KNOWLEDGE DISCOVERY AGENT SYSTEM AND METHOD

• US 20080016020A1
• Filed: 07/23/2007
• Published: 01/17/2008
• Est. Priority Date: 05/22/2002
• Status: Active Grant

• Current Assignee: Digital Reasoning Systems, Inc (Smarsh Incorporated)
• Original Assignee: Digital Reasoning Systems, Inc (Smarsh Incorporated)
• Inventors: Estes, Timothy
• Granted Patent: US 7,882,055 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

Claims

1. A system for processing information, comprising:

a computer for running software programs in a distributed network, said computer including a processing means in communication with said distributed network;

at least one storage means in communication with said processing means for storing programs and information; and

at least one data agent in said distributed network for conducting a specific response to commands generated by said processing means;

wherein said computer, said at least one storage means, and said at least one data agent are operable for;

learning associations of natural language artifacts in unstructured data sources, wherein said artifacts include at least one of words, phrases, subjects, predicates, modifiers, and other syntactic forms; and

learning semantic and syntactic relationships in structured data sources, wherein said structured data sources are in conventional formats used by relational database systems;

further wherein learned associations resulting from said learning associations of natural language artifacts are formed using grouping of one natural language artifact in an interaction window with another at least one natural language artifact in said interaction window, based on a criteria of shared features of one or more sets from said grouping constituting measurements from said data sources;

further wherein said criteria of shared features are dynamically determined without the use of a priori classifications and using conditional probability constraints between sets of learned associations; and

further wherein said grouping creates a network of conditional probabilities between all encountered natural language artifacts or a subset thereof, determined by consideration of conditional interaction probabilities based on a history of measurements from said data sources.

2. The system of claim 1, further comprising:

means for representing learned associations in a specific format;

wherein said specific format is compatible for operations for mapping between a plurality of data structures and languages comprising one or more of arrays, vector spaces, first order predicate logic, Conceptual Graphs, SQL, and typed programming languages; and

further wherein said typed program languages comprise one or more of Java, C++, and other conventional programming languages.

3. The system of claim 1, further comprising:

means for constructing hierarchies of association across a state space of term usage compatible for interpolation of mapping functions between sets of terms;

wherein said mapping functions include one or more of fuzzy-type, weighted-type, or other types of mapping functions.

4. The system of claim 3, further comprising:

means for generating a structure of mapping functions comprising sets of terms in particular semantic positions;

wherein said structure comprises a formal semantic structure of one or more of programming languages, modal logics, frame systems, and ontologies of objects and relationships.

5. The system of claim 1, further comprising:

means for collecting data input generated by interaction with a human user; and

sensors for learning from said input.

6. The system of claim 5, further comprising:

means for utilizing results of said learning by said sensors to reorganize and alter mapping functions induced from analyzed input; and

means for aligning said mapping functions according to human natural usage information in said results of said learning;

wherein said data input is in the form of structured data or unstructured data.

7. The system of claim 1, further comprising:

a chatbot comprising a chatbot engine for engaging in dialogue with a user through natural language;

a conversational inference module for translating requests from said chatbot to said computer, said at least one storage means, and said at least one data agent; and

at least one data extractor connected to an existing third-party information system and operable for interfacing therewith in response to requests processed by said chatbot and said conversational inference module.

8. The system of claim 7, wherein said existing third-party information system is a medical information system selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care providers network systems.

9. The system of claim 1, said at least one data agent further operable for interfacing with medical information systems selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care provider network systems.

10. The system of claim 1, further comprising:

at least one network data agent, operable for connecting at least one preselected physician information system to at least one health care provider network, and further operable for extracting data from said at least one preselected physician information system and providing said data to said at least one health care provider network.

11. The system of claim 1, said at least one data agent further operable for clustering and visualizing data pertaining to defense intelligence.

12. The system of claim 11, further comprising:

a human analyst of defense intelligence data, wherein said clustering and visualizing are provided to said human analyst as supplemental means for analyzing said defense intelligence data.

13. A method, comprising the steps of:

providing a computer for running software programs in a distributed network, said computer including a processing means in communication with said distributed network;

providing at least one storage means in communication with said processing means for storing programs and information;

providing at least one data agent in said distributed network for conducting a specific response to commands generated by said processing means; and

configuring said computer, said at least one storage means, and said at least one data agent to be operable for;

learning associations of natural language artifacts in unstructured data sources, wherein said artifacts include at least one of words, phrases, subjects, predicates, modifiers, and other syntactic forms; and

learning semantic and syntactic relationships in structured data sources, wherein said structured data sources comprise entities in conventional formats used by relational database systems;

wherein learned associations resulting from said learning associations of natural language artifacts are formed using grouping of one natural language artifact in an interaction window with another at least one natural language artifact in said interaction window, based on a criteria of shared features of one or more sets from said grouping constituting measurements from said data sources;

further wherein said criteria of shared features are dynamically determined without the use of a priori classifications, using conditional probability constraints between sets of learned associations; and

further wherein said grouping creates a network of conditional probabilities between all encountered natural language artifacts or a subset thereof, determined by consideration of conditional interaction probabilities based on a history of measurements from said data sources.

14. The method of claim 13, further comprising the step of:

representing learned associations in a specific format;

wherein said specific format is compatible for operations for mapping between a plurality of data structures and languages comprising one or more of arrays, vector spaces, first order predicate logic, Conceptual Graphs, SQL, and typed programming languages; and

further wherein said typed program languages comprise one or more of Java, C++, and other conventional programming languages.

15. The method of claim 13, further comprising the step of:

constructing hierarchies of association across a state space of term usage compatible for interpolation of mapping functions between sets of terms;

wherein said mapping functions include one or more of fuzzy-type, weighted-type, or other types of mapping functions; and

further wherein said sets of terms have corresponding particular syntactic positions.

16. The method of claim 15, further comprising the step of:

generating a structure of mapping functions composed of sets of terms in particular semantic positions;

wherein said structure is a formal semantic structure of one or more of programming languages, modal logics, frame systems, and ontologies of objects and relationships.

17. The method of claim 13, further comprising the steps of:

collecting data input generated by interaction with a human user; and

learning from said input.

18. The method of claim 17, further comprising the steps of:

utilizing results of said learning to reorganize and alter mapping functions induced from analyzed input; and

aligning said mapping functions according to human natural usage information in said results of said learning;

wherein said input data is in the form of structured information or unstructured information.

19. The method of claim 13, further comprising the steps of:

providing a chatbot comprising a chatbot engine for engaging in dialogue with a user through natural language;

providing a conversational inference module for translating requests from said chatbot to said computer, said at least one storage means, and said at least one data agent;

providing at least one data extractor, for connecting to an existing third-party information system and for interfacing therewith in response to requests processed by said chatbot and said conversational inference module; and

connecting said at least one data extractor to said existing third-party information system.

20. The method of claim 19, wherein said existing third-party information system is a medical information system selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care providers network systems.

21. The method of claim 13, further comprising the step of:

providing at least one network data agent, operable for connecting at least one preselected physician information system to at least one health care provider network, and further operable for extracting data from said at least one preselected physician information system and providing said data to said at least one health care provider network.

22. The method of claim 13, further comprising the step of:

clustering and visualizing data pertaining to defense intelligence.

23. The method of claim 22, further comprising the step of:

providing the results of said clustering and visualizing to a human analyst of defense intelligence data.

24. A dynamic conceptual network system, comprising:

a computer for running software programs in a distributed network, said computer including a processing means in communication with said distributed network;

at least one storage means in communication with said processing means for storing programs and information; and

at least one data agent in said distributed network for conducting a specific response to commands generated by said processing means;

wherein said computer, said at least one storage means, and said at least one data agent are constructed and adapted for learning associations of natural language artifacts in unstructured data sources, wherein said artifacts include at least one of words, phrases, subjects, predicates, modifiers, and other syntactic forms.

25. The dynamic conceptual network system of claim 24, wherein said computer, said at least one storage means, and said at least one data agent are further constructed and adapted for learning semantic and syntactic relationships in structured data sources, and further wherein said structured data sources are in conventional formats used by relational database systems.

26. The dynamic conceptual network system of claim 24,

wherein the learned associations resulting from said learning associations of natural language artifacts are formed using grouping of one natural language artifact in an interaction window with another at least one natural language artifact in said interaction window, based on a criteria of shared features of one or more sets from said grouping constituting measurements from said data sources;

further wherein said criteria of shared features are dynamically determined without the use of a priori classifications and using conditional probability constraints between sets of learned associations; and

further wherein said grouping creates a network of conditional probabilities between all encountered natural language artifacts or a subset thereof, determined by consideration of conditional interaction probabilities based on a history of measurements from said data sources.

27. The dynamic conceptual network system of claim 25,

wherein the learned associations resulting from said learning associations of natural language artifacts are formed using grouping of one natural language artifact in an interaction window with another at least one natural language artifact in said interaction window, based on a criteria of shared features of one or more sets from said grouping constituting measurements from said data sources;

further wherein said criteria of shared features are dynamically determined without the use of a priori classifications and using conditional probability constraints between sets of learned associations; and

further wherein said grouping creates a network of conditional probabilities between all encountered natural language artifacts or a subset thereof, determined by consideration of conditional interaction probabilities based on a history of measurements from said data sources.

28. The dynamic conceptual network system of claim 27, further comprising means for representing learned associations in a specific format;

wherein said specific format is compatible for operations for mapping between a plurality of data structures and languages comprising one or more of arrays, vector spaces, first order predicate logic, Conceptual Graphs, SQL, and typed programming languages; and

further wherein said typed program languages comprise one or more of Java, C++, and other conventional programming languages.

29. The dynamic conceptual network system of claim 27, further comprising means for constructing hierarchies of association across a state space of term usage compatible for interpolation of mapping functions between sets of terms;

wherein said mapping functions include one or more of fuzzy-type, weighted-type, or other types of mapping functions; and

further wherein said sets of terms have corresponding particular syntactic positions.

30. The dynamic conceptual network system of claim 27, further comprising means for generating a structure of mapping functions composed of sets of terms in particular semantic positions;

wherein said structure is a formal semantic structure of one or more of programming languages, modal logics, frame systems, and ontologies of objects and relationships.

31. The dynamic conceptual network system of claim 27, further comprising:

means for collecting data input generated by interaction with a human user;

sensors for learning from said input;

means for utilizing results of said learning by said sensors to reorganize and alter mapping functions induced from analyzed input; and

means for aligning said mapping functions according to human natural usage information in said results of said learning;

wherein said data input is in the form of structured data or unstructured data.

32. The dynamic conceptual network system of claim 27, further comprising:

a chatbot comprising a chatbot engine constructed and adapted for engaging in dialogue with a user through natural language;

a conversational inference module constructed and adapted for translating requests from said chatbot to said computer, said at least one storage means, and said at least one data agent; and

at least one data extractor connected to an existing third-party information system and constructed and adapted for interfacing therewith in response to requests processed by said chatbot and said conversational inference module.

33. The dynamic conceptual network system of claim 27, wherein said existing third-party information system is a medical information system selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care providers network systems.

34. The dynamic conceptual network system of claim 27, further constructed and adapted for interfacing with medical information systems selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care provider network systems.

35. The dynamic conceptual network system of claim 27, further comprising:

at least one network data agent, constructed and adapted for connecting at least one preselected physician information system to at least one health care provider network, and further constructed and adapted for extracting data from said at least one preselected physician information system and providing said data to said at least one health care provider network.

36. The system of claim 27, further constructed and adapted to cluster and visualize data pertaining to defense intelligence and further comprising a human analyst of defense intelligence data, wherein said clustering and visualizing are provided to said human analyst as supplemental means for analyzing data.

37. A method for processing information, comprising the steps of:

providing a computer for running software programs in a distributed network, said computer including a processing means in communication with said distributed network;

providing at least one storage means in communication with said processing means for storing programs and information;

providing at least one data agent in said distributed network for conducting a specific response to commands generated by said processing means;

configuring said computer, said at least one storage means, and said at least one data agent to be operable for;

learning associations of natural language artifacts in unstructured data sources, wherein said artifacts include at least one of words, phrases, subjects, predicates, modifiers, and other syntactic forms; and

learning semantic and syntactic relationships in structured data sources, wherein said structured data sources comprise entities in conventional formats used by relational database systems;

wherein learned associations resulting from said learning associations of natural language artifacts are formed using grouping of one natural language artifact in an interaction window with another at least one natural language artifact in said interaction window, based on a criteria of shared features of one or more sets from said grouping constituting measurements from said data sources;

further wherein said criteria of shared features are dynamically determined without the use of a priori classifications, using conditional probability constraints between sets of learned associations; and

further wherein said grouping creates a network of conditional probabilities between all encountered natural language artifacts or a subset thereof, determined by consideration of conditional interaction probabilities based on a history of measurements from said data sources.

38. The method of claim 37, further comprising the step of:

representing learned associations in a specific format;

wherein said specific format is compatible for operations for mapping between a plurality of data structures and languages comprising one or more of arrays, vector spaces, first order predicate logic, Conceptual Graphs, SQL, and typed programming languages; and

further wherein said typed program languages comprise one or more of Java, C++, and other conventional programming languages.

39. The method of claim 37, further comprising the step of:

constructing hierarchies of association across a state space of term usage compatible for interpolation of mapping functions between sets of terms, wherein said mapping functions include one or more of fuzzy-type, weighted-type, or other types of mapping functions, wherein said sets of terms have corresponding particular syntactic positions; and

generating a structure of mapping functions composed of sets of terms in particular semantic positions, wherein said structure is a formal semantic structure of one or more of programming languages, modal logics, frame systems, and ontologies of objects and relationships.

40. The method of claim 37, further comprising the steps of:

collecting data input generated by interaction with a human user;

learning from said input;

utilizing results of said learning to reorganize and alter mapping functions induced from analyzed input; and

aligning said mapping functions according to human natural usage information in said results of said learning;

wherein said input data is in the form of structured information or unstructured information.

41. The method of claim 37, further comprising the steps of:

providing a chatbot comprising a chatbot engine for engaging in dialogue with a user through natural language;

providing a conversational inference module for translating requests from said chatbot to said computer, said at least one storage means, and said at least one data agent;

providing at least one data extractor, for connecting to an existing third-party information system and for interfacing therewith in response to requests processed by said chatbot and said conversational inference module; and

connecting said at least one data extractor to said existing third-party information system;

wherein said existing third-party information system is a medical information system selected from the group comprising physician offices systems, hospital systems, corporate systems, and health care providers network systems.

42. The method of claim 37, further comprising the step of:

providing at least one network data agent for connecting at least one preselected physician information system to at least one health care provider network, and further operable for extracting data from said at least one preselected physician information system and providing said data to said at least one health care provider network.

43. The method of claim 37, further comprising the steps of:

clustering and visualizing data pertaining to defense intelligence; and

providing the results of said clustering and visualizing to a human analyst of defense intelligence data.