System and method for identifying the context of a statement made to a virtual robot

• US 6,314,410 B1
• Filed: 04/27/1998
• Issued: 11/06/2001
• Est. Priority Date: 06/04/1997
• Status: Expired due to Term

• Current Assignee: Micro Focus LLC (Open Text Corporation)
• Original Assignee: NativeMinds, Inc. (Healthstream Incorporated)
• Inventors: Benson, Scott S., Dillinger, Ray S., Tackett, Walter A.
• Primary Examiner(s): Powell, Mark R.
• Assistant Examiner(s): Holmes, Michael B.
• Application Number:
  US09/067,322
• Time in Patent Office: 1,289 Days
• Field of Search: 706/11, 706/45-47, 706/50, 706/927
• US Class Current: 706/11
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]

Abstract

In an automated interface program designed to interact and communicate with users, said program executing actions when a category among a predefined set of categories is activated, a method is disclosed for interpreting the context of a user input, the steps of said method comprising: associating subjects with categories; maintaining a list of the subjects associated with the most recently activated category; testing conditions in categories such that the condition is true if the comprises at least one subject in common with said list of subjects; and activating a set of categories, said set comprising those categories whose conditions are satisfied based on the list of subjects.

Claims

1. A method for testing the context of an input when selecting a set of categories to activate in an automated interface program designed to interact and communicate with users, said method comprising:

(a) defining at least one category associated with actions executed by the automated interface program during interaction with a user, wherein one or more subjects may be associated with the at least one category, and wherein the at least one category includes a focused condition;

(b) maintaining a list of the subjects associated with the most recently activated set of categories;

(c) receiving natural language input from a user;

(d) activating a category if the focused condition of the category matches the input and the subject associated with the category is on the list of the subjects associated with the most recently activated set of categories; and

(e) selecting one or more activated categories for execution by the automated interface program.

2. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein step (a) further comprises:

associating subject keywords with categories by including said keywords in a script language defining said categories.

3. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein step (b) further comprises:

(i) upon a user input, finding the set of activated categories; and

(ii) finding the set of subject keywords associated with said set of categories found in step (i).

4. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein said set of categories further comprises priority categories.

5. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein said set of categories further comprises default categories.

6. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein said set of categories further comprises standard categories.

7. The method for testing the context of an input when selecting a set of categories to activate as recited in claim 1 wherein the step of testing conditions in said categories further comprises:

testing each said category having said condition in order of execution.

8. A system for testing the context of an input when selecting a set of categories to activate in an automated interface program designed to interact and communicate with users, said system comprising:

(a) means for defining at least one category associated with actions executable by the automated interface program during interaction with a user, wherein one or more subjects may be associated with the at least one category, and wherein the at least one category includes a focused condition;

(b) means for maintaining a list of the subjects associated with the most recently activated set of categories;

(c) means for receiving natural language input from a user;

(d) means for activating a category if the focused condition of the category matches the input and the subject associated with the category is on the list of the subjects associated with the most recently activated set of categories; and

(e) means for selecting one or more activated categories for execution by the automated interface program.

9. A mechanism for placing conditions within scripts defining categories that allow the BOT to determine whether a particular category is appropriate to a current conversation with a user, said mechanism comprising:

(a) means for including said conditions in a BOT script defining a category associated with actions executable by the automated interface program during interaction with a user, wherein one or more subject keywords may be associated with the category, said conditions relating subject keywords to said category;

(b) means for maintaining an active subjects list comprising subject keywords associated with categories;

(c) means for activating one or more categories upon a user input when conditions associated with actions associated with the one or more categories are satisfied, wherein said conditions are satisfied if a subject keyword associated with a category matches a subject keyword on the active subjects list; and

(d) means for selecting one or more activated categories for execution by the automated interface program.

10. A method for identifying the context of input received from a user in an automated interface program, wherein the context of the received user input influences the generation of contextually pertinent output in the automated interface program, the method comprising:

defining at least one category associated with actions executable by the automated interface program during interaction with a user, wherein one or more subjects may be associated with the at least one category;

maintaining an active subject list comprising subjects associated with the at least one category;

receiving user input;

activating the at least one category if the at least one category matches the received user input, wherein the activation of the at least one category is influenced by an association of the at least one category with a subject on the active subject list;

updating the active subject list; and

selecting one or more activated categories for execution by the automated interface program.

11. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein the step of updating the active subject list further comprises adding subjects associated with activated categories to the active subject list.

12. The method for identifying the context of input received from a user in an automated interface program as recited in claim 11, wherein the step of updating the active subject list further comprises clearing the active subject list prior to updating the active subject list.

13. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein the step of defining at least one category further comprises defining a priority category type wherein a priority category is examined before categories of other types.

14. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein the step of defining at least one category further comprises defining a default category type wherein a default category is examined after categories of other types.

15. The method for identifying the context of input received from a user in an automated interface program as recited in claim 14, wherein a default category is examined if no actions are executed in association with another category.

16. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein the step of defining at least one category further comprises defining a standard category type, wherein a standard category is examined after all priority categories are examined and before any default category is examined.

17. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein the step of defining at least one category further comprises defining a sequence category type, wherein a sequence category is examined only when a request to examine the sequence category is executed in association with another category.

18. The method for identifying the context of input received from a user in an automated interface program as recited in claim 17, further comprising the steps of:

executing one or more actions associated with an examined sequence category;

receiving additional user input;

examining one or more priority categories in response to the additional user input, wherein actions associated with a priority category that matches the additional user input are executed; and

executing one or more unexecuted actions associated with the examined sequence category.

19. The method for identifying the context of input received from a user in an automated interface program as recited in claim 17, further comprising the steps of:

executing one or more actions associated with an examined sequence category;

identifying a second category that matches a natural language component within the natural language input;

executing one or more actions associated with the second category; and

executing one or more unexecuted actions associated with the examined sequence category.

20. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, further comprising the step of maintaining a category data structure comprising category entries, wherein a category entry is associated with the at least one category and includes subjects associated with the at least one category.

21. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein updating the active subject list further comprises maintaining the current state of the active subject list when there are no subjects associated with categories activated by the received user input.

22. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein an action associated with the at least one category and executable by the automated interface program may comprise an explicit focusing mechanism.

23. The method for identifying the context of input received from a user in an automated interface program as recited in claim 22, wherein the explicit focusing mechanism may comprise a focus command associated with a category.

24. The method for identifying the context of input received from a user in an automated interface program as recited in claim 23, wherein the step of updating the active subjects list further comprises adding to the active subjects list subjects associated with a category associated with an executed focus command.

25. The method for identifying the context of input received from a user in an automated interface program as recited in claim 22, wherein the explicit focusing mechanism may comprise a focus subjects command associated with one or more subjects.

26. The method for identifying the context of input received from a user in an automated interface program as recited in claim 25, wherein the step of updating the active subjects list further comprises adding to the active subjects list the subjects associated with an executed focus subjects command.

27. The method for identifying the context of input received from a user in an automated interface program as recited in claim 25, wherein the step of updating the active subjects list further comprises adding subjects associated with categories associated with the one or more subjects associated with an executed focus subjects command.

28. The method for identifying the context of input received from a user in an automated interface program as recited in claim 10, wherein an executable action associated with the at least one category may be associated with a condition, wherein the condition is associated with a specificity value, wherein the specificity value influences the selection of activated categories for execution by the automated interface program.

29. The method for identifying the context of input received from a user in an automated interface program as recited in claim 28, wherein the condition may comprise a focused condition, wherein a focused condition is true if one or more subjects associated with the at least one category are included in the active subjects list.

30. The method for identifying the context of input received from a user in an automated interface program as recited in claim 29, wherein the specificity value of a focused condition is influenced by the number of subjects associated with the category associated with the focused condition that also appear in the subjects included in the active subjects list.

31. A system for identifying the context of input received from a user in an automated interface program, wherein the context of the received user input influences the generation of contextually pertinent output in the automated interface program, the system comprising:

an interface configured to receive input from a user;

an active subject list comprising a data structure having zero or more subjects;

a processor comprising a computer useable medium including computer readable program code embodied in the medium configured to interact with a user, the computer readable program code including;

computer readable program code configured to define at least one category associated with actions executable by the automated interface program during interaction with a user, wherein one or more subjects may be associated with the at least one category;

computer readable program code configured to activate at least one category if the at least one category matches the received user input, wherein the activation of the at least one category is influenced by an association of the at least one category with a subject on the active subject list;

computer readable program code configured to update the active subject list; and

computer readable program code configured to select one or more activated categories for execution by the automated interface program.

32. A computer program product for identifying the context of input received from a user in an automated interface program, wherein the context of the input influences the generation of contextually pertinent output in the automated interface program, the computer program product comprising:

an interface configured to receive input from a user;

an active subject list comprising a data structure having zero or more subjects;

computer readable program code configured to define the at least one category associated with actions executable by the automated interface program during interaction with a user,

computer readable program code configured to activate the at least one category if the at least one category matches the received user input, wherein the activation of the at least one category may be influenced by an association of the at least one category with a subject on the active subject list;

computer readable program code configured to update the active subject list; and

computer readable program code configured to select one or more activated categories for execution by the automated interface program.