Cloud-assisted perceptual computing analytics

1. A computing device comprising:

one or more sensor to collect data for perceptual computing;

a processor; and

storage to store instructions to direct the processor to:

calculate an analytics disposition result based on the data collected by the one or more sensor, wherein the analytics disposition result includes a respective calculated prediction result for each of a plurality of analytics subject categories;

calculate a respective confidence level associated with the prediction result for each of the plurality of analytics subject categories;

determine an overall confidence level based on the calculated confidence level for one or more of the analytics subject categories;

compare the overall confidence level to a threshold; and

send the data to a cloud computing device in response to the overall confidence level being below the threshold.

2. The computing device of claim 1 , wherein the computing device comprises an Internet-of-Things (IoT) device, and wherein the computing device comprises a client computing device external to a cloud comprising the cloud computing device.

3. The computing device of claim 1 , wherein the computing device comprises a client computing device comprising an IoT network server, an IoT gateway device, or an IoT smart sensor, wherein the client computing device to communicate with the cloud computing device via a network comprising a local area network or a wide area network, or both.

4. The computing device of claim 1 , wherein the computing device comprises an IoT edge device or a node to communicate with other sensors not comprising the first sensor, and wherein the threshold comprises a numerical value specified by a user.

5. The computing device of claim 1 , wherein the overall confidence level is a function of multiple confidence levels assigned by the computing device respectively to the analytics subject categories.

6. The computing device of claim 5 , wherein the function is a weighted average of a user-defined subset of the multiple confidence levels assigned by the computing device respectively to the analytics subject categories.

7. The computing device of claim 1 , wherein the computing device to initiate an action by the computing device in response to the overall confidence level being above the threshold.

8. The computing device of claim 1 , wherein to calculate an analytics disposition result comprises determining a prediction result for an analytics subject category for the data collected by the sensor.

9. The computing device of claim 8 , wherein each confidence level comprises a probability that the prediction result for the analytics subject category matches a pre-dispositioned result for the analytics subject category.

10. The computing device of claim 1 , the instructions to direct the processor to receive a new overall confidence level calculated by the cloud computing device.

11. The computing device of claim 1 , wherein the analytics subject categories include one or more of gender, age, emotion, pose, gaze, facial expression, speech, and/or proximity.

12. A computing device comprising:

one or more sensor to collect data for perceptual computing;

a first processor; and

a first memory storing a first code executable by the first processor to:

calculate a first analytics disposition result based on the data collected by the one or more sensor, wherein the first analytics disposition result includes a respective calculated first prediction result for each of a plurality of analytics subject categories;

calculate a respective first confidence level associated with the first prediction result for each of the plurality of analytics subject categories;

determine a first overall confidence level based on the calculated first confidence level for one or more of the analytics subject categories;

compare the first overall confidence level to a first threshold; and

send the data to a cloud computing device in response to the first overall confidence level being below the first threshold.

13. The computing device of claim 12 , wherein the computing device comprises a client computing device comprising an IoT edge device.

14. The computing device of claim 12 , wherein the first threshold comprises a numerical value specified by a user, and wherein the first overall confidence level is a function of multiple confidence levels assigned by the computing device respectively to the analytics subject categories.

15. The computing device of claim 14 , wherein the function is a weighted average of a user-defined subset of the multiple confidence levels assigned by the computing device respectively to the analytics subject categories.

16. The computing device of claim 12 , wherein the first memory stores code executable by the first processor to initiate an action by the computing device in response to the first overall confidence level being above the first threshold.

17. The computing device of claim 12 , wherein the cloud computing device comprises:

a second processor; and

a second memory storing a second code executable by the second processor to:

calculate a second analytics disposition result based on the data received from the computing device, wherein the second analytics disposition result includes a respective calculated second prediction result for each of the plurality of analytics subject categories;

calculate a respective second confidence level associated with the second prediction result for each of the plurality of analytics subject categories;

determine a second overall confidence level based on the calculated second confidence level for one or more of the analytics subject categories;

compare the second overall confidence level to a second threshold; and

initiate an action by the computing device in response to the second overall confidence level being above the second threshold.

18. The computing device of claim 12 , wherein the computing device comprises an Internet of Things (IoT) device, the IoT device comprising a gateway, an edge device, or an aggregation device.

19. The computing device of claim 12 , the instructions to direct the processor to receive a new overall confidence level calculated by the cloud computing device.

20. The computing device of claim 12 , wherein the analytics subject categories include one or more of gender, age, emotion, pose, gaze, facial expression, speech, and/or proximity.

21. A method by a computing device, comprising:

calculating an analytics disposition result based on data collected by one or more sensor, wherein the analytics disposition result includes a respective calculated prediction result for each of a plurality of analytics subject categories;

calculating a respective confidence level associated with the prediction result for each of the plurality of analytics subject categories;

determining an overall confidence level based on the calculated confidence level for one or more of the analytics subject categories;

comparing the overall confidence level to a threshold; and

sending the data to a cloud computing device in response to the overall confidence level being below the threshold.

22. The method of claim 21 , wherein the computing device is a client computing device comprising an IoT edge device.

23. The method of claim 21 , comprising receiving a value of the threshold from a user, wherein the overall confidence level is a function of multiple confidence levels calculated and assigned respectively by the computing device to the analytics subject categories.

24. The method of claim 23 , wherein the function comprises a weighted average of a user-defined subset of the multiple confidence levels assigned respectively by the computing device to the analytics subject categories.

25. The method of claim 21 , comprising initiating an action by the computing device in response to the overall confidence level being above the threshold.

26. The method of claim 21 , comprising communicating with the cloud computing device via a network, wherein the network comprises a local area network or a wide area network, or both.

27. The method of claim 21 , comprising receiving a new overall confidence level calculated by the cloud computing device.

28. The method of claim 21 , wherein the analytics subject categories include one or more of gender, age, emotion, pose, gaze, facial expression, speech, and/or proximity.

29. At least one non-transitory computer-readable medium, comprising instructions to direct a processor to:

calculate an analytics disposition result based on data collected by one or more sensor, wherein the analytics disposition result includes a respective calculated prediction result for each of a plurality of analytics subject categories;

calculate a respective confidence level associated with the prediction result for each of the plurality of analytics subject categories;

determine an overall confidence level based on the calculated confidence level for one or more of the analytics subject categories;

compare the overall confidence level to a threshold; and

send the data to a cloud computing device in response to the overall confidence level being below the threshold.

30. The at least one computer-readable medium of claim 29 , comprising instructions to direct the processor to receive a value of the threshold from a user.

31. The at least one computer-readable medium of claim 29 , comprising instructions to direct the processor to initiate an action in response to the overall confidence level being above the threshold.

32. The at least one computer-readable medium of claim 29 , comprising instructions to direct the processor to receive a new overall confidence level calculated by the cloud computing device.

33. The at least one computer-readable medium of claim 29 , wherein the analytics subject categories include one or more of gender, age, emotion, pose, gaze, facial expression, speech, and/or proximity.