Sensory feedback system with active learning

1. A method of computer learning to provide soothing output via a soothing device, the method comprising:

monitoring, by one or more processors, input from a plurality of sensors, wherein the sensors are configured to measure one or both of (i) environmental conditions surrounding one or more users and (ii) a state of the one or more users;

detecting, by the one or more processors, a sensor input from the plurality of sensors that meets at least one criteria that indicates that soothing output from a first device is to be provided to at least one user;

generating, by the one or more processors, a determination that a first instance of soothing output is to be provided based, at least in part, on a determination that a first type of soothing output is predicted to soothe at least one user based, at least in part, on a set of selection criteria that are stored in computer memory;

generating, by the one or more processors, the first instance of soothing output by sending a first set of electronic signals that activate the first device, wherein, post activation, the soothing output generated by the first device (i) includes the first type of soothing output and (ii) is configured to be detectable by one or more senses of the at least one user;

generating, by the one or more processors, at least one modified selection criteria based on a given selection criteria of the set of selection criteria, wherein the given selection criteria (i) is stored in computer memory and (ii) is modified based, at least in part, on a determined level of distress of the at least one user that is determined after the first type of soothing output is generated for a time period;

determining that a second type of soothing output is predicted to increase a level of soothing of the at least one user based, at least in part, on the at least one modified selection criteria; and

responsive to the level of distress of the at least one user at least meeting a threshold after the first type of soothing output is generated for the time period, generating, by the one or more processors, a second instance of soothing output, for the at least one user, by sending a second set of electronic signals that activate the first device, wherein the second instance of soothing output includes soothing output that is selected based on both the first type of soothing output and the second type of soothing output.

2. The method of claim 1 , the method including:

determining, by the one or more processors, that a given soothing output is to be provided based, at least in part, on a determination that the given soothing output will soothe both the at least one user and a second user.

3. The method of claim 1 , the method including:

determining, by the one or more processors, that the second type of soothing output is to be provided based, at least in part, on a determination that the second type of soothing output will soothe the at least one user; and

using, by the one or more processors, first device to provide the second type of soothing output to the at least one user.

4. The method of claim 3 , the method including:

determining, by the one or more processors, that a selection criteria of the second type of soothing output indicates that the second type of soothing output is to be provided.

5. The method of claim 1 , the method including:

determining, by the one or more processors, a source of distress of the at least one user; and

determining, by the one or more processors, the first type of soothing output based, at least in part, on the source of distress of the at least one user.

6. The method of claim 5 , the method including:

predicting, by the one or more processors, a future occurrence of distress for the at least one user based, at least in part, on a known source of distress for the at least one user; and

providing, by the one or more processors, the first type of soothing output before a subsequent exposure of the at least one user to the known source of distress.

7. The method of claim 1 , the method including:

determining, by the one or more processors, one or both of the first type of soothing output and the second type of soothing output based, at least in part, on a matching between a characteristic of the at least one user and a characteristic included in a set of records that associates user characteristics with types of soothing output, wherein the characteristic includes at least one of i) vocalizations of the at least one user, ii) movement of the at least one user, iii) a history of behavior of the at least one user, iv) a stage of development of the at least one user, v) a schedule of care activity provided for the at least one user, and vi) an environment of the at least one user.

8. The method of claim 1 , the method including:

determining, by the one or more processors, one or both of the first type of soothing output and the second type of soothing output, at least in part, on a monitored soothing output that was previously provided to the at least one user by a caregiver.

9. The method of claim 1 , the method including:

indicating, by the one or more processors, to a caregiver of the at least one user, a third type of soothing output to be provided to the at least one user.

10. The method of claim 1 , the method including:

analyzing, by the one or more processors, the input to determine that the at least one user is in distress, wherein the input is captured by a second device that monitors at least one of i) the at least one user, and ii) an environment of the at least one user.

11. A computer program product for computer learning to provide soothing output, the computer program product comprising:

one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:

program instructions to monitor input from a plurality of sensors, wherein the sensors are configured to measure one or both of (i) environmental conditions surrounding one or more users and (ii) a state of the one or more users;

program instructions to detect a sensor input from the plurality of sensors that meets at least one criteria that indicates that soothing output from a first device is to be provided to at least one user;

program instructions to generate a determination that a first instance of soothing output is to be provided based, at least in part, on a determination that a first type of soothing output is predicted to soothe at least one user based, at least in part, on a set of selection criteria that are stored in computer memory;

program instructions to generate the first instance of soothing output by sending a first set of electronic signals that activate the first device, wherein, post activation, the soothing output generated by the first device (i) includes the first type of soothing output and (ii) is configured to be detectable by one or more senses of the at least one user;

program instructions to generate at least one modified selection criteria based on a given selection criteria of the set of selection criteria, wherein the given selection criteria (i) is stored in computer memory and (ii) is modified based, at least in part, on a determined level of distress of the at least one user that is determined after the first type of soothing output is generated for a time period;

program instructions to determine that a second type of soothing output is predicted to increase a level of soothing of the at least one user based, at least in part, on the at least one modified selection criteria; and

program instructions to respond to the level of distress of the at least one user at least meeting a threshold after the first type of soothing output is generated for the time period, by generating a second instance of soothing output, for the at least one user, by sending a second set of electronic signals that activate the first device, wherein the second instance of soothing output includes soothing output that is selected based on both the first type of soothing output and the second type of soothing output.

12. The computer program product of claim 11 , the program instructions including:

program instructions to determine that a given soothing output is to be provided based, at least in part, on a determination that the given soothing output will soothe both the at least one user and a second user.

13. The computer program product of claim 11 , the program instructions including:

program instructions to determine that the second type of soothing output is to be provided based, at least in part, on a determination that the second type of soothing output will soothe the at least one user; and

program instructions to use the first device to provide the second type of soothing output to the at least one user.

14. The computer program product of claim 13 , the program instructions including:

program instructions to determine that a selection criteria of the second type of soothing output indicates that the second type of soothing output is to be provided.

15. The computer program product of claim 11 , the program instructions including:

program instructions to determine a source of distress of the at least one user; and

program instructions to determine one or both of the first type of soothing output and the second type of soothing output based, at least in part, on the source of distress of the at least one user.

16. The computer program product of claim 11 , the program instructions including:

program instructions to predict a future occurrence of distress for the at least one user based, at least in part, on a known source of distress for the at least one user; and

program instructions to provide one or both of the first type of soothing output and the second type of soothing output before a subsequent exposure of the at least one user to the known source of distress.

17. The computer program product of claim 11 , the program instructions including:

program instructions to determine one or both of the first type of soothing output and the second type of soothing output based, at least in part, on a matching between a characteristic of the at least one user and a characteristic included in a set of records that associates user characteristics with types of soothing output, wherein the characteristic includes at least one of i) vocalizations of the at least one user, ii) movement of the at least one user, iii) a history of behavior of the at least one user, iv) a stage of development of the at least one user, v) a schedule of care activity provided for the at least one user, and vi) an environment of the at least one user.

18. The computer program product of claim 11 , the program instructions including:

program instructions to determine one or both of the first type of soothing output and the second type of soothing output based, at least in part, on a monitored soothing output that was previously provided to the at least one user by a caregiver.

19. The computer program product of claim 11 , the program instructions including:

program instructions to indicate to a caregiver of the at least one user, a third type of soothing output to be provided to the at least one user.

20. The computer program product of claim 11 , the program instructions including:

program instructions to analyze the input to determine that the at least one user is in distress, wherein the input is captured by a second device that monitors at least one of i) the at least one user, and ii) an environment of the at least one user. an environment of the at least one user.