Semantic geotokens

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing geographically relevant search results. In one aspect, a method includes receiving a geotoken for a resource. The geotoken can be a resource token that references a geographic location. A semantic geotoken can be selected using the received geotoken. The semantic geotoken is a standardized representation of the geographic location that includes one or more location-specific terms. The semantic geotoken is stored with a reference to the resource. Neighboring locations for the geographic location are determined. The neighboring locations are within a predetermined distance of the geographic location. Semantic geotokens for the neighboring locations are selected and stored with the reference to the resource. Data specifying the semantic geotokens and the reference to the resource are provided.

1 . A method of geocoding resources based on contained text, the method comprising:
 obtaining bodies of text included in resources;   identifying tokens in the bodies of text based on those tokens referring to geographic locations;   identifying canonical identifiers of the geographic locations based on the tokens; and   for a given resource referencing a given geographic location:
 identifying a related resource that belongs to a same website or a domain as the given resource; 
 and 
 designating the given resource and the related resource as relevant to the given geographic location in memory. 
   
     
     
         2 . The method of  claim 1 , comprising:
 for the given geographic location, selecting a canonical identifier of a neighboring geographic location based on proximity to the given geographic location; and   designating the given resource as relevant to the neighboring geographic location by associating the given resource in memory with the selected canonical identifier.   
     
     
         3 . The method of  claim 2 , comprising:
 receiving a search query associated with a reference to the neighboring geographic location;   mapping the reference to the neighboring geographic location to the canonical identifier of the neighboring geographic location;   obtaining search results responsive to the search query, at least one obtained search result referencing the given resource;   adjusting a result score for the given resource based on the given resource being associated with the canonical identifier of the neighboring geographic location; and   responsive to the result score, sending the given resource as a search result.   
     
     
         4 . The method of  claim 2 , wherein designating the given resource as relevant to the neighboring geographic location comprises:
 calculating a distance between the given geographic location and the neighboring geographic location; and   scoring relevance of the given resource to the neighboring geographic location based on the distance and a scored relevance of the given resource to the given geographic location.   
     
     
         5 . The method of  claim 1 , further comprising scoring relevance of the given resource to the given geographic location including:
 calculating a likelihood that the given resource is relevant to the given geographic location based on quantity, placement, or specificity of tokens in the given resource that refer to the given geographic location.   
     
     
         6 - 7 . (canceled) 
     
     
         8 . The method of  claim 1 , further comprising scoring relevance of the given resource to the given geographic location including:
 calculating likelihoods that the given resource is relevant to the given geographic location based on different references in the given resource to the given geographic location, the different references having different text, wherein a respective likelihood is calculated for each of the different references; and   selecting a highest calculated likelihood to score relevance.   
     
     
         9 . The method of  claim 1 , comprising:
 for the given geographic location, selecting a canonical identifier of an overlapping geographic location that overlaps the given geographic location; and   designating the given resource as relevant to the overlapping geographic location by associating the given resource in memory with the selected canonical identifier.   
     
     
         10 . (canceled) 
     
     
         11 . A system, comprising:
 one or more processors; and   memory storing instructions that when executed by at least some of the one or more processors effectuate operations comprising:
 obtaining bodies of text included in resources; 
 identifying tokens in the bodies of text based on those tokens referring to geographic locations; 
 identifying canonical identifiers of the geographic locations based on the tokens; and 
 for a given resource referencing a given geographic location:
 identifying a related resource that belongs to a same website or a domain as the given resource; 
 designating the given resource and the related resource as relevant to the given geographic location in memory. 
 
   
     
     
         12 . The system of  claim 11 , wherein the operations comprise:
 for the given geographic location, selecting a canonical identifier of a neighboring geographic location based on proximity to the given geographic location; and   designating the given resource as relevant to the neighboring geographic location by associating the given resource in memory with the selected canonical identifier.   
     
     
         13 . The system of  claim 12 , wherein the operations comprise:
 receiving a search query associated with a reference to the neighboring geographic location;   mapping the reference to the neighboring geographic location to the canonical identifier of the neighboring geographic location;   obtaining search results responsive to the search query, at least one obtained search result referencing the given resource;   adjusting a result score for the given resource based on the given resource being associated with the canonical identifier of the neighboring geographic location; and   responsive to the result score, sending the given resource as a search result.   
     
     
         14 . The system of  claim 12 , wherein designating the given resource as relevant to the neighboring geographic location comprises:
 calculating a distance between the given geographic location and the neighboring geographic location; and   scoring relevance of the given resource to the neighboring geographic location based on the distance and a scored relevance of the given resource to the given geographic location.   
     
     
         15 . The system of  claim 11 , wherein the operations further comprise scoring relevance of the given resource to the given geographic location including:
 calculating a likelihood that the given resource is relevant to the given geographic location based on quantity, placement, or specificity of tokens in the given resource that refer to the given geographic location.   
     
     
         16 - 17 . (canceled) 
     
     
         18 . The system of  claim 11 , wherein the operations further comprise scoring relevance of the given resource to the given geographic location including:
 calculating likelihoods that the given resource is relevant to the given geographic location based on different references in the given resource to the given geographic location, the different references having different text, wherein a respective likelihood is calculated for each of the different references; and   selecting a highest calculated likelihood to score relevance.   
     
     
         19 . The system of  claim 11 , wherein the operations comprise:
 for the given geographic location, selecting a canonical identifier of an overlapping geographic location that overlaps the given geographic location; and   designating the given resource as relevant to the overlapping geographic location by associating the given resource in memory with the selected canonical identifier.   
     
     
         20 . (canceled) 
     
     
         21 . The method of  claim 1 , further comprising identifying off-page resources that refer to the given resource. 
     
     
         22 . The method of  claim 1 , further comprising scoring relevance of the given resource to the given geographic location based on both tokens in the given resource and tokens in the off-page resources that share the canonical identifier of the given geographic location. 
     
     
         23 . The method of  claim 1 , further comprising scoring relevance of the related resource to the given geographic location based on tokens in the given resource. 
     
     
         24 . The system of  claim 11 , wherein the operations comprise:
 identifying off-page resources that refer to the given resource.   
     
     
         25 . The system of  claim 11 , wherein the operations comprise:
 scoring relevance of the given resource to the given geographic location based on both tokens in the given resource and tokens in the off-page resources that share the canonical identifier of the given geographic location.   
     
     
         26 . The system of  claim 11 , wherein the operations comprise:
 scoring relevance of the related resource to the given geographic location based on tokens in the given resource.