Methods and systems for supervising displayed content

1. A method comprising:

generating, by one or more computing devices, data representing a plurality of images of interfaces displayed by a device configured to supervise content displayed to a user;

determining, by the one or more computing devices and based at least in part on one or more machine learning (ML) models and the data representing the plurality of images, whether the interfaces displayed by the device include content of a type designated by a content supervisor of the user for identification;

determining, by the one or more computing devices, based at least in part on the one or more ML models, for at least one image of the images of interfaces displayed by the device, and based at least in part on multiple values representing likelihoods that bounded regions within one or more interfaces depicted by the image include content of the type designated for identification, a value representing a likelihood that the one or more interfaces depicted by the image include content of the type designated for identification; and

generating, by the one or more computing devices, data representing a graphical user interface (GUI) for presentation to the content supervisor, the GUI indicating whether the interfaces displayed by the device include content of the type designated for identification.

2. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include sexually explicit imagery.

3. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include sexually explicit imagery of the user.

4. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include imagery depicting violence.

5. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include imagery associated with gambling.

6. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include social-media content.

7. The method of claim 1 , wherein determining whether the interfaces include content of the type designated for identification comprises determining whether the interfaces include content associated with at least one of bullying, suicidal ideation, or psychological concerns.

8. The method of claim 1 , wherein:

the device configured to supervise content displayed to the user comprises a user device that displayed the interfaces;

generating the data representing the plurality of images of the interfaces comprises generating, by the user device, the data representing the plurality of images of the interfaces;

determining whether the interfaces include content of the type designated for identification comprises determining, by the user device, whether the interfaces include content of the type designated for identification;

generating the data representing the GUI for presentation to the content supervisor comprises generating, by a computing device physically distinct and remotely located from the user device, the data representing the GUI for presentation to the content supervisor; and

the method comprises communicating, by the user device, to the computing device physically distinct and remotely located from the user device, and via one or more networks, data indicating whether the interfaces include content of the type designated for identification.

9. The method of claim 1 , wherein:

the device configured to supervise content displayed to the user comprises a user device that displayed the interfaces;

generating the data representing the plurality of images of the interfaces comprises generating, by the user device, the data representing the plurality of images of the interfaces;

determining whether the interfaces include content of the type designated for identification comprises determining, by a computing device physically distinct and remotely located from the user device, whether the interfaces include content of the type designated for identification; and

the method comprises communicating, by the user device, to the computing device physically distinct and remotely located from the user device, and via one or more networks, the data representing the plurality of images of interfaces displayed by the user device.

10. The method of claim 1 , comprising:

receiving, by the one or more computing devices, feedback data generated based at least in part on input provided by the content supervisor via the GUI confirming whether the interfaces displayed by the device include content of the type designated for identification; and

updating, by the one or more computing devices and based at least in part on the feedback data, the one or more ML models.

11. The method of claim 1 , comprising determining, by the one or more computing devices and based at least in part on the one or more ML models, one or more bounded regions within the interfaces displayed by the device that include content of the type designated for identification.

12. The method of claim 11 , wherein generating the data representing the GUI comprises generating data identifying the one or more bounded regions within the interfaces displayed by the device that include content of the type designated for identification.

13. The method of claim 11 , comprising determining, by the one or more computing devices, based at least in part on the one or more ML models, and for each bounded region of the one or more bounded regions within the interfaces, a value representing a likelihood that the bounded region includes content of the type designated for identification.