Personalized professional content recommendation

• US 9,171,085 B2
• Filed: 08/06/2013
• Issued: 10/27/2015
• Est. Priority Date: 03/07/2012
• Status: Active Grant

• Current Assignee: UT-Battelle LLC
• Original Assignee: UT-Battelle LLC
• Inventors: Xu, Songhua
• Primary Examiner(s): DWIVEDI, MAHESH H
• Application Number:
  US13/960,509
• Publication Number:
  US 20130325858A1
• Time in Patent Office: 812 Days
• Field of Search: 707/754
• US Class Current: 1/1
• 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 16/9535 Search customisation based on user profiles and personalisation

Abstract

A personalized content recommendation system includes a client interface configured to automatically monitor a user'"'"'s information data stream transmitted on the Internet. A hybrid contextual behavioral and collaborative personal interest inference engine resident to a non-transient media generates automatic predictions about the interests of individual users of the system. A database server retains the user'"'"'s personal interest profile based on a plurality of monitored information. The system also includes a server programmed to filter items in an incoming information stream with the personal interest profile and is further programmed to identify only those items of the incoming information stream that substantially match the personal interest profile.

Claims

1. A method of providing personalized content recommendations, comprising:

at an electronic device comprising a processor and a memory storing instructions for execution by the processor performing the acts comprising;

automatically monitoring a user'"'"'s information stream to identify a user'"'"'s interest in a topic from a range of data sources through a publicly accessible distributed network;

automatically generating a content signature that includes semantically salient content elements from the monitored user'"'"'s information, a network address to the monitored user'"'"'s information that the semantically salient content is based upon, and a plurality of densities of topics embodied in the salient content elements;

automatically generating a personal interest profile from the monitored user information and storing the personal interest profile in a memory of the computing device, the memory stored with user'"'"'s preferences based on a plurality of monitored behaviors;

filtering items in an information stream with the personal interest profile and the content signatures; and

transmitting only those items of information that match the user'"'"'s personal interest profile to the user.

2. The method of claim 1 further comprising ranking the items of information based on a measure of an absolute relevance of the items of information to the user.

3. The method of claim 1 further comprising ranking the items of information based on a measure of an absolute relevance of the items of information.

4. The method of claim 1 further comprising ranking the items of information based on a measure of an absolute relevance of the items of information to a corpus of items of information.

5. The method of claim 1 where the personal interest profile is based on the contribution of the user to the user information.

6. The method of claim 1 where the personal interest profile comprises a plurality of objects stored in a cache in which the objects represent a interest level of the user and a disinterest level of the user.

7. The method of claim 1 where the personal interest profile comprises an object that represents a time and a temporal object that represents a user'"'"'s information needs and preferences in time.

8. The method of claim 1 where the computing device comprises a mobile computing device.

9. The method of claim 1 where the computing device comprises a non-mobile computing device.

10. The method of claim 1 further comprising displaying only those items that match the user'"'"'s personal interest profile.

11. The method of claim 1 where the personal interest profile is based on a user event.

12. The method of claim 1 further comprising extracting a content signature based on the monitored user information stream by modeling document level individual users'"'"' dwell times.

13. The method of claim 1 further comprising extracting a content signature based on the monitored user information stream by modeling dwell times.

14. The method of claim 1 further comprising identifying consumed content at a Web page level through a comparison of time stamps of the user'"'"'s information stored in the memory.

15. The method of claim 1 where the personal interest profile comprises an aggregation of user profiles having similar characteristics.

16. The method of claim 1 further comprising automatically detecting a shift in the personal interest profile.

17. A personalized content recommendation system comprising:

a client interface device configured to automatically generate a content signature that includes semantically salient content elements from monitored user'"'"'s information data stream transmitted on a publicly accessible network without human intervention, the content signature includes a network address to the monitored user'"'"'s information that the semantically salient content is based upon, and a plurality of densities of topics embodied in the salient content elements;

a collaborative personal interest inference engine resident to a non-transient media and configured to generate automatic predictions about the interests of the user;

a database server that retains a personal interest profile based on a plurality of monitored past behaviors; and

a server programmed to filter items in an incoming information stream with the personal interest profile, the content signature, and programmed to identify only those items of the incoming information stream that match the personal interest profile.

18. The system of claim 17 where the server is further programmed to rank the items of the incoming information based on a measure of the absolute relevance of the items of information to the user.

19. The system of claim 17 where the server is further programmed to rank the items of the incoming information based on a measure of the absolute relevance of the items of information.

20. The system of claim 17 where the server is further programmed to rank the items of the incoming information based on a measure of the absolute relevance of the items of the incoming information stream to a corpus of items of information.