Automatic generation and transmission of a status of a user and/or predicted duration of the status

Abstract

Automatically generating and/or automatically transmitting a status of a user. The status is transmitted for presentation to one or more additional users via corresponding computing device(s) of the additional user(s). Some implementations are directed to determining both: a status of a user, and a predicted duration of that status; and generating a status notification that includes the status and that indicates the predicted duration. Some implementations are additionally or alternatively directed to utilizing at least one trust criterion in determining whether to provide a status notification of a user to an additional user and/or in determining what status notification to provide to the additional user. Some implementations are additionally or alternatively directed to training and/or use of machine learning model(s) in determining a status of a user and/or a predicted duration of that status.

What is claimed is: 
     
         1 . A method implemented by one or more processors, comprising:
 receiving, by a computing device of a user, user input indicating types of status notifications associated with the user;   receiving, by the computing device of the user, an electronic communication over a network interface, the electronic communication being sent to the user by an additional user, and the electronic communication being sent by the additional user, to the computing device of the user, via an additional computing device of the additional user;   determining, by the computing device of the user and based on sensor data generated by the computing device of the user, a user activity currently engaged in by the user, wherein determining the user activity currently engaged in by the user includes:
 processing the sensor data generated by the computing device of the user using a machine learning model trained based on past sensor data of the user and user-provided modifications to previously determined user activities, and 
 determining the user activity currently engaged in by the user based on output of the machine learning model; 
   determining, by the computing device of the user, that the user activity currently engaged in by the user is associated with a particular first type of status notification, of the types of status notifications indicated by the user input;   identifying, by the computing device of the user, one or more groups of user contacts that are each associated with at least one of the types of status notifications;   determining, by the computing device of the user, that the additional user is included in a particular group of user contacts, of the one or more groups of user contacts, that is associated with the particular first type of status notification; and   transmitting, over the network interface, a status notification of the particular first type from the computing device of the user to the additional computing device of the additional user based on receiving the electronic communication from the additional computing device of the additional user,
 wherein transmitting the status notification over the network interface causes presentation of the status notification to the additional user via the additional computing device of the additional user. 
   
     
     
         2 . The method of  claim 1 , further comprising:
 receiving, at the computing device of the user, additional user input indicating that the user is currently engaged in a different user activity;   re-training the machine learning model based on the sensor data and the additional user input indicating that the user is currently engaged in the different user activity; and   processing the sensor data using the re-trained machine learning model to generate subsequent output; and   identifying the different user activity currently engaged in by the user based on the subsequent output.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining, by the computing device of the user and based on the sensor data generated by the computing device of the user, a predicted duration for the user activity currently engaged in by the user, wherein determining the predicted duration for the user activity currently engaged in by the user includes:
 processing the sensor data generated by the computing device of the user using an additional machine learning model trained based on the past sensor data of the user and user-provided modifications to previously determined predicted durations for one or more previously determined user activities, and 
 determining the predicted duration of the user activity currently engaged in by the user based on output of the additional machine learning model. 
   
     
     
         4 . The method of  claim 3 , wherein the particular first type of status notification is a type of status notification in which both the user activity and the predicted duration of the user activity are visible to the additional user when the additional computing device presents the status notification for presentation to the additional user. 
     
     
         5 . The method of  claim 3 , further comprising:
 receiving, by the computing device of the user, additional user input indicating a modification to the determined predicted duration for the user activity currently engaged in by the user; and   re-training the additional machine learning model based on the sensor data and the modification to the determined predicted duration for the user activity.   
     
     
         6 . The method of  claim 1 , further comprising:
 determining, by the computing device of the user and based on the sensor data generated by the computing device of the user, a predicted duration for the user activity currently engaged in by the user, wherein determining the predicted duration for the user activity currently engaged in by the user includes:   determining that at least a portion of the sensor data indicates a particular type of location of the user;   determining an average predicted duration for user activities of a plurality of users at the particular type of location; and   determining the predicted duration for the user activity currently engaged in by the user based on the average predicted duration for user activities of the plurality of users at the particular type of location.   
     
     
         7 . The method of  claim 1 , further comprising:
 determining, based on second sensor data generated by a second computing device of a second user, a second user activity currently engaged in by the second user;   processing the second sensor data generated by the second computing device using an additional machine learning model trained based on past sensor data of the second user and user-provided modifications to previously determined predicted durations for one or more previously determined user activities;   determining a predicted duration for the second user activity currently engaged in by the second user based on the output of the additional machine learning model.   
     
     
         8 . The method of  claim 7 , wherein determining the user activity currently engaged in by the user includes:
 processing an indication of the predicted duration for the second user activity using the machine learning model; and   determining a predicted duration of the user activity based on the output of the machine learning model.   
     
     
         9 . The method of  claim 8 , wherein processing the indication of the predicted duration for the second user activity using the machine learning model is performed based on determining that the second user activity of the second user corresponds to a particular class of user activities that is associated with the user activity currently engaged in by the user. 
     
     
         10 . A system, comprising:
 one or more processors; and   memory containing instructions that, when executed by at least one of the one or more processors, causes the one or more processors to perform operations comprising:   receiving, at a computing device of a user, user input indicating types of status notifications associated with the user;   receiving, at the computing device of the user, an electronic communication over a network interface, the electronic communication being sent to the user by an additional user, and the electronic communication being sent by the additional user, to the computing device of the user, via an additional computing device of the additional user;   determining, based on sensor data generated by the computing device of the user, a user activity currently engaged in by the user, wherein determining the user activity currently engaged in by the user includes:
 processing the sensor data generated by the computing device of the user using a machine learning model to generate output, wherein the machine learning model is trained based on past sensor data of the user and user-provided modifications to previously determined user activities, and 
 determining the user activity currently engaged in by the user based on output of the machine learning model; 
   determining that the additional user is associated with a particular first type of status notification, of the types of status notifications indicated by the user input, based on identifying that the user has previously chosen to share status notifications of the particular first type with the additional user in the past; and   transmitting, over the network interface, the status notification of the particular first type from the computing device of the user to the additional computing device of the additional user based on receiving the electronic communication from the additional computing device of the additional user,
 wherein transmitting the status notification over the network interface causes presentation of the status notification, in which the user activity of the user is visible, to the additional user via the additional computing device of the additional user. 
   
     
     
         11 . The system of  claim 10 , wherein the particular first type of status notification is a type of status notification, of the types of status notifications indicated by the user input, in which the user activity is visible when a corresponding status notification of the particular first type is provided for presentation. 
     
     
         12 . The system of  claim 11 , wherein determining that the additional user is associated with the particular first type of status notification includes:
 determining that the additional user is a saved contact on the computing device of the user and that the user communicates with the additional user with at least a threshold frequency, or   determining that one or more electronic documents stored on the computing device of the user, other than previously sent or received electronic communications of the user, include explicit indications from the user that the user trusts the additional user.   
     
     
         13 . The system of  claim 10 , the operations further comprising:
 receiving, at the computing device of the user, additional user input indicating that the user is currently engaged in a different user activity;   re-training the machine learning model based on the sensor data and the additional user input indicating that the user is currently engaged in the different user activity; and   processing the sensor data using the re-trained machine learning model to generate subsequent output; and   identifying the different user activity currently engaged in by the user based on the subsequent output.   
     
     
         14 . The system of  claim 13 , wherein the status notification provided for presentation to the additional user at the additional computing device includes a visible indication of the different user activity currently engaged in by the user. 
     
     
         15 . The system of  claim 10 , the operations further comprising:
 determining, based on the sensor data generated by the computing device of the user, a predicted duration for the user activity currently engaged in by the user, wherein determining the predicted duration for the user activity currently engaged in by the user includes:
 processing the sensor data generated by the computing device of the user using an additional machine learning model trained based on the past sensor data of the user and user-provided modifications to previously determined predicted durations for one or more previously determined user activities, and 
 determining the predicted duration of the user activity currently engaged in by the user based on output of the additional machine learning model. 
   
     
     
         16 . The system of  claim 15 , wherein the particular first type of status notification is a type of status notification in which both the user activity and the predicted duration of the user activity are visible to the additional user when the additional computing device presents the status notification for presentation to the additional user. 
     
     
         17 . The system of  claim 15 , the operations further comprising:
 receiving, by the computing device of the user, additional user input indicating a modification to the determined predicted duration for the user activity currently engaged in by the user; and   re-training the additional machine learning model based on the sensor data and the modification to the determined predicted duration for the user activity.   
     
     
         18 . The system of  claim 10 , the operations further comprising:
 determining, based on the sensor data generated by the computing device of the user, a predicted duration for the user activity currently engaged in by the user, wherein determining the predicted duration for the user activity currently engaged in by the user includes:
 determining that at least a portion of the sensor data indicates a particular type of location of the user; 
 determining an average predicted duration for user activities of a plurality of users at the particular type of location; and 
 determining the predicted duration for the user activity currently engaged in by the user based on the average predicted duration for user activities of the plurality of users at the particular type of location. 
   
     
     
         19 . The system of  claim 10 , further comprising:
 determining, based on second sensor data generated by a second computing device of a second user, a second user activity currently engaged in by the second user;   processing the second sensor data generated by the second computing device using an additional machine learning model trained based on past sensor data of the second user and user-provided modifications to previously determined predicted durations for one or more previously determined user activities;   determining a predicted duration for the second user activity currently engaged in by the second user based on the output of the additional machine learning model.   
     
     
         20 . The system of  claim 19 , wherein determining the user activity currently engaged in by the user includes:
 processing an indication of the predicted duration for the second user activity using the machine learning model; and   determining a predicted duration of the user activity based on the output of the machine learning model.