Systems and methods for online user profiling and segmentation

• US 8,504,411 B1
• Filed: 09/14/2009
• Issued: 08/06/2013
• Est. Priority Date: 09/14/2009
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: AOL Advertising Incorporated (Apollo Global Management, Inc.)
• Inventors: Subasic, Pero, Holtan, Hans Marius, Shukla, Manu, Kwon, Jaimyoung, Qu, Yan, Cabacungan, Robert S., Mehta, Rohan A., Chang, Jay L., Coloma, Kenin A. H., Cohen, Neil, Whitney, Brian
• Primary Examiner(s): Rines, David
• Application Number:
  US12/558,891
• Time in Patent Office: 1,422 Days
• Field of Search: 705 711- 742, 705 141- 1473
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

A computer-implemented method is provided for managing online user profiles. The method includes receiving information about online activity of a user, the information including at least a unique user ID and a URL requested by the user; fetching textual content associated with the URL requested by the user; generating one or more keywords based on the textual content; and generating or updating a user profile of the user to include the one or more keywords. A system for managing online user profiles is also provided.

Claims

1. A computer-implemented method for managing online user profiles, the method comprising:

generating, by at least one processor, a prioritization table based on impression counts associated with a plurality of URLs;

retrieving, over an electronic network, textual data associated with the plurality of URLs, the retrieving being performed based on the prioritization table, such that URLs with higher impression counts have their textual content retrieved before URLs with lower impression counts;

generating, and storing in a database, one or more keywords in relation to each of the URLs, based on respective textual content retrieved for each of the URLs;

receiving information about online activity of a user, the information including at least a unique user ID and a URL requested by the user;

searching the database for one or more keywords stored in relation to the requested URL; and

generating or updating, by the at least one processor, a user profile of the user to include the one or more keywords stored in relation to the requested URL.

2. The method of claim 1, wherein the information further includes one or more of a timestamp, geographical information, demographic information, user session information, contextual information, and user events information.

3. The method of claim 1, wherein the information is received in the form of a behavioral log, a leadback log, a click log, an action log, or an impression log.

4. The method of claim 1, wherein the information is received from one or more of an advertiser of a product or service, a publisher of a web site, an ad server, or a third party facilitator of online advertising.

5. The method of claim 1, wherein a plurality of URLs are received, and the method further includes at least one of filtering out certain URLs, grouping URLs by host, and prioritizing URLs based on a number of Web pages associated with each host.

6. The method of claim 1, wherein the one or more keywords are generated by parsing HTML content associated with a URL and classifying the parsed content into categories.

7. The method of claim 1, further comprising the step of generating a page profile for a URL based on keywords generated for the URL.

8. The method of claim 1, further comprising adding weights to the keywords based on the textual content associated with the URL.

9. The method of claim 8, wherein the weights are added to the keywords based on their position and element membership on a web page of the URL, their recency, or their frequency in the web page.

10. The method of claim 1, wherein the user profile is generated or updated by aggregating any information received relating to the unique user ID.

11. The method of claim 1, wherein logs of online activity are received relating to a plurality users, and the method comprises generating, updating, and storing user profiles for each of the plurality of users in a directory.

12. The method of claim 10, further comprising partitioning the user profiles into segments based on content of the user profiles.

13. A system for managing online user profiles, the system comprising:

a processor system configured to;

fetch, over an electronic network, textual data associated with a plurality of URLs, the fetching being performed according to a prioritization sequence based on impression counts, such that URLs with higher impression counts have their textual content fetched before URLs with lower impression counts;

generate, and store in a database system, one or more keywords in relation to each of the URLs, based on respective textual content fetched for each of the URLs;

receive information about online activity of a user, the information including at least a unique user ID and a URL requested by the user;

search the database for one or more keywords stored in relation to the requested URL; and

generate or update a user profile of the user to include the one or more keywords stored in relation to the requested URL; and

a database system configured to store one or more of the information, the textual content, the keywords, and the user profile.

14. The system of claim 13, wherein logs of online activity are received relating to a plurality of users, and the method comprises generating, updating, and storing user profiles for each of the plurality of users in a directory stored in the database system.

15. The system of claim 14, wherein the processor is further configured to partition the user profiles into segments based on content of the user profiles.

16. The system of claim 13, wherein the processor is further configured to generate a page profile for a URL based on keywords generated for the URL;

and store the page profile in the database system.

17. The system of claim 13, further comprising a plurality of clustered processors and memory devices.

18. The system of claim 13, wherein the system is disposed in communication with a plurality of ad servers through a network.

19. The system of claim 13, wherein the system further includes a user interface.

20. A computer-readable storage medium storing a computer program which, when executed by a computer, causes the computer to perform a method of online user profiles, the method comprising:

fetching, over an electronic network, textual data associated with a plurality of URLs, the fetching being performed according to a prioritization sequence based on impression counts, such that URLs with higher impression counts have their textual content fetched before URLs with lower impression counts;

generating, and storing in a database, one or more keywords in relation to each of the URLs, based on respective textual content fetched for each of the URLs;

receiving information about online activity of a user, the information including at least a unique user ID and a URL requested by the user;

searching the database for one or more keywords stored in relation to the requested URL; and

generating or updating, using at least one processor, a user profile of the user to include the one or more keywords stored in relation to the requested URL.