Analytics-based update of digital content

• US 10,075,510 B2
• Filed: 03/13/2014
• Issued: 09/11/2018
• Est. Priority Date: 03/13/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Reilly, James, Shalabi, Sami Mohammed, Agarwal, Mehul, Depinet, Michael Scott
• Primary Examiner(s): Pulliam, Christyann R
• Assistant Examiner(s): Lamardo, Viker A
• Application Number:
  US14/210,050
• Publication Number:
  US 20150264115A1
• Time in Patent Office: 1,643 Days
• Field of Search: 706 12
• 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 configuring a plurality of client devices to request updated digital content at future times, prior to when respective users of the plurality of client devices are predicted to consume the updated digital content, the method comprising:

receiving analytics data describing how a particular client device from the plurality of client devices has been used in the past to consume the digital content;

generating, based on the analytics data and for a user of the particular client device, a prediction model defining a feature space describing features representative of future time intervals for requesting the updated digital content;

generating, using the prediction model, prediction data indicating initial time intervals during which the client device is predicted to have network connectivity by which to issue a request for updated digital content and by which to establish a network session with a server sourcing the updated digital content, prior to subsequent time intervals during which the client device is predicted to be used to consume the digital content;

configuring the particular client device to request the updated digital content in the initial time intervals and prior to the subsequent time intervals by providing the prediction data to the particular client device;

receiving, from the particular client device, in the initial time intervals and prior to the subsequent time intervals, the request for the updated digital content; and

in response to receiving the request, configuring the particular client device to use the updated digital content when responding to user requests for the updated digital content made during the subsequent time intervals by at least providing, in the initial time intervals and prior to the subsequent time intervals, the updated digital content to the particular client device.

2. The method of claim 1,

wherein generating the prediction model based on the analytics data further comprises training, based on the analytics data, a classifier to make predictions for the features in the feature space, and

wherein determining the prediction data comprises using the classifier to predict the future time intervals for requesting the updated digital content.

3. The method of claim 1,

wherein providing the prediction data to the client device comprises providing, to the client device, information indicating a list of future time intervals in which the client device will be used to consume digital content, each future time interval in the list of future time intervals occurring in the initial time intervals and prior to the subsequent time intervals, and

wherein receiving the request comprises receiving the request according to the list of future time intervals.

4. A non-transitory computer-readable storage medium storing executable computer program instructions for configuring a plurality of client devices to request updated digital content at future times, prior to when respective users of the plurality of client devices are predicted to consume the updated digital content, the computer program instructions comprising instructions for:

receiving analytics data describing how a particular client device from the plurality of client devices has been used in the past to consume the digital content;

generating, based on the analytics data and for a user of the particular client device, a prediction model defining a feature space describing features representative of future time intervals for requesting the updated digital content;

generating, using the prediction model, prediction data indicating initial time intervals during which the client device is predicted to have network connectivity by which to issue a request for updated digital content and by which to establish a network session with a server sourcing the updated digital content, prior to subsequent time intervals during which the client device is predicted to be used to consume the digital content;

configuring the particular client device to request the updated digital content in the initial time intervals and prior to the subsequent time intervals by providing the prediction data to the particular client device;

receiving, from the particular client device, in the initial time intervals and prior to the subsequent time intervals, the request for the updated digital content; and

in response to receiving the request, configuring the particular client device to use the updated digital content when responding to user requests for the updated digital content made during the subsequent time intervals by at least providing in the initial time intervals and prior to the subsequent time intervals, the updated digital content to the particular client device.

5. The computer-readable storage medium of claim 4, wherein the computer program instructions for generating the prediction model based on the analytics data further comprise instructions for:

training, based on the analytics data, a classifier to make predictions for the features in the feature space, and

wherein determining the prediction data comprises using the classifier to predict the future time intervals for requesting the updated digital content.

6. The computer-readable storage medium of claim 4, wherein the computer program instructions for providing the prediction data to the client device comprise instructions for:

providing, to the client device, information indicating a list of future time intervals in which the client device will be used to consume digital content, each future time interval in the list of future time intervals occurring in the initial time intervals and prior to the subsequent time intervals,

receiving the request comprises receiving the request according to the list of future time intervals.

7. The computer-readable storage medium of claim 4, wherein the prediction data includes a predetermined time-based schedule specifying the initial time intervals during which the client device is predicted to have network connectivity by which to issue a request for updated digital content prior to the subsequent time intervals during which the client device is predicted to be used to consume the digital content.

8. The computer-readable storage medium of claim 7, wherein the time-based schedule is determined based on activeness of the user.

9. A computing system for configuring a plurality of client devices to request updated digital content at future times, prior to when respective users of the plurality of client devices are predicted to consume the updated digital content, the computing system 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;

receiving analytics data describing how a particular client device from the plurality of client devices has been used in the past to consume the digital content;

generating, based on the analytics data and for a user of the particular client device, a prediction model defining a feature space describing features representative of future time intervals for requesting the updated digital content;

generating, using the prediction model, prediction data indicating initial time intervals during which the client device is predicted to have network connectivity by which to issue a request for updated digital content and by which to establish a network session with a server sourcing the updated digital content, prior to subsequent time intervals during which the client device is predicted to be used to consume the digital content;

configuring the particular client device to request the updated digital content in the initial time intervals and prior to the subsequent time intervals by providing the prediction data to the particular client device;

receiving, from the particular client device, in the initial time intervals and prior to the subsequent time intervals, the request for the updated digital content; and

in response to receiving the request, configuring the particular client device to use the updated digital content when responding to user requests for the updated digital content made during the subsequent time intervals by at least providing, in the initial time intervals and prior to the subsequent time intervals, the updated digital content to the particular client device.

10. The computing system of claim 9,

wherein generating the prediction model further comprises training a classifier to make predictions for the features in the feature space using the analytics data, and

wherein determining the prediction data comprises using the trained classifier to predict the future time intervals for requesting the updated digital content.

11. The computing system of claim 9, wherein the prediction data includes a predetermined time-based schedule specifying the initial time intervals during which the client device is predicted to have network connectivity by which to issue a request for updated digital content prior to the subsequent time intervals during which the client device is predicted to be used to consume the digital content.

12. The computing system of claim 11, wherein the time-based schedule is determined based on activeness of the user.