Analytics-based Update of Digital Content

• US 20150264115A1
• Filed: 03/13/2014
• Published: 09/17/2015
• Est. Priority Date: 03/13/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Shalabi, Sami Mohammed, Agarwal, Mehul, Reilly, James, Depinet, Michael Scott
• Granted Patent: US 10,075,510 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

Content on a client device is updated. Analytics data describing how a user uses the client device to consume digital content are received. The analytics data are generated by the client device responsive to observations of how the user uses the client device to consume digital content. A prediction model is generated based on the analytics data and used to predict when the user will consume digital content on the client device. Prediction data describing the prediction are provided to the client device. The client device uses the prediction data to request updated digital content prior to when the user is predicted to consume digital content on the client device.

Claims

1. A computer-implemented method of updating content on a client device, the method comprising:

receiving analytics data describing how a user uses the client device to consume digital content;

generating a prediction model based on the analytics data;

predicting, using the prediction model, when the user will consume digital content on the client device; and

providing updated digital content to the client device based on the prediction of when the user will consume digital content on the client device.

2. The method of claim 1, wherein generating the prediction model based on the analytics data comprises:

defining a feature space describing features for which predictions can be made; and

training a classifier to make predictions for features in the feature space using the analytics data;

wherein the predicting comprises using the classifier to predict when the user will use the client device to consume digital content.

3. The method of claim 2, wherein the feature space comprises time intervals, the predictions predict whether the user will use the client device to consume digital content in the time intervals and whether the client device will have network connectivity during the time intervals, and the client device is adapted to use the prediction data to request updated digital content in a time interval when the client device is predicted to have network connectivity prior to a time interval when the user is predicted to consume digital content on the client device.

4. The method of claim 1, wherein providing updated digital content comprises:

providing prediction data describing the prediction to the client device;

wherein the client device is adapted to use the prediction data to request the updated digital content prior to when the user is predicted to consume digital content on the client device.

5. The method of claim 4, wherein providing the prediction data to the client device comprises:

analyzing the prediction to determine when the user is predicted to use the client device to consume digital content;

scheduling a content update request at a time determined responsive to when the user is predicted to use the client device to consume digital content; and

providing the scheduled content update request to the client device.

6. The method of claim 4, wherein providing the prediction data to the client device comprises:

providing prediction data indicating a list of future time intervals in which the user is predicted to consume digital content on the client device to the client device;

wherein the client device is adapted to use the prediction data to schedule a request for updated digital content.

7. The method of claim 1, wherein providing updated digital content to the client device comprises:

pushing the updated digital content to the client device at a time determined responsive to the prediction of when the user will consume digital content on the client device.

8. A non-transitory computer-readable storage medium storing executable computer program instructions for updating content on a client device, the computer program instructions comprising instructions for:

receiving analytics data describing how a user uses the client device to consume digital content;

generating a prediction model based on the analytics data;

predicting, using the prediction model, when the user will consume digital content on the client device; and

providing updated digital content to the client device based on the prediction of when the user will consume digital content on the client device.

9. The computer-readable storage medium of claim 8, wherein the computer program instructions for generating the prediction model based on the analytics data comprise instructions for:

defining a feature space describing features for which predictions can be made; and

training a classifier to make predictions for features in the feature space using the analytics data;

wherein the predicting comprises using the classifier to predict when the user will use the client device to consume digital content.

10. The computer-readable storage medium of claim 9, wherein the feature space comprises time intervals, the predictions predict whether the user will use the client device to consume digital content in the time intervals and whether the client device will have network connectivity during the time intervals, and the client device is adapted to use the prediction data to request updated digital content in a time interval when the client device is predicted to have network connectivity prior to a time interval when the user is predicted to consume digital content on the client device.

11. The computer-readable storage medium of claim 8, wherein providing updated digital content comprises:

providing prediction data describing the prediction to the client device;

wherein the client device is adapted to use the prediction data to request the updated digital content prior to when the user is predicted to consume digital content on the client device.

12. The computer-readable storage medium of claim 11, wherein the computer program instructions for providing the prediction data to the client device comprise instructions for:

analyzing the prediction to determine when the user is predicted to use the client device to consume digital content;

scheduling a content update request at a time determined responsive to when the user is predicted to use the client device to consume digital content; and

providing the scheduled content update request to the client device.

13. The computer-readable storage medium of claim 11, wherein the computer program instructions for providing the prediction data to the client device comprise instructions for:

providing prediction data indicating a list of future time intervals in which the user is predicted to consume digital content on the client device to the client device;

wherein the client device is adapted to use the prediction data to schedule a request for updated digital content.

14. The computer-readable storage medium of claim 8, wherein providing updated digital content to the client device comprises:

pushing the updated digital content to the client device at a time determined responsive to the prediction of when the user will consume digital content on the client device.

15. A client device for consuming digital content, comprising:

a computer processor for executing computer program instructions; and

a non-transitory computer-readable storage medium storing computer program instructions executable to perform steps comprising;

determining analytics data describing how a user uses the client device to consume digital content;

generating, based on the analytics data, prediction data describing when the user is predicted to consume digital content on the client device; and

requesting, from a server, updated digital content at a time prior to when the user is predicted to consume digital content on the client device determined in response to the prediction data.

16. The client device of claim 15, wherein determining the analytics data comprises:

observing how the user uses the client device to consume digital content; and

generating the analytics data describing the user interactions responsive to the observations.

17. The client device of claim 15, wherein generating prediction data comprises:

generating a prediction model based on the analytics data; and

predicting, using the prediction model, when the user will consume digital content on the client device.

18. The client device of claim 17, wherein generating the prediction model based on the analytics data comprises:

defining a feature space describing features for which predictions can be made;

training a classifier to make predictions for features in the feature space using the analytics data;

predicting, using the trained classifier, when the user will use the client device to consume digital content; and

generating the prediction data describing the prediction.

19. The client device of claim 18, wherein the feature space comprises time intervals and the predictions predict whether the user will use the client device to consume digital content in the time intervals.

20. The client device of claim 18, wherein the feature space comprises time intervals, the predictions predict whether the user will use the client device to consume digital content in the time intervals and whether the client device will have network connectivity during the time intervals, and the client device is adapted to use the prediction data to request updated digital content at a time interval when the client device is predicted to have network connectivity prior to a time interval when the user is predicted to consume digital content on the client device.