Computer-implemented system and method for automating call center phone calls
View Patent ↗A system and method for processing a call between a caller and a live agent is provided. A stream of verbal speech utterances is received from the caller and converted into text. Text messages are received from the agent in response to the stream of verbal speech utterances and converted into synthesized speech utterances. The synthesized speech utterances are provided to the caller. A record of the call is processed and presented to a further live agent for manipulation. The manipulated record is stored.
1. A computer-implemented system for automating call center phone calls, comprising:
a telephony interface to receive a stream of verbal speech utterances from a callee of a call made from a call center;
an agent application to process the verbal speech utterances through a customer support scenario controlled by a live agent of the call center;
a post-call processor to identify one or more characteristics of the callee based on the verbal speech utterances;
a command processor to automate an outgoing call to a different callee with characteristics similar to the characteristics of the callee of the call made from the call center;
a script engine to receive a user selection of one or more scripts, each script comprising a grammar that defines a set of executable instructions for a question-and-response dialog and to affect an execution of the selected script; and
a performance module comprising at least one of:
a start module to begin the execution of the selected script;
an adjustment module to adjust a point of the execution within the selected script; and
a repeat module to repeat a portion of the selected script.
2. A system according to claim 1 , further comprising:
a speech recognition engine to convert the verbal speech utterances into text;
a display to present the text to the agent;
a text-to-speech agent to receive outgoing text messages from the agent and to convert the text messages into an outgoing stream of synthesized speech; and
the telephony interface to provide the outgoing stream of the synthesized speech to the callee.
3. A system according to claim 2 , wherein the text messages comprise one or more of pre-formed responses selected by the live agent or responses written by the live agent.
4. A system according to claim 2 , further comprising:
the speech recognition engine to perform speech recognition on the verbal speech utterances.
5. A system according to claim 1 , further comprising:
a macro module to generate a macro for the automation of the outgoing call.
6. A system according to claim 1 , wherein the characteristics comprise at least one of a role, gender, and language of the callee.
7. A system according to claim 1 , further comprising:
a record of the call made to the callee; and
the command processor to manipulate the record comprising at least one of reordering and ranking of the verbal speech utterances.
8. A system according to claim 7 , further comprising:
an annotation module to receive from the agent an annotation to one of the verbal speech utterances within the record; and
a database to store the annotation with the verbal speech utterance for which the annotation was received.
9. A computer-implemented method for automating call center phone calls, comprising the steps of:
receiving a stream of verbal speech utterances from a callee of a call made from a call center;
processing the verbal speech utterances through a customer support scenario controlled by a live agent of the call center;
identifying one or more characteristics of the callee based on the verbal speech utterances;
automating an outgoing call to a different callee with characteristics similar to the characteristics of the callee of the call made from the call center;
receiving a user selection of one or more scripts, each script comprising a grammar that defines a set of executable instructions for a question-and-response dialog;
affecting an execution of the selected script; and
performing at least one of beginning the execution of the selected script, adjusting a point of the execution within the selected script, and repeating a portion of the selected script,
wherein the steps are performed by a suitably programmed computer.
10. A method according to claim 9 , further comprising:
converting the verbal speech utterances into text and presenting the text to the agent;
receiving outgoing text messages from the agent and converting the text messages into an outgoing stream of synthesized speech; and
providing the outgoing stream of the synthesized speech to the callee.
11. A method according to claim 10 , wherein the text messages comprise one or more of pre-formed responses selected by the live agent or responses written by the live agent.
12. A method according to claim 10 , further comprising:
performing speech recognition on the verbal speech utterances.
13. A method according to claim 9 , further comprising:
generating a macro for the automation of the outgoing call.
14. A method according to claim 9 , wherein the characteristics comprise at least one of a role, gender, and language of the callee.
15. A method according to claim 9 , further comprising:
creating a record of the call made to the callee; and
manipulating the record comprising at least one of reordering and ranking of the verbal speech utterances.
16. A method according to claim 15 , further comprising:
receiving from the agent an annotation to one of the verbal speech utterances within the record; and
storing the annotation with the verbal speech utterance for which the annotation was received.