Machine learning based content delivery

• US 10,311,372 B1
• Filed: 12/19/2014
• Issued: 06/04/2019
• Est. Priority Date: 12/19/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hotchkies, Blair Livingstone, Bowman, Bradley Scott, Cerda, Paul Christopher, Chong, Min, Chor, Anthony T., Dirac, Leo Parker, Granade, Kevin Andrew, Pant, Udip, Scott, Sean Michael
• Primary Examiner(s): Cassity, Robert A
• Assistant Examiner(s): Coughlan, Peter D
• Application Number:
  US14/578,099
• Time in Patent Office: 1,628 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/2885 Hierarchically arranged intermediate devices, e.g. for hierarchical caching
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics
• 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

Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

Claims

1. A computer-implemented method for facilitating content delivery, the computer-implemented method comprising:

under control of a hardware computing device configured with specific computer executable instructions,

training a machine learning model that predicts content delivery performance based, at least in part, on historical data related to content requests over a specified period of time;

providing a first separable portion of the machine learning model to a user computing device;

obtaining an incoming content request from the user computing device, wherein the incoming content request includes information generated by the first separable portion of the machine learning model executing on the user computing device;

identifying a predicted content delivery performance that results from an application of a second separable portion of the machine learning model to a candidate content delivery strategy for configuring a content page corresponding to the incoming content request in a first above-the-fold (ATF) configuration; and

in response to a determination that the predicted content delivery performance satisfies a predetermined condition;

configuring the requested content page in the first ATF configuration;

generating a response to the incoming content request in accordance with configuring the requested content page in the first ATF configuration, wherein the generated response indicates a priority for retrieving network resources to be displayed in an ATF portion of the requested content page; and

transmitting the generated response to the user computing device, wherein reception of the generated response causes the user computing device to retrieve the network resources in accordance with the priority indicated in the generated response.

2. The computer-implemented method of claim 1, wherein the first separable portion of the machine learning model is trained on the user computing device.

3. The computer-implemented method of claim 1, wherein identifying the predicted content delivery performance comprises providing the information generated by the first separable portion of the machine learning model into the second separable portion of the machine learning model.

4. The computer-implemented method of claim 1, wherein the first separable portion of the machine learning model receives input data from the user computing device.

5. The computer-implemented method of claim 4, wherein at least one portion of the input data is derived from information accessible exclusively to the user computing device.

6. A computer-implemented method comprising:

under control of a hardware computing device configured with specific computer executable instructions,

obtaining a machine learning model trained to facilitate content delivery in response to content requests;

causing a first separable portion of the machine learning model to be provided to a user computing device;

in response to a first content request submitted by the user computing device, identifying a first content delivery strategy for configuring a content page corresponding to the first content request in a first above-the-fold (ATF) configuration as a result of the first separable portion of the machine learning model executing on the user computing device; and

configuring the content page in the first ATF configuration and indicating a priority for retrieving network resources to be displayed in an ATF portion of the content page.

7. The computer-implemented method of claim 6 further comprising updating the first separable portion of the machine learning model based, at least in part, on content delivery performance data related to the implementation of the first delivery strategy.

8. The computer-implemented method of claim 7 further comprising causing the updated first separable portion of the machine learning model to be provided to the user computing device.

9. The computer-implemented method of claim 8 further comprising, in response to a second content request submitted by the user computing device, identifying a second content delivery strategy as a result of the updated first separable portion of the machine learning model executing on the user computing device.

10. The computer-implemented method of claim 6, wherein the machine learning model corresponds to a decision tree model or an artificial neural network model.

11. A system comprising:

a data store configured to at least store computer-executable instructions; and

a hardware processor in communication with the data store, the hardware processor configured to execute the computer-executable instructions to at least;

obtain a machine learning model trained to facilitate content delivery in response to content requests;

cause a first separable portion of the machine learning model to be provided to a user computing device;

in response to a first content request submitted by the user computing device, identify a first content delivery strategy for configuring a content page corresponding to the first content request in a first above-the-fold (ATF) configuration as a result of the first separable portion of the machine learning model executing on the user computing device; and

configure the content page in the first ATF configuration and indicating a priority for retrieving network resources to be displayed in an ATF portion of the content page.

12. The system of claim 11, wherein the hardware processor is further configured to cause a second separable portion of the machine learning model to be provided to the user computing device.

13. The system of claim 12, wherein the second separable portion of the machine learning model is selected based, at least in part, on information related to the first content request.

14. The system of claim 12, wherein the hardware processor is further configured to, in response to a second content request submitted by the user computing device, identify a second content delivery strategy as a result of the second separable portion of the machine learning model executing on the user computing device.

15. The system of claim 12, wherein the implementation of the first content delivery strategy includes causing the second separable portion of the machine learning model to be provided to the user computing device machine.

16. A non-transitory computer readable storage medium storing computer executable instructions that when executed by a processor perform operations comprising:

obtaining a machine learning model trained to facilitate content delivery in response to content requests;

causing a first separable portion of the machine learning model to be provided to a first user computing device;

in response to a first content request submitted by the first user computing device, identifying a first content delivery strategy for configuring a content page corresponding to the first content request in a first above-the-fold (ATF) configuration as a result of the first separable portion of the machine learning model executing on the first user computing device; and

configuring the content page in the first ATF configuration and indicating a priority for retrieving network resources to be displayed in an ATF portion of the content page.

17. The non-transitory computer-readable storage medium of claim 16, wherein the operations further comprise causing a second separable portion of the machine learning model to be provided to a second user computing device.

18. The non-transitory computer-readable storage medium of claim 17, wherein the first separable portion of the machine learning model includes the second separable portion.

19. The non-transitory computer-readable storage medium of claim 16, wherein the operations further comprise obtaining updates to the machine learning model.

20. The non-transitory computer-readable storage medium of claim 16, wherein the operations further comprises causing updates to the first separable portion of the machine learning model to be provided to the first user computing device.