User comfort monitoring and notification
Some implementations disclosed herein present multimedia content to a user, identify a comfort state of the user (e.g., happy, unhappy, distressed, etc.) based on body data of the user (e.g., facial expressions, hand movements, physiological data, etc.), and update the multimedia content based on the identified comfort state.
1. A method comprising:
at a device comprising a processor and a display:
presenting a multimedia environment;
obtaining a first set of data regarding a body via a first sensor, wherein the first set of data corresponds to a facial expression;
obtaining a second set of data regarding physiological data via a second sensor, wherein the second set of data corresponds to a physiological response during the presentation of the multimedia environment;
determining a comfort state while viewing the multimedia environment based on: i) decoding facial expressions and ii) identifying the physiological response as being associated with the comfort state by detecting a change in a sound of a user while the user is speaking; and
updating the multimedia environment based on determining the comfort state.
2. The method of claim 1 , wherein determining the comfort state includes classifying the comfort state as a particular comfort state from amongst a plurality of predefined classes of comfort states.
3. The method of claim 1 , wherein determining the comfort state is based on a context selected from a group consisting of a setting of a physical environment or the multimedia environment, a sensitivity, a history of comfort states, and an activity.
4. The method of claim 1 , wherein determining the comfort state is based on at least two of:
an image captured by a camera sensor;
a motion captured by a motion sensor;
a heart rate captured by a heart rate sensor;
a blood oxygen level captured by a pulse oximeter sensor;
a blood pressure captured by a blood pressure sensor;
a temperature captured by a thermometer sensor; or
an electro-cardiogram (EKG) captured by an EKG sensor.
5. The method of claim 1 , wherein determining the comfort state is based on a machine learning algorithm.
6. The method of claim 1 , wherein updating the multimedia environment includes displaying a message.
7. The method of claim 6 , wherein the message includes a notification of the comfort state.
8. The method of claim 6 , wherein the message suggests to take a break from the multimedia environment.
9. The method of claim 6 , wherein the message provides at least one of: i) an option to report content or another user in the multimedia environment to an authority, guardian, or moderator, and ii) an option to block content or another user in the multimedia environment.
10. The method of claim 1 , further comprising recording information associated with the data regarding the body, the comfort state, or the updating of the multimedia environment.
11. The method of claim 1 , wherein the data regarding the body and data regarding the comfort state is stored in a secure enclave on the device to restrict access and transmission to other devices.
12. The method of claim 1 , wherein the device is a head-mounted device (HMD) and the multimedia environment comprises a computer-generated reality (CGR) environment.
13. The method of claim 1 , wherein detecting the change in the sound of the user while the user is speaking comprises detecting a change in at least one of a tone of voice, a spoken language, an utterance, and breathing.
14. A method comprising:
at a device comprising a processor and a display:
presenting a multimedia environment;
obtaining a first set of data associated with audio of a voice via a first sensor;
obtaining a second set of data regarding physiological data via a second sensor, wherein the second set of data corresponds to a physiological response during the presentation of the multimedia environment;
determining a comfort state while viewing the multimedia environment and speaking for a period of time based on the voice and identifying the physiological response as being associated with the comfort state; and
updating the multimedia environment based on determining the comfort state.
15. The method of claim 14 , wherein determining the comfort state includes classifying the comfort state as a particular comfort state from amongst a plurality of predefined classes of comfort states.
16. The method of claim 14 , wherein determining the comfort state is based on a context selected from a group consisting of a setting of a physical environment or the multimedia environment, a sensitivity, a history of comfort states, and an activity.
17. The method of claim 14 , wherein determining the comfort state based on the voice is based on at least one of a tone of voice, a spoken language, an utterance, or breathing.
18. The method of claim 14 , wherein updating the multimedia environment includes displaying a message.
19. The method of claim 18 , wherein the message includes a notification of the comfort state.
20. The method of claim 18 , wherein the message provides at least one of: i) an option to report content or another user in the multimedia environment to an authority, guardian, or moderator, and ii) an option to block content or another user in the multimedia environment.
21. A system comprising:
a device with a display;
a processor; and
a non-transitory computer-readable storage medium comprising instructions that upon execution by the processor cause the processor to perform operations, the operations comprising:
presenting a multimedia environment;
obtaining a first set of data regarding a body via a first sensor, wherein the first set of data corresponds to a facial expression;
obtaining a second set of data regarding physiological data via a second sensor, wherein the second set of data corresponds to a physiological response during the presentation of the multimedia environment;
determining a comfort state while viewing the multimedia environment based on: i) decoding facial expressions and ii) identifying the physiological response as being associated with the comfort state by detecting a change in a sound of a user while the user is speaking; and
updating the multimedia environment based on determining the comfort state.