Device telemetry for user experience predictions

Patent metadata

Field	Value
Publication number	US-9760912-B2
Application number	US-201414311807-A
Country	US
Kind code	B2
Filing date	Jun 23, 2014
Priority date	Jun 23, 2014
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

In some examples, one or more processors of a computing system may receive telemetry data from a plurality of devices, user identifications (IDs) of a set of users of the plurality of the devices, and information from social media indicative of user sentiments toward the devices. The computing system may predict user experience related to the devices based at least in part on the telemetry data, the user IDs, and the information from the social media.

First claim

I claim:

1. A method, comprising:
receiving, by one or more processors, telemetry data from a plurality of devices, user identifications (IDs) of a first set of users of the plurality of devices, and information from social media indicative of user sentiments toward the plurality of devices;
predicting, by the one or more processors, the user sentiments toward the plurality of devices based at least in part on the telemetry data, the user IDs, and the information from the social media, wherein the user sentiments comprise at least one of a positive sentiment toward the plurality of devices, a potential problem with the plurality of devices, or a particular user case with respect to the plurality of devices; and
in response to the prediction, performing an operation comprising:
providing an offer for an add-on product to at least one user of the first set of users having the positive sentiment toward the plurality of devices, and
providing at least one of a corrective information, a suggestion, or an upgrade to at least one user of the first set of users predicted to have the potential problem with the plurality of devices.

2. The method of claim 1 , wherein the receiving comprises preprocessing one or more streams of the telemetry data from the plurality of devices to provide preprocessed telemetry data by scaling the received telemetry data.

3. The method of claim 2 , further comprising:
performing dimensionality reduction in the preprocessed telemetry data.

4. The method of claim 3 , wherein the performing the dimensionality reduction comprises performing the dimensionality reduction using singular value decomposition.

5. The method of claim 4 , wherein the singular value decomposition comprises principal component analysis.

6. The method of claim 3 , further comprising:
matching at least a portion of the user sentiments to one or more of the user IDs; and
associating the matched one or more of the user IDs to one or more of the plurality of devices associated with at least one of the one or more streams of the telemetry data.

7. The method of claim 6 , further comprising:
clustering a second set of users of the plurality of devices into a plurality of clusters of users, wherein each of the plurality of clusters of users is associated with a respective user sentiment toward the plurality of devices, and wherein the second set of users is greater than the first set of users.

8. The method of claim 7 , wherein each of the plurality of clusters of users includes users sharing similar experiences related to the plurality of devices.

9. The method of claim 7 , further comprising:
adjusting, based at least, in part, on the clustering, the dimensionality reduction to preserve dimensional data in the preprocessed telemetry data relevant to the user sentiments.

10. The method of claim 7 , further comprising:
generating, based at least, in part, on the clustering, a first list of users from the second set of users having the positive sentiment toward the plurality of devices, a second list of users from the second set of users with the potential problem with the plurality of devices, and a third list of users from the second set of users with the particular user case with respect to the plurality of devices.

11. A non-transitory computer-readable medium that stores executable instructions that, in response to execution, cause one or more processors to perform or control performance of operations to:
preprocess one or more streams of telemetry data from a plurality of devices to provide preprocessed telemetry data by scaling the telemetry data;
obtain user identifications (IDs) of users of the plurality of devices and information from social media indicative of user sentiments toward the plurality of devices;
predict the user sentiments toward the plurality of devices based at least, in part, on the telemetry data, the user IDs, and the information from the social media, wherein the user sentiments comprise at least one of a positive sentiment toward the plurality of devices, a potential problem with the plurality of devices, or a particular user case with respect to the plurality of devices; and
in response to the prediction, perform or control the performance of at least one of the operations to:
send an offer for an add-on product to at least one user of the first set of users having the positive sentiment toward the plurality of devices, and
send at least one of corrective information, a suggestion, or an upgrade to at least one user of the first set of users predicted to have the potential problem with the plurality of devices.

12. The non-transitory computer-readable medium of claim 11 , wherein the executable instructions comprise instructions that, in response to execution, cause the one or more processors to perform or control performance of at least one of the operations to:
perform dimensionality reduction in the preprocessed telemetry data.

13. The non-transitory computer-readable medium of claim 12 , wherein to perform the dimensionality reduction, the executable instructions further comprise instructions that cause the one or more processors to perform or control performance of the at least one of the operations to perform the dimensionality reduction by use of singular value decomposition.

14. The non-transitory computer-readable medium of claim 13 , wherein the singular value decomposition comprises principal component analysis.

15. The non-transitory computer-readable medium of claim 12 , wherein the executable instructions comprise instructions that, in response to execution, cause the one or more processors to perform or control performance of at least one of the operations to:
match at least a portion of the user sentiments to one or more of the user IDs; and
correlate the matched one or more of the user IDs to one or more of the plurality of devices associated with at least one of the one or more streams of the telemetry data.

16. The non-transitory computer-readable medium of claim 15 , wherein the executable instructions comprise instructions that, in response to execution, cause the one or more processors to perform or control performance of at least one of the operations to:
cluster a second set of users of the plurality of devices into a plurality of clusters of users, wherein each of the plurality of clusters of users is associated with a respective user sentiment toward the plurality of devices, and wherein the second set of users is greater than the first set of users.

17. The non-transitory computer-readable medium of claim 16 , wherein each of the plurality of clusters of users includes users sharing similar experiences related to the plurality of devices.

18. The non-transitory computer-readable medium of claim 16 , wherein the executable instructions comprise instructions that, in response to execution, cause the one or more processors to perform or control performance of at least one of the operations to:
adjust, based at least, in part, on the clustered second set of users, the dimensionality reduction to preserve dimensional data in the preprocessed telemetry data relevant to the user sentiments.

19. The non-transitory computer-readable medium of claim 16 , wherein the executable instructions comprise instructions that, in response to execution, cause the one or more processors to perform or control performance of at least one of the operations to:
generate, based at least, in part, on the clustered second set of users, a first list of users from the second set of users having the

Assignees

• Empire Technology Dev Llc

Inventors

• Kruglick Ezekiel

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q30/0282 Primary

  Rating or review of business operators or products · CPC title

• G06Q50/01

  Physics · mapped topic

• G06Q10/10

  Office automation; Time management · CPC title

• H04L51/043

  using or handling presence information · CPC title