System and method for bayesian matching of web search results

Abstract

Provided are a system and method for matching search results from multiple websites. In one example, the method includes calculating a probability that a search result of a first website corresponds to a same item as a search result of a second website based on Bayes theorem, in response to the calculated probability being greater than a predetermined threshold, determining that the search result of the first website and the search result of the second website are a match, and displaying an aggregated list of search results combined from the first website and the second website based on the watched search results. By auto-matching search results using Bayes theorem, a true match can be determined that is more accurate in comparison to a manual matching operation performed by a human.

What is claimed is: 
     
         1 . An apparatus comprising:
 a memory configured to store search results from a plurality of websites including a first website and a second website; and   a processor configured to determine a probability that a search result of the first website corresponds to a same item as a search result of the second website based on a comparison between a value of content within the search result of the first website and a corresponding value of content within the search result of the second website, and, in response to the probability being greater than a threshold, removing, via the processor, the search result of the second website to generate modified search results.   
     
     
         2 . The apparatus of  claim 1 , wherein the processor is further configured to add content from the search result of the second website to the search result of the first website to generate a unified search result for the first and second websites, and display the unified search result. 
     
     
         3 . The apparatus of  claim 1 , wherein the processor is configured to input the values of the search result of the first website and the corresponding values of the search result of the second website into a predefined theorem to generate the probability. 
     
     
         4 . The apparatus of  claim 1 , wherein the processor is configured to determine the probability that search results of the first and second websites correspond to the same item based on a comparison between respective name values within content of the search results of the first and second website. 
     
     
         5 . The apparatus of  claim 1 , wherein the processor is configured to determine the probability that search results of the first and second websites correspond to the same item based on a comparison between respective address values within content of the search results of the first and second website. 
     
     
         6 . The apparatus of  claim 1 , wherein the processor is configured to determine the probability that search results of the first and second websites correspond to the same item based on a comparison between respective rating values within content of the search results of the first and second website. 
     
     
         7 . The apparatus of  claim 1 , wherein the processor is configured to determine the probability that search results of the first and second websites correspond to the same item based on a comparison between respective amenities values within content of the search results of the first and second website. 
     
     
         8 . The apparatus of  claim 1 , wherein the processor is configured to determine the probability that search results of the first and second websites correspond to the same item based on a comparison between a plurality of attributes within the search result of the first website and a corresponding plurality of attributes within the search result and second website. 
     
     
         9 . A method comprising:
 receiving, via a processor, search results from a plurality of websites including a first website and a second website;   determining, via the processor, a probability that a search result of the first website corresponds to a same item as a search result of the second website based on a comparison between a value of content within the search result of the first website and a corresponding value of content within the search result of the second website; and   in response to the probability being greater than a threshold, removing, via the processor, the search result of the second website to generate modified search results.   
     
     
         10 . The method of  claim 9 , further comprising adding content from the search result of the second website to the search result of the first website to generate a unified search result for the first and second websites, and displaying the unified search result. 
     
     
         11 . The method of  claim 9 , wherein the determining comprises inputting the values of the search result of the first website and the corresponding values of the search result of the second website into a predefined theorem to generate the probability. 
     
     
         12 . The method of  claim 9 , wherein the determining comprises inputting the values of the search result of the first website and the corresponding values of the search result of the second website into a predefined theorem to generate the probability. 
     
     
         13 . The method of  claim 9 , wherein the determining comprises determining the probability that search results of the first and second websites correspond to the same item based on a comparison between respective address values within content of the search results of the first and second website. 
     
     
         14 . The method of  claim 9 , wherein the determining comprises determining the probability that search results of the first and second websites correspond to the same item based on a comparison between respective rating values within content of the search results of the first and second website. 
     
     
         15 . The method of  claim 9 , wherein the determining comprises determining the probability that search results of the first and second websites correspond to the same item based on a comparison between respective amenities values within content of the search results of the first and second website. 
     
     
         16 . The method of  claim 9 , wherein the determining comprises determining the probability that search results of the first and second websites correspond to the same item based on a comparison between a plurality of attributes within the search result of the first website and a corresponding plurality of attributes within the search result and second website. 
     
     
         17 . A non-transitory computer readable medium storing instructions that when executed cause a computer to perform a method comprising:
 receiving, via a processor, search results from a plurality of websites including first website and a second website;   determining, via the processor, a probability that a search result of the first website corresponds to a same item as a search result of the second website based on a comparison between a value of content within the search result of the first website and a corresponding value of content within the search result of the second website; and   in response to the probability being greater than a threshold, removing, via the processor, the search result of the second website gar generate modified search results.   
     
     
         18 . The non-transitory computer readable medium of  claim 17 , wherein the method further comprises adding content from the search result of the second website to the search result of the first website generate a unified search result for the first and second websites, and displaying the unified search result. 
     
     
         19 . The non-transitory computer readable medium of  claim 17 , wherein the determining comprises inputting the values of the search result of the first website and the corresponding values of the search result of the second website into a predefined theorem to generate the probability. 
     
     
         20 . The non-transitory computer readable medium of  claim 17 , wherein the determining comprises determining the probability that search results of the first and second websites correspond to the same item based on a comparison between a plurality of attributes within the search result of the first website and a corresponding plurality of attributes within the search result and second website.