System, Method and Computer Program for Faceted Classification Synthesis

• US 20070118542A1
• Filed: 01/22/2007
• Published: 05/24/2007
• Est. Priority Date: 03/30/2005
• Status: Active Grant

• Current Assignee: Primal Fusion Inc.
• Original Assignee: Primal Fusion Inc.
• Inventors: Sweeney, Peter
• Granted Patent: US 7,849,090 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 16/84 Mapping; Conversion
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A method (system and computer program product) performs facet classification synthesis to relate concepts represented by concept definitions defined in accordance with a faceted data set comprising facets, facet attributes, and facet attribute hierarchies. Dimensional concept relationships are expressed between the concept definitions. Two concept definitions are determined to be related in a particular dimensional concept relationship by examining whether at least one of explicit relationships and implicit relationships exist in the faceted data set between the respective facet attributes of the two concept definitions.

Claims

1. A method for performing faceted classification synthesis to relate concepts represented by concept definitions defined in accordance with a faceted data set comprising facets, facet attributes, and facet attribute hierarchies, said method comprising:

expressing dimensional concept relationships between the concept definitions, wherein two concept definitions are determined to be related in a particular dimensional concept relationship by examining whether at least one of explicit relationships and implicit relationships exist in the faceted data set between the respective facet attributes of the two concept definitions.

2. The method of claim 1 comprising defining the dimensional concept relationships in accordance with intersecting sets of the facet attributes within the concept definitions thereby to infer the implicit relationships between the concepts definitions.

3. The method of claim 1 comprising defining the dimensional concept relationships in accordance with whether the attributes of the respective concept definitions are related, directly or indirectly, as defined by the facet attribute hierarchy thereby to infer the explicit relationships between the concepts definitions.

4. The method of claim 1 comprising assembling the dimensional concept relationships in a dimensional concept hierarchy.

5. The method of claim 4 comprising defining a dimensional axis, from one or more facet attributes, with which to generate a dimensional concept hierarchy from the dimensional concept relationships.

6. The method of claim 5 comprising defining a plurality of dimensional axes, each axis defined in accordance with respective sets of one or more facet attributes, to define a plurality of dimensional concept hierarchies.

7. The method of claim 5 comprising at least one of:

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if all of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions; and

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if a subset of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions.

8. The method of claim 5 comprising selecting the one or more facet attributes for defining said dimensional axis, said selecting in accordance with at least one of:

the respective priorities of the facet attributes in the facet attribute hierarchy; and

a particular concept definition comprising the one or more facet attributes to ascribe a particular meaning to said dimensional axis.

9. The method of claim 4 comprising evaluating sets of dimensional concept relationships for the presence of indirect relationships and assembling the dimensional concept hierarchy without the indirect relationships.

10. The method of claim 4 comprising determining a priority for the concept definitions in the dimensional concept hierarchy based on at least one of priorities of facet attributes in the facet attribute hierarchy and a count of the number of facet attributes in the respective concept definitions of related concepts.

11. The method of claim 4 comprising defining a dimensional concept taxonomy by assigning facet attributes to content nodes of a domain to be classified in accordance with concepts associated with the content nodes, said concepts represented by concept definitions in the dimensional concept hierarchy defined using said facet attributes.

12. The method of claim 1 wherein the concepts are represented initially by preliminary concept definitions, wherein the relationships between the concepts are represented in an input concept hierarchy and wherein the method comprises:

revising said preliminary concept definitions, extending the preliminary concept definitions with additional facet attributes in response to whether any two relationships in the input concept hierarchy may be related, directly or indirectly, in a dimensional concept relationship by at least one of explicit relationships and implicit relationships in the faceted data set.

13. The method of claim 1 comprising, for a domain to be classified:

defining a domain-specific facet attribute hierarchy comprising unique keywords as representative of facet attributes in the domain.

14. The method of claim 13 comprising defining a dimensional concept taxonomy for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions, said taxonomy comprising a hierarchy of dimensional concept relationships generated from the concept definitions and the domain-specific facet hierarchy, wherein each concept definition is mapped to one or more representative keywords of the domain-specific facet hierarchy.

15. The method of claim 1 comprising defining said dimensional concept relationships for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions.

16. The method of claim 15 comprising examining concept nodes for their respective one or more concept definitions.

17. The method of claim 15 wherein said defining said dimensional concept relationships for a domain to be classified is limited to processing a localized region of the domain using content nodes proximal to a selected content node.

18. A computer system for performing faceted classification synthesis to relate concepts represented by concept definitions defined in accordance with a faceted data set comprising facets, facet attributes, and facet attribute hierarchies, the computer system configured for:

expressing dimensional concept relationships between the concept definitions, wherein two concept definitions are determined to be related in a particular dimensional concept relationship by examining whether at least one of explicit relationships and implicit relationships exist in the faceted data set between the respective facet attributes of the two concept definitions.

19. The computer system of claim 18 wherein the system is configured for defining the dimensional concept relationships in accordance with intersecting sets of the facet attributes within the concept definitions thereby to infer the implicit relationships between the concepts definitions.

20. The computer system of claim 18 wherein the system is configured for defining the dimensional concept relationships in accordance with whether the attributes of the respective concept definitions are related, directly or indirectly, as defined by the facet attribute hierarchy thereby to infer the explicit relationships between the concepts definitions.

21. The computer system of claim 18 wherein the system is configured for assembling the dimensional concept relationships in a dimensional concept hierarchy.

22. The computer system of claim 21 wherein the system is configured for defining a dimensional axis, from one or more facet attributes, with which to generate a dimensional concept hierarchy from the dimensional concept relationships.

23. The computer system of claim 22 wherein the system is configured for defining a plurality of dimensional axes, each axis defined in accordance with respective sets of one or more facet attributes, to define a plurality of dimensional concept hierarchies.

24. The computer system of claim 22 wherein the system is configured for at least one of:

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if all of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions; and

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if a subset of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions.

25. The computer system of claim 22 wherein the system is configured for selecting the one or more facet attributes for defining said dimensional axis, said selecting in accordance with at least one of:

the respective priorities of the facet attributes in the facet attribute hierarchy; and

a particular concept definition comprising the one or more facet attributes to ascribe a particular meaning to said dimensional axis.

26. The computer system of claim 21 wherein the system is configured for evaluating sets of dimensional concept relationships for the presence of indirect relationships and assembling the dimensional concept hierarchy without the indirect relationships.

27. The computer system of claim 21 wherein the system is configured for determining a priority for the concept definitions in the dimensional concept hierarchy based on at least one of priorities of facet attributes in the facet attribute hierarchy and a count of the number of facet attributes in the respective concept definitions of related concepts.

28. The computer system of claim 21 wherein the system is configured for defining a dimensional concept taxonomy by assigning facet attributes to content nodes of a domain to be classified in accordance with concepts associated with the content nodes, said concepts represented by concept definitions in the dimensional concept hierarchy defined using said facet attributes.

29. The computer system of claim 18, wherein the concepts are represented initially by preliminary concept definitions, wherein the relationships between the concepts are represented in an input concept hierarchy and wherein the system is configured for:

revising said preliminary concept definitions, extending the preliminary concept definitions with additional facet attributes in response to whether any two relationships in the input concept hierarchy may be related, directly or indirectly, in a dimensional concept relationship by at least one of explicit relationships and implicit relationships in the faceted data set.

30. The computer system of claim 18 wherein the system is configured for, for a domain to be classified, defining a domain-specific facet attribute hierarchy comprising unique keywords as representative of facet attributes in the domain.

31. The computer system of claim 30 wherein the system is configured for defining a dimensional concept taxonomy for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions, said taxonomy comprising a hierarchy of dimensional concept relationships generated from the concept definitions and the domain-specific facet hierarchy, wherein each concept definition is mapped to one or more representative keywords of the domain-specific facet hierarchy.

32. The computer system of claim 18 wherein the system is configured for defining said dimensional concept relationships for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions.

33. The computer system of claim 32 wherein the system is configured for examining concept nodes for their respective one or more concept definitions.

34. The computer system of claim 32 wherein said defining said dimensional concept relationships for a domain to be classified is limited to processing a localized region of the domain using content nodes proximal to a selected content node.

35. A computer program product storing instructions and data to configure a computer system for performing faceted classification synthesis to relate concepts represented by concept definitions defined in accordance with a faceted data set comprising facets, facet attributes, and facet attribute hierarchies, the instructions and data configuring the computer system for:

expressing dimensional concept relationships between the concept definitions, wherein two concept definitions are determined to be related in a particular dimensional concept relationship by examining whether at least one of explicit relationships and implicit relationships exist in the faceted data set between the respective facet attributes of the two concept definitions.

36. The computer program product of claim 35 wherein the instructions and data configure the computer system for defining the dimensional concept relationships in accordance with intersecting sets of the facet attributes within the concept definitions thereby to infer the implicit relationships between the concepts definitions.

37. The computer program product of claim 35 wherein the instructions and data configure the computer system for defining the dimensional concept relationships in accordance with whether the attributes of the respective concept definitions are related, directly or indirectly, as defined by the facet attribute hierarchy thereby to infer the explicit relationships between the concepts definitions.

38. The computer program product of claim 35 wherein the instructions and data configure the computer system for assembling the dimensional concept relationships in a dimensional concept hierarchy.

39. The computer program product of claim 38 wherein the instructions and data configure the computer system for defining a dimensional axis, from one or more facet attributes, with which to generate a dimensional concept hierarchy from the dimensional concept relationships.

40. The computer program product of claim 39 wherein the instructions and data configure the computer system for defining a plurality of dimensional axes, each axis defined in accordance with respective sets of one or more facet attributes, to define a plurality of dimensional concept hierarchies.

41. The computer program product of claim 39 wherein the instructions and data configure the computer system for at least one of:

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if all of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions; and

relating two concept definitions in a particular dimensional concept relationship, on a particular dimensional axis, if a subset of the facet attributes of a one of the two concept definitions are related to all or a subset of facet attributes of another of the two concept definitions.

42. The computer program product of claim 39 wherein the instructions and data configure the computer system for selecting the one or more facet attributes for defining said dimensional axis, said selecting in accordance with at least one of:

the respective priorities of the facet attributes in the facet attribute hierarchy; and

a particular concept definition comprising the one or more facet attributes to ascribe a particular meaning to said dimensional axis.

43. The computer program product of claim 38 wherein the instructions and data configure the computer system for evaluating sets of dimensional concept relationships for the presence of indirect relationships and assembling the dimensional concept hierarchy without the indirect relationships.

44. The computer program product of claim 38 wherein the instructions and data configure the computer system for determining a priority for the concept definitions in the dimensional concept hierarchy based on at least one of priorities of facet attributes in the facet attribute hierarchy and a count of the number of facet attributes in the respective concept definitions of related concepts.

45. The computer program product of claim 38 wherein the instructions and data configure the computer system for defining a dimensional concept taxonomy by assigning facet attributes to content nodes of a domain to be classified in accordance with concepts associated with the content nodes, said concepts represented by concept definitions in the dimensional concept hierarchy defined using said facet attributes.

46. The computer program product of claim 35, wherein the concepts are represented initially by preliminary concept definitions, wherein the relationships between the concepts are represented in an input concept hierarchy and wherein the instructions and data configure the computer system for:

revising said preliminary concept definitions, extending the preliminary concept definitions with additional facet attributes in response to whether any two relationships in the input concept hierarchy may be related, directly or indirectly, in a dimensional concept relationship by at least one of explicit relationships and implicit relationships in the faceted data set.

47. The computer program product of claim 35 wherein the instructions and data configure the computer system for, for a domain to be classified, defining a domain-specific facet attribute hierarchy comprising unique keywords as representative of facet attributes in the domain.

48. The computer program product of claim 47 wherein the instructions and data configure the computer system for defining a dimensional concept taxonomy for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions, said taxonomy comprising a hierarchy of dimensional concept relationships generated from the concept definitions and the domain-specific facet hierarchy, wherein each concept definition is mapped to one or more representative keywords of the domain-specific facet hierarchy.

49. The computer program product of claim 35 wherein the instructions and data configure the computer system for defining said dimensional concept relationships for a domain to be classified, said domain comprising one or more content nodes each associated with one or more concepts represented by the concept definitions.

50. The computer program product of claim 49 wherein the instructions and data configure the computer system for examining concept nodes for their respective one or more concept definitions.

51. The computer program product of claim 49 wherein said defining said dimensional concept relationships for a domain to be classified is limited to processing a localized region of the domain using content nodes proximal to a selected content node.