Methods and apparatus for storing and retrieving knowledge

• US 6,823,325 B1
• Filed: 11/22/2000
• Issued: 11/23/2004
• Est. Priority Date: 11/23/1999
• Status: Expired due to Fees

• Current Assignee: Hyperknowledge Management Services AG
• Original Assignee: Trevor Davies
• Inventors: Hanlon, Mark D., Davies, Trevor B., Tromans, Christopher R.
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US09/721,473
• Time in Patent Office: 1,462 Days
• Field of Search: 706/50, 706/61, 703/22, 707/4, 715/531
• US Class Current: 706/50
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 9/453 Help systems

Abstract

Apparatus for storing and retrieving knowledge includes a natural language parser, a knowledge research agent, and a directional (compass) search agent. Methods for storing and retrieving knowledge can include directional searching which combines a query text with a relationship to search, and automated knowledge model construction based upon contents of an existing knowledge model and external information searches.

Claims

1. A computer-implemented system for storing and retrieving knowledge, comprising:

a processor executing a sequence of instructions, and a memory, the sequence of instructions defining;

a text analyzer having an input which receives a signal representing information expressed as natural language and which produces at an output a signal representing annotated information;

a parser having an input which receives the annotated information signal from the text analyzer and which produces and stores in the memory a linked knowledge model thereof; and

a user interface presenting at least one pair of complementary relationships to an operator, through which the operator can navigate the linked knowledge model to retrieve knowledge;

wherein

the linked knowledge model includes a first node defining a first task and a second node defining a second task, each stored in the memory, the first node and the second node forward and backward linked to each other, the first task defining why the second task is performed and the second task defining how the first task is performed.

2. The system of claim 1, further comprising:

a knowledge research agent having an input receiving the linked knowledge model and having an output on which the knowledge research agent produces a query compatible with an external search engine.

3. The system of claim 2, wherein the hyperknowledge agent automatically augments the linked knowledge model with new information found by executing the query on the external search engine.

4. The system of claim 1, the parser further comprising:

a rules engine executing a plurality of rules defining a structure of knowledge embedded in information expressed in natural language.

5. The system of claim 4, the linked knowledge model including connected noun/verb phrase pairs, and wherein the plurality of rules define how sentences in natural language relate to connected noun/verb phrase pairs in the linked knowledge model.

6. The system of claim 5, wherein the rules include at least one semantic rule.

7. The system of claim 5, wherein the rules include at least one syntactic rule.

8. The system of claim 5, wherein the rules include at least one context rule.

9. A computer-implemented method for retrieving knowledge from a computer memory, comprising:

presenting on a computer display to an operator a selector by which the operator indicates one of a pair of complementary relationships and a query input by which the operator indicates query text; and

combining the one of the pair of complementary relationships indicated and the query text to form a query signal by which knowledge is retrieved from the computer memory having the knowledge stored therein.

10. The method of claim 9, wherein the selector defines four directions characterized by complementary pairs of directions, each direction representing a relationship.

11. The method of claim 10, wherein the selector is presented in a graphical form resembling a compass rose.

12. The method of claim 9, further comprising:

storing knowledge in a linked knowledge model including noun/verb phrase pairs;

searching the linked knowledge model for a first noun/verb phrase pair defined by the query text; and

retrieving a second noun/verb phrase pair from the linked knowledge model bearing the indicated one of the pair of complementary relationships to the first noun/verb phrase pair.

13. The method of claim 12, wherein searching further comprises:

parsing a natural language query text into a searchable boolean expression.

14. A method for storing knowledge, comprising:

parsing a natural language document into a linked knowledge model including connected noun/verb phrase pairs;

identifying portions of the linked knowledge model in which a level of knowledge represented is lower relative to other portions of the linked knowledge model; and

executing searches of external information for additional knowledge related to the identified portions of the linked knowledge model.

15. The method of claim 14, wherein the identified portions of the linked knowledge model include a first noun/verb phrase pair lacking a second noun/verb phrase pair related by at least one of two complementary relationships defined between noun/verb phrase pairs.

16. A software product including a machine readable medium on which is encoded a sequence of software instructions which when executed direct performance of a method comprising:

storing in a computer memory a linked knowledge model;

presenting on a computer-controlled display, to an operator, a selector by which the operator, indicates one of a pair of complementary relationships and a query input by which the operator indicates query text;

combining the one of the pair of complementary relationships indicated and the query text to form a query by which knowledge is retrieved from the linked knowledge model stored in the computer memory, and

displaying the retrieved knowledge on the computer-controlled display.

17. The software product of claim 16, wherein the selector defines four directions characterized by complementary pairs of directions, each direction representing a relationship.

18. The software product of claim 16, wherein the selector is presented in a graphical form resembling a compass rose.

19. The software product of claim 16, further comprising:

storing nodes of the linked knowledge model as noun/verb phrase pairs;

searching the linked knowledge model for a first noun/verb phrase pair defined by the query text; and

retrieving a second noun/verb phrase pair from the linked knowledge model bearing the indicated one of the pair of complementary relationships to the first noun/verb phrase pair.

20. The software product of claim 16, wherein searching further comprises:

parsing a natural language query text into a searchable boolean expression.

21. A software product including a machine readable medium on which is encoded a sequence of software instructions which when executed direct performance of a method comprising:

receiving a signal representing a natural language document,

parsing the natural language document into a linked knowledge model including connected noun/verb phrase pairs;

storing the linked knowledge model in a computer memory;

identifying, by comparing numbers of links, portions of the linked knowledge model in which a degree of knowledge represented is lesser relative to other portions of the linked knowledge model; and

executing computer-implemented searches of external computer memories in which are stored additional information for additional knowledge related to the identified portions of the linked knowledge model.

22. The software product of claim 21, wherein the identified portions of the linked knowledge model include a first noun/verb phrase pair lacking a second noun/verb phrase pair related by at least one of two complementary relationships defined between noun/verb phrase pairs.