Systems for generating a global product taxonomy

Abstract

Techniques for generating a globally applicable taxonomy of e-commerce goods are described. According to various exemplary embodiments described herein, a taxonomy management system is configured to analyze item listing titles and user search queries in order to identify a set of globally applicable product types that serve as universal descriptors of the underlying things or objects that are the subject of an item listing or the likely user intended subject of a user search query. Such globally applicable product types are agnostic as to any specific product inventory or product category structure of an e-commerce website. After the taxonomy management system identifies product types, the taxonomy management system may incorporate the identified product types into a global product taxonomy that identifies the globally applicable product types.

1 . (canceled) 
     
     
         2 . A method comprising:
 converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;   determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;   identifying frequent terms in leaf categories associated with the category structure of the webpage;   determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and   assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.   
     
     
         3 . The method of  claim 2 , further comprising:
 determining that the remaining ones of the tokens corresponds to a single candidate token;   determining that the single candidate token is a type in the global taxonomy; and   incorporating the type into the global taxonomy.   
     
     
         4 . The method of  claim 2 , wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value. 
     
     
         5 . The method of  claim 2 , further comprising:
 classifying the highest weighted candidate token as a type in the global taxonomy; and   incorporating the type into the global taxonomy.   
     
     
         6 . The method of  claim 2 , further comprising:
 identifying a group of the highest weighted candidate tokens;   displaying, via a user interface, the group of the highest weighted candidate tokens;   receiving, via the user interface, a user specification of one of the displayed candidate tokens;   classifying the user specified candidate token as a type in the global taxonomy; and   incorporating the token into the global taxonomy.   
     
     
         7 . The method of  claim 2 , further comprising:
 generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.   
     
     
         8 . The method of  claim 7 , further comprising:
 receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;   determining a type in the global taxonomy, based on the listing title;   determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and   notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.   
     
     
         9 . A system comprising:
 a processor and executable instructions accessible on a computer-readable medium that, when executed, cause the processor to perform operations comprising:   converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;   determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;   identifying frequent terms in leaf categories associated with the category structure of the webpage;   determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and   assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.   
     
     
         10 . The system of  claim 9 , further comprising:
 determining that the remaining ones of the tokens corresponds to a single candidate token;   determining that the single candidate token is a type in the global taxonomy; and   incorporating the type into the global taxonomy.   
     
     
         11 . The system of  claim 9 , wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value. 
     
     
         12 . The system of  claim 9 , further comprising:
 classifying the highest weighted candidate token as a type in the global taxonomy; and   incorporating the type into the global taxonomy.   
     
     
         13 . The system of  claim 9 , further comprising:
 identifying a group of the highest weighted candidate tokens;   displaying, via a user interface, the group of the highest weighted candidate tokens;   receiving, via the user interface, a user specification of one of the displayed candidate tokens;   classifying the user specified candidate token as a type in the global taxonomy; and   incorporating the token into the global taxonomy.   
     
     
         14 . The system of  claim 9 , further comprising:
 generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.   
     
     
         15 . The system of  claim 14 , further comprising:
 receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;   determining a type in the global taxonomy, based on the listing title;   determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and   notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.   
     
     
         16 . A non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more processors of a machine that cause the machine to perform operations comprising:
 converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;   determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;   identifying frequent terms in leaf categories associated with the category structure of the webpage;   determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and   assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.   
     
     
         17 . The storage medium of  claim 16 , wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value. 
     
     
         18 . The storage medium of  claim 16 , further comprising:
 classifying the highest weighted candidate token as a type in the global taxonomy; and   incorporating the type into the global taxonomy.   
     
     
         19 . The system of  claim 16 , further comprising:
 identifying a group of the highest weighted candidate tokens;   displaying, via a user interface, the group of the highest weighted candidate tokens;   receiving, via the user interface, a user specification of one of the displayed candidate tokens;   classifying the user specified candidate token as a type in the global taxonomy; and   incorporating the token into the global taxonomy.   
     
     
         20 . The system of  claim 16 , further comprising:
 generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.   
     
     
         21 . The system of  claim 20 , further comprising:
 receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;   determining a type in the global taxonomy, based on the listing title;   determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and   notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.