METHOD AND SYSTEM FOR MANAGING SINGLE AND MULTIPLE TAXONOMIES

• US 20070250487A1
• Filed: 04/19/2007
• Published: 10/25/2007
• Est. Priority Date: 04/19/2006
• Status: Active Grant

• Current Assignee: Elisa Sartori
• Original Assignee: Mobile Content Networks Incorporated
• Inventors: Reuther, Phyllis
• Granted Patent: US 7,974,984 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/367 Ontology

Abstract

A system and method may include retrieving a first taxonomy comprising at least one first category and one or more second taxonomies, at least one second category being associated with at least one of the one or more second taxonomies. The system and method may further include creating a new taxonomy by merging the first taxonomy with the second taxonomy based on a comparison of a first category profile of the at least one first category with a second category profile of the at least one second category.

Claims

1. A computer implemented method comprising the steps of:

retrieving a first taxonomy comprising a first plurality of categories;

retrieving one or more second taxonomies, a second plurality of categories being associated with the one or more second taxonomies;

comparing a category profile of each of the first plurality of categories to a category profile of each of the second plurality of categories to identify matching categories and non-matching categories; and

creating a third taxonomy that includes the matching categories and the non-matching categories.

2. The method of claim 1, wherein the each of the first plurality of categories and each of the second plurality of categories are associated with one or more content items.

3. The method of claim 1, wherein the comparing applies a comparator function that identifies a match when a comparison between category profiles is above a threshold value.

4. A method comprising:

retrieving a first taxonomy comprising at least one first category and one or more second taxonomies, at least one second category being associated with at least one of the one or more second taxonomies; and

creating a new taxonomy by merging the first taxonomy with the second taxonomy based on a comparison of a first category profile of the at least one first category with a second category profile of the at least one second category.

5. The method of claim 4, further comprising receiving a selection of a taxonomy type.

6. The method of claim 4, further comprising identifying a category comparator function for performing the comparison.

7. The method of claim 6, further comprising applying the comparator function to the first category profile and to the second category profile to determine whether the at least one first category matches the at least one second category.

8. The method of claim 7, wherein the comparator function identifies a match if the comparison is above a threshold.

9. The method of claim 8, where in the event that the comparison is not above the threshold, further comprising adding both the at least one first category and the at least one second category to the new taxonomy.

10. The method of claim 8, where in the event that the comparison is above the threshold, further comprising:

adding the at least one first category to the new taxonomy; and

creating an association between the at least one first category and the at least one second category.

11. The method of claim 4, further comprising ordering the first taxonomy relative to the second taxonomy based on which of the first taxonomy and the second taxonomy includes a greater number of categories.

12. The method of claim 4, further comprising creating a category list comprising the at least one first category and the at least one second category.

13. The method of claim 4, further comprising creating intra-taxonomy mappings to associate the at least one first category with the at least one second category in the new taxonomy.

14. The method of claim 4, wherein category profiles are generated using Single Vector Machines (SVM).

15. The method of claim 4, wherein category profiles are generated using k-Nearest Neighbor (knn) classification.

16. The method of claim 4, further comprising creating an intra-taxonomy mapping for the new taxonomy.

17. The method of claim 16, wherein the intra-taxonomy mapping creates parent-child relationships between categories in the new taxonomy.

18. The method of claim 16, wherein the intra-taxonomy mapping creates a tree structure in the new taxonomy.

19. A system comprising:

a first content source communicatively coupled to a network, the first content source to store a first taxonomy having at least one first category;

a second content source communicatively coupled to the network, the second content source to store a second taxonomy having at least one second category;

a client device communicatively coupled to a network, the client device to generate data identifying a first taxonomy and a second taxonomy; and

a server communicatively coupled to the network, the server to receive the data and to retrieve the first taxonomy and the second taxonomy, the server being further configured to create a new taxonomy by merging the first taxonomy with the second taxonomy based on a comparison of a first category profile of the at least one first category with a second category profile of the at least one second category.

20. An apparatus comprising:

a source connector module to retrieve a first taxonomy and a second taxonomy from one or more content sources, the first taxonomy having at least one first category and the second taxonomy having at least one second category;

a category content module to generate a first category profile for the at least one first category and a second category profile for the at least one second category; and

a taxonomy merge program module to create a new taxonomy by merging the first taxonomy with the second taxonomy based on a comparison of the first category profile with the second category profile.