Navigating a Taxonomy Using Search Queries

Abstract

Disclosed are various embodiments for navigating a taxonomy using search queries. A search query is parsed in order to identify one or more item categories. A confidence score for each item categories is generated. When the confidence score meets a threshold, a pool of items associated with a respective category is selected. When the confidence score fails to meets the threshold, the pool of items is selected from the collection of items.

Therefore, the following is claimed: 
     
         1 . A system, comprising:
 at least one computing device; and   at least one application executable in the at least one computing device, wherein when executed, the at least one application causes the at least one computing device to at least:
 receive a search query from a client device; 
 identify a category based at least in part on at least one term of the search query; 
 generate a confidence score associated with the category based at least in part on a frequency that at least a portion of the search query occurs within a description of the category; 
 select a pool of items from a first collection of items included within the category when the confidence score meets a threshold, the first collection of items being a subset of a second collection of items associated with a plurality of categories; 
 generate a user interface including at least a portion of the pool of items that have been selected; and 
 transmit data encoding the user interface to the client device. 
   
     
     
         2 . The system of  claim 1 , wherein, when executed, the at least one application further causes the at least one computing device to at least identify at least one refinement based at least in part on the at least one term of the search query. 
     
     
         3 . The system of  claim 2 , wherein the at least one refinement is identified based at least in part on a comparison of a list of predefined refinements associated with the category and the at least one term of the search query. 
     
     
         4 . The system of  claim 2 , wherein, when executed, the at least one application further causes the at least one computing device to at least translate the at least one refinement into an item attribute. 
     
     
         5 . The system of  claim 4 , wherein the user interface further comprises a respective link to a detailed network page for individual items from the pool of items that are selected, the detailed network page having the item attribute preselected for the individual items. 
     
     
         6 . The system of  claim 2 , wherein the pool of items are selected further based at least in part on the at least one refinement. 
     
     
         7 . The system of  claim 1 , where, when executed, the at least one application further causes the at least one computing device to at least:
 receive another search query from the client device;   generate another confidence score associated with at least one category of the plurality of categories, the at least one category being identified based at least in part on at least a portion of the other search query;   determine that the other confidence score fails to meet the threshold; and   generate another user interface including another pool of items selected from the second collection of items in response to the other confidence score failing to meet the threshold, the other user interface further comprising a disambiguation tool allowing for selection of a particular category of the plurality of categories.   
     
     
         8 . A method, comprising:
 parsing, via at least one computing device, a search query into a plurality of keywords, the search query being received from a client device;   identifying, via the at least one computing device, a category associated with a plurality of items based at least in part on at least one of the plurality of keywords matching a category term of the category;   determining, via the at least one computing device, a frequency that at least a portion of the search query occurs within a description of the category;   generating, via the at least one computing device, a confidence score associated with the category, the confidence score being based at least in part on the frequency that the at least a portion of the search query occurs within the description of the category;   selecting, via the at least one computing device, at least one item from a collection of items included within the category in response to the confidence score meeting or exceeding a threshold, the collection of items being a subset of a plurality of items associated with a plurality of categories;   generating, via the at least one computing device, a user interface including the at least one item that has been selected; and   transmitting, via the at least one computing device, data encoding the user interface to the client device.   
     
     
         9 . The method of  claim 8 , further comprising identifying, via the at least one computing device, a refinement based at least in part on a particular keyword of the plurality of keywords. 
     
     
         10 . The method of  claim 9 , further comprising identifying, via the at least one computing device, at least one synonym associated with the particular keyword, wherein the refinement is based at least in part on the at least one synonym. 
     
     
         11 . The method of  claim 8 , further comprising:
 retrieving, via the at least one computing device, a list of refinements associated with the category; and   comparing, via the at least one computing device, individual refinements of the list of refinements with individual keywords of the search query to determine a quality of match between the list of refinements and the search query, wherein the confidence score is further based at least in part on the quality of match.   
     
     
         12 . The method of  claim 8 , wherein the user interface includes a disambiguation tool. 
     
     
         13 . The method of  claim 12 , wherein the disambiguation tool allows for deselection of the category. 
     
     
         14 . The method of  claim 8 , further comprising:
 receiving, via the at least one computing device, another search query from the client device;   generating, via the at least one computing device, another confidence score associated with at least one category of the plurality of categories, the at least one category being identified according to at least one term of the other search query;   selecting, via the at least one computing device, at least one other item from the plurality of items in response to the other confidence score failing to meet the threshold; and   generating, via the at least one computing device, another user interface including the at least one other item and a disambiguation tool, the disambiguation tool being configured to allow for selection of a particular category from the plurality of categories.   
     
     
         15 . A non-transitory computer-readable medium embodying a program executable in at least one computing device, wherein, when executed the program causes the at least one computing device to at least:
 compare a plurality of category keywords with at least a portion of a search query received from a client device to identify a plurality of item categories;   determine, for individual item categories of the plurality of item categories, a frequency of occurrence of the at least a portion of the search query in a description of a respective item category;   generate, for the individual item categories, a respective confidence score based at least in part on the frequency of occurrence;   determine that the respective confidence score for at least one item category of the plurality of items categories meets or exceeds a threshold;   generate a user interface including a plurality of items associated with the at least one item category; and   transmit data encoding the user interface to the client device.   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein, when executed, the program further causes the at least one computing device to at least identify at least one item attribute based at least in part on one or more terms of the search query. 
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the plurality of items is a subset of a collection of items associated with the at least one item category, and when executed, the program further causes the at least one computing device to select the plurality of items from the collection of items based at least in part on the at least one item attribute. 
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein the user interface further includes a disambiguation tool configured to allow deselection of the at least one category. 
     
     
         19 . The non-transitory computer-readable medium of  claim 15 , wherein the user interface further includes a plurality of links for a plurality of detail network pages for the plurality of items. 
     
     
         20 . The non-transitory computer-readable medium of  claim 15 , wherein, when executed, the program further causes the at least one computing device to at least parse the search query into a plurality of search query keywords.