Taxonomy based targeted search advertising

1. A campaign creation system, comprising:

a server and storage;

wherein the server is configured to:

obtain source data describing a plurality of landing pages, where the landing pages include information describing a plurality of offers;

obtain a list of initial keywords, where the keywords in the initial list of keywords comprise keyword components;

build a taxonomy based on the source data and the initial list of keywords, where the taxonomy uniquely maps the plurality of landing pages to categories and attributes and maps the keyword components to the categories and attributes;

specify target concepts based on combinations of keyword components from the initial keywords, 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;

identify a plurality of offer concepts based on the information describing the plurality of offers, where each offer concept is a specific set of categories and attributes within the taxonomy identified using the information describing the offer in the source data describing the plurality of landing pages;

match target concepts to relevant offer concepts within the plurality of concepts based on the specific sets of categories and attributes within the taxonomy of the target and offer concepts;

once a specific offer concept is matched as relevant to a specific target concept, identify one or more of the plurality of landing pages that are relevant to the specific target concept based on the attributes within the taxonomy of the specific relevant offer concept;

generate one or more anticipated creatives based on the specific sets of categories and attributes of the relevant offer concepts;

generate adgroups comprising:

at least one of the one or more anticipated creatives targeted toward at least one keyword identified based on the specific target concept matched to the specific relevant offer concept used to generate the anticipated creative; and

at least one of the landing pages identified as relevant to the specific target concept based on the attributes in the taxonomy of the specific relevant offer concept;

deploy the adgroups to a search engine provider, where the search engine provider is configured to present one or more of the anticipated creatives from the uploaded adgroups in response to one or more search keywords received using the search engine provider.

2. The system of claim 1 , wherein the categories are arranged as a hierarchy of categories with associated attributes.

3. The system of claim 1 , wherein the taxonomy supports the recursive definition of a first category as an attribute of a second category.

4. The system of claim 1 , wherein:

each category is identified using a category name; and

each attribute is specified as a key value pairs.

5. The system of claim 4 , 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.

6. The system of claim 5 , 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.

7. The system of claim 4 , wherein the server is further configured to match target concepts to relevant offer concepts by:

identifying concepts representing unique combinations of category names and attribute values within the taxonomy; and

predicting keywords that are relevant to the identified concepts.

8. The system of claim 7 , wherein:

the server is further configured to identify concepts representing unique combinations of category names and attribute values by:

identifying surface concepts using unique combinations of category names and attribute values; and

identifying deep concepts to which at least one surface concept is subordinate; and

the server is further configured to predict keywords that are relevant to the identified concepts by predicting keywords that are relevant to the identified deep concepts.

9. The system of claim 8 , wherein the server is further configured to infer additional attributes of a surface concept using an inference engine.

10. The system of claim 7 , wherein the server is further configured to predicting keywords that are relevant to the identified concepts by generating a set of keywords using keyword components within the taxonomy that are associated with the category name and attribute values that form the basis of the concept.

11. The system of claim 10 , wherein the server is further configured to generate a set of keywords using keyword components within the taxonomy that are associated with the category name and attribute values that form the basis of the concept by generating keywords using the keyword components based upon grammar patterns.

12. The system of claim 11 , wherein the grammar patterns are associated with specific category names within the taxonomy.

13. The system of claim 12 , wherein at least one of the grammar patterns includes a grammar component and a semantic component.

14. The system of claim 13 , wherein the server is further configured to generate at least one keyword by combining the semantic components of a plurality of grammar patterns in accordance with the grammar components of the grammar patterns.

15. The system of claim 10 , wherein the server is further configured to predict keywords that are relevant to the identified concepts by:

estimating keyword search volume using search volumes associated with the grammar patterns and keyword components used to generate the keyword; and

filtering keywords for relevancy to an identified concept based upon the estimated keyword search volume.

16. The system of claim 7 , wherein the server is further configured to match target concepts to relevant offer concepts by identifying at least one target based on a keyword predicted to be relevant to a target concept.

17. The system of claim 16 , wherein the server is further configured to match target concepts to relevant offer concepts by identifying at least one targeting criteria for the at least one target, where the at least one targeting criteria is 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 the search query originated.

18. The system of claim 17 , wherein the server is further configured to match target concepts to relevant offer concepts by selecting an offer concept for a specific target based upon the estimated performance of the offer concept with respect to search queries targeted by the specific target.

19. The system of claim 1 , wherein the server is further configured to automatically generate one or more anticipated creatives based on the specific sets of categories and attributes of the relevant offer concepts and at least one of the keyword components.

20. The system of claim 1 , wherein the server is further configured to specifying target concepts by:

generating additional keywords based on the keyword components and grammar rules; and

utilizing the additional keywords when specifying the target concepts.

21. The system of claim 20 , wherein the generated additional keywords are not included in the list of initial keywords.

22. A campaign creation system, comprising:

a server and storage;

wherein the server is configured to:

obtain source data describing a plurality of landing pages, where the landing pages include information describing a set of offers;

obtain a list of initial keywords, where the keywords in the initial list of keywords comprise keyword components;

build a taxonomy based on the source data and the initial list of keywords, where the taxonomy uniquely maps the plurality of landing pages to categories and attributes and maps the keyword components to the categories and attributes;

specify target concepts based on combinations of keyword components from the initial keywords, 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;

identify a plurality of offer concepts based on the information describing the plurality of offers, where each offer concept is a specific set of categories and attributes within the taxonomy identified using the information describing the offer in the source data describing the plurality of landing pages;

match 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 by:

identifying at least one surface concept within the taxonomy based on the target concepts and the relevant offer concepts, where a surface concept in the at least one surface concept comprises keywords and attributes contained in at least one of the target concepts and at least one of the plurality of offer concepts;

identifying at least one deep concept to which at least one surface concept is subordinate within the taxonomy, where a deep concept comprises all of the category name and attribute values that can be used to describe the at least one target concept and the at least one offer concept; and

predicting keywords that are relevant to the identified deep concepts, where the predicted keywords map the at least one target concept to the at least one offer concept;

once a specific offer concept is matched as relevant to a specific target concept, identify one or more of the plurality of landing pages that are relevant to the specific target concept based on the attributes within the taxonomy of the specific relevant offer concept;

automatically generate one or more anticipated creatives based on the specific sets of categories and attributes of the relevant offer concepts;

automatically generate adgroups comprising:

at least one of the one or more anticipated creatives targeted toward at least one keyword identified based on the specific target concept matched to the specific relevant offer concept used to generate the anticipated creative; and

at least one of the landing pages identified as relevant to the specific target concept based on the attributes in the taxonomy of the specific relevant offer concept; and

deploy the adgroups to a search engine provider, where the search engine provider is configured to present one or more of the anticipated creatives from the uploaded adgroups in response to one or more search keywords received using the search engine provider.