System and method for processing multi-modal communications during a call session
View Patent ↗A system and method for processing multi-modal communications during a call session are provided. A call is received from a caller and assigned to an agent. A caller identification is assigned to the call. Voice communication from the call is processed and displayed. One or more text messages from the caller are received during the call. The caller identification is assigned to each of the text messages. The text messages are matched to the call using the caller identification and are displayed to the agent for review during the call.
1. A system for processing multi-modal communications during a call session, comprising:
a telephony interface to receive a call from a caller;
a messaging server to assign a caller identification to the call and to further assign the call to an agent;
a speech recognition module to process voice communication from the call;
a text message processor to receive one or more text messages from the caller during the call, to assign the caller identification to each of the received text messages, and to match the text messages to the call using the caller identification; and
an agent console to display the processed voice communication and the text messages to the agent for review during the call.
2. A system according to claim 1 , further comprising:
a flag module to flag the text messages as verbatim data provided by the caller.
3. A system according to claim 1 , further comprising:
outgoing text messages sent in reply to the voice communication from the caller that are each converted into an outgoing stream of synthesized speech.
4. A system according to claim 1 , wherein the agent console displays the processed voice communication for the call with processed voice communication from one or more other calls.
5. A system according to claim 1 , wherein the processing of the voice communication comprises:
a speech to text module to transcribe the voice communication into speech utterances.
6. A system according to claim 1 , further comprising:
a response module to automatically generate a reply to the received voice communication based on a similar voice communication previously received by at least one of the caller or another caller.
7. A system according to claim 6 , wherein the response module determines the similar voice communication based on at least one of a most frequent voice communication and a most recent voice communication.
8. A system according to claim 1 , further comprising:
a call log to log the call and to store the text messages.
9. A system according to claim 1 , wherein the agent comprises at least one of a live person, an automated prompt, and a combination of the live person and the automated prompt.
10. A system according to claim 9 , further comprising:
a sliding scale module to vary a level of participation between the live person and the automated prompt.
11. A system according to claim 1 , further comprising:
a scheduling module to identify a scheduling request within the voice communication from the caller, to allow the agent access to a calendar associated with the caller, and to book an appointment for the caller in response to the scheduling request; and
an outgoing stream of synthesized speech to confirm the appointment.
12. A method for processing multi-modal communications during a call session, comprising:
receiving a call from a caller and assigning a caller identification to the call;
assigning the call to an agent;
processing voice communication from the call and displaying the processed voice communication;
receiving one or more text messages from the caller during the call and assigning the caller identification to each of the received text messages;
matching the text messages to the call using the caller identification; and
displaying the text messages to the agent for review during the call.
13. A method according to claim 12 , further comprising:
flagging the text messages as verbatim data provided by the caller.
14. A method according to claim 12 , further comprising:
sending outgoing text messages in reply to the voice communication from the caller that is converted into an outgoing stream of synthesized speech.
15. A method according to claim 12 , further comprising:
providing the processed voice communication for the call on a display with processed voice communication from one or more other calls.
16. A method according to claim 12 , wherein the processing of the voice communication comprises:
transcribing the voice communication into speech utterances.
17. A method according to claim 12 , further comprising:
automatically generating a reply to the received voice communication based on a similar voice communication previously received by at least one of the caller or another caller.
18. A method according to claim 17 , further comprising:
determining the similar voice communication based on at least one of a most frequent voice communication and a most recent voice communication.
19. A method according to claim 12 , further comprising:
logging the call in a call log; and
storing the text messages with the call log.
20. A method according to claim 12 , wherein the agent comprises at least one of a live person, an automated prompt, and a combination of the live person and the automated prompt.
21. A method according to claim 20 , further comprising:
varying a level of participation between the live person and the automated prompt.
22. A method according to claim 12 , further comprising:
identifying a scheduling request within the voice communication from the caller;
allowing the agent access to a calendar associated with the caller;
booking an appointment for the caller in response to the scheduling request; and
confirming the appointment by converting the appointment into an outgoing stream of synthesized speech.