least one user input for said selected functionality; 
 apply a trained neural network model on said received plurality of first recordings to recognize a first input pattern corresponding to said at least one user input; 
 control said trained neural network model to:
 determine a complexity level of said first input pattern under recognition based on a set of criteria; and 
 associate said recognized first input pattern with said selected functionality in a case where said determined complexity level of said first input pattern is greater than a first threshold complexity, wherein said trained neural network model is trained based on said set of criteria and said first threshold complexity; 
 
 store said association in a memory; and 
 transmit a control signal to said controlled electronic equipment to control said selected functionality each time a user provides said recognized first input pattern to said device. 
   
     
     
         18 . The device according to  claim 17 , wherein said circuitry is further configured to:
 receive a plurality of second recordings for said selected functionality;   apply said trained neural network model on said received plurality of second recordings to recognize a second input pattern;   associate said recognized first input pattern and said second input pattern with said selected functionality; and   control said selected functionality based on said first input pattern or said second input pattern.   
     
     
         19 . The device according to  claim 17 , wherein said circuitry is further configured to:
 receive a user input of said recognized first input pattern to control said selected functionality after said association of said selected functionality with said recognized first input pattern; and   train said trained neural network model based on said received user input as a learning input to said trained neural network model.   
     
     
         20 . A method, comprising:
 in an electronic equipment:
 receiving information designating a functionality selected among a plurality of controllable functionalities; 
 receiving a plurality of recordings of a same group of at least one user input for said selected functionality; 
 applying a trained neural network model on said received plurality of recordings to recognize an input pattern corresponding to said same group of said at least one user input; 
 controlling said trained neural network model to:
 determine a complexity level of said input pattern under recognition based on a set of criteria; and 
 associate said recognized input pattern with said selected functionality in a case where said determined complexity level of said input pattern is greater than a threshold complexity, wherein said trained neural network model is trained based on said set of criteria and said threshold complexity; 
 
 storing said association in a memory; and 
 controlling said selected functionality based on said stored association.