Dynamic categorizations for electronic advertising

• US 8,832,129 B1
• Filed: 09/15/2012
• Issued: 09/09/2014
• Est. Priority Date: 09/04/2008
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hansen, Lucas P.
• Primary Examiner(s): Beausoliel, Jr., Robert
• Assistant Examiner(s): Pham, Michael
• Application Number:
  US13/621,080
• Time in Patent Office: 724 Days
• Field of Search: None
• US Class Current: 707/758
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

An advertiser submitting a sponsored ad to a provider can determine aspects of the ad, such as creative elements and bid price, based on a dynamic categorization of an item and/or landing page associated with the ad. An algorithm can be used that utilizes a browse tree for each item to be displayed to a user following a sponsored link, for example, and attempts to find a node in the browse tree that appears at the lowest level in the tree and with a sufficient appearance frequency. When consensus is reached for a node in the browse tree that meets these criteria, a corresponding categorization is determined, which can be used to determine appropriate aspects to be used for the sponsored ad, at least until enough information is obtained such that aspects can be determined independent of the categorization.

Claims

1. A computer-implemented method of determining an advertising template for a landing page, comprising:

under control of one or more computer systems configured with executable instructions,

receiving a request to select an advertising template for a landing page from among a plurality of advertising templates, the landing page associated with one or more items each corresponding to a respective set of one or more categories of a plurality of categories;

determining a hierarchical category browse tree corresponding to the plurality of categories, each category corresponding to one of a plurality of category browse nodes in the hierarchical browse tree, each category browse node associated with one of the plurality of advertising templates;

determining a plurality of browse paths through the hierarchical category browse tree, the plurality of browse paths corresponding to the respective set of one or more categories associated with each item of the landing page and determined based at least in part by traversing the hierarchical category browse tree from a highest level until reaching the category browse node corresponding to one category of the respective set of one or more categories associated with each item of the landing page; and

for each level of the hierarchical category browse tree, beginning with a lowest level and until the advertising template for the landing page has been selected,

determining a frequency of appearance for each category browse node at a current level that is included in one of the plurality of browse paths;

selecting for the landing page the advertising template associated with the category browse node having a highest frequency of appearance when at least one category browse node at the current level meets a specified frequency threshold; and

selecting for the landing page a default advertising template when the current level is the highest level of the hierarchical category browse tree and no category browse node is able to meet the specified frequency threshold.

2. The computer-implemented method of claim 1, wherein:

each category browse node inherits the advertising template of a parent category browse node if no advertising template has been specifically associated with the category browse node.

3. The computer-implemented method of claim 1, wherein:

each advertising template comprises at least one of text, one or more graphics, one or more images, one or more videos, or one or more audio components.

4. A computer-implemented method of determining a category for a landing page, comprising:

under control of one or more computer systems configured with executable instructions,

receiving a request to determine a category for a landing page from among a plurality of categories, the landing page associated with one or more items each corresponding to a respective set of one or more categories of the plurality of categories;

determining a hierarchical category browse tree corresponding to the plurality of categories, each category corresponding to one of a plurality of category browse nodes in the hierarchical browse tree;

determining a plurality of browse paths through the hierarchical category browse tree, the plurality of browse paths corresponding to the respective set of one or more categories associated with each item of the landing page and determined based at least in part by traversing the hierarchical category browse tree from a highest level until reaching the category browse node corresponding to one category of the respective set of one or more categories associated with each item of the landing page; and

for each level of the hierarchical category browse tree, beginning with a lowest level and until the category for the landing page has been selected,

determining a count for each category browse node at the level that is based at least in part upon a respective number of traversals of the category browse node by each browse path of the plurality of browse paths;

selecting for the landing page the category associated with the category browse node with a highest count when at least one category browse node at the level meets a specified threshold; and

selecting for the landing page a default category when the level is the highest level and no category browse node at the level meets the specified threshold.

5. The computer-implemented method of claim 4, wherein:

each category browse node of the hierarchical category browse tree is associated with an advertising template.

6. The computer-implemented method of claim 5, wherein:

each category browse node inherits the advertising template of a parent category browse node when no advertising template has been specifically associated with the category browse node.

7. The computer-implemented method of claim 5, further comprising:

updating the advertising template associated with a specified category browse node of the hierarchical category browse tree with an updated advertising template.

8. The computer-implemented method of claim 7, wherein:

each descendant category browse node of the specified category browse node automatically inherits the updated advertising template of the specified category browse node.

9. The computer-implemented method of claim 7, wherein:

a descendant category browse node of the specified category browse node inherits the updated advertising template by directly associating the descendant category browse node with the updated advertising template.

10. The computer-implemented method of claim 7, wherein:

the specified category browse node and a second specified category browse node that is not a descendant category browse node of the specified category browse node are configured such that at least one of;

(a) the specified category browse node inherits the updated advertising template of the second specified category browse node or (b) the second specified category browse node inherits the updated advertising template of the specified category browse node.

11. The computer-implemented method of claim 5, wherein:

each advertising template comprises at least one of text, one or more graphics, one or more images, one or more videos, or one or more audio components.

12. The computer-implemented method of claim 5, further comprising:

submitting to a provider a sponsored advertisement including the advertising template associated with the category browse node corresponding to the category selected for the landing page.

13. The computer-implemented method of claim 12, wherein:

the sponsored advertisement further includes a navigational element that is directed to the landing page when the navigational element is selected.

14. The computer-implemented method of claim 4, wherein:

the specified threshold is variable based at least in part upon at least one of a predetermined rank of the category corresponding to the category browse node, an order of the one or more items as they appear on the landing page, sales revenue, profit, visits, or a specified goal.

15. The computer-implemented method of claim 4, wherein:

the count is variable based at least in part upon at least one of a predetermined rank of the category corresponding to the category browse node, an order of the one or more items as they appear on the landing page, sales revenue, profit, visits, or a specified goal.

16. The computer-implemented method of claim 4, wherein:

the hierarchical category browse tree is truncated to remove at least one second category browse node and each child category browse node of the second category browse node.

17. A system for dynamically determining a categorization for an item, comprising:

a processor; and

a non-transitory memory device including instructions that, when executed by the processor, cause the processor to;

receive a request to determine a category for a landing page from among a plurality of categories, the landing page associated with one or more items each corresponding to a respective set of one or more categories of the plurality of categories;

determine a hierarchical category browse tree corresponding to the plurality of categories, each category corresponding to one of a plurality of category browse nodes in the hierarchical browse tree;

determine a plurality of browse paths through the hierarchical category browse tree, the plurality of browse paths corresponding to the respective set of one or more categories associated with each item of the landing page and determined based at least in part by traversing the hierarchical category browse tree from a highest level until reaching the category browse node corresponding to one category of the respective set of one or more categories associated with each item of the landing page; and

for each level of the hierarchical category browse tree, beginning with a lowest level and until the category for the landing page has been selected,

determine a count for each category browse node at the level that is based at least in part upon a respective number of traversals of the category browse node by each browse path of the plurality of browse paths;

select for the landing page the category associated with the category browse node with a highest count when at least one category browse node at the level meets a specified threshold; and

select for the landing page a default category when the level is the highest level and no category browse node at the level meets the specified threshold.

18. The system of claim 17, wherein:

each category browse node of the hierarchical category browse tree is associated with an advertising template.

19. The system of claim 18, wherein:

wherein each category browse node inherits the advertising template of a parent category browse node if no advertising template has been specifically associated with the category browse node.

20. The system of claim 18, wherein:

each advertising template comprises at least one of text, one or more graphics, one or more images, one or more videos, or one or more audio components.

21. The system of claim 18, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

submit to a provider a sponsored advertisement including the advertising template associated with the category browse node corresponding to the category selected for the landing page.

22. A non-transitory computer-readable medium including instructions for determining a category for a landing page, the instructions when executed by a processor of a computing device cause the computing device to:

receive a request to determine a category for a landing page from among a plurality of categories, the landing page associated with one or more items each corresponding to a respective set of one or more categories of the plurality of categories;

determine a hierarchical category browse tree corresponding to the plurality of categories, each category corresponding to one of a plurality of category browse nodes in the hierarchical browse tree;

determine a plurality of browse paths through the hierarchical category browse tree, the plurality of browse paths corresponding to the respective set of one or more categories associated with each item of the landing page and determined based at least in part by traversing the hierarchical category browse tree from a highest level until reaching the category browse node corresponding to one category of the respective set of one or more categories associated with each item of the landing page; and

for each level of the hierarchical category browse tree, beginning with a lowest level and until the category for the landing page has been selected,

determine a count for each category browse node at the level that is based at least in part upon a respective number of traversals of the category browse node by each browse path of the plurality of browse paths;

select for the landing page the category associated with the category browse node with a highest count when at least one category browse node at the level meets a specified threshold; and

select for the landing page a default category when the level is the highest level and no category browse node at the level meets the specified threshold.

23. The non-transitory computer-readable medium of claim 22, wherein:

each category browse node of the hierarchical category browse tree is associated with an advertising template.

24. The non-transitory computer-readable medium of claim 23, wherein:

each category browse node inherits the advertising template of a parent category browse node if no advertising template has been specifically associated with the category browse node.

25. The non-transitory computer-readable medium of claim 23, wherein:

each advertising template comprises at least one of text, one or more graphics, one or more images, one or more videos, and one or more audio components.

26. The non-transitory computer-readable medium of claim 23, wherein the instructions when executed further cause the computing device to:

submit to a provider a sponsored advertisement including the advertising template associated with the category browse node corresponding to the category selected for the landing page.