Method, system, and computer program for user-driven dynamic generation of semantic networks and media synthesis

• US 8,676,722 B2
• Filed: 05/01/2009
• Issued: 03/18/2014
• Est. Priority Date: 05/01/2008
• Status: Active Grant

• Current Assignee: Primal Fusion Inc.
• Original Assignee: Primal Fusion Inc.
• Inventors: Black, Alexander David, Sweeney, Peter, Good, Robert, Barlow-Busch, Robert
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): SITIRICHE, LUIS A
• Application Number:
  US12/671,846
• Publication Number:
  US 20100235307A1
• Time in Patent Office: 1,782 Days
• Field of Search: None
• US Class Current: 706/12
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

This invention relates generally to classification systems. More particularly this invention relates to a system, method, and computer program to dynamically generate a domain of information synthesized by a classification system or semantic network. The invention discloses a method, system, and computer program providing a means by which an information store comprised of knowledge representations, such as a web site comprised of a plurality of web pages or a database comprised of a plurality of data instances, may be optimally organized and accessed based on relational links between ideas defined by one or more thoughts identified by an agent and one or more ideas embodied by the data instances. Such means is hereinafter referred to as a “thought network”.

Claims

1. A computer implemented method for generating a semantic network, the method comprising:

representing an information domain as a data set, the data set being defined by data entities and one or more relationships between the data entities;

receiving a text query from a human user; and

synthesizing, or facilitating the synthesizing of, by one or more computer processors, a semantic network in response to the text query, the synthesizing comprising;

translating the text query from the human user into an active concept;

including the active concept as a node in the semantic network;

deriving relationships between the active concept and selected data entities from the information domain; and

populating the semantic network at least in part with the selected data entities from the information domain and the derived relationships between the selected data entities and the active concept.

2. The computer implemented method of claim 1, further comprising enabling one or more of:

(a) interactions between the data entities and data received from the human user; and

(b) interactions between the human user and the data entities based on the data received from the human user,

by one or more synthesis operations.

3. The computer implemented method of claim 1, further comprising integrating the active concept from the text query with the data entities.

4. The computer implemented method of claim 1, further comprising providing the human user with means to traverse the semantic network by selecting data entities related to the active concept.

5. The computer implemented method of claim 1, further comprising synthesizing the semantic network dynamically in response to the text query received from the human user.

6. The computer implemented method of claim 4, further comprising storing one or more aspects of learning derived from the semantic network to a storage medium.

7. The computer implemented method of claim 6, further comprising basing the learning on selecting the data entities related to active concept.

8. The computer implemented method of claim 6, further comprising storing the one or more aspects of learning for use in dynamic generation of one or more other semantic networks.

9. The computer implemented method of claim 6, further comprising storing concepts of the semantic network to the storage medium.

10. The computer implemented method of claim 9, further comprising storing relationships between the concepts in the storage medium.

11. The computer implemented method of claim 1, wherein translating the query comprises label-to-concept translation.

12. The computer implemented method of claim 11, wherein the label-to-concept translation comprises defining a label representing the text query, and generating from the label a representation of the active concept.

13. The computer implemented method of claim 12, wherein the defining the label comprises:

(a) allowing the human user to define the label;

or

(b) obtaining the label from another knowledge representation.

14. The computer implemented method of claim 11, further comprising applying the label-to-concept translation to synthesizing the semantic network by:

separating the label into one or more word components thereof;

obtaining from the information domain a plurality of keywords associated with the one or more word components;

ranking the keywords based on matching of the keywords with the one or more word components; and

creating concept definitions based on the ranking of the keywords.

15. The computer implemented method of claim 1, further comprising allowing the human user to specify one or more parameters to limit the synthesis of the semantic network being generated.

16. The computer implemented method of claim 15, wherein the one or more parameters are selected from the group consisting of a domain, an axis direction, one or more maximum degrees of separation, one or more maximum degrees of depth, and a maximum number of network nodes.

17. The computer implemented method of claim 1, further comprising storing the data set to a storage medium, wherein the data set includes means to create a semantic network.

18. The computer implemented method of claim 17, further comprising first encoding the data entities, the relationships, and labels, prior to storing the data set to the storage medium.

19. The computer implemented method of claim 1, further comprising allowing one or more cognitive agents to select one or more parts of the data set to populate one or more domains.

20. The computer implemented method of claim 1, further comprising synthesizing a second semantic network based on the data entities and relationships in the information domain.

39. The computer implemented method of claim 1, wherein the data entities comprise media or content.

40. The computer implemented method of claim 39, wherein the content comprises text, audio, images, and/or video.

41. The computer implemented method of claim 1, wherein the act of synthesizing a semantic network comprises facilitating acquisition of, storage of, and recollection of the active concept and/or existing synthesized semantic networks related to the active concept.

42. The computer implemented method of claim 1, wherein synthesizing the semantic network comprises creating both nodes and edges to complement reasoning across existing semantic networks.

43. The computer implemented method of claim 1, wherein the synthesizing comprises acquiring source material from any number of information domains.

44. The computer implemented method of claim 1, further comprising dynamically synthesizing new semantic networks using aggregations of data sets.

21. A computer system for generating a semantic network, the computer system comprising:

(a) one or more computers configured to receive a text query from a human user and to provide, or provide access to, an information domain represented by a data set defined by data entities and one or more relationships between the data entities; and

(b) a thought processor operable to synthesize, or facilitate the synthesis of, by one or more computer processors, a semantic network in response to the text query, the synthesis comprising;

translating the text query from the human user into an active concept;

including the active concept as a node in the semantic network;

deriving relationships between the active concept and selected data entities from the information domain; and

populating the semantic network at least in part with the selected data entities from the information domain and the derived relationships between the selected data entities and the active concept.

22. The computer system of claim 21, wherein the thought processor is operable to synthesize the semantic network dynamically upon receiving the text query from the human user to facilitate new mappings.

23. The computer system of claim 22, wherein the new mappings provide one or more of the following:

basic lookup functions;

attribute hierarchy;

or concept matching.

24. At least one non-transitory computer-readable medium storing computer instructions that, when executed by one or more computer processors, perform a method for enabling generation of a semantic network accessible through a web interface that enables a human user to initiate one or more computers to generate the semantic network, the method comprising:

(a) obtaining, or obtaining access to, an information domain, the information domain being represented by a data set representing the information domain, the data set being defined by data entities and one or more relationships between the data entities;

(b) receiving a text query from the human user; and

(c) synthesizing a semantic network in response to the text query, the synthesizing comprising;

translating the text query from the human user into an active concept;

including the active concept as a node in the semantic network;

deriving relationships between the active concept and selected data entities from the information domain; and

populating the semantic network at least in part with the selected data entities from the information domain and the derived relationships between the selected data entities and the active concept.

25. The at least one non-transitory computer-readable medium of claim 24, wherein the web interface is provided by a web application.

26. A computer implemented method for synthesizing media utilizing a semantic network, the method comprising:

(a) generating, or facilitating the generation of, by one or more computer processors, a thought network including;

an active concept translated from a text query received from a human user, selected data entities from an information domain, and relationships derived between the active concept and the selected data entities, the generating comprising;

including the active concept as a node in the thought network, and

populating the thought network at least in part with the selected data entities from the information domain and the derived relationships between the active concept and the selected data entities; and

(b) transforming the thought network to generate and provide one or more forms of synthesized media to the human user.

27. The computer implemented method of claim 26, further comprising providing client-directed synthesized media based on a consumer-directed interaction whereby the consumer performs one of the following steps:

(a) providing input to direct the generation of the synthesized media;

or

(b) selecting synthesized media from the one or more forms provided.

28. The computer implemented method of claim 26, wherein the synthesized media is web-integrable media.

29. The computer implemented method of claim 26, further comprising storing the synthesized media as a content inventory.

30. The computer implemented method of claim 26, wherein the transforming comprises auto-generation of synthesized media, wherein the auto-generation does not involve consumer interaction or input.

31. The computer implemented method of claim 26, wherein the synthesized media is produced in batches.

32. The computer implemented method of claim 26, further comprising regenerating synthesized media after consumer interaction or input.

33. The computer implemented method of claim 30, wherein auto-generation is facilitated by utilization of a surrogate measure for direction provided by the consumer.

34. The computer implemented method of claim 26, further comprising re-using static data as building blocks for an instantaneous generation of synthesized media based entirely on consumer input.

35. The computer implemented method of claim 26, wherein the transforming is performed by one or more software agents.

36. The computer implemented method of claim 26, further comprising providing a user interface for the consumer to input or select content elements.

37. The computer implemented method of claim 26, further comprising making the generated media available for the consumer to display, export and edit.

38. The computer implemented method of claim 26, further comprising integrating the generated media with mass market networks.

45. The computer implemented method of claim 33, wherein utilizing the surrogate measure comprises utilizing an existing media source.