Contextual advertising with user features

• US 20120047020A1
• Filed: 08/19/2010
• Published: 02/23/2012
• Est. Priority Date: 08/19/2010
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Hatch, Andrew O., Ratnaparkhi, Adwait, Bagherjeiran, Abraham H., Joshi, Amruta S.
• Granted Patent: US 9,031,863 B2
• Time in Patent Office: Days
• US Class Current: 705/14.66
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

Disclosed are apparatus and methods for apparatus and methods for facilitating contextual selection of advertisements for displaying online via a computer network. In general, user features in the form of text are provided in conjunction with web page content for contextual advertisement matching. In one embodiment, a request for an advertisement to be displayed in a current web page that has been requested by a current user is received. The current user is associated with one or more current user characteristics from a plurality of different user characteristics, and the current web page has an associated content. A mapping model and the one or more current user characteristics are used to obtain a plurality of user-relevant terms for each of the one or more current user characteristics. A combination of the content of the current web page and obtained user-relevant terms are provided for selecting an advertisement for displaying with the current web page based on such combination.

Claims

1. A method for facilitating contextual selection of advertisements for displaying online via a computer network, comprising:

receiving a request for an advertisement to be displayed in a current web page that has been requested by a current user, wherein the current user is associated with one or more current user characteristics from a plurality of different user characteristics, wherein the current web page has an associated content;

using a mapping model and the one or more current user characteristics, obtaining a plurality of user-relevant terms for each of the one or more current user characteristics; and

providing a combination of the content of the current web page and obtained user-relevant terms for selecting an advertisement for displaying with the current web page based on such combination.

2. The method as recited in claim 1, wherein the different user characteristics comprise a plurality of different user categories that relate to user interest or expertise in such different user categories and/or a plurality of different user demographics.

3. The method as recited in claim 1, further comprising:

mapping each of the plurality of different user characteristics to a plurality of user-relevant terms that are also relevant for contextual advertisement selection to generate one or more mapping models.

4. The method of claim 3, wherein the mapping is based on collected user activity information.

5. The method of claim 4, wherein the user activity information comprises a plurality of specified activity categories for different activities, a plurality of specified web pages that have been selected by a plurality of users, and a plurality of terms from the specified web pages.

6. The method of claim 5, wherein the mapping comprises learning the mapping model based on the terms from the specified web pages and the specified activity categories.

7. The method of claim 6, wherein the learning comprises using a regression technique and one or more topic models.

8. The method of claim 5, further comprising extracting the terms from the specified web pages that are relevant for advertisement selection.

9. The method of claim 6, wherein the learning comprises maximizing a likelihood function based on the specified web pages and the specified activity categories.

10. An apparatus comprising at least a processor and a memory, wherein the processor and/or memory are configured to perform the following operations:

receiving a request for an advertisement to be displayed in a current web page that has been requested by a current user, wherein the current user is associated with one or more current user characteristics from a plurality of different user characteristics, wherein the current web page has an associated content;

using a mapping model and the one or more current user characteristics, obtaining a plurality of user-relevant terms for each of the one or more current user characteristics; and

providing a combination of the content of the current web page and obtained user-relevant terms for selecting an advertisement for displaying with the current web page based on such combination.

11. The apparatus as recited in claim 10, wherein the different user characteristics comprise a plurality of different user categories that relate to user interest or expertise in such different user categories and/or a plurality of different user demographics.

12. The apparatus as recited in claim 10, wherein the processor and/or memory are further configured to perform the following operation:

mapping each of the plurality of different user characteristics to a plurality of user-relevant terms that are also relevant for contextual advertisement selection to generate one or more mapping models, wherein the mapping is based on collected user activity information.

13. The apparatus of claim 12, wherein the user activity information comprises a plurality of specified activity categories for different activities, a plurality of specified web pages that have been selected by a plurality of users, and a plurality of terms from the specified web pages and wherein the mapping comprises learning the mapping model based on the terms from the specified web pages and the specified activity categories.

14. The apparatus of claim 13, wherein the learning comprises maximizing a likelihood function based on the specified web pages and the specified activity categories.

15. At least one computer readable storage medium having computer program instructions stored thereon that are arranged to perform the following operations:

receiving a request for an advertisement to be displayed in a current web page that has been requested by a current user, wherein the current user is associated with one or more current user characteristics from a plurality of different user characteristics, wherein the current web page has an associated content;

using a mapping model and the one or more current user characteristics, obtaining a plurality of user-relevant terms for each of the one or more current user characteristics; and

providing a combination of the content of the current web page and obtained user-relevant terms for selecting an advertisement for displaying with the current web page based on such combination.

16. The at least one computer readable storage medium as recited in claim 15, wherein the different user characteristics comprise a plurality of different user categories that relate to user interest or expertise in such different user categories and/or a plurality of different user demographics.

17. The at least one computer readable storage medium as recited in claim 16, wherein the computer program instructions stored thereon that are further arranged to perform the following operation:

mapping each of the plurality of different user characteristics to a plurality of user-relevant terms that are also relevant for contextual advertisement selection to generate one or more mapping models, wherein the mapping is based on collected user activity information.

18. The at least one computer readable storage medium of claim 17, wherein the user activity information comprises a plurality of specified activity categories for different activities, a plurality of specified web pages that have been selected by a plurality of users, and a plurality of terms from the specified web pages and wherein the mapping comprises learning the mapping model based on the terms from the specified web pages and the specified activity categories.

19. The at least one computer readable storage medium of claim 18, wherein the learning comprises maximizing a likelihood function based on the specified web pages and the specified activity categories.

20. The at least one computer readable storage medium of claim 19, wherein the computer program instructions stored thereon that are further arranged to perform the following operation:

extracting the terms from the specified web pages that are relevant for advertisement selection.