Inferring search category synonyms

Abstract

Systems and methods for inferring category synonyms from prior result data may include identifying prior query data including query information and category information relating to the prior result data; determining whether the query information is a synonym for the category information; and using the query information and the category information in subsequent search requests if it is determined that the query information is a synonym for the category information.

1 .- 25 . (canceled) 
     
     
         26 . A method, comprising:
 identifying, using one or more computers, a first query and a first result category related to a first search result responsive to the first query, where the first result category includes one or more terms;   classifying, using one or more computers, the first query as a categorical query;   determining, using one or more computers, that the first query and the first result category should be treated as synonyms based on classifying the first query as a categorical query; and   assigning, using one or more computers, the first result category as a category synonym for the first query based on the determination that the first query and the first result category should be treated as synonyms.   
     
     
         27 . The method of  claim 26 , further comprising:
 receiving a second query related to the first query; and   modifying the second query to include the one or more terms of the first result category.   
     
     
         28 . The method of  claim 26 , where the categorical query comprises query terms that relate to a business category. 
     
     
         29 . The method of  claim 26 , further comprising determining that the first query and the first result category should be treated as synonyms based on the first query having a high name perplexity. 
     
     
         30 . The method of  claim 29 , further comprising determining that the first query has a high name perplexity, where determining includes:
 determining a number of business names associated with the first query; and   identifying that the first query has a high name perplexity in response to determining that the number of business names associated with the first query is above a threshold.   
     
     
         31 . The method of  claim 26 , further comprising:
 identifying a second query and a second result category related to a second search result responsive to the second query, where the second result category includes one or more terms;   determining that the second query and the second result category should not be treated as synonyms based on the second query having a low name perplexity; and   foregoing assigning the second result category as a category synonym for the second query based on the determination that the second query and the second result category should not be treated as synonyms.   
     
     
         32 . The method of  claim 31 , further comprising determining that the second query has a low name perplexity, where determining includes:
 determining a number of business names associated with the second query; and   identifying that the second query has a low name perplexity in response to determining that the number of business names associated with the second query is not above a threshold.   
     
     
         33 . A system, comprising:
 one or more computers configured to perform operations comprising:
 identifying a first query and a first result category related to a first search result responsive to the first query, where the first result category includes one or more terms; 
 classifying the first query as a categorical query; 
 determining that the first query and the first result category should be treated as synonyms based on classifying the first query as a categorical query; and 
 assigning the first result category as a category synonym for the first query based on the determination that the first query and the first result category should be treated as synonyms. 
   
     
     
         34 . The system of  claim 33 , where the one or more computers are further configured to perform operations comprising:
 receiving a second query related to the first query; and   modifying the second query to include the one or more terms of the first result category.   
     
     
         35 . The system of  claim 33 , where the categorical query comprises query terms that relate to a business category. 
     
     
         36 . The system of  claim 33 , where the one or more computers are further configured to perform operations comprising determining that the first query and the first result category should be treated as synonyms based on the first query having a high name perplexity. 
     
     
         37 . The system of  claim 36 , where the one or more computers are further configured to perform operations comprising determining that the first query has a high name perplexity, where determining includes:
 determining a number of business names associated with the first query; and   identifying that the first query has a high name perplexity in response to determining that the number of business names associated with the first query is above a threshold.   
     
     
         38 . The system of  claim 33 , where the one or more computers are further configured to perform operations comprising:
 identifying a second query and a second result category related to a second search result responsive to the second query, where the second result category includes one or more terms;   determining that the second query and the second result category should not be treated as synonyms based on the second query having a low name perplexity; and   foregoing assigning the second result category as a category synonym for the second query based on the determination that the second query and the second result category should not be treated as synonyms   
     
     
         39 . The system of  claim 38 , where the one or more computers are further configured to perform operations comprising determining that the second query has a low name perplexity, where determining that the second query has a low name perplexity includes:
 determining a number of business names associated with the second query; and   identifying that the second query has a low name perplexity in response to determining that the number of business names associated with the second query is not above a threshold.   
     
     
         40 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
 identifying a first query and a first result category related to a first search result responsive to the first query, where the first result category includes one or more terms;   classifying the first query as a categorical query;   determining that the first query and the first result category should be treated as synonyms based on classifying the first query as a categorical query; and   assigning the first result category as a category synonym for the first query based on the determination that the first query and the first result category should be treated as synonyms.   
     
     
         41 . The computer-readable medium of  claim 40 , where the instructions further cause the one or more computers to perform operations comprising:
 receiving a second query related to the first query; and   modifying the second query to include the one or more terms of the first result category.   
     
     
         42 . The computer-readable medium of  claim 40 , where the categorical query comprises query terms that relate to a business category. 
     
     
         43 . The computer-readable medium of  claim 40 , where the instructions further cause the one or more computers to perform operations comprising determining that the first query and the first result category should be treated as synonyms based on the first query having a high name perplexity. 
     
     
         44 . The computer-readable medium of  claim 43 , where the instructions further cause the one or more computers to perform operations comprising determining that the first query has a high name perplexity, where determining includes:
 determining a number of business names associated with the first query; and   identifying that the first query has a high name perplexity in response to determining that the number of business names associated with the first query is above a threshold.   
     
     
         45 . The computer-readable medium of  claim 40 , where the instructions further cause the one or more computers to perform operations comprising:
 identifying a second query and a second result category related to a second search result responsive to the second query, where the second result category includes one or more terms;   determining that the second query and the second result category should not be treated as synonyms based on the second query having a low name perplexity; and   foregoing assigning the second result category as a category synonym for the second query based on the determination that the second query and the second result category should not be treated as synonyms