Controlling screen time based on context
A computer-implemented technique controls consumption of applications by a supervisee (e.g., a child). The technique detects when a supervisee attempts to interact with an application. In response, the technique receives context input signals that describe a current context affecting the supervisee. The technique then generates an output result based on the current context information and a set of rules expressed by rule logic. The technique then controls interaction by the supervisee with the application based on the output result. In one implementation, the technique automatically generates the rule logic, which may correspond to a set of discrete rules and/or a machine-trained model that implicitly expresses the rules. At least some of the rules specify amounts of time allocated to the supervisee for interaction with the plural applications in plural contexts. According to another illustrative aspect, the technique uses a machine-trained model to automatically classify a new application.
1. One or more computing devices for controlling interaction by supervisees with applications, comprising:
hardware logic circuitry, the hardware logic circuitry including: (a) one or more hardware processors that perform operations by executing machine-readable instructions stored in a memory, and/or (b) one or more other hardware logic units that perform the operations using a collection of configured logic gates, the operations including:
automatically enumerating different instances of input information describing different respective contexts in which a supervisee may interact with a particular application, at least two contexts of the different respective contexts identifying different locations at which the supervisee may interact with the particular application;
for the different instances of input information associated with the different respective contexts, using a machine-trained model to map each instance of input information of said different instances of input information, associated with a particular context, to a particular time limit value, the particular time limit value specifying an amount of time that the supervisee is permitted to interact with the particular application in the particular context, the particular time limit value being automatically generated by the machine-trained model by transforming input features that describe the particular context to the particular time limit value, said using the machine-trained model generating plural time limit values associated with the different respective contexts;
generating a report that describes the plural time limit values generated by the machine-trained model for the particular application for the different respective contexts;
providing the report to a supervisor of the supervisee;
detecting a current context of the supervisee; and
controlling interaction by the supervisee with a given application based on an identified time limit value that applies to the current context and the given application, as generated by the machine-trained model.
2. The one or more computing devices of claim 1 , wherein a training system produces the machine-trained model based on a set of training examples, each positive training example specifying information regarding a particular scenario paired with a specified time limit value for the scenario.
3. The one or more computing devices of claim 1 , wherein the machine-trained model determines the particular time limit value for the particular application based, in part, on a context signal provided by another machine-trained model that describes a category associated with the particular application.
4. The one or more computing devices of claim 1 , wherein the report includes different user interface presentations that present information regarding the different respective contexts and associated time limit values in different respective ways.
5. The one or more computing devices of claim 1 , wherein the report also shows a map on a user interface presentation that designates different regions associated with the different respective contexts that have been enumerated, and time limit values associated with the different regions generated by the machine-trained model.
6. The one or more computing devices of claim 1 , wherein the report distinguishes time values that have been produced by the machine-trained model from at least one time limit value that has been manually selected by the supervisor.
7. A computer-implemented method for controlling interaction by supervisees with applications, comprising:
automatically enumerating different instances of input information describing different respective contexts in which a supervisee may interact with a particular application, at least two contexts of the different respective contexts identifying different locations at which the supervisee may interact with the particular application;
for the different instances of input information associated with the different respective contexts, using a machine-trained model to map each instance of input information of said different instances of input information, associated with a particular context, to a particular time limit value, the particular time limit value specifying an amount of time that the supervisee is permitted to interact with the particular application in the particular context, the particular time limit value being automatically generated by the machine-trained model by transforming input features that describe the particular context to the particular time limit value, said using the machine-trained model generating plural time limit values associated with the different respective contexts;
generating a report that describes the plural time limit values generated by the machine-trained model for the particular application for the different respective contexts;
providing the report to a supervisor of the supervisee;
detecting a current context of the supervisee; and
controlling interaction by the supervisee with a given application based on an identified time limit value that applies to the current context and the given application, as generated by the machine-trained model.
8. The method of claim 7 , wherein a training system produces the machine-trained model based on a set of training examples, each positive training example specifying information regarding a particular scenario paired with a specified time limit value for the scenario.
9. The method of claim 7 , wherein the machine-trained model determines the particular time limit value for the particular application based, in part, on a context signal provided by another machine-trained model that describes a category associated with the particular application.
10. The method of claim 7 , wherein the report includes different user interface presentations that present information regarding the different respective contexts and associated time limit values in different respective ways.
11. The method of claim 7 , wherein the report also shows a map on a user interface presentation that designates different regions associated with the different respective contexts that have been enumerated, and time limit values associated with the different regions generated by the machine-trained model.
12. The method of claim 7 , wherein the report distinguishes time values that have been produced by the machine-trained model from at least one time limit value that has been manually selected by the supervisor.
13. A computer-readable storage medium for storing computer-readable instructions, the computer-readable instructions, when executed by one or more hardware processors, performing a method that comprises:
automatically enumerating different instances of input information describing different respective contexts in which a supervisee may interact with a particular application, at least two contexts of the different respective contexts identifying different locations at which the supervisee may interact with the particular application;
for the different instances of input information associated with the different respective contexts, using a machine-trained model to map each instance of input information of said different instances of input information, associated with a particular context, to a particular time limit value, the particular time limit value specifying an amount of time that the supervisee is permitted to interact with the particular application in the particular context, the particular time limit value being automatically generated by the machine-trained model by transforming input features that describe the particular context to the particular time limit value, said using the machine-trained model generating plural time limit values associated with the different respective contexts;
generating a report that describes the plural time limit values generated by the machine-trained model for the particular application for the different respective contexts;
providing the report to a supervisor of the supervisee;
detecting a current context of the supervisee; and
controlling interaction by the supervisee with a given application based on an identified time limit value that applies to the current context and the given application, as generated by the machine-trained model.
14. The computer-readable storage medium of claim 13 , wherein a training system produces the machine-trained model based on a set of training examples, each positive training example specifying information regarding a particular scenario paired with a specified time limit value for the scenario.
15. The computer-readable storage medium of claim 13 , wherein the machine-trained model determines the particular time limit value for the particular application based, in part, on a context signal provided by another machine-trained model that describes a category associated with the particular application.
16. The computer-readable storage medium of claim 13 , wherein the report includes different user interface presentations that present information regarding the different respective contexts and associated time limit values in different respective ways.
17. The computer-readable storage medium of claim 13 , wherein the report also shows a map on a user interface presentation that designates different regions associated with the different respective contexts that have been enumerated, and time limit values associated with the different regions generated by the machine-trained model.
18. The computer-readable storage medium of claim 13 , wherein the report distinguishes time values that have been produced by the machine-trained model from at least one time limit value that has been manually selected by the supervisor.