PERSONALIZATION ENGINE FOR BUILDING A USER PROFILE

• US 20110066615A1
• Filed: 10/28/2009
• Published: 03/17/2011
• Est. Priority Date: 06/27/2008
• Status: Active Grant

• Current Assignee: CBS Interactive Inc. (ViacomCBS Incorporated)
• Original Assignee: CBS Interactive Inc. (ViacomCBS Incorporated)
• Inventors: Osborne, Thomas, Potter, John, PRADHAN, Tushar
• Granted Patent: US 8,140,515 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

Users of electronic documents are classified for profiling and targeting of additional relevant content. Behavioral data is gathered from user registration information and user activity, and user documents and actions are categorized. Registration information is combined with collaborative and editorial data to provide user profile information. Author-generated document classification information is analyzed and assigned a first taxonomic noun to characterize the document. User-generated tags characterizing a portion of the document are assigned a second taxonomic noun. Search terms that resulted in the user accessing the document are identified and assigned a third taxonomic noun. Attributes related to how the document was accessed are evaluated and assigned a fourth taxonomic noun. The document is processed using pattern rules to extract a fifth taxonomic noun. The taxonomic nouns are aggregated to determine a composite set of taxonomic nouns, and the user is categorized using the taxonomic nouns, and/or the author-generated classification.

Claims

1. A computer-implemented method for building a user profile, the method comprising:

labeling and storing user registration information in a database as a set of demographic nouns;

analyzing author-generated classification information regarding a document with a user profiling server and assigning a set of first taxonomic nouns to characterize the user based upon the author-generated classification information;

examining a user-generated tag from a client computer with the user profiling server_and characterizing the user of the document and assigning a set of second taxonomic nouns to characterize the user based upon the user-generated tag characterization;

identifying a search term with the user profiling server that resulted in the user accessing the document from a content provider site server and assigning a set of third taxonomic nouns to characterize the user based upon the search term;

evaluating attributes with the user profiling server that are related to the manner in which the user accesses the document from the content provider site server and assigning a set of fourth taxonomic nouns to characterize the user based upon the attributes related to the manner in which the document was accessed;

processing the document with a content analysis server to extract a set of fifth taxonomic nouns to characterize the user;

aggregating the set of first taxonomic nouns, the set of second taxonomic nouns, the set of third taxonomic nouns, the set of fourth taxonomic nouns, and the set of fifth taxonomic nouns into a composite set of taxonomic nouns with a user profiling server; and

building a user profile with the user profiling server based upon at least one of the demographic nouns, the composite set of taxonomic nouns, and the author-generated classification information.

2. The computer-implemented method for building a user profile of claim 1, wherein the user registration information characterizing the user of the document includes at least one of an item listed in a profile of the user and a technology implementation setting.

3. The computer-implemented method for building a user profile of claim 1, wherein the author-generated information includes metadata assigned to the document.

4. The computer-implemented method for building a user profile of claim 1, wherein the attributes related to the manner in which the user accessed the document include at least one of a network type used to access the document, a Web site from which the document was accessed, an electronic correspondence to which the document was associated, a time of day the document was accessed, a referrer who directed the user to the document, and a user category used by a database storing the document to describe the user.

5. The computer-implemented method for building a user profile of claim 1, wherein the attributes related to the manner in which the user accessed the document include at least one of a comment by the user, a rating by the user, a download by the user, and a purchase of a product or a service by the user indicating a level of a user'"'"'s relative interest in the document in relation to other documents available to the user.

6. The computer-implemented method for building a user profile of claim 1, wherein building the user profile includes deriving a user cluster of related users.

7. The computer-implemented method for building a user profile of claim 6, wherein building the user profile further includes:

computing a similarity measure between the user profile of the user of the electronic document and other user profiles of the cluster of related users; and

building a group of related users based upon the user profile of the user of the electronic document and the user profiles of the cluster of related users.

8. The computer-implemented method for building a user profile of claim 1 further comprising:

assigning a value index to the user based upon the user profile.

9. The computer-implemented method for building a user profile of claim 8, wherein the value index includes a weighting of at least one of the number of demographic nouns, the total number of taxonomic nouns, and the number of unique taxonomic nouns.

10. The computer-implemented method for building a user profile of claim 8, wherein the value index assigned to the user dynamically changes based upon subsequent user activity.

11. The computer-implemented method for building a user profile of claim 10, wherein the subsequent user activity includes at least one of sharing the user'"'"'s interests, clicking on a newsletter, participating in a discussion, reading or writing a blog, downloading a white paper, purchasing a product or a service, reviewing a product or service, sharing a document, posting to a social network, sending an email, and disclosing information about the user.

12. The computer-implemented method for building a user profile of claim 8 further comprising:

collecting a number of user profiles to build a group of related users based upon the user profiles; and

building an audience profile based upon the group of related users.

13. The computer-implemented method for building a user profile of claim 12 further comprising:

mining user data from at least one of a Web page, a uniform resource locator, a natural language document, a network address, an Internet Protocol address, and a database;

combining the mined user data with the collected user profiles; and

creating a user mart of the combined mined user data and the collected user profiles to tie domains together and track user activity.

14. The computer-implemented method for building a user profile of claim 1, wherein the attributes related to the manner in which the user accessed the document include at least one of sharing the user'"'"'s interests, clicking on a newsletter, participating in a discussion, reading or writing a blog, downloading a white paper, purchasing a product or a service, reviewing a product or service, sharing a document, posting to a social network, sending an email, and disclosing information about the user.

15. A computer-implemented method for building a user profile, the method comprising:

labeling and storing user registration information in a database as a set of demographic nouns;

determining a composite set of taxonomic nouns with a user profiling server, the composite set of taxonomic nouns representing the user profile based upon taxonomic nouns, the taxonomic nouns being prepared by one or more of the following steps;

analyzing author-generated classification information regarding a document with the user profiling server and assigning a set of first taxonomic nouns to characterize the user based upon the author-generated classification information;

examining a user-generated tag from a client computer with the user profiling server and characterizing the user of the document and assigning a set of second taxonomic nouns to characterize the user based upon the user-generated tag characterization;

identifying a search term with the user profiling server that resulted in the user accessing the document from a content provider site server and assigning a set of third taxonomic nouns to characterize the user based upon the search term;

evaluating attributes with the user profiling server that are related to the manner in which a user accesses the document from the content provider site server and assigning a set of fourth taxonomic nouns to characterize the user based upon the attributes related to the manner in which the document was accessed; and

processing the document with a content analysis server to extract a set of fifth taxonomic nouns to characterize the user; and

building the user profile with the user profiling server, the user profile based upon at least one of the demographic nouns, the composite set of taxonomic nouns, and the author-generated classification information.

16. A system for building a user profile, the system comprising:

a user profiling server configured to;

label and store user registration information in a database as a set of demographic nouns;

analyze author-generated classification information regarding a user of a document and assign a set of first taxonomic nouns to characterize the user based upon the author-generated classification information;

examine a user-generated tag from a client computer characterizing the user of the document and assign a set of second taxonomic nouns to characterize the user based upon the user-generated tag characterization;

a content analysis server configured to;

identify a search term that resulted in the user accessing the document from a content provider site server and assign a set of third taxonomic nouns to characterize the user based upon the search term;

evaluate attributes related to the manner in which a user accesses the document from the content provider site server and assign a set of fourth taxonomic nouns to characterize the user based upon the attributes related to the manner in which the document was accessed; and

a pattern rules server configured for processing the document to extract a set of fifth taxonomic nouns to characterize the user;

wherein the user profiling server is further configured for aggregating the set of first taxonomic nouns, the set of second taxonomic nouns, the set of third taxonomic nouns, the set of fourth taxonomic nouns, and the set of fifth taxonomic nouns into a composite set of taxonomic nouns that represent the user and for building a user profile based upon at least one of the demographic nouns, the composite set of taxonomic nouns, and the author-generated classification scheme.

17. A computer program product with instructions recorded thereon for building a user profile, the computer program product storing instructions comprising:

instructions for labeling and storing user registration information in a database as a set of demographic nouns;

instructions for analyzing author-generated classification information regarding a document with a user profiling server and assigning a set of first taxonomic nouns to characterize the user based upon the author-generated classification information;

instructions for examining a user-generated tag from a client computer with the user profiling server and characterizing the user of the document and assigning a set of second taxonomic nouns to characterize the user based upon the user-generated tag characterization;

instructions for identifying a search term with the user profiling server that resulted in the user accessing the document from a content provider site server and assigning at set of third taxonomic nouns to characterize the user based upon the search term;

instructions for evaluating attributes with the user profiling server that are related to the manner in which a user accesses the document from the content provider site server and assigning a set of fourth taxonomic nouns to characterize the user based upon the attributes related to the manner in which the document was accessed;

instructions for processing the document with a content analysis server to extract a set of fifth taxonomic nouns to characterize the user;

instructions for aggregating the set of first taxonomic nouns, the set of second taxonomic nouns, the set of third taxonomic nouns, the set of fourth taxonomic nouns, and the set of fifth taxonomic nouns into a composite set of taxonomic nouns with a user profiling server; and

instructions for building a user profile with the user profiling server based upon at least one of the demographic nouns, the composite set of taxonomic nouns, and the author-generated classification information.