Servicing of information requests in a voice user interface
View Patent ↗A VoiceXML Dialog Engine (“VDE”) is employed to handle requests via a brokered session from a media communications server. The VDE interfaces with one or more information providers, such as a script server or an audio server, in order to service the requests received via the brokered session. The VDE can provide a response to the requests to the media communications server based on information retrieved from the information providers.
1. A method comprising:
receiving an input from a media communications server via a session brokered based on a distribution of processing load;
interpreting a request for information in the input;
communicating the request for information to a communication interface; and
receiving information from the communication interface responsive to the request for information.
2. The method of claim 1 , wherein the information comprises a script.
3. The method of claim 2 , wherein the script comprises a markup language document.
4. The method of claim 2 , further comprising:
interpreting the script to produce one or more prompts; and
sending the one or more prompts to the media communications server.
5. The method of claim 4 , wherein the one or more prompts comprise a dynamic audio prompt, the method further comprising:
retrieving an audio file corresponding to the dynamic audio prompt from the communication interface; and
sharing the audio file with the media communications server.
6. The method of claim 4 , wherein the one or more prompts comprise an instruction to the media communications server to access an audio file from a shared data area.
7. The method of claim 4 , wherein the one or more prompts comprise a text-to-speech request.
8. The method of claim 4 , further comprising:
sending an additional one or more prompts to the media communications server in an append instruction.
9. The method of claim 4 , further comprising:
instructing the media communications server to play the one or more prompts.
10. The method of claim 4 , wherein the one or more prompts comprise a voice recognition instruction, the method further comprising:
instructing the media communications server to play the voice recognition instruction; and
receiving a voice recognition result.
11. The method of claim 10 , further comprising:
sending a grammar list to the media communications server.
12. The method of claim 1 , further comprising:
receiving, at the media communications server, a dialog input from a communications subsystem;
requesting, at the media communications server, a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;
sending, from the media communications server, the request for information to the dialog engine based on the dialog input; and
receiving, at the media communications server, the information from the dialog engine.
13. The method of claim 12 , further comprising:
performing speech recognition on the dialog input to generate a speech recognition result, wherein the request for information comprises the speech recognition result.
14. A system comprising:
a communications interface; and
one or more processors configured to:
receive an input from a media communications server via a session brokered based on a distribution of processing load;
interpret a request for information in the input;
communicate the request for information over the communications interface; and
receive information responsive to the request for information over the communications interface.
15. The system of claim 14 , wherein the information comprises a script.
16. The system of claim 15 , wherein the script comprises a markup language document.
17. The system of claim 15 , wherein the one or more processors are further configured to:
interpret the script to produce one or more prompts; and
send the one or more prompts to the media communications server.
18. The system of claim 17 , wherein the one or more prompts comprise a dynamic audio prompt, the one or more processors further configured to:
retrieve an audio file corresponding to the dynamic audio prompt from the communications interface; and
share the audio file with the media communications server.
19. The system of claim 17 , wherein the one or more prompts comprise an instruction to the media communications server to access an audio file from a shared data area.
20. The system of claim 17 , wherein the one or more prompts comprise a text-to-speech request.
21. The system of claim 17 , wherein the one or more processors are further configured to:
send an additional one or more prompts to the media communications server in an append instruction.
22. The system of claim 17 , wherein the one or more processors are further configured to:
instruct the media communications server to play the one or more prompts.
23. The system of claim 17 , wherein the one or more prompts comprise a voice recognition instruction, the one or more processors further configured to:
instruct the media communications server to play the voice recognition instruction; and
receive a voice recognition result.
24. The system of claim 23 , wherein the one or more processors are further configured to:
send a grammar list to the media communications server.
25. The system of claim 14 , wherein the one or more processors are further configured to:
receive, at the media communications server, a dialog input from a communications subsystem;
request, at the media communications server, a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;
send, from the media communications server, the request for information to the dialog engine based on the dialog input; and
receive, at the media communications server, the information from the dialog engine.
26. The system of claim 25 , wherein the one or more processors are further configured to:
perform speech recognition on the dialog input to generate a speech recognition result, wherein the request for information comprises the speech recognition result.
27. A tangible non-transitory computer-readable medium having stored thereon computer-executable instructions, execution of which, by a computing device, cause the computing device to perform operations comprising:
receiving an input from a media communications server via a session brokered based on a distribution of processing load;
interpreting a request for information in the input;
communicating the request for information to a communication interface; and
receiving information from the communication interface responsive to the request for information.
28. The computer-readable medium of claim 27 , wherein the information comprises a script.
29. The computer-readable medium of claim 28 , wherein the script comprises a markup language document.
30. The computer-readable medium of claim 28 , the method further comprising:
interpreting the script to produce one or more prompts; and
sending the one or more prompts to the media communications server.
31. The computer-readable medium of claim 30 , wherein the one or more prompts comprise a dynamic audio prompt, the method further comprising:
retrieving an audio file corresponding to the dynamic audio prompt from the communication interface; and
sharing the audio file with the media communications server.
32. The computer-readable medium of claim 30 , wherein the one or more prompts comprise an instruction to the media communications server to access an audio file from a shared data area.
33. The computer-readable medium of claim 30 , wherein the one or more prompts comprise a text-to-speech request.
34. The computer-readable medium of claim 30 , the method further comprising:
sending an additional one or more prompts to the media communications server in an append instruction.
35. The computer-readable medium of claim 30 , the method further comprising:
instructing the media communications server to play the one or more prompts.
36. The computer-readable medium of claim 30 , wherein the one or more prompts comprise a voice recognition instruction, the method further comprising:
instructing the media communications server to play the voice recognition instruction; and
receiving a voice recognition result.
37. The computer-readable medium of claim 36 , the method further comprising:
sending a grammar list to the media communications server.
38. The computer-readable medium of claim 27 , the method further comprising:
receiving, at the media communications server, a dialog input from a communications subsystem;
requesting, at the media communications server, a dialog engine from a broker operable to distribute a processing load across a plurality of dialog engines;
sending, from the media communications server, the request for information to the dialog engine based on the dialog input; and
receiving, at the media communications server, the information from the dialog engine.
39. The computer-readable medium of claim 38 , the method further comprising:
performing speech recognition on the dialog input to generate a speech recognition result, wherein the request for information comprises the speech recognition result.