Adaptive learning methods for selecting page components to include on dynamically generated pages

• US 9,135,359 B2
• Filed: 01/16/2015
• Issued: 09/15/2015
• Est. Priority Date: 03/19/2002
• Status: Expired due to Term

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Dicker, Russell A., Cottrell, Robert G., York, Jeremy C.
• Primary Examiner(s): BILGRAMI, ASGHAR H
• Application Number:
  US14/598,718
• Publication Number:
  US 20150134478A1
• Time in Patent Office: 242 Days
• Field of Search: 709/219, 709/228, 705/14, 705/26
• US Class Current: 1/1
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing

Abstract

A subset of a set of components is selected for inclusion on a dynamically-generated web page within a particular user context. Each component may, for example, contain content generated by a respective code module or service. The subset of components is selected based on scores associated with the components in the set. The score of a component is preferably determined based on measurements of user activity resulting from exposures of the components to users in the particular context.

Claims

1. A computer process for selecting components to include on dynamically generated pages, the method comprising:

storing a plurality of context definitions in computer storage, each of which defines a different respective context, of a plurality of contexts, in which a page component can be included on a page;

collecting context-specific exposure data reflective of exposure events in which the page component is selected for inclusion on a page;

collecting context-specific activity data reflective of user interactions with the page component as included on a page, the context-specific activity data based on monitored interactions of a plurality of users;

calculating a plurality of context-specific scores for the page component based on the collected context-specific exposure data and context-specific activity data, each score representing an effectiveness of the page component within a respective one of the contexts; and

responding to page requests from user computing devices by using the context-specific scores, in combination with context data associated with the page requests, to determine whether to select the page component for inclusion on requested pages;

said process performed by execution of program instructions by a computing system that comprises a server.

2. The process of claim 1, wherein at least some of the context definitions include user attributes.

3. The process of claim 1, wherein at least some of the context definitions include browsing session attributes.

4. The process of claim 1, wherein the plurality of contexts correspond to a particular page template, and the context-specific scores are based on user interactions with pages generated using the page template.

5. The process of claim 1, wherein at least some of the contexts are defined, at least partly, based on contents of an electronic shopping cart.

6. The process of claim 1, wherein the page component is a dynamic page component that displays content selected by a server-executed code module such that the content of the page component depends upon a context in which the page component is displayed.

7. The process of claim 1, wherein the page component displays a context-dependent list of catalog items.

8. The process of claim 1, wherein responding to page requests comprises:

receiving a page request from a user computing device;

determining a plurality of attributes associated with the page request;

mapping the plurality of attributes to one of the context definitions to determine a context of the page request;

looking up the context-specific score corresponding to the determined context; and

determining, based on the context-specific score and on context-specific scores for other page components, whether to include the page component on a page generated in response to the page request.

9. The process of claim 8, wherein the plurality of attributes include at least (a) an attribute of a user of the user computing device, and (b) an attribute of a current browsing session of the user.

10. The process of claim 8, wherein the page request is generated in response to a user request to add a catalog item to an electronic shopping carts, and wherein the plurality of attributes include a category of the catalog item.

11. A computer-implemented method of selecting content to include on a page generated dynamically in response to a request from a user device of a user, the method comprising:

identifying a plurality of attributes associated with the request, including at least one of the following;

(a) an attribute of the user, (b) an attribute of a current browsing session of the user;

mapping the plurality of attributes to a context defined in computer storage, said context being one of a plurality of defined contexts in which the page is capable of being requested;

for each of a plurality of candidate components, determining a respective context-specific score that reflects an effectiveness of the candidate component in the context, wherein each score is dependent upon responses of prior users to presentation of the respective component in said context; and

selecting, based at least in part on the scores, a subset of said plurality of candidate components to present to the user on a page generated in response to the request.

12. The method of claim 11, wherein the scores are additionally dependent upon attributes of the prior users.

13. The method of claim 11, wherein the plurality of attributes includes an attribute of the user.

14. The method of claim 11, wherein the plurality of attributes includes an identifier associated with the page.

15. The method of claim 11, wherein the plurality of attributes includes an identifier of a prior page accessed by the user during the current browsing session.

16. The method of claim 11, wherein the plurality of attributes includes information about a catalog item represented in an electronic shopping cart of the user.

17. The method of claim 11, wherein the page identifies a catalog item selected by the user to add to an electronic shopping cart, and wherein selecting the subset of components comprises taking into consideration information about the catalog item.

18. The method of claim 17, wherein at least one of the components in the subset displays a listing of additional catalog items that are related to the catalog item selected by the user to add to the shopping cart.

19. The method of claim 17, the subset of candidate components is selected based additionally on a randomization function.

20. A system for selecting components to include on dynamically generated pages, the system comprising:

a plurality of page components represented in computer storage;

a plurality of context definitions stored in computer storage, each context definition defining a different respective context in which the page components can be included on a page;

a data repository of context-specific exposure data reflective of exposure events in which the page components are selected for inclusion on a page;

a data repository of context-specific activity data reflective of user interactions with the page components as included on pages, the context-specific activity data based on monitored interactions of a plurality of users; and

a computer system programmed with executable instructions to calculate, for each page component, a plurality of context-specific scores, each of which corresponds to a respective one of the contexts, the scores based on the collected context-specific exposure data and the context-specific activity data, each score representing an effectiveness of a corresponding page component in a respective one of the contexts.

21. The system of claim 20, further comprising a component selection module that uses the scores to dynamically select the page components to include on pages in response to requests from user devices.