System and method for creating user profiles

• US 8,655,916 B2
• Filed: 09/22/2006
• Issued: 02/18/2014
• Est. Priority Date: 09/22/2006
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Roy, Howard Scott
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US11/525,486
• Publication Number:
  US 20080077614A1
• Time in Patent Office: 2,706 Days
• Field of Search: 707600-831, 707/899, 707999001-999206
• US Class Current: 707/790
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: H04L 51/56 Unified messaging, e.g. interactions between e-mail, instant messaging or converged IP messaging [CPM]

Abstract

A computer-implemented method for constructing a profile for a target user is disclosed. The method comprises monitoring electronic communications across a network to identify at least one electronic communication that identifies a target user as an intended message recipient, extracting metadata from content associated with the at least one electronic communication; and constructing a user profile for the target user on the basis of the extracted metadata. It is assumed that the message senders send their messages, including associated content, to a given target user with the belief that the content is of some interest to the target user on the basis of some knowledge regarding the target user'"'"'s personality, preferences, tastes and the like. In this manner, a profiling entity may indirectly construct a profile of the target user based on the content sent by one or more message senders to the target user.

Claims

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

monitoring personal electronic communications across a network to identify at least one given personal electronic communication identifying a target user as an intended recipient of the given personal electronic communication, the given personal electronic communication including one or more content items;

extracting metadata from the one or more content items and said at least one identified personal electronic communication, wherein the one or more content items include at least an attachment;

storing the extracted metadata in a profiling database, indexed for the target user; and

constructing a user profile for the target user on the basis of the extracted metadata;

matching the extracted metadata in the target user profile with extracted metadata in a second user profile for a second target user to determine one or more profile similarities between the target user profile and the second target user profile; and

suggesting additional content to the target user based on the one or more profile similarities between the target user profile and the second target user profile, wherein the additional content is at least one of an article, music, a video, artwork.

2. The method of claim 1, wherein the extracted metadata comprises at least one of a topic, a source, an author, a locality and a language.

3. The method of claim 1, further comprising determining whether to construct said user profile for the target user based on the extracted metadata.

4. The method of claim 3, wherein said determination is based on a statistical threshold test.

5. The method of claim 3, further comprising, upon determining that said user profile for the target user will not be constructed from the extracted metadata, returning to said monitoring step to monitor additional electronic communications.

6. The method of claim 1, wherein said constructing step is based on a machine learning technique.

7. The method of claim 1, wherein said one or more content items included in the electronic communication is an e-mail attachment.

12. The method of claim 1, wherein each content item comprises one of text, audio, video, an image, and a control.

8. A profiling system for indirectly profiling a user over a distributed network, the system comprising:

a monitoring module configured to monitor personal electronic transmissions transmitted across a network to identify at least one personal electronic transmission identifying a target user as an intended message recipient, the at least one personal electronic transmission including one or more content items;

a metadata extraction module configured to extract metadata from the one or more content items and the at least one personal electronic transmission, wherein the one or more content items include at least an attachment;

a profiling database for storing the extracted metadata;

a profile creation module for constructing a user profile for the target user based on said extracted metadata; and

a comparison module for matching the extracted metadata in the target user profile with extracted metadata in a second user profile for a second target user so as to determine one or more profile similarities between the target user profile and the second target user profile and suggesting additional content to the target user based on the one or more profile similarities between the target user profile and the second target user profile, wherein the additional content is at least one of an article, music, a video, artwork.

9. The profiling system of claim 8, further comprising a user profile determination module for determining whether the extracted metadata describes content transmitted to the target user.

10. The profiling system of claim 9, wherein a test for determining whether the extracted metadata describes content transmitted to the target user is a statistical threshold test.

11. The profiling system of claim 8, wherein the profile creation module constructs said user machine learning technique.