System, method, and product of manufacture for implementing an EAIL (enhanced artificial intelligence language) engine

• US 7,337,157 B2
• Filed: 02/19/2003
• Issued: 02/26/2008
• Est. Priority Date: 02/19/2003
• Status: Active Grant

• Current Assignee: Kurzweil Technologies, Inc.
• Original Assignee: Kurzweil Technologies, Inc.
• Inventors: Kurzweil, Raymond C., Bridges, Matthew
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US10/370,051
• Publication Number:
  US 20040162797A1
• Time in Patent Office: 1,833 Days
• Field of Search: 706/45, 706/46, 706/48, 704/8, 704/9, 704/275, 715/727
• US Class Current: 706/45
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems

Abstract

A method of forming a knowledge base for processing an input includes linking a plurality of attributes to a plurality of response templates using a plurality of Boolean expressions. Each attribute includes a set of patterns where each pattern within the set is equivalent.

Claims

1. A computer implemented method of producing a knowledge base that receives a user input and applies the user input to the knowledge base to generate an appropriate response from the knowledge base, the method comprising:

linking a plurality of attributes to a plurality of response templates using a plurality of Boolean expressions, with each attribute including a set of patterns, each pattern within the set being expressions that are semantically equivalent.

2. The method of claim 1 wherein expressions in the patterns are not syntactically equivalent.

3. The method of claim 1 wherein linking the plurality of attributes to the plurality of response templates comprises:

forming a megacategory, the megacategory links a combination of attributes to one of the plurality of response templates using one of the plurality of Boolean expressions.

4. The method claim 1 wherein linking the plurality of attributes to the plurality of response templates comprises:

forming a megacategory, the megacategory links one of the plurality of attributes to one of the plurality of response templates.

5. The method of claim 3 wherein the combination of attributes using one of the plurality of Boolean expressions comprises:

a name for each attribute in the combination; and

an operator.

6. The method of claim 5 wherein the operator is a logical AND operator.

7. The method of claim 3, wherein the megacategory comprises a “

that”

tag containing a pattern that is syntactically equivalent to patterns within the attributes.

8. The method of claim 3 wherein the megacategory comprises:

a hierarchy of levels of megacategories to facilitate matching the megacategory to the input.

9. The method of claim 3, further comprising:

grouping a plurality of megacategories into a topic having a topic name; and

adding a topic variable to one of the plurality of response templates.

10. The method of claim 9, further comprising:

matching a megacategory to the input when the topic name matches the topic variable.

11. The method of claim 1, further comprising:

storing the plurality of attributes and the plurality of response templates.

12. The method of claim 1, further comprising:

converting an AIML category having one pattern and one response template to an equivalent combination of one attribute and one megacategory, the one megacategory comprising the one response template; and

storing the equivalent combination.

13. An article comprising a machine-readable medium that stores executable instructions for forming a knowledge base for processing an input, the instructions causing a machine to:

link a plurality of attributes to a plurality of response templates using a plurality of Boolean expressions, each attribute including a set of patterns, with each pattern within the set being semantically equivalent.

14. The article of claim 13 wherein the patterns are not syntactically equivalent.

15. The article of claim 13 wherein the instructions causing a machine to link the plurality of attributes to the plurality of response templates comprises the instructions causing a machine to:

form a megacategory, the megacategory linking a combination of attributes to one of the plurality of response templates using one of the plurality of Boolean expressions.

16. The article of claim 13 wherein the instructions causing a machine to link the plurality of attributes to the plurality of response templates comprises instructions causing a machine to:

form a megacategory, the megacategory linking one of the plurality of attributes to one of the plurality of response templates.

17. The article of claim 15 wherein the combination of attributes using one of the plurality of Boolean expressions comprises:

a name for each attribute in the combination; and

an operator.

18. The article of claim 17 wherein the operator is a logical AND operator.

19. The article of claim 15, wherein the megacategory comprises a “

that”

tag containing a pattern that is syntactically equivalent to patterns within the attributes.

20. The article of claim 15 wherein the megacategory comprises:

a hierarchy of levels of megacategories to facilitate -matching the megacategory to the input.

21. The article of claim 15, further comprising instructions causing a machine to:

group a plurality of megacategories into a topic having a topic name; and

add a topic variable to one of the plurality of response templates.

22. The article of claim 21, further comprising instructions causing a machine to:

match a megacategory to the input when the topic name matches the topic variable.

23. The article of claim 13, further comprising instructions causing a machine to:

store the plurality of attributes and the plurality of response templates.

24. The article of claim 13, further comprising instructions causing a machine to:

convert an AIML category having one pattern and one response template to an equivalent combination of one attribute and one megacategory, the one megacategory comprising the one response template; and

store the equivalent combination.

25. An apparatus comprising:

a memory that stores executable instructions for a knowledge base for processing an input; and

a processor that executes the instructions to;

link a plurality of attributes to a plurality of response templates using a plurality of Boolean expressions, each attribute including a set of patterns, each pattern within the set being semantically equivalent.

26. The apparatus of claim 25 wherein the patterns are not syntactically equivalent.

27. The apparatus of claim 25 wherein instructions to link the plurality of attributes to the plurality of response templates comprises instructions to:

form a megacategory, the megacategory linking a combination of attributes to one of the plurality of response templates using one of the plurality of Boolean expressions.

28. The apparatus of claim 27, wherein the megacategory comprises a “

that”

tag containing a pattern that is syntactically equivalent to patterns within the attributes.

29. The apparatus of claim 27 wherein the megacategory comprises:

a hierarchy of levels of megacategories to facilitate matching the megacategory to the input.

30. The apparatus of claim 27, further comprising instructions to:

group a plurality of megacategories into a topic having a topic name; and

add a topic variable to one of the plurality of response templates.

31. The apparatus of claim 30, further comprising instructions to:

match a megacategory to the input when the topic name matches the topic variable.

32. The apparatus claim 25 wherein instructions to link the plurality of attributes to the plurality of response templates comprises instructions to:

form a megacategory, the megacategory linking one of the plurality of attributes to one of the plurality of response templates.

33. The apparatus of claim 32 wherein the combination of attributes using one of the plurality of Boolean expressions comprises:

a name for each attribute in the combination; and

an operator.

34. The apparatus of claim 33 wherein the operator is a logical AND operator.

35. The apparatus of claim 25, further comprising instructions to:

store the plurality of attributes and the plurality of response templates.

36. The apparatus of claim 25, further comprising instructions to:

convert an AIML category having one pattern and one response template to an equivalent combination of one attribute and one megacategory, the one megacategory comprising the one response template; and

store the equivalent combination.