Neural network system and method for controlling information output based on user feedback

• US 7,120,615 B2
• Filed: 08/30/2004
• Issued: 10/10/2006
• Est. Priority Date: 02/02/1999
• Status: Expired due to Term

• Current Assignee: Hyper Search LLC (IPValuation Partners, LLC)
• Original Assignee: Thinkalike LLC
• Inventors: Pope, Ivan, Sullivan, Alan
• Primary Examiner(s): DAVIS, GEORGE B
• Application Number:
  US10/928,278
• Publication Number:
  US 20050086186A1
• Time in Patent Office: 771 Days
• Field of Search: 706/15, 706/11
• US Class Current: 706/15
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/063 using electronic means
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

A system and method for controlling information output based on user feedback about the information is provided that comprises a plurality of information sources providing information. The information sources may be electronic mail providers, chat participants, or page links. At least one neural network module selects one or more of a plurality of objects to receive information from the plurality of information sources based at least in part on a plurality of inputs and a plurality of weight values during that epoch. At least one server, associated with the neural network module, provides one or more of the objects to a plurality of recipients. The objects may comprise electronic mail messages, chat participants viewers, or slots within a link directory page. The recipients provide feedback about the information during an epoch. At the conclusion of an epoch, the neural network takes all of the feedback that has been provided from the recipients and generates a rating value for each of the plurality of objects. Based on the rating value and the selections made, the neural network redetermines the weight values within the network. The neural network then selects the objects to receive information during a subsequent epoch using the redetermined weight values and the inputs for that subsequent epoch.

Claims

1. A system for controlling information output based on user feedback about the information comprising:

a plurality of information sources for providing information;

an artificial intelligence agent for selecting one or more of a plurality of objects in which information from the plurality of information sources is placed based at least in part on a plurality of inputs and a plurality of weight values, the plurality of inputs including a new query;

at least one server, associated with the artificial intelligence agent, for providing one or more of the objects to one or more recipients, each of the one or more recipients having a display for displaying the information in the selected objects; and

recipients for enabling one or more users to generate feedback about the information,

wherein the artificial intelligence agent selects at least one of the weight values at the end of an epoch, the epoch comprises selecting an object corresponding to one of the information sources and selects, in response to a subsequent query, which objects to receive information using the at least one of the reselected weight values and inputs associated with the subsequent query.

2. The system of claim 1, wherein the information sources are web pages and the information comprises web page links.

3. The system of claim 1, wherein the one or more objects comprise slots in a link directory page.

4. The system of claim 1, wherein the epoch comprises a selection of a web link.

5. The system of claim 1, wherein the epoch comprises a visit to a web page.

6. A system for controlling information output based on user feedback comprising:

a server for providing pieces of information to a recipient via a plurality of slots that present the pieces of information to a user; and

an artificial intelligence module for communicating with the server and for ranking the pieces of information such that the pieces of information are placed in given ones of the plurality of slots,

wherein when one of the slots is selected by the user, such act of selection comprises feedback to the artificial intelligence module about a corresponding piece of information and the artificial intelligence module reranks the pieces of information, and

wherein, in response to a subsequent query, at least one of the pieces of information is either placed in a slot different from a slot in which the piece of information was previously placed and presented to the user as a result of the reranking or not placed in any of the slots presented to the user.

7. The system of claim 6, wherein one or more of the pieces of information comprise links to web sites.

8. The system of claim 6, wherein one or more of the pieces of information comprise chat participants.

9. The system of claim 6, wherein one or more of the pieces of information comprise email participants.

10. The system of claim 6, wherein an attribute of the user is considered in redetermining the ranking of the pieces of information is placed.