Enhanced artificial intelligence language

• US 7,984,005 B2
• Filed: 04/27/2010
• Issued: 07/19/2011
• Est. Priority Date: 03/04/2003
• Status: Active Grant

• Current Assignee: Kurzweil Technologies, Inc.
• Original Assignee: Kurzweil Technologies, Inc.
• Inventors: Bridges, Matthew, Kurzweil, Raymond C.
• Primary Examiner(s): Fernandez Rivas; Omar F
• Application Number:
  US12/768,132
• Publication Number:
  US 20100205140A1
• Time in Patent Office: 448 Days
• Field of Search: None
• US Class Current: 706/45
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154

Abstract

A method of implicitly forming a context in a dialogue with a computer includes forming megacategories linking one or more attributes to one of a plurality of response templates. The method also includes determining a megacategory by comparing attributes having true variables from a previous input to attributes having true variables in the present input and selecting an appropriate response template corresponding to the megacategory.

Claims

1. A method of implicitly forming a context in a dialogue with a computer, comprising:

forming by a computer a plurality of megacategories, with megacategories being combinations of one or more attributes linking to one response template, of a plurality of response templates with each of the plurality of the formed megacategories linked by associated attributes to a corresponding one of the plurality of response templates;

selecting by the computer from the formed megacategories, a suitable megacategory for a present input involved with a dialog with the computer by comparing attributes having true variables from a previous input in the dialog to attributes having true variables in the present input; and

selecting by the computer an appropriate response template corresponding to the selected megacategory.

2. The method of claim 1 wherein each attribute is associated with a set of patterns and each pattern within the set of patterns is semantically equivalent.

3. The method of claim 2, further comprising:

determining by the computer which attributes have patterns that match portions of the present input to the dialogue, each attribute having a variable used to record whether a match exists.

4. The method of claim 3, further comprising:

marking a variable of attributes true, for those attributes having matched patterns.

5. The method of claim 3, further comprising:

storing a list of matched attributes for each user input.

6. A computer program product tangible embodied on a machine-readable storage device the computer program product comprising executable instructions for forming a context in a dialogue with a computer, the instructions causing a machine to:

form megacategories, with megacategories being combinations of one or more attributes linking to one response template, of a plurality of response templates with each of the plurality of the formed megacategories linked by associated attributes to a corresponding one of the plurality of response templates;

select from the formed megacategories a suitable megacategory for a present input involved with a dialog with the machine by comparing attributes having true variables from a previous input to attributes having true variables in the present input; and

select an appropriate response template corresponding to the megacategory.

7. The computer program product of claim 6 wherein each attribute is associated with a set of patterns and each pattern within the set of patterns is semantically equivalent.

8. The computer program product of claim 7, further comprising instructions causing a machine to:

determine which attributes have patterns that match portions of the present input to the dialogue with each attribute having a variable used to record whether a match exists.

9. The computer program product of claim 8, further comprising instructions causing a machine to:

mark a variable of attributes true, for those attributes having matched patterns.

10. The computer program product of claim 8, further comprising:

storing a list of matched attributes for each user input.

11. An apparatus comprising:

a memory that stores executable instructions forming a context in a dialogue with a computer; and

a processor that executes the instructions to;

form megacategories, with megacategories being combinations of attributes linking to one response template of a plurality of response templates with each of the plurality of the formed megacategories linked by associated attributes to a corresponding one of the plurality of response templates;

select from the formed megacategories a suitable megacategory for a present input involved with a dialog with the apparatus by comparing attributes having true variables from a previous input to attributes having true variables in the present input; and

select an appropriate response template corresponding to the megacategory.

12. The apparatus of claim 11 wherein each attribute is associated with a set of patterns and each pattern within the set of patterns is semantically equivalent.

13. The apparatus of claim 12, further comprising instructions to:

determine which attributes have patterns that match portions of a user'"'"'s present input to the dialogue with each attribute having a variable used to record whether a match exists.

14. The apparatus of claim 13, further comprising instructions to:

mark a variable of attributes true, for those attributes having matched patterns.

15. The apparatus of claim 13, further comprising instructions to:

store a list of matched attributes for each user input.