Contextual based search suggestion

Abstract

Methods, systems and programming for providing query suggestions based on user's previous search query. In one example, an input including a prefix of a first query is received from a user in a user session. At least a second query that was previously received from the user in the user session is then obtained. A third query is obtained based on the second query and the prefix of the first query. One or more query suggestions are provided to the user as a response to the input. The one or more query suggestions include the third query.

We claim: 
     
         1 . A method, implemented on at least one machine each of which has at least one processor, storage, and a communication platform connected to a network for providing query suggestions, the method comprising:
 receiving a first query from a user device during a first session;   obtaining at least one contextual suggestion based on a query prefix of the first query and at least a second query that was received from the user device during the first session;   obtaining at least one regular query suggestion based on the first query; and   providing the at least one contextual suggestion and the at least one regular query suggestion to the user device as a response to the first query.   
     
     
         2 . The method of  claim 1 , wherein the at least one contextual suggestion comprises high co-occurrence query pairs mined from previous user sessions. 
     
     
         3 . The method of  claim 1 , further comprising:
 receiving the second query from the user device with the first query, wherein the user device is configured to log queries submitted by the user device during one or more sessions.   
     
     
         4 . The method of  claim 1 , further comprising:
 receiving an identifier associated with the user device with the first query; and   retrieving the second query from a user session database based on the identifier, the user session database storing previously submitted queries for various user identifiers.   
     
     
         5 . The method of  claim 1 , wherein a number of the at least one contextual suggestion and the at least one regular query suggestion is at least one of predetermined and dynamically adjustable based on a number of characters in the query prefix. 
     
     
         6 . The method of  claim 1 , further comprising:
 generating blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion, wherein the blended suggestions are provided to the user device as the response.   
     
     
         7 . The method of  claim 1 , further comprising:
 determining a relevance score associated with each of the at least one contextual suggestion and the at least one regular query suggestion;   generating blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion by ranking each of the at least one contextual suggestion and the at least one regular query suggestion by the relevance score associated therewith.   
     
     
         8 . A system for providing query suggestions, comprising:
 a search serving engine configured to receive a first query from a user device during a first session; and   a search suggestion engine configured to:
 obtain at least one contextual suggestion based on a query prefix of the first query and at least a second query that was received from the user device during the first session, and 
 obtaining at least one regular query suggestion based on the first query, wherein the search serving engine is further configured to:
 provide the at least one contextual suggestion and the at least one regular query suggestion to the user device as a response to the first query. 
 
   
     
     
         9 . The system of  claim 8 , wherein the at least one contextual suggestion comprises high co-occurrence query pairs mined from previous user sessions. 
     
     
         10 . The system of  claim 8 , wherein the search serving engine is configured to receive the second query from the user device with the first query, wherein the user device is configured to log queries submitted by the user device during one or more sessions. 
     
     
         11 . The system of  claim 8 , further comprising:
 a user session recording module configured to:
 receive an identifier associated with the user device with the first query; and 
 retrieve the second query from a user session database based on the identifier, the user session database storing previously submitted queries for various user identifiers. 
   
     
     
         12 . The system of  claim 8 , wherein a number of the at least one contextual suggestion and the at least one regular query suggestion is at least one of predetermined and dynamically adjustable based on a number of characters in the query prefix. 
     
     
         13 . The system of  claim 8 , wherein the search suggestion engine comprises:
 a query suggestion generation unit configured to generate blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion, wherein the blended suggestions returned to the search serving engine to be provided to the user device as the response.   
     
     
         14 . The system of  claim 8 , wherein the search suggestion engine is further configured to:
 determine a relevance score associated with each of the at least one contextual suggestion and the at least one regular query suggestion, and the search suggestion engine comprises:   a query suggestion generation unit configured to generate blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion by ranking each of the at least one contextual suggestion and the at least one regular query suggestion by the relevance score associated therewith.   
     
     
         15 . A non-transitory machine-readable medium having information recorded thereon for providing query suggestions, wherein the information, when read by at least one processor of a machine, causes the machine to:
 receive a first query from a user device during a first session;   obtain at least one contextual suggestion based on a query prefix of the first query and at least a second query that was received from the user device during the first session;   obtain at least one regular query suggestion based on the first query; and   provide the at least one contextual suggestion and the at least one regular query suggestion to the user device as a response to the first query.   
     
     
         16 . The non-transitory machine-readable medium of  claim 15 , wherein the information, when read by the at least one processor, further causes the machine to:
 receive the second query from the user device with the first query, wherein the user device is configured to log queries submitted by the user device during one or more sessions.   
     
     
         17 . The non-transitory machine-readable medium of  claim 15 , wherein the information, when read by the at least one processor, further causes the machine to:
 receive an identifier associated with the user device with the first query; and   retrieve the second query from a user session database based on the identifier, the user session database storing previously submitted queries for various user identifiers.   
     
     
         18 . The non-transitory machine-readable medium of  claim 15 , wherein a number of the at least one contextual suggestion and the at least one regular query suggestion is at least one of predetermined and dynamically adjustable based on a number of characters in the query prefix. 
     
     
         19 . The non-transitory machine-readable medium of  claim 15 , wherein the information, when read by the at least one processor, further causes the machine to:
 generate blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion, wherein the blended suggestions are provided to the user device as the response.   
     
     
         20 . The non-transitory machine-readable medium of  claim 15 , wherein the information, when read by the at least one processor, further causes the machine to:
 determine a relevance score associated with each of the at least one contextual suggestion and the at least one regular query suggestion;   generate blended suggestions comprising the at least one contextual suggestion and the at least one regular query suggestion by ranking each of the at least one contextual suggestion and the at least one regular query suggestion by the relevance score associated therewith.