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

• US 20070038588A1
• Filed: 10/10/2006
• Published: 02/15/2007
• Est. Priority Date: 02/02/1999
• Status: Active Grant

• Current Assignee: Hyper Search LLC (IPValuation Partners, LLC)
• Original Assignee: Thinkalike LLC
• Inventors: Sullivan, Alan, Pope, Ivan
• Granted Patent: US 8,260,733 B2
• Time in Patent Office: Days
• US Class Current: 706/25
• 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

1-48. -48. (canceled)

49. In a networked computer system, a system for controlling information output based on user feedback comprising:

means for conveying information to a user in response to a user query, said information being displayed in a ranked list; and

means for receiving an indication of a selection of a portion of the information in the ranked list, wherein the act of selection comprises an epoch in which the selection is used to redetermine how at least some of said information is ranked in the list,

wherein, in response to a subsequent query, at least a portion of said information is displayed in a different position in the ranked list.

50. The system of claim 49, wherein the means for receiving an indication receives the indication from a pointing device of a computer.

51. The system of claim 50, wherein the pointing device comprises a computer mouse.

52. The system of claim 49, wherein the information comprises links to web sites.

53. The system of claim 49, wherein the information comprises chat participants.

54. The system of claim 49, wherein the information comprises email participants.

55. The system of claim 49, wherein attributes of a particular user are considered in redetermining how said information is ranked in the list.

56. A method of controlling information output based on user feedback comprising:

conveying a list of information to a user in response to a user query;

detecting an act of selecting an entry in the list of information, wherein the act of selecting comprises an epoch; and

causing an update to an order of the list of information at an end of the epoch such that in response to a subsequent query, the entry is placed in a different position or placed in none of the positions in the list of information that is conveyed to a subsequent user that made the subsequent query.

57. The method of claim 56, wherein the list of information comprises links to web sites.

58. The method of claim 56, wherein the list of information comprises chat participants.

59. The method of claim 56, wherein the list of information comprises email participants.

60. The method of claim 56, further comprising:

considering attributes of a particular user in determining the position of the entry in the list of information.

61. The method of claim 56, wherein the act of selecting an entry comprises a mouse click.

62. The method of claim 56, wherein the act of selecting an entry comprises visiting a web site.

63. A method for controlling information output based on user feedback comprising:

sending, from a server and over an electronic network, information to a user in response to a user query, the information being presented to the user in a series of slots;

detecting that the user has selected one of the slots, the act of selecting the one of the slots comprising feedback to the server; and

updating, based on the feedback, the order of how the information is to be presented to a subsequent user in response to a subsequent query.

64. The method of claim 63, wherein the information comprises links to web sites.

65. The method of claim 63, wherein the information comprises chat participants.

66. The method of claim 63, wherein the information comprises email participants.

67. The method of claim 63, further comprising:

considering attributes of a particular user in the step of updating.