Systems and methods for predicting consequences of misinterpretation of user commands in automated systems

• US 20060167696A1
• Filed: 01/27/2005
• Published: 07/27/2006
• Est. Priority Date: 01/27/2005
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: International Business Machines Corporation
• Inventors: Viswanathan, Mahesh, Kanevsky, Dimitri, Sicconi, Roberto, Chaar, Jarir Kamel
• Granted Patent: US 7,437,297 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Systems and methods are provided for processing and executing commands in automated systems. For example, command processing systems and methods are provided which can automatically determine, evaluate or otherwise predict consequences of execution of misrecognized or misinterpreted user commands in automated systems and thus prevent undesirable or dangerous consequences that can result from execution of misrecognized/misinterpreted commands.

Claims

1. A method for processing commands in an automated system, comprising:

receiving a user command;

processing the user command;

evaluating consequences of executing the user command based on command processing results; and

performing a preventative action if it is determined that execution of the user command could result in an undesirable consequence.

2. The method of claim 1, wherein processing the user command comprises interpreting the user command.

3. The method of claim 2, wherein processing further comprises determining a degree of ambiguity of interpretation of the user command.

4. The method of claim 3, further comprising confirming the accuracy of the user command as interpreted, if the degree of ambiguity of interpretation is not acceptable.

5. The method of claim 4, wherein confirming the accuracy of the user command comprises automatically re-interpreting the user command using another interpretation process.

6. The method of claim 4, wherein confirming the accuracy of the user command comprises querying the user for confirmation.

7. The method of claim 3, further comprising the step of executing the user command as interpreted if the degree of ambiguity of interpretation is acceptable.

8. The method of claim 1, wherein evaluating consequences of executing the user command comprises:

determining a potential consequence of executing the user command;

determining a likelihood that the potential consequence can actually occur; and

classifying an impact of the potential consequence based on the determined likelihood that the potential consequence can actually occur.

9. The method of claim 8, wherein determining a likelihood comprises:

receiving information that indicates current environmental conditions;

determining a relation, if any, between the potential consequence and the current environmental conditions; and

determining a likelihood that the potential consequence can actually occur based on related current environmental conditions.

10. The method of claim 1, wherein processing the user command comprises determining a plurality of alternative interpretations of the user commands and a likelihood measure of each alternative interpretation.

11. The method of claim 1, wherein performing a preventative action comprises automatically generating an alert signal or notification message to provide notification of the undesirable consequence of executing the user command.

12. The method of claim 1, wherein performing a preventative action comprises generating a user query to obtain clarification of the user command.

13. The method of claim 12, wherein generating a user query comprises compiling a question to request user confirmation of the user command as interpreted or an alternative interpretation of the user command.

14. The method of claim 1, wherein performing a preventative action comprises preventing execution of the command if it is determined that execution of the user command could result in a consequence that does not meet a predetermined threshold of desirability.

15. The method of claim 1, wherein performing a preventative action comprises automatically re-processing the user command using one or more additional data processing modes.

16. The method of claim 1, wherein performing a preventative action comprises executing the command regardless of the undesirable consequence and providing an alert or notification of the undesirable consequence substantially contemporaneously with execution of the command.

17. The method of claim 1, wherein interpreting the user request comprises performing speech recognition to process a voice command.

18. The method of claim 1, wherein interpreting the user command comprises performing natural language understanding to process a voice command.

19. The method of claim 1, wherein interpreting the user command comprises performing a user state recognition process to evaluate the user'"'"'s state.

20. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for processing commands in an automated system, the method steps comprising:

receiving a user command;

processing the user command;

evaluating consequences of executing the user command based on command processing results; and

performing a preventative action if it is determined that execution of the user command could result in an undesirable consequence.

21. An automated system, comprising:

a command processing system that processes input commands; and

a command execution system that executes an input command based on command processing results provided by the command processing system,

wherein the command processing system is adapted to evaluate consequences of executing input commands and take preventative actions for execution of input commands that could result in undesirable consequences.

22. The system of claim 21, wherein the command processing system, comprises:

an automatic recognition system for recognizing input patterns associated with the input command;

a command interpretation system to interpret input commands based on recognition results generated by the automatic recognition system; and

a consequence evaluation system to evaluate consequences of executing input commands based on interpretation results generated by the command interpretation system; and

a feedback system to perform preventative actions for executing input commands when consequence evaluation results of an input command indicate an undesirable consequence of executing the input command.

23. The system of claim 22, wherein the command processing system further comprises an ambiguity evaluation system to determine a degree of ambiguity of recognition results or interpretation results of an input command.

24. The system of claim 22, wherein the consequence evaluation system comprises:

means for determining a potential consequence of executing an input command;

means for determining a likelihood that the potential consequence can actually occur; and

means for classifying an impact of the potential consequence based on the determined likelihood that the potential consequence can actually occur.

25. The system of claim 24, wherein the means for determining likelihood comprises:

means for receiving information that indicates current environmental conditions;

means for determining a relation, if any, between the potential consequence and the current environmental conditions; and

means for determining a likelihood that the potential consequence can actually occur based on related current environmental conditions, if any.

26. The system of claim 22, wherein the feedback system comprises a notification system to generate an alert signal or notification message to provide notification of an undesirable consequence of executing an input command.

27. The system of claim 22, wherein the feedback system comprises a query compiler to generate a user query to obtain clarification of an input command.

28. The system of claim 27, wherein the query compiler compiles a question to request user confirmation of an input command as interpreted or an alternative interpretation of the input command.

29. The system of claim 22, wherein the automatic recognition system comprises a speech recognition system.

30. The system of claim 22, wherein the automatic recognition system comprises a natural language understanding system.

31. The system of claim 22, wherein the automatic recognition system comprises an image recognition system.

32. The system of claim 22, wherein the automatic recognition system comprises a user state recognition system.