Taxonomy based targeted search advertising

Abstract

One embodiment of the invention includes automatically generating adgroups for use in a search advertising by obtaining source data describing a set of product data describing a set of products, obtaining a list of initial keywords, obtaining a taxonomy based on the source data and the initial list of keywords, identifying a set of category data based on the source data and the taxonomy, where an identified category in the set of category data classifies at least one piece of product data based on the attribute-value pairs for the piece of product data and keyword components within the taxonomy, identifying one or more landing pages that are relevant to at least one piece of product data based on the set of product data and the set of category data, and automatically generating adgroups comprising the identified set of category data, product data, and the identified landing pages.

What is claimed: 
     
         1 . A method of automatically generating adgroups for use in a search advertising, comprising:
 obtaining source data describing a set of product data using a adgroup creation server system, where a piece of product data comprises a set of attribute-value pairs describing a set of products;   obtaining a list of initial keywords using the adgroup creation server system, where the keywords in the initial list of keywords comprise keyword components;   obtaining a taxonomy based on the source data and the initial list of keywords using the adgroup creation server system, where the taxonomy uniquely maps the source data to a set of categories and attributes and maps the keyword components to the categories and attributes;   identifying a set of category data based on the source data and the taxonomy using the adgroup creation server system, where an identified category in the set of category data classifies at least one piece of product data based on the attribute-value pairs for the piece of product data and the keyword components within the taxonomy;   identifying one or more landing pages that are relevant to at least one piece of product data based on the set of product data and the set of category data using the adgroup creation server system; and   automatically generating adgroups comprising the identified set of category data, product data corresponding to the set of category data, and the identified landing pages using the adgroup creation server system.   
     
     
         2 . The method of  claim 1 , further comprising deploying the adgroups to a search engine provider using the adgroup creation server system, where the search engine provider is configured to present one or more advertisements generated using the deployed adgroups in response to one or more search keywords received using the search engine provider. 
     
     
         3 . The method of  claim 1 , further comprising:
 obtaining keyword performance data based on the initial keywords using the adgroup creation server system, where the keyword performance data describes the performance of the keywords within at least one advertising campaign;   identifying product keyword data based on the categories and attributes within the taxonomy and the product data using the adgroup creation server system, where the product keyword data comprises a set of updated keyword components describing the set of products described by the product data; and   automatically generating the adgroups based on the identified set of category data, the product keyword data, and the identified landing pages using the adgroup creation server system.   
     
     
         4 . The method of  claim 3 , wherein at least one of the updated keywords components corresponds to the keyword components in the list of initial keywords. 
     
     
         5 . The method of  claim 4 , further comprising identifying corresponding keywords by:
 identifying surface concepts within the taxonomy based unique combinations of category names and attribute values using the adgroup creation server system;   identifying deep concepts within the taxonomy to which at least one surface concept is subordinate using the adgroup creation server system; and   predicting the updated keywords that are relevant to the product data by predicting keywords that are relevant to the identified deep concepts using the adgroup creation server system.   
     
     
         6 . The method of  claim 4 , wherein identifying corresponding keywords further comprises generating a set of keywords using keyword components within the taxonomy that are associated with the category name and attribute values described in the product data using the adgroup creation server system. 
     
     
         7 . The method of  claim 3 , wherein identifying the product keyword data further comprises generating keywords using the keyword components based upon grammar patterns using the adgroup creation server system. 
     
     
         8 . The method of  claim 7 , wherein the grammar patterns are associated with specific category names within the taxonomy. 
     
     
         9 . The method of  claim 7 , wherein at least one of the grammar patterns includes a grammar component and a semantic component. 
     
     
         10 . The method of  claim 9 , wherein at least one keyword in the product keyword data is generated by combining the semantic components of a plurality of grammar patterns in accordance with the grammar components of the grammar patterns using the adgroup creation server system. 
     
     
         11 . The method of  claim 7 , wherein identifying product keyword data further comprises:
 estimating keyword search volume using search volumes associated with the grammar patterns and keyword components used to generate the keyword using the adgroup creation server system; and   filtering keywords for relevancy to an identified concept based upon the estimated keyword search volume using the adgroup creation server system.   
     
     
         12 . The method of  claim 7 , wherein the grammar patterns are defined based on a template provided by a search engine provider. 
     
     
         13 . The method of  claim 12 , wherein the set of category data comprises attributes based on the provided template and the set of category data. 
     
     
         14 . The method of  claim 3 , wherein identifying the product keyword data is based on at least one targeting criteria selected from the group consisting of keyword match type, intent, geographic location, profile information, language, and information derived from a cookie contained within a browser application from which a search query originated. 
     
     
         15 . The method of  claim 1 , wherein automatically generating the adgroups using the adgroup creation server system is further based on at least one of the keyword components. 
     
     
         16 . The method of  claim 1 , wherein the categories are arranged as a hierarchy of categories with associated attributes. 
     
     
         17 . The method of  claim 1 , wherein the taxonomy supports recursive definition of a first category as an attribute of a second category. 
     
     
         18 . The method of  claim 1 , wherein:
 each category is identified using a category name; and   each attribute is specified as key/value pairs.   
     
     
         19 . The method of  claim 18 , wherein the taxonomy includes a set of category names and attribute values that describe products that are the subject of offers within the plurality of landing pages. 
     
     
         20 . The method of  claim 18 , wherein each product described within a landing page is identified using a unique identifier that is derived from at least one attribute value that describes the product. 
     
     
         21 . The method of  claim 1 , further comprising:
 obtaining an initial advertising campaign comprising a set of category data, a set of product data, and a set of landing pages using the adgroup creation server system; and   incorporating the generated adgroups into the initial advertising campaign.   
     
     
         22 . The method of  claim 1 , further comprising:
 specifying target concepts based on combinations of keyword components from the initial keywords using the adgroup creation server system, where each target concept has a specific set of categories and attributes within the taxonomy defined based upon the different categories and attributes of the keyword components that are combined to form the target concept;   identifying a plurality of offer concepts based on the source data using the adgroup creation server system, where each offer concept is a specific set of categories and attributes within the taxonomy;   mapping target concepts to relevant offer concepts within the plurality of offer concepts based on the specific sets of categories and attributes within the taxonomy of the target and offer concepts using the adgroup creation server system; and   utilizing the target concepts and the offer concepts to identify the set of category data using the adgroup creation server system.   
     
     
         23 . The method of  claim 22 , further comprising utilizing the target concepts and the offer concepts to identify the one or more landing pages using the adgroup creation server system. 
     
     
         24 . A adgroup creation server system, comprising:
 a processor; and   a memory connected to the processor;   wherein the processor is configured to:
 obtain source data describing a set of product data, where a piece of product data comprises set of attribute-value pairs describing a set of products; 
 obtain a list of initial keywords, where the keywords in the initial list of keywords comprise keyword components; 
 obtain a taxonomy based on the source data and the initial list of keywords, where the taxonomy uniquely maps the source data to a set of categories and attributes and maps the keyword components to the categories and attributes; 
 identify a set of category data based on the source data and the taxonomy, where an identified category in the set of category data classifies at least one piece of product data based on the attribute-value pairs for the piece of product data and the keyword components within the taxonomy; 
 identify one or more landing pages that are relevant to at least one piece of product data based on the set of product data and the set of category data; and 
 automatically generate adgroups comprising the identified set of category data, product data corresponding to the set of category data, and the identified landing pages.