Multi-participant, mixed-initiative voice interaction system

• US 8,856,009 B2
• Filed: 03/25/2009
• Issued: 10/07/2014
• Est. Priority Date: 03/25/2008
• Status: Active Grant

• Current Assignee: Value8 Co., Ltd. (Wisefin Co., Ltd.)
• Original Assignee: Intelligent Mechatronic Systems Inc. (Trak Global Group Ltd.)
• Inventors: Basir, Otman A., Miners, William Ben
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US12/410,864
• Publication Number:
  US 20090248420A1
• Time in Patent Office: 2,022 Days
• Field of Search: None
• US Class Current: 704/270.1
• CPC Class Codes: H04M 1/57 Arrangements for indicating or recording the number of the calling subscriber at the called subscriber's set at the operator set in a manual exchange H04M5/20
• CPC Class Codes: H04M 1/6075 adapted for handsfree use in a vehicle H04M1/6058 takes precedence; arrangements for holding telephones in a vehicle B60R11/0241
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails
• CPC Class Codes: H04M 2250/02 including a Bluetooth interface
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

A voice interaction system includes one or more independent, concurrent state charts, which are used to model the behavior of each of a plurality of participants. The model simplifies the notation and provide a clear description of the interactions between multiple participants. These state charts capture the flow of voice prompts, the impact of externally initiated events and voice commands, and capture the progress of audio through each prompt. This system enables a method to prioritize conflicting and concurrent events leveraging historical patterns and the progress of in-progress prompts.

Claims

1. A voice interaction system comprising:

a processor programmed to initiate audible prompts, the processor receiving speech commands from a user, wherein the processor is programmed via a state chart model to receive events from a plurality of sources, prioritize the events and change states based upon the events, based upon the priority of the events and based upon the state chart model.

2. The voice interaction system of claim 1 further including:

a speaker generating the audible prompts initiated by the processor; and

a microphone receiving the speech command from the user.

3. The voice interaction system of claim 1 wherein the prioritization is based upon a stored set of user preferences.

4. The voice interaction system of claim 3 wherein the prioritization indicates priority of email messages.

5. The voice interaction system of claim 3 wherein the prioritization is based upon historical usage patterns of the user.

6. The voice interaction system of claim 1 wherein the processor introduces a delay prior to at least some of the audible prompts and wherein the processor determines whether a first audible prompt of the plurality of audible prompts should be generated during the delay.

7. The voice interaction system of claim 6 wherein the processor compares a priority of a first audible prompt during the delay to a priority of a second audible prompt to determine whether the first audible prompt or the second audible prompt should be generated.

8. The voice interaction system of claim 1 wherein the processor initiates a plurality of audible setup prompts to guide a user in setting up the system.

9. The voice interaction system of claim 8 wherein the plurality of setup prompts include prompts for assisting in pairing the system to a wireless device.

10. The voice interaction system of claim 1 wherein the state chart model is one of a plurality of independent state chart models, wherein the processor is programmed via the plurality of state chart models to receive events from the plurality of sources, prioritize the events and change states based upon the events, based upon the priority of the events and based upon the plurality of state chart models.

11. The voice interaction system of claim 1 where the state chart model includes a first state in which a first one of the plurality of sources is not connected to the processor.

12. The voice interaction system of claim 1 wherein the processor changes states in the state chart model based upon the events received from all of the plurality of sources.

13. A method of operating a voice interaction system including the steps of:

a) receiving speech commands from a user at a processor;

b) receiving a plurality of events from a plurality of sources at the processor, including the speech commands from the user;

c) prioritizing the plurality of events from the plurality of sources with the processor;

d) changing states in the processor based upon a state chart model, the received events and the priority of the events; and

e) generating a plurality of audible prompts with the processor based upon said step d).

14. The method of claim 13 wherein the prioritization is based upon a stored set of user preferences.

15. The method of claim 13 further including the steps of introducing a delay prior to a first audible prompt of the plurality of audible prompts and during the delay determining whether the first audible prompt should be generated.

16. The method of claim 15 further including the step of during the delay comparing a priority of the first audible prompt to a priority of a second audible prompt to determine whether the first audible prompt or the second audible prompt should be presented.

17. The method of claim 16 further including the step of initiating a plurality of audible setup prompts to guide a user in pairing the system to a wireless device.

18. A method of operating a voice interaction system including the steps of:

a) receiving speech commands from a user at a processor;

b) receiving a plurality of events from a plurality of sources at the processor, including the speech commands from the user;

c) prioritizing the plurality of events from the plurality of sources in the processor;

d) generating a plurality of audible prompts with the processor based upon the received events and the priority of the events, including determining a first audible prompt to be presented;

e) introducing a delay by the processor after said step d) and prior to presenting the first audible prompt; and

f) during the delay, deciding in the processor whether to present the first audible prompt.

19. The method of claim 18 wherein said step f) further includes the step of, during the delay, deciding between presenting the first audible prompt or a second audible prompt based upon a prioritization of the first audible prompt and the second audible prompt.

20. The method of claim 18 wherein said step f) further includes the step of determining between whether to present the first audible prompt or whether to not present the first audible prompt.

21. The method of claim 18 wherein said step f) further includes the step of determining not to present the first audible prompt.

22. The method of claim 18 wherein said step e) further includes the step of introducing the delay by the processor after said step d) and prior to presenting any of the plurality of audible prompts.

23. The method of claim 21 wherein said step f) further includes the step of, during the delay, deciding between presenting the first audible prompt or a second audible prompt generated during the delay based upon a prioritization of the first audible prompt and the second audible prompt.