Bridge for non-voice communications user interface to voice-enabled interactive voice response system
A bridging for using a non-voice-based user interface, such as a text chat interface, with a voice-enabled interactive voice response system which, during a non-voice-based communication session with a client user device, receives from the client user device, a non-voice entry entered by a client user into the communication session; identifies one or more elements in the non-voice entry constrained by one or more allowed responses by the voice-enabled interactive voice response system; maps the one or more elements to one or more of the allowed responses; and passes the mapped one or more identified elements to a voice-enabled interactive voice response system as a input via emulation of a voice recognition analysis response.
1. A method for bridging a non-voice-based user interface to a voice-enabled interactive voice response system comprising:
during a communication session with a client user device, receiving, by a computer, from the client user device, an entry representing a response by a client user into the communication session;
identifying, by a computer, using one or more Natural Language Understanding processes, one or more non-uttered non-DTMF elements in at least a portion of the entry, wherein the identifying is constrained by one or more voice markup grammars according to a voice recognition analysis protocol for a voice-enabled interactive voice response system;
mapping, by a computer, the one or more identified non-uttered non-DTMF elements to generate one or more of the voice markup grammar returns from the non-uttered non-DTMF elements; and
passing, by a computer, the generated voice-markup grammar returns to an interactive voice response system as a user input;
thereby emulating the voice recognition analysis protocol upon non-uttered non-DTMF input and without utterance-driven speech recognition.
2. The method as set forth in claim 1 wherein the entry comprises a text entry.
3. The method as set forth in claim 1 further comprising:
subsequent to the passing of the mapped elements to the interactive voice response:
receiving, by a computer, from the voice-enabled interactive voice response system a next greeting, prompt, form or menu;
converting, by a computer, the next greeting, prompt, form or menu to a next text-based message; and
entering, by a computer, the converted next text-based message into the text-based communication session with a client user device.
4. The method as set forth in claim 3 wherein the received next greeting, prompt, form or menu comprises a voice-enabled extensible markup language document.
5. The method as set forth in claim 4 wherein the converting comprises extracting a text string from the voice-enabled extensible markup language document representing a text alternative to a digital voice recording in the voice-enabled extensible markup language document.
6. The method as set forth in claim 1 further comprising:
prior to the receiving of the entry from the client user device:
receiving, by a computer, from a voice-enabled interactive voice response system an initial greeting, prompt, form or menu;
converting, by a computer, the initial greeting, prompt, form or menu to an initial text-based message; and
entering, by a computer, the converted initial text-based message into the text-based communication session with a client user device.
7. The method as set forth in claim 6 wherein the received initial greeting, prompt, form or menu comprises a voice-enabled extensible markup language document.
8. The method as set forth in claim 7 wherein the converting comprises extracting a text string from the voice-enabled extensible markup language document representing a text alternative to a digital voice recording in the voice-enabled extensible markup language document.
9. The method as set forth in claim 1 wherein the voice markup grammars comprise a voice-enabled extensible markup language (VMXL) grammar.
10. The method as set forth in claim 1 wherein the communication session is selected from a group consisting of a web chat session, a conversation of Short Message Service messages, a conversation of mobile computing platform application program messages, a conversation of electronic mail messages, and a conversation of social media messages.
11. A computer program product for bridging a non-voice-based user interface to a voice-enabled interactive voice response system comprising:
a tangible, computer-readable memory device embodying program instructions for causing a processor to, when executed, perform steps of:
during a communication session with a client user device, receiving from the client user device, an entry representing a response by a client user into the communication session;
identifying, using one or more Natural Language Understanding processes, one or more non-uttered non-DTMF elements in at least a portion of the entry, wherein the identifying is constrained by one or more voice markup grammars according to a voice recognition analysis protocol for a voice-enabled interactive voice response system;
mapping the one or more identified non-uttered non-DTMF elements to generate one or more of the voice markup grammar returns from the non-uttered non-DTMF elements; and
passing the generated voice-markup grammar returns to an interactive voice response system as a user input;
thereby emulating the voice recognition analysis protocol upon non-uttered non-DTMF input and without utterance-driven speech recognition.
12. The computer program product as set forth in claim 11 wherein the received entry comprises a text entry.
13. The computer program product as set forth in claim 11 wherein the program instructions further comprise program instructions to:
prior to the receiving of the unstructured natural language non-voice entry from the client user device:
receive from a voice-enabled interactive voice response system an initial greeting, prompt, form or menu;
convert the initial greeting, prompt, form or menu to an initial text-based message; and
enter the converted initial text-based message into the text-based communication session with a client user device; and
subsequent to the passing of the mapped elements to the interactive voice response:
receive from the voice-enabled interactive voice response system a next greeting, prompt, form or menu;
convert the next greeting, prompt, form or menu to a next text-based message; and
enter the converted next text-based message into the text-based communication session with a client user device.
14. The computer program product as set forth in claim 13 wherein the received greeting, prompt, form or menu comprises a voice-enabled extensible markup language document, wherein the allowed responses by the voice-enabled interactive voice response system comprises elements from a voice-enabled extensible markup language grammar.
15. The computer program product as set forth in claim 11 wherein the communication session is selected from a group consisting of a web chat session, a conversation of Short Message Service messages, a conversation of mobile computing platform application program messages, a conversation of electronic mail messages, and a conversation of social media messages.
16. A system for bridging a non-voice-based user interface to a voice-enabled interactive voice response system comprising:
a computer processor; and
a tangible, computer-readable memory device embodying program instructions for causing the processor to, when executed, perform steps of:
during a communication session with a client user device, receiving from the client user device, an entry representing a response by a client user into the communication session;
identifying, using one or more Natural Language Understanding processes, one or more non-uttered non-DTMF elements in at least a portion of the entry, wherein the identifying is constrained by one or more voice markup grammars according to a voice recognition analysis protocol for a voice-enabled interactive voice response system;
mapping the one or more identified non-uttered non-DTMF elements to generate one or more of the voice markup grammar returns from the non-uttered non-DTMF elements; and
passing the generated voice-markup grammar returns to an interactive voice response system as a user input;
thereby emulating the voice recognition analysis protocol upon non-uttered non-DTMF input and without utterance-driven speech recognition.
17. The system as set forth in claim 16 wherein the received comprises a text entry.
18. The system as set forth in claim 16 wherein the program instructions further comprise program instructions to:
prior to the receiving of the unstructured natural language non-voice entry from the client user device:
receive from a voice-enabled interactive voice response system an initial greeting, prompt, form or menu;
convert the initial greeting, prompt, form or menu to an initial text-based message; and
enter the converted initial text-based message into the text-based communication session with a client user device; and
subsequent to the passing of the mapped elements to the interactive voice response:
receive from the voice-enabled interactive voice response system a next greeting, prompt, form or menu;
convert the next greeting, prompt, form or menu to a next text-based message; and
enter the converted next text-based message into the text-based communication session with a client user device.
19. The system as set forth in claim 18 wherein the received greeting, prompt, form or menu comprises a voice-enabled extensible markup language document, wherein the allowed responses by the voice-enabled interactive voice response system comprises elements from a voice-enabled extensible markup language grammar.
20. The system as set forth in claim 16 wherein the communication session is selected from a group consisting of a web chat session, a conversation of Short Message Service messages, a conversation of mobile computing platform application program messages, a conversation of electronic mail messages, and a conversation of social media messages.