Negative associations for generation of refinement options

Abstract

A computer-implemented method is provided, including receiving a search query from a user during a search session, and presenting information to the user responsively to the search query. After an indication that the user takes an action related to the search session is received, a portion of the presented information is identified that the user did not select prior to taking the action, and respective scores are assigned to search results generated responsively to the search query, including lowering one or more of the scores of the respective search results that are characterized by the non-selected portion of the presented information. The search results are ranked according to the scores, and presented to the user. Other embodiments are also described.

1 - 12 . (canceled) 
     
     
         13 . A computer-implemented method comprising:
 receiving, by a search system, a search query from a user during a search session;   presenting information to the user responsively to the search query; and   identifying, by the search system, a portion of the presented information that the user did not select;   generating, by the search system, a set of refinement options for optional addition to the search query, by assigning respective candidate scores to candidate terms that are candidates for inclusion in the set of refinement options, lowering one or more of the candidate scores of the respective candidate terms that are characterized by the non-selected portion of the presented information, and selecting a portion of the candidate terms for inclusion in the set based on the respective candidate scores; and   presenting the set of refinement options to the user.   
     
     
         14 . The method according to  claim 27 , wherein the action is selected from the group consisting of: selecting a portion of the information, submitting the search query, modifying the search query, and requesting additional search results for the search query. 
     
     
         15 - 19 . (canceled) 
     
     
         20 . Apparatus comprising:
 an interface; and   a processor, which is configured to receive, via the interface, a search query from a user during a search session; presenting information to the user, via the interface, responsively to the search query; identify a portion of the presented information that the user did not select; generate a set of refinement options for optional addition to the search query, by assigning respective candidate scores to candidate terms that are candidates for inclusion in the set of refinement options, lowering one or more of the candidate scores of the respective candidate terms that are characterized by the non-selected portion of the presented information, and selecting a portion of the candidate terms for inclusion in the set based on the respective candidate scores; and present the set of refinement options to the user, via the interface.   
     
     
         21 - 25 . (canceled) 
     
     
         26 . A computer software product, comprising a non-transitory tangible computer-readable medium in which program instructions are stored, which instructions, when read by a computer, cause the computer to receive a search query from a user during a search session; presenting information to the user responsively to the search query; identify a portion of the presented information that the user did not select; generate a set of refinement options for optional addition to the search query, by assigning respective candidate scores to candidate terms that are candidates for inclusion in the set of refinement options, lowering one or more of the candidate scores of the respective candidate terms that are characterized by the non-selected portion of the presented information, and selecting a portion of the candidate terms for inclusion in the set based on the respective candidate scores; and present the set of refinement options to the user, via the interface. 
     
     
         27 . The method according to  claim 13 , wherein identifying the portion comprises after receiving an indication that the user takes an action related to the search session, identifying the portion of the refinement options that the user did not select prior to taking the action. 
     
     
         28 . The method according to  claim 13 , wherein presenting the information comprises presenting search results to the user responsively to the search query, and wherein identifying the portion of the presented information that the user did not select comprises identifying one or more of the presented search results that the user did not select. 
     
     
         29 . The method according to  claim 28 , wherein presenting the search results comprises displaying the search results in real time as the search query is entered by the user. 
     
     
         30 . The method according to  claim 13 , further comprising constructing an association graph that includes one or more graph terms as vertices linked by edges, which edges have respective edge scores that represent respective strengths of association of the respective vertices linked thereby, wherein receiving the search query comprises receiving the search query that comprises one or more of the graph terms of the association graph, and wherein assigning the respective candidate scores comprises assigning the respective candidate scores using the association graph. 
     
     
         31 . The method according to  claim 30 , wherein identifying the portion of the presented information comprises identifying non-selected graph terms that appear in the non-selected portion, and wherein lowering the one or more of the candidate scores comprises damping the edge score of an edge of the association graph between two of the vertices respectively representing two of the non-selected graph terms. 
     
     
         32 . The method according to  claim 30 , wherein the association graph comprises a personal association graph of the user, which represents interactions of a plurality of documents with the user during one or more searches conducted during one or more search sessions. 
     
     
         33 . The method according to  claim 30 , wherein the association graph comprises a session association graph, which represents interactions of one or more documents with the user during one or more searches conducted by the user during a single search session. 
     
     
         34 . The method according to  claim 30 , wherein generating the set of refinement options comprises selecting as the refinement options a portion of respective graph terms of the association graph directly linked to the graph terms of the search query by respective edges of the association graph. 
     
     
         35 . The apparatus according to  claim 20 , wherein the processor is configured to identify the portion after receiving an indication, via the interface, that the user takes an action related to the search session, identifying the portion of the refinement options that the user did not select prior to taking the action. 
     
     
         36 . The apparatus according to  claim 35 , wherein the action is selected from the group consisting of: selecting a portion of the information, submitting the search query, modifying the search query, and requesting additional search results for the search query. 
     
     
         37 . The apparatus according to  claim 20 , wherein the information includes search results, and wherein the processor is configured to present, via the interface, the search results to the user responsively to the search query, and to identify one or more of the presented search results that the user did not select as the portion of the presented information that the user did not select. 
     
     
         38 . The apparatus according to  claim 37 , wherein the processor is configured to display the search results in real time as the search query is entered by the user. 
     
     
         39 . The apparatus according to  claim 20 , wherein the processor is configured to construct an association graph that includes one or more graph terms as vertices linked by edges, which edges have respective edge scores that represent respective strengths of association of the respective vertices linked thereby, receive the search query that comprises one or more of the graph terms of the association graph, and assign the respective candidate scores using the association graph. 
     
     
         40 . The apparatus according to  claim 39 , wherein the processor is configured to identify non-selected graph terms that appear in the non-selected portion, and to lower the one or more of the candidate scores by damping the edge score of an edge of the association graph between two of the vertices respectively representing two of the non-selected graph terms. 
     
     
         41 . The apparatus according to  claim 39 , wherein the association graph comprises a personal association graph of the user, which represents interactions of a plurality of documents with the user during one or more searches conducted during one or more search sessions. 
     
     
         42 . The apparatus according to  claim 39 , wherein the association graph comprises a session association graph, which represents interactions of one or more documents with the user during one or more searches conducted by the user during a single search session. 
     
     
         43 . The apparatus according to  claim 39 , wherein the processor is configured to generate the set of refinement options by selecting as the refinement options a portion of respective graph terms of the association graph directly linked to the graph terms of the search query by respective edges of the association graph.