BEHAVIORAL RETARGETING SYSTEM AND METHOD FOR COOKIE-DISABLED DEVICES

• US 20140297394A1
• Filed: 11/19/2013
• Published: 10/02/2014
• Est. Priority Date: 03/26/2013
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Li, Wentong, Mao, Yi
• Granted Patent: US 10,482,495 B2
• Time in Patent Office: Days
• US Class Current: 705/14.41
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06T 1/0021 Image watermarking
• CPC Class Codes: G06T 1/0064 Geometric transfor invariant watermarking, e.g. affine transform invariant
• CPC Class Codes: G06T 3/02 Affine transformations for image registration G06T3/147; for image mosaicing G06T3/4038
• CPC Class Codes: H04N 21/41415 involving a public display, viewable by several users in a public space outside their home, e.g. movie theatre, information kiosk

Abstract

A system is provided for retargeting advertisements and is based on a database storing user behavior data related to information for a plurality of consumers. An index-lookup processes the user behavior data and translates the user behavior data into a plurality of indices. A data loading module processes the plurality of indices and generates a multi-indexed user behavior cube. An online query module receives a request for an advertisement and processes the request to determine one or more related user attributes and retrieves user behavior data from the multi-indexed user behavior cube using the related user attributes. An ad recommendation module receives the set of user behaviors and generates a list of recommended advertisements using the set of user behaviors data and an advertiser retargeting criterion.

Claims

1. A system for retargeting advertisements, the system comprising:

a database configured to store user behavior data comprising information related to a plurality of consumers;

an index-lookup module configured to process the user behavior data and translate the user behavior data into a plurality of indices;

a data loading module configured to process the plurality of indices and to generate a multi-indexed user behavior cube;

an online query module configured to receive an advertisement request and to process the request to determine one or more related user attributes;

wherein the online query module is further configured to retrieve a set of one or more user behaviors from the multi-indexed user behavior cube using at least the one or more related user attributes; and

an ad recommendation module configured to receive the set of user behaviors and to generate a list of recommended advertisements using the set of user behaviors data and an advertiser retargeting criterion.

2. The system of claim 1, wherein the set of one or more user behaviors comprises a subset of the stored user behavior data.

3. The system of claim 2, wherein the online query module is further configured to process the subset of stored user behavior data to generate a filtered list of user behaviors.

4. The system of claim 1, wherein the multi-indexed user behavior cube defines an association between the plurality of indices.

5. The system of claim 4, wherein the multi-indexed user behavior cube comprises one or more indices organized in a linked structure, hashmap, or associative array.

6. The system of claim 1 further comprising a performance feedback module configured to receive the set of one or more user behaviors and to retrieve performance data for the one or more user behaviors.

7. The system of claim 6, wherein the performance feedback module is further configured to process the set of one or more user behaviors using the performance data and to produce data results relating to one or more user behaviors impact on advertising conversions.

8. The system of claim 1, wherein the index-lookup module is further configured to receive additional user behavior data in real-time, and to process the additional user behavior data to generate or update indices in real-time.

9. The system of claim 1, wherein the list of recommended advertisements are selected from a data cache of advertisements.

10. The system of claim 1, wherein the multi-indexed user behavior cube comprises a data cache distributed over a plurality of databases.

11. A non-transitory computer readable medium having stored therein data representing instructions executable by a programmed processor for measuring, the storage medium comprising instructions operative for:

storing user behavior data to a database, the user behavior data defining one or more aspects of a plurality of user'"'"'s interactions with web content;

processing the user behavior data to generate a plurality of indices, wherein each index defines a relationship between one or more targeting attributes and the user behavior data;

processing the plurality of indices to generate a multi-indexed user behavior hypercube defining a relationship between the plurality of indices;

receiving a request for an advertisement and processing the request to identify a set of user targeting attributes;

retrieving, from the multi-indexed user behavior hypercube, a subset of user behavior data using at least the set of user targeting attributes;

generating a list of recommended advertisements using the subset of user behavior data.

12. The storage medium of claim 11, wherein the multi-indexed user behavior hypercube comprises a keyed database storing the plurality of indices.

13. The storage medium of claim 12, wherein the subset of user behavior data is retrieved using a permutation of the set one or more user targeting attributes as a key.

14. The storage medium of claim 11, further comprising instructions for processing the subset of user behavior data using performance feedback data to produce data results relating to the user behavior data'"'"'s impact on advertising conversions

15. The storage medium of claim 11, further comprising instructions for receiving additional user behavior data and updating the database in real-time.

16. The storage medium of claim 11, wherein the database comprises data received from a combination of advertiser data, census data, third-party data, data search history data, or purchase history data.

17. A method for retargeting advertisements, the method comprising:

storing user data to a database;

processing the user data to generate a plurality of indices;

processing the plurality of indices to generate a poly-indexed user data cube;

receiving a request for an advertisement;

processing the request to determine one or more targeting criteria;

retrieving user data from the poly-indexed user data cube using the one or more targeting criteria;

generating a list of one or more targeted advertisements using the user data retrieved from the poly-indexed user data cube.

18. The method of claim 17, further comprising processing the subset of user data using performance data to produce data results relating to the user data'"'"'s impact on advertising conversions.

19. The method of claim 17, further comprising receiving additional user data and updating the database with the additional user data in real-time.

20. The method of claim 19, further comprising processing the additional user data to generate a plurality of additional indices, and processing the plurality of additional indices to augment the poly-indexed user data cube with the additional indices.