Method and system for web user profiling and selective content delivery

• US 8,108,245 B1
• Filed: 04/21/2000
• Issued: 01/31/2012
• Est. Priority Date: 09/17/1999
• Status: Expired due to Term

• Current Assignee: Cox Communications Incorporated (Cox Enterprises Incorporated)
• Original Assignee: Cox Communications Incorporated (Cox Enterprises Incorporated)
• Inventors: Hosea, Devin F., Rascon, Arthur P., Zimmerman, Richard S., Oddo, Anthony Scott, Thurston, Nathaniel
• Primary Examiner(s): BOYCE, ANDRE D
• Application Number:
  US09/558,755
• Time in Patent Office: 4,302 Days
• Field of Search: 705/7.33, 705/10
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: H04L 67/025 for remote control or remote monitoring of applications
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

A method and system are provided for accurately and anonymously profiling Web users and for selectively delivering content such as advertisements to users based on their profiles. The system uses behavioral information preferably collected at the users'"'"' point of connection to the Internet to anonymously profile their interests and demographics. It accurately matches and delivers content to the users to which they will likely be most receptive. Advertisers can use the system to launch effective advertising campaigns delivering selected Web content to chosen target audiences. The system uses feedback from users to determine the effectiveness of an advertising campaign and allows dynamic modification of the advertising campaign by, e.g., altering the target audience, to optimize results.

Claims

1. A method of profiling a Web user, comprising:

detecting, at an ISP (Internet service provider) server, an outgoing URL page request from a client;

capturing, at the ISP server, the packets associated with the detected URL page request,

extracting, from the packets captured at the ISP server, a Uniform Resource Locator (URL) identifying a network path to a Web site satisfying the URL page request;

obtaining, at the ISP server, an IP (Internet protocol) address from a client;

storing the extracted URL and the IP address obtain form the client in a database;

correlating, at the ISP server, the IP address obtained from the client with a permanent anonymous user identifier using an IP address to anonymous user ID (AID) cross-reference table;

associating the extracted URL with the permanent anonymous user identifier correlated with the IP address obtained from the client;

for each permanent anonymous user identifier correlated with the IP address obtained from the client, storing the URL of the Web site satisfying the URL page request and the permanent anonymous user identifier correlated with the IP address obtained from the client;

cross-referencing, at the ISP server, the extracted URL with demographic information in a categorized URL database profiling Web sites based on demographic characteristics of users accessing the profiled Web sites;

extracting, at the ISP server, a set of the demographic information associated with the Web site cross-referenced to the extracted URL;

extracting content affinity from a categorized listing of URLs that translate the extracted URL into a content preference for the profiled Web site associated with the extracted URL; and

providing a user profile for the permanent anonymous user identifier based on the extracted URL and the extracted content affinity obtained by translating the extracted URL into the content preference for the profiled Web site associated with the extracted URL.

2. The method of claim 1, wherein the profile of the user contains data selected from demographic data.

3. The method of claim 2 wherein said demographic data is selected from the group consisting of user'"'"'s age, user'"'"'s gender, user'"'"'s income and user'"'"'s highest attained education level.

4. The method of claim 1, wherein the profile of the user contains psychographic data.

5. The method of claim 4 wherein said psychographic data includes data on the user'"'"'s interests.

6. The method of claim 1, further comprising providing a database associating each of said plurality of Web sites with demographic characteristics of known persons who have accessed said sites.

7. The method of claim 6 wherein said database is provided by a Web site ratings service.

8. The method of claim 1, wherein the user profile comprises an update combined with an existing user profile.

9. The method of claim 8 wherein the generating a user profile comprises combining the profiles of the Web sites requested by a user identifier to the existing user profile using an averaging algorithm.

10. The method of claim 9 wherein said user profile includes data on a plurality of demographic categories, each associated with a rating, and the method further comprises filling in a value for the rating for any demographic category having a low confidence measure.

11. The method of claim 10 wherein filling in a value comprises using an average rating of persons having similar profiles to that of said user for a category having a low confidence measure.

12. The method of claim 11 wherein said average rating is determined using a clustering algorithm.

13. The method of claim 1 further comprising erasing records of which Web sites said user has visited after developing the user'"'"'s profile to protect user privacy.

14. The method of claim 1, further comprising delivering selective advertising to the user identifier based on the user profile associated with the user identifier.

15. The method of claim 14 wherein delivering selective advertising comprises transmitting a pop-up advertisement to a display of a computer associated with a user identifier.

16. The method of claim 1, wherein the developing a user profile for user identifier further comprises generating, for a user associated a user identifier, a user profile having a rating for categories of Web sites of interest to the user and a confidence measure representing an estimate of accuracy of a category'"'"'s rating.

17. A computer for profiling a Web user, comprising:

a memory for storing a program;

a processor operative with the program to detect, at an ISP (Internet service provider) server, an outgoing URL page request from a client, to capture, at the ISP server, the packets associated with the detected URL page request, to extract, from the packets captured at the ISP server, a Uniform Resource Locator (URL) identifying a network path to a Web site satisfying the URL page request, to obtain, at the ISP server, an IP (Internet protocol) address from a client, to store the extracted URL and the IP address obtain form the client in a database, to correlate, at the ISP server, the IP address obtained from the client with a permanent anonymous user identifier using an IP address to anonymous user ID (AID) cross-reference table, to associate the extracted URL with the permanent anonymous user identifier correlated with the IP address obtained from the client, for each permanent anonymous user identifier correlated with the IP address obtained from the client, to store the URL of the Web site satisfying the URL page request and the permanent anonymous user identifier correlated with the IP address obtained from the client, to cross-reference, at the ISP server, the extracted URL with demographic information in a categorized URL database profiling Web sites based on demographic characteristics of users accessing the profiled Web sites, to extract, at the ISP server, a set of the demographic information associated with the Web site cross-referenced to the extracted URL, to extract content affinity from a categorized listing of URLs that translate the extracted URL into a content preference for the profiled Web site associated with the extracted URL, and to provide a user profile for the permanent anonymous user identifier based on the extracted URL and the extracted content affinity obtained by translating the extracted URL into the content preference for the profiled Web site associated with the extracted URL.

18. The computer of claim 17, wherein the profile of the user contains data selected from demographic data.

19. The computer of claim 18 wherein the demographic data is selected from the group consisting of user'"'"'s age, user'"'"'s gender, user'"'"'s income and user'"'"'s highest attained education level.

20. The computer of claim 17, wherein the profile of the user contains psychographic data.

21. The computer of claim 20 wherein said psychographic data includes data on the user'"'"'s interests.

22. The computer of claim 17, further comprising a database associating each of said plurality of Web sites with demographic characteristics of known persons who have accessed said sites.

23. The computer of claim 22 wherein said database is provided by a Web site ratings service.

24. The computer of claim 17, wherein the user profile of the user identifier comprises an existing user profile.

25. The computer of claim 24 wherein the processor generates a user profile by combining the profiles of the Web sites requested by a user identifier to the existing user profile using an averaging algorithm.

26. The computer of claim 25 wherein said user profile includes data on a plurality of demographic categories, each associated with a rating, and the processor fills in a value for the rating for any demographic category having a low confidence measure.

27. The computer of claim 26 wherein the processor fills in a value by using an average rating of persons having similar profiles to that of said user far a category having a low confidence measure.

28. The computer of claim 27 wherein said average rating is determined using a clustering algorithm.

29. The computer of claim 17, wherein the processor erases records of which Web sites said user has visited after developing the user'"'"'s profile to protect user privacy.

30. The computer of claim 17, wherein the processor delivers selective advertising to the user identifier based on the user profile associated with the user identifier.

31. The computer of claim 30 wherein the processor delivers selective advertising by transmitting a pop-up advertisement to a display of a computer associated with a client having the user identifier.

32. A non-transitory computer readable medium comprising a program for profiling a Web user by performing the steps of:

detecting, at an ISP (Internet service provider) server, an outgoing URL page request from a client;

capturing, at the ISP server, the packets associated with the detected URL page request,

extracting, from the packets captured at the ISP server, a Uniform Resource Locator (URL) identifying a network path to a Web site satisfying the URL page request;

obtaining, at the ISP server, an IP (Internet protocol) address from a client;

storing the extracted URL and the IP address obtain form the client in a database;

correlating, at the ISP server, the IP address obtained from the client with a permanent anonymous user identifier using an IP address to anonymous user ID (AID) cross-reference table;

associating the extracted URL with the permanent anonymous user identifier correlated with the IP address obtained from the client;

for each permanent anonymous user identifier correlated with the IP address obtained from the client, storing the URL of the Web site satisfying the URL page request and the permanent anonymous user identifier correlated with the IP address obtained from the client;

cross-referencing, at the ISP server, the extracted URL with demographic information in a categorized URL database profiling Web sites based on demographic characteristics of users accessing the profiled Web sites;

extracting, at the ISP server, a set of the demographic information associated with the Web site cross-referenced to the extracted URL;

extracting content affinity from a categorized listing of URLs that translate the extracted URL into a content preference for the profiled Web site associated with the extracted URL; and

providing a user profile for the permanent anonymous user identifier based on the extracted URL and the extracted content affinity obtained by translating the extracted URL into the content preference for the profiled Web site associated with the extracted URL.