Categorizing objects, such as documents and/or clusters, with respect to a taxonomy and data structures derived from such categorization

• US 8,229,957 B2
• Filed: 04/22/2005
• Issued: 07/24/2012
• Est. Priority Date: 04/22/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gehrking, David, Law, Ching, Maxwell, Andrew
• Primary Examiner(s): LY, CHEYNE D
• Application Number:
  US11/112,716
• Publication Number:
  US 20060242147A1
• Time in Patent Office: 2,650 Days
• Field of Search: 707/100, 707/737, 707/740, 707/778
• US Class Current: 707/778
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A Website may be automatically categorized by (a) accepting Website information, (b) determining a set of scored clusters (e.g., semantic, term co-occurrence, etc.) for the Website using the Website information, and (c) determining at least one category (e.g., a vertical category) of a predefined taxonomy using at least some of the set of clusters.

Claims

1. A computer-implemented method comprising:

a) accepting, by a computer system including at least one computer, Website information associated with a Website;

b) determining, by the computer system and the accepted Website information, a set of scored clusters, wherein the score of each of the scored clusters is indicative of how conceptually significant the cluster is to the Website;

c) determining, by the computer system, at least one category of a predefined taxonomy of categories using at least some of the set of clusters, wherein categories of the predefined taxonomy are hierarchical and correspond to at least one of (A) related products that are likely to be found in Website content, (B) related services that are likely to be found in Website content, or (C) related industries that are likely to be found in Website content;

d) associating, by the computer system, the Website with the determined at least one category to create an association;

e) storing, by the computer system, the association of the Website with the determined at least one category; and

f) determining, by the computer system, an advertisement relevant to the Website at least using the stored association of the Website with the determined at least one category,

wherein the act of determining at least one category of a predefined taxonomy using at least some of the clusters includes

(A) using information of the at least some of the clusters to look up one or more categories, and

(B) for at least some of the one or more categories, determining a score based on a sum of values including (1) an intra-category cluster score of the category, and (2) intra-category cluster scores of categories that are descendants of the category in the hierarchical taxonomy.

2. The computer-implemented method of claim 1 wherein the act determining a set of scored clusters for the Website using the Website information uses pageviews and activation scores on individual Webpages of the Website.

3. The computer implemented method of claim 1 wherein the act of determining at least one category of a predefined taxonomy using at least some of the clusters further includes

determining a set of one or more concepts using the set of scored clusters, and

determining the at least one category using at least some of the set of one or more concepts.

4. The computer-implemented method of claim 1 wherein the act of determining at least one category of a predefined taxonomy using at least some of the clusters further includes,

determining a deepest hierarchical level category having a determined score which is greater than a predetermined threshold.

7. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often.

8. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often on Web pages.

9. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in product catalogs.

10. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in articles.

11. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in speech.

12. The computer-implemented method of claim 1 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in discussion or e-mail threads.

5. Apparatus comprising:

a) at least one processor; and

b) at least one storage device storing processor-executable instructions which, when executed by the at least one processor, perform a method including

1) accepting Website information,

2) determining a set of scored clusters for the Website using the Website information associated with a Website, wherein the score of each of the scored clusters is indicative of how conceptually significant the cluster is to the Website,

3) determining at least one category of a predefined taxonomy of categories using at least some of the set of clusters, wherein categories of the predefined taxonomy are hierarchical and correspond to at least one of (A) related products that are likely to be found in Website content, (B) related services that are likely to be found in Website content, or (C) related industries that are likely to be found in Website content,

4) associating the Website with the determined at least one category to create an association,

5) storing the association of the Website with the determined at least one category, and

6) determining an advertisement relevant to the Website at least using the stored association of the Website with the determined at least one category,

wherein the act of determining at least one category of a predefined taxonomy using at least some of the clusters includes

(A) using information of the at least some of the clusters to look up one or more categories, and

(B) for at least some of the one or more categories, determining a score based on a sum of values including (1) an intra-category cluster score of the category, and (2) intra-category cluster scores of categories that are descendants of the category in the hierarchical taxonomy.

6. A computer-implemented method comprising:

a) accepting, using a computer system including at least one computer, Website information associated with a Website;

b) determining, using the computer system, a set of scored clusters for the Website using the Website information;

c) determining, using the computer system, at least one category of a predefined taxonomy of categories using at least some of the set of clusters, wherein categories of the predefined taxonomy are hierarchical and correspond to related content formats that are likely to be found in Website content;

d) associating, using the computer system, the Website with the determined at least one category to create an association;

e) storing, using the computer system, the association of the Website with the determined at least one category; and

f) determining, using the computer system, an advertisement relevant to the Website at least using the stored association of the Website with the determined at least one category,

wherein the act of determining at least one category of a predefined taxonomy using at least some of the set of clusters includes

(A) using information of the at least some of the set of clusters to look up one or more categories, and

(B) for at least some of the one or more categories, determining a score based on a sum of values including (1) an intra-category cluster score of the category, and (2) intra-category cluster scores of categories that are descendants of the category in the hierarchical taxonomy.

13. The computer-implemented method of claim 6 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often.

14. The computer-implemented method of claim 6 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in product catalogs.

15. The computer-implemented method of claim 6 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in articles.

16. The computer-implemented method of claim 6 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in speech.

17. The computer-implemented method of claim 6 wherein each cluster of the set of scored clusters includes terms that tend to co-occur often in discussion or e-mail threads.