LAYERED PROMPTING: SELF-CALIBRATING INSTRUCTIONAL PROMPTING FOR VERBAL INTERFACES

• US 20090210232A1
• Filed: 02/15/2008
• Published: 08/20/2009
• Est. Priority Date: 02/15/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Sanchez, Russell I.
• Granted Patent: US 8,165,884 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

A plurality of prompting layers configured to provide varying levels of detailed assistance in prompting a user are maintained. A prompt from a current prompting layer is presented to a user. Input is received from the user. A level of detail in prompting the user is adaptively changed based on user behavior. Upon the user making a hesitant verbal gesture that reaches a threshold duration, a transition is made from the current prompting layer to a more detailed prompting layer. Upon the user interrupting the prompt with a valid input, a transition is made from the current prompting layer to a less detailed prompting layer.

Claims

1. A computer-implemented method, comprising:

configuring a system to provide auditory stimulus and act on auditory input;

maintaining a plurality of verbal prompting layers for one or more functions supported by the system, each of the verbal prompting layers being associated with an attributable familiarity level of a user and being configured to communicate varying levels of explanatory detail to provide assistance to the user in performing the one or more functions;

associating a current verbal prompting layer with the user;

initiating a prompt to for the auditory input;

receiving the auditory input;

identifying a timing event in presentation of the auditory input including one of;

a hesitant verbal gesture between a completion of the prompt and a start of the auditory input including one or more of;

a failure to respond;

nonsubstantive speech;

repetition of a verbal command; and

a request for assistance; and

an interruption of the prompt by the start of a valid auditory input;

evaluating the timing event relative to a threshold associated with transitioning to a next verbal prompting layer;

when the timing event surpasses a threshold, transitioning the current verbal prompting layer to a next verbal prompting layer; and

presenting an audible prompt from the next verbal prompting layer.

2. The computer-implemented method of claim 1, wherein:

when the identified timing event includes the hesitant verbal gesture and the hesitant verbal gesture reaches a duration exceeding the threshold, selecting a more detailed verbal prompting layer as the next verbal prompting layer; and

when the identified timing event includes the interruption of the prompt ahead of the threshold, selecting a less detailed verbal prompting layer as the next verbal prompting layer.

3. The computer-implemented method of claim 2, further comprising, when the timing event includes the hesitant verbal gesture and the hesitant verbal gesture reaches an additional threshold:

transitioning to a successively more detailed verbal prompting layer; and

presenting an additional audible prompt from the successively more detailed verbal prompting layer.

4. The computer-implemented method of claim 3, wherein the hesitant verbal gesture includes one of a succession of hesitant verbal gestures and an extended hesitant verbal gesture, automatically transitioning to a most detailed verbal prompting layer.

5. The computer-implemented method of claim 2, further comprising, when the hesitant verbal gesture includes the pause and fails to reach of the duration exceeding the threshold and occurs between content entries related to the one or more functions, treating the pause as a delimiter between the content entries.

6. The computer-implemented method of claim 1, wherein the plurality of layers of verbal prompting includes two or more of:

a terse prompt acknowledging availability of one or more functions;

a name prompt presenting names of the one or more functions;

a brief prompt explaining the one or more functions;

an explicit prompt explaining a syntax of the one or more functions;

a detailed prompt describing the operation of the one or more functions; and

a tutorial prompt guiding the user through one or more steps in using the one or more functions.

7. The computer-implemented method of claim 1, further comprising generating conversational cues acknowledging the receiving of the auditory input.

8. The computer-implemented method of claim 1, further comprising:

including one or more introductory prompts associated with at least one of the verbal prompt layers and configured to provide introductory information to the user;

monitoring a number of times the one or more introductory prompts has been presented; and

after the one or more introductory prompts has been presented a predetermined number of times, discontinuing presentation of the one or more introductory prompts.

9. The computer-implemented method of claim 1, further comprising one of:

maintaining the current verbal prompting layer associated with the user between sessions; and

when a time between sessions exceeds a nonuse interval, transitioning the current verbal prompting layer to a more detailed verbal prompting layer.

11. The computer-readable storage medium of claim 1, further comprising instructions, when the duration of the hesitant verbal gesture reaches one or more successive delay thresholds exceeding a previously-reached delay threshold, to transition to a successively more detailed prompting layer.

12. The computer-readable storage medium of claim 11, wherein the hesitant verbal gesture includes one of a succession of hesitant verbal gestures and an extended hesitant verbal gesture, automatically transition to a most detailed prompting layer.

10. A computer-readable storage medium storing instructions executable by a computing system to generate a result, comprising instructions to:

maintain a plurality of prompting layers to assist a user in using for one or more functions supported by a system, each of the prompting layers providing prompts at a level of detail from other prompting layers;

associate a current prompting layer with a user;

present a prompt from the current prompting layer to the user;

receive input from the user;

upon identifying a hesitant verbal gesture in the input, measure a duration of the hesitant verbal gesture;

when the duration reaches a delay threshold, transition from the current prompting layer to a next more detailed prompting layer; and

present a prompt from the next more detailed prompting layer.

13. The computer-readable storage medium of claim 10, further comprising instructions, when the user presents a valid input interrupting the prompt, to transition to a less detailed prompting layer.

14. The computer-readable storage medium of claim 10, further comprising instructions to generate cues acknowledging the receiving of the input.

15. The computer-readable storage medium of claim 10, further comprising instructions to:

present one or more introductory prompts associated with at least one of the prompting layers and configured to provide introductory information to the user;

monitor a number of times the one or more introductory prompts has been presented; and

after the one or more introductory prompts have been presented a predetermined number of times, discontinue presenting the one or more introductory prompts.

16. A computer-implemented method, comprising:

maintaining a plurality of prompting layers configured to provide varying levels of detailed assistance in prompting a user;

presenting a prompt from a current prompting layer;

receiving input from a user;

adaptively changing a level of detail in prompting the user based on user behavior including;

upon the user making a hesitant verbal gesture in presenting the input and the hesitant verbal gesture reaching a threshold duration, transitioning from the current prompting layer to a more detailed prompting layer; and

upon the user interrupting the prompt with a valid input, transitioning from the current prompting layer to a less detailed prompting layer.

17. The computer-implemented method of claim 16, further comprising, upon the user continuing to make the hesitant verbal gesture in presenting the input, transitioning to one or more successively more detailed prompting layers.

18. The computer-implemented method of claim 16, further comprising, upon the user interrupting a less detailed prompt from the less detailed prompting layer with the valid input, transitioning to a next less detailed prompting layer.

19. The computer-implemented method of claim 16, further comprising generating cues acknowledging the receiving of the input.

20. The computer-implemented method of claim 16, further comprising:

including one or more introductory prompts associated with at least one of the prompting layers and configured to provide introductory information to the user;

monitoring a number of times the one or more introductory prompts has been presented; and

after the one or more introductory prompts has been presented a predetermined number of times, discontinuing presentation of the one or more introductory prompts.