Business Lines

Abstract

Some embodiments provide a method for evaluating a content segment for relevancy to several of categories. The method retrieves the content segment. For each of the several categories, the method determines the relevancy of the content segment to the category by using a scoring model for the category. The scoring model accounts for (i) the presence of key word sets in the content segment and (ii) the context of the key word sets in the content segment. For each of the several categories, the method tags the content segment when the content segment is determined as relevant to the category.

What is claimed is: 
     
         1 . A method for evaluating a content segment for relevancy to a plurality of categories, the method comprising:
 retrieving the content segment;   for each of a plurality of categories, determining the relevancy of the content segment to the category by using a scoring model for the category that accounts for (i) the presence of key word sets in the content segment and (ii) the context of the key word sets in the content segment.   for each of the plurality of categories, tagging the content segment when the content segment is determined as relevant to the category.   
     
     
         2 . The method of  claim 1 , wherein determining the relevancy of the content segment comprises calculating a score for the content segment using the scoring model. 
     
     
         3 . The method of  claim 2 , wherein the scoring model comprises (i) a set of pairs of word sets, (ii) scores for the pairs of word sets, each pair of word sets comprising a key word set and a second word set, and (iii) a definition of context that specifies when a second word set is in the context of a key word set. 
     
     
         4 . The method of  claim 3 , wherein calculating the score for a particular content segment comprises:
 identifying each key word set from the model that is in the content segment;   for each identified key word set, associating as a word set pair the key word set and each word set within the context of the key word set in the content segment; and   aggregating scores for each of the identified word set pairs to calculate the score for the content segment.   
     
     
         5 . The method of  claim 4 , wherein aggregating the scores comprises calculating an average of the word set pair scores. 
     
     
         6 . The method of  claim 4 , wherein when an associated word set pair is not in the model, the word set pair is assigned a default score. 
     
     
         7 . The method of  claim 4 , wherein when an associated word set pair is not in the model, the word set pair is not accounted for in the calculation of the content segment score. 
     
     
         8 . The method of  claim 1 , wherein tagging a content segment comprises modifying a database entry for the content segment. 
     
     
         9 . A system for evaluating a plurality of content segments for relevancy to a plurality of different categories, the system comprising:
 a crawler for searching a network for new content segments on a regular basis and downloading the new content segments;   a content segment evaluator for determining whether the new content segments are relevant to each of the plurality of different categories by using content relevance models for the categories, wherein at least one of the content relevance models for a particular category is a context-based model that accounts for the appearance of key word sets in the content segments and the context of the key word set appearances; and   a content segment tagger for tagging a particular content segment with a particular category and a relevancy score for the category when the content segment is relevant to the category.   
     
     
         10 . The system of  claim 9 , wherein the network searched by the crawler is the Internet. 
     
     
         11 . The system of  claim 10 , wherein the new content segments comprise text documents newly available on the Internet. 
     
     
         12 . The system of  claim 9  further comprising a database with an entry for each new content segment. 
     
     
         13 . The system of  claim 12 , wherein the content segment tagger is for modifying the database entry of a particular content segment when the content segment is relevant to a particular category. 
     
     
         14 . The system of  claim 13 , wherein modifying the database entry of the particular content segment comprises entering an identifier for the particular category and the relevancy score for the particular category into a field of the database entry. 
     
     
         15 . The system of  claim 9  further comprising a model development application for defining the content relevance models. 
     
     
         16 . The system of  claim 15 , wherein the model development application is further for modifying the content relevance models using the newly categorized content segments. 
     
     
         17 . A method for determining which of a plurality of content segments are relevant to a particular category, the method comprising:
 receiving a plurality of unclassified content segments;   evaluating each of the unclassified content segments using a first keyword-location based content relevance model to identify a set of content segments that are potentially relevant to the particular category; and   evaluating each of the potentially relevant content segments using a second context-based content relevance model to identify a set of content segments that are relevant to the particular category.   
     
     
         18 . The method of  claim 17 , wherein the particular category comprises one of a company, product, person, or industry. 
     
     
         19 . The method of  claim 17 , wherein the first keyword-location based content relevance model scores a content segment based on the presence of particular key word sets in the content segment and the location of the key word sets. 
     
     
         20 . The method of  claim 19 , wherein a key word set in a title of a content segment generates a higher score than a key word set in a body of the content segment. 
     
     
         21 . The method of  claim 17 , wherein the second context-based content relevance model scores a content segment based on the presence of various groups of word sets in the content segment.