Keyword generation method and apparatus

• US 20060206516A1
• Filed: 03/08/2006
• Published: 09/14/2006
• Est. Priority Date: 03/10/2005
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Efficient Frontier
• Inventors: Mason, Zachary
• Granted Patent: US 10,515,374 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Methods, apparatuses, and articles for receiving one or more indicators indicating one or more degrees of relevance or irrelevance of one or more items or entities to advertising keywords of interest, generating one or more advertising keyword suggestions suggesting one or more advertising keywords based at least in part on whether there are predetermined relationships among the suggested one or more advertising keywords, and between some of the suggested one or more advertising keywords and the one or more items or entities, are described herein.

Claims

1. A method comprising:

receiving one or more indicators indicating one or more degrees of relevance or irrelevance of one or more items or entities to advertising keywords of interest; and

generating one or more advertising keyword suggestions suggesting one or more advertising keywords based at least in part on whether there are predetermined relationships among the suggested one or more advertising keywords, and between some of the suggested one or more advertising keywords and the one or more items or entities.

2. The method of claim 1, wherein the one or more items or entities comprise at least a selected one of keywords, words, merchants, web sites, or categories of an ontology, and the one or more indicators comprise one or more indicators indicating relevance or irrelevance of the at least selected one of keywords, words, merchants, web sites, or categories of an ontology to advertising keywords of interest.

3. The method of claim 1, wherein the one or more indicators comprise negative values when indicating one or more degrees of irrelevance of the one or more items or entities to advertising keywords of interest.

4. The method of claim 1, wherein said generating comprises performing a spreading activation analysis on a plurality of keyword and item or entity pairs having a predetermined relationship between the keywords and the items or entities, based at least in part on the received one or more indicators.

5. The method of claim 4, further comprising storing the keyword and item/entity pairs having the relationship in a database, and retrieving the stored keyword and item/entity pairs from the database for the spreading activation analysis.

6. The method of claim 5, wherein said retrieving comprises retrieving a subset of all keyword and item/entity pairs stored in the database.

7. The method of claim 4, wherein said performing of the spreading activation analysis comprises generating a data structure for a graph having nodes and segments connecting the nodes, with at least a selected one of the keywords or the items/entities occupying either the nodes or the segments.

8. The method of claim 7, wherein said performing of the spreading activation analysis further comprises assigning an amount of activation to a subset of the nodes based at least in part on the received one or more indicators, and iteratively propagating the amount of activations to other connected nodes, until an end of propagation criterion is met.

9. The method of claim 8, wherein the end of propagation criterion comprises a selected one of a convergence threshold having been met, or a number of iterations has been performed.

10. The method of claim 1, wherein said generating comprises generating a non-final set of one or more advertising keyword suggestions, and filtering or constraining the non-final set to generate a final set of one or more advertising keyword suggestions.

11. The method of claim 10, wherein said filtering or constraining of the non-final set to generate a final set of one or more advertising keyword suggestions comprises computing a predictive measure of an advertising effectiveness measure for each of the non-final set of advertising keyword suggestions, and filtering or constraining the non-final set based at least in part on the computed predictive measure of the advertising effectiveness measure.

12. An apparatus comprising:

a processor; and

a generator designed to be operated by the processor to receive one or more indicators indicating one or more degrees of relevance or irrelevance of one or more items or entities to advertising keywords of interest, and to generate in response one or more advertising keyword suggestions suggesting one or more advertising keywords based at least in part on whether there are predetermined relationships among the suggested one or more advertising keywords, and between the suggested one or more advertising keywords and the one or more items or entities.

13. The apparatus of claim 12, wherein the one or more items or entities comprise at least a selected one of keywords, words, merchants, web sites, or categories of an ontology, and the one or more indicators comprise one or more indicators indicating relevance or irrelevance of the at least selected one of keywords, words, merchants, web sites, or categories of an ontology to advertising keywords of interest.

14. The apparatus of claim 12, wherein the generator is adapted to perform a spreading activation analysis on a plurality of keyword and item or entity pairs having a predetermined relationship between the keywords and the items or entities, based at least in part on the received one or more indicators.

15. The apparatus of claim 14, further comprising a database coupled to the generator, and the generator is further adapted to store the keyword and item/entity pairs having the relationship in the database, and to retrieve the stored keyword and item/entity pairs from the database for the spreading activation analysis.

16. The apparatus of claim 14, wherein the generator is further adapted to generate a data structure for a graph having nodes and segments connecting the nodes, with at least a selected one of the keywords or the items/entities occupying either the nodes or the segments.

17. The apparatus of claim 16, wherein the generator is adapted to assign an amount of activation to a subset of the nodes based at least in part on the received one or more indicators, and to iteratively propagate the amount of activations to other connected nodes, until an end of propagation criterion is met.

18. The apparatus of claim 12, wherein said generator is further adapted to generate a non-final set of one or more advertising keyword suggestions, and to filter or constrain the non-final set to generate a final set of one or more advertising keyword suggestions.

19. An article of manufacture comprising:

a storage medium; and

a plurality of programming instructions designed to program and implement a generator for an apparatus, to enable the apparatus to receive one or more indicators indicating one or more degrees of relevance or irrelevance of one or more items or entities to advertising keywords of interest, and to generate in response one or more advertising keyword suggestions suggesting one or more advertising keywords based at least in part on whether there are predetermined relationships between the suggested one or more advertising keywords and the one or more items or entities.

20. The article of claim 19, wherein the one or more items or entities comprise at least a selected one of keywords, words, merchants, web sites, or categories of an ontology, and the one or more indicators comprise one or more indicators indicating relevance or irrelevance of the at least selected one of keywords, words, merchants, web sites, or categories of an ontology.

21. The article of claim 19, wherein the generator is further designed to enable the apparatus to perform a spreading activation analysis on a plurality of keyword and item or entity pairs having a predetermined relationship between the keywords and the items or entities, based at least in part on the received one or more indicators.

22. The article of claim 21, wherein the generator is further designed to enable the apparatus to generate a data structure for a graph having nodes and segments connecting the nodes, with at least a selected one of the keywords or the items/entities occupying either the nodes or the segments.

23. The article of claim 22, wherein the generator is designed to assign an amount of activation to a subset of the nodes based at least in part on the received one or more indicators, and to iteratively propagate the amount of activations to other connected nodes, until an end of propagation criterion is met.