Automated processing of appropriateness determination of content for search listings in wide area network searches

Abstract

A method and system for improving the efficiency of a database processing system for evaluating candidate data items representing search listings that are submitted for inclusion into a search engine database. Candidate search listings are automatically assessed for quality, style, and relevance to evaluate risk of unfavorable reception by a user and of potential exposure volume. Search listings which are higher-risk or higher-volume are routed through manual editorial review while lower-risk, lower-volume search listings are routed for immediate inclusion in the search database without manual editorial evaluation. Accordingly, human editorial efforts can be devoted to manual review of high-risk or high-volume search listings while efficiency is simultaneously improved in the processing system as a whole.

1 . A method for evaluating fitness of a data item for inclusion in a network-accessible database, the method comprising: 
 determining a likelihood that the data item comports with a content policy; and    determining whether human review of the data item is required before including the data item in the network-accessible database based on the likelihood that the data item comports with the content policy.    
     
     
         2 . The method of  claim 1 , further comprising: 
 determining that human review is not required before including the data item in the network-accessible database based on the likelihood that the data item comports with the content policy; and    including the data item in the network-accessible database.    
     
     
         3 . The method of  claim 1 , further comprising: 
 determining that human review is required before including the data item in the network-accessible database based on the likelihood that the data item comports with the content policy;    performing human review of the data item; and    including the data item in the network-accessible database;    
     
     
         4 . The method of  claim 1 , further comprising: 
 modifying the data item to comport with the content policy;    determining that the data item as modified is fit for inclusion in the network-accessible database; and    including the data item in the network-accessible database.    
     
     
         5 . The method of  claim 1 , further comprising: 
 predicting a frequency of access of the data item; and    determining whether human review of the data item is required before including the data item in the network-accessible database based on the predicted frequency of access of the data item.    
     
     
         6 . The method of  claim 5 , further comprising: 
 determining that human review is not required before including the data item in the network-accessible database based on the predicted frequency of access of the data item; and    including the data item in the network-accessible database.    
     
     
         7 . The method of  claim 5 , further comprising: 
 determining that human review is required before including that data item in the network-accessible database based on the predicted frequency of access of the data item;    performing human review of the data item; and    including the data item in the network-accessible database.    
     
     
         8 . The method of  claim 1 , wherein the network-accessible database is accessible through a hypertext transport protocol.  
     
     
         9 . The method of  claim 1 , wherein the network-accessible-database comprises a computerized network search engine and the data item is a search listing comprising a search term and a title.  
     
     
         10 . The method of  claim 9 , wherein the content policy specifies a requisite degree of relevance for the search listing.  
     
     
         11 . The method of  claim 1 , wherein the content policy prohibits at least one blocked term and human review of the data item is required at least when the data item comprises at least one blocked term.  
     
     
         12 . The method of  claim 1 , wherein the content policy comprises at least one suspect term and human review of the data item is required at least when the data item comprises at least one suspect term.  
     
     
         13 . The method of  claim 1 , wherein the content policy comprises at least one sexual term and human review of the data item is required at least when the data item comprises at least one suspect term.  
     
     
         14 . The method of  claim 1 , wherein the content policy comprises at least one gambling term and human review of the data item is required at least when the data item comprises at least one gambling term.  
     
     
         15 . A method for evaluating fitness of a search listing for inclusion in a search listing database, the method comprising: 
 determining whether a search listing comprises at least one violation of a content policy, the content policy comprising at least one condition under which the search listing is determined unfit for inclusion in the search listing database;    rejecting the search listing from inclusion in the search listing database in response to determining the search listing comprises at least one violation of the content policy; and    including the search listing in the search listing database in response to determining the search listing does not comprise at least one violation of the content policy.    
     
     
         16 . The method of  claim 15 , wherein the content policy blocks one or more blocked terms.  
     
     
         17 . The method of  claim 15 , wherein the content policy requires human review for one or more suspect terms.  
     
     
         18 . The method of  claim 15 , wherein the content policy requires human review for one or more sexual terms.  
     
     
         19 . The method of  claim 15 , wherein the content policy requires human review for one or more gambling terms.  
     
     
         20 . The method of  claim 19 , wherein the content policy requires human review for non-sensical content.  
     
     
         21 . The method of  claim 15 , wherein the content policy requires a degree of relevance for the search listing.  
     
     
         22 . The method of  claim 21 , wherein the search listing comprises a search term and a title, and the degree of relevance is based on the search term and the title.  
     
     
         23 . The method of  claim 21 , wherein the search listing comprises a search term and a description, and the degree of relevance is based on the search term and the description.  
     
     
         24 . The method of  claim 21 , wherein the search listing comprises a title and a description, and the degree of relevance is based on the title and the description.  
     
     
         25 . The method of  claim 21 , wherein the search listing comprises a search term and refers to a document, and the degree of relevance is based on the search term and the document.  
     
     
         26 . The method of  claim 21 , wherein the search listing comprises a description and refers to a document, and the degree of relevant is based on the description and the document.  
     
     
         27 . The method of  claim 21 , wherein the step of determining whether a search listing comprises at least one violation of a content policy comprises: 
 determining the degree of relevance of the search listing; and    adjusting the degree of relevance of the search listing using a semantic alternative of the search term.    
     
     
         28 . The method of  claim 27 , wherein the semantic alternative is a synonym of the search term.  
     
     
         29 . The method of  claim 27 , wherein the semantic alternative is a hyponym of the search term.  
     
     
         30 . The method of  claim 27 , wherein the semantic alternative is a meronym of the search term.  
     
     
         31 . The method of  claim 27 , further comprising: 
 preprocessing the search listing prior to determining a degree of relevance of the search listing.    
     
     
         32 . The method of  claim 31 , wherein preprocessing comprises tokenization of the search listing.  
     
     
         33 . The method of  claim 31 , wherein preprocessing comprises rendering the search listing case-insensitive.  
     
     
         34 . The method of  claim 31 , wherein preprocessing comprises rendering the search listing verb-tense-insensitive.  
     
     
         35 . The method of  claim 31 , wherein preprocessing comprises correcting spelling of content of the search listing.  
     
     
         36 . The method of  claim 31 , wherein preprocessing comprises removal of stop words from the search listing.