Intelligent query system and method using phrase-code frequency-inverse phrase-code document frequency module

• US 7,698,333 B2
• Filed: 04/22/2005
• Issued: 04/13/2010
• Est. Priority Date: 07/22/2004
• Status: Active Grant

• Current Assignee: Factiva Incorporated
• Original Assignee: Factiva Incorporated
• Inventors: Cipollone, Peter M.
• Primary Examiner(s): Rones; Charles
• Assistant Examiner(s): KUDDUS, DANIEL A
• Application Number:
  US11/112,439
• Publication Number:
  US 20060031218A1
• Time in Patent Office: 1,817 Days
• Field of Search: None
• US Class Current: 707/731
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/367 Ontology

Abstract

An intelligent query system and method used in a search and retrieval system provides an end-user the most relevant, meaningful, up-to-date, and precise search results. The system and method allows an end-user to benefit from an experienced recommendation that is tailored to a specific industry. The system and method recognizes that the phrases “strike outs” and “home run” are much more strongly correlated with “BASE” as opposed to “EQUITIES.” When a search is conducted or a lookup is done in a map, the system and method recommends the strongest correlation as “BASE.”

Claims

1. An intelligent query method, comprising the steps of:

providing a plurality of multimedia documents each containing a plurality of content items using an electronic document feed;

categorizing each of the documents into at least one of a plurality of pre-defined content based taxonomies, each taxonomy having an associated substantive content and corresponding taxonomy elements; and

using a computer-implemented categorization engine;

filtering the plurality of content items in each document into at least two groups;

discarding at least one of the groups of content items for each document;

for each document, correlating each of the non-discarded content items in the document with the taxonomy elements corresponding to the at least one taxonomy in which the document is categorized;

storing the correlated taxonomy elements and non-discarded content items for each document in an electronic database; and

calculating a correlation value between the non-discarded content items for each document and the correlated taxonomy elements;

wherein calculating the correlation value comprises applying a phrase code frequency inverse phrase code document frequency (PCF-IPCDF) scoring model to the correlated taxonomy elements; and

wherein the PCF-IPCDF scoring model comprises a phrase-code frequency (PCF), the PCF being the number of times a phrase p appears in multimedia documents containing a code c, multiplied by an inverse phrase code document frequency (IPCDF), the IPCDF being a logarithm of;

the number of documents coded with c divided by the number of documents for which the phrase p and code c appear together.

2. The method of claim 1 further comprising loading the non-discarded content items for each document and the correlated taxonomy elements with the highest correlation values into a map structure for facilitating deduction of a taxonomy element based on its associated substantive content.