SYSTEM AND METHOD FOR MULTI-RESOLUTION INFORMATION FILTERING

• US 20110090540A1
• Filed: 04/08/2010
• Published: 04/21/2011
• Est. Priority Date: 08/13/2009
• Status: Active Grant

• Current Assignee: Telcordia Technologies Incorporated (Telefonaktiebolaget LM Ericsson)
• Original Assignee: Telcordia Technologies Incorporated (Telefonaktiebolaget LM Ericsson)
• Inventors: Panagos, Euthimios, Loeb, Shoshana K.
• Granted Patent: US 8,462,392 B2
• Time in Patent Office: Days
• US Class Current: 358/403
• CPC Class Codes: C12Q 1/6827 for detection of mutation or polymorphism
• CPC Class Codes: C12Q 1/6837 using probe arrays or probe chips C12Q1/6874 takes precedence
• CPC Class Codes: C12Q 2565/518 characterised by the immobilisation of the nucleic acid sample or target
• CPC Class Codes: Y02A 50/30 Against vector-borne diseases, e.g. mosquito-borne, fly-borne, tick-borne or waterborne diseases whose impact is exacerbated by climate change

Abstract

A method for ranking a plurality of documents relevant to a user profile comprises determining a high resolution representation for the user profile, computing a high resolution representation for each document, calculating a rank for each document based on the high resolution representation of the document and the high resolution representation of the user profile, recalculating the rank for each document based on a lower resolution representation of the document and/or a lower resolution representation of the user profile when the rank of each document is not satisfactory, and outputting a number of the plurality of documents sorted by the rank of each document, when the rank is satisfactory. The high resolution representation can be a discrete wavelet transform. The lower resolution representation can be recalculated by averaging the values of the discrete wavelet transform. Outputting the number of documents can comprise displaying the documents on a device.

Claims

1. A method for ranking a plurality of documents relevant to a user profile, comprising steps of:

determining a high resolution representation for the user profile;

computing a high resolution representation for each document of the plurality of documents;

calculating a rank for each document based on the high resolution representation of the document and the high resolution representation of the user profile;

recalculating the rank for each document based on a lower resolution representation of the document and/or a lower resolution representation of the user profile when the rank of each document is not satisfactory; and

outputting a number of the plurality of documents sorted by the rank of each document, when the rank is satisfactory.

2. The method according to claim 1, wherein the documents are obtained in response to a query.

3. The method according to claim 1, wherein the high resolution representation for each document and for the user profile is a discrete wavelet transform.

4. The method according to claim 3, wherein the lower resolution representation for each document is recalculated by averaging the values of the discrete wavelet transform for each document.

5. The method according to claim 1, wherein outputting the number of documents comprises displaying the documents on a device and the number of documents is based on size of the device displaying the documents.

6. A computer readable storage medium storing a program of instructions executable by a machine to perform a method for ranking a plurality of documents relevant to a user profile, comprising:

determining a high resolution representation for the user profile;

computing a high resolution representation for each document of the plurality of documents;

calculating a rank for each document based on the high resolution representation of the document and the high resolution representation of the user profile;

recalculating the rank for each document based on a lower resolution representation of the document and/or a lower resolution representation of the user profile when the rank of each document is not satisfactory; and

outputting a number of the plurality of documents sorted by the rank of each document, when the rank is satisfactory.

7. The program according to claim 6, wherein the documents are obtained in response to a query.

8. The computer readable medium according to claim 6, wherein the high resolution representation for each document and for the user profile is a discrete wavelet transform.

9. The computer readable medium according to claim 8, wherein the lower resolution representation for each document is recalculated by averaging the values of the discrete wavelet transform for each document.

10. The computer readable medium according to claim 6, wherein outputting the number of documents comprises displaying the documents on a device and the number of documents is based on size of the device displaying the documents.

11. A system for ranking a plurality of documents relevant to a user profile, comprising:

a processor;

a multiresolution ranking module operable to determine a high resolution representation for the user profile, compute a high resolution representation for each document of the plurality of documents, calculate a rank for each document based on the high resolution representation of the document and the high resolution representation of the user profile, and, when the rank of each document is not satisfactory, recalculate the rank for each document based on a lower resolution representation of the document and/or a lower resolution representation of the user profile; and

an output device operable to output a number of the plurality of documents sorted by the rank of each document, when the rank is satisfactory.

12. The system according to claim 11, wherein the documents are obtained in response to a query.

13. The system according to claim 11, wherein the high resolution representation for each document and for the user profile is a discrete wavelet transform.

14. The system according to claim 13, wherein the lower resolution representation for each document is recalculated by averaging the values of the discrete wavelet transform for each document.

15. The system according to claim 11, wherein the output device displays the documents and the number of documents is based on size of the output device.