Using a speech analytics system to control pre-recorded scripts for debt collection calls
A speech analytics system (“SAS”) monitors speech from a remote party and agent to determine when text-based guidance information (“TBGI”) and a script control icon is to be provided to the agent. The agent may respond to a particular context with certain information, either by verbally informing the remote party or causing a prerecorded script to be played to the remote party. In one embodiment, the SAS monitors the agent's speech to ascertain if an expected speech response is provided by the agent within a first time period. If not, the SAS may cause another TBGI and script control icon to be presented to the agent, and again monitor the agent's speech to ascertain if an expected speech response is provided by the agent within a second time period. If the agent again fails to respond properly, then data may be written indicating a compliance failure.
1. A system for playing a recorded script on a call involving an agent and a remote party comprising:
a call handler in a contact center configured to originate the call as an outbound call to the remote party, wherein the agent of the contact center is connected to the call via the call handler;
a speech analytics component, bridged onto the outbound call by the call handler, the speech analytics component configured to analyze speech of the remote party; and
a processor configured to:
receive an event reporting message indicating detection of a first keyword by the speech analytics component in the speech of the remote party,
cause an icon to be displayed on a computer display of a computer used by the agent based on the event reporting message indicating detection of the first keyword, wherein selection of the icon by the agent causes the recorded script to be played to the remote party,
receive an input from the agent at the computer selecting the icon, and
play the recorded script to the remote party in response to the agent selecting the icon.
2. The system of claim 1 , wherein the processor is further configured to:
start a timer in response to receiving the event reporting message reporting detection of the first keyword; and
stop the timer in response to receiving a second event reporting message indicating detection of a second keyword in speech uttered during the call.
3. The system of claim 1 , wherein the processor is further configured to:
mute a microphone used by the agent prior to playing the recorded script to the remote party.
4. The system of claim 3 , wherein the processor is further configured to:
unmute the microphone used by the agent after playing the recorded script to the remote party.
5. The system of claim 1 , wherein the processor is further configured to:
start a timer in response to detecting the first keyword; and
display a warning on the computer display to the agent in response to not receiving a second event reporting message prior to expiry of the timer.
6. The system of claim 1 , wherein the processor is configured to:
select the icon for display from among a plurality of icons, wherein each of the plurality of icons is associated with a corresponding recorded script to be played to the remote party upon selection of a corresponding icon by the agent.
7. The system of claim 1 , wherein the processor is configured to:
remove the icon from the display after playing the recorded script to the agent.
8. A method for playing a recorded audio script on a call involving an agent of a contact center and a remote party, comprising:
originating the call as an outbound call by a call handler in the contact center to the remote party, wherein the agent is connected to the call via the call handler;
bridging a speech analytics component onto the call by the call handler, wherein the speech analytics component is configured to analyze speech of the remote party during the call and report detection of a first keyword by sending an event reporting message; and
receiving by a processor the event reporting message indicating detection of the first keyword by the speech analytics component in the speech of the remote party;
causing an icon to be displayed by the processor on a computer display of a computer used by the agent based on receiving the event reporting message, wherein selection of the icon by the agent causes the recorded script to be played to the remote party;
receiving an input from the agent at the computer selecting the icon; and
playing the recorded script to the remote party in response to the agent selecting the icon.
9. The method of claim 8 , further comprising:
starting a timer by the processor in response to detecting the first keyword; and
stopping the timer by the processor in response to receiving a second event reporting message indicating detection of a second keyword in speech uttered during the call.
10. The method of claim 8 , further comprising:
muting a microphone used by the agent prior to playing the recorded script to the remote party.
11. The method of claim 10 , further comprising:
unmuting the microphone used by the agent after playing the recorded script to the remote party.
12. The method of claim 8 , further comprising:
starting a timer by the processor in response to receiving the event reporting message indicating detection of the first keyword; and
displaying a warning on the computer display to the agent in response to not receiving a second event reporting message prior to expiry of the timer.
13. The method of claim 8 , further comprising:
selecting by the processor the icon for display from among a plurality of icons, wherein each of the plurality of icons is associated with a corresponding recorded script to be played to the remote party upon selection of a corresponding icon by the agent.
14. The method of claim 8 , further comprising:
removing the icon from the display after the recorded script is played.
15. A non-transitory computer readable medium storing instructions that when executed by a processor cause the processor to:
receive an event reporting message from a speech analytics component bridged onto a call by a call handler of a contact center, wherein the call involves an agent of the contact center and a remote party, the event reporting message indicating detection of a first keyword detected by the speech analytics component in the speech of the remote party;
determining an icon for display from among a plurality of icons, wherein each of the plurality of icons is associated with a corresponding recorded script to be played to the remote party upon selection of a corresponding icon by the agent;
causing the icon to be displayed on a computer display of a computer used by the agent;
receiving an input from the computer provided by the agent selecting the icon; and
causing the corresponding recorded script associated with the icon to be played to the remote party.
16. The non-transitory computer readable medium of claim 15 , further storing instructions causing the processor to:
muting a microphone used by the agent prior to playing the recorded script to the remote party.
17. The non-transitory computer readable medium of claim 16 , further storing instructions causing the processor to:
unmute the microphone used by the agent after playing the recorded script to the remote party.
18. The non-transitory computer readable medium of claim 15 , further storing instructions causing the processor to:
remove the icon from the display after the recorded script is played.
19. The non-transitory computer readable medium of claim 15 , further storing instructions causing the processor to:
start a timer in response to receiving the event reporting message indicating detection of the first keyword; and
display a warning on the computer display to the agent in response to not receiving a second event reporting message prior to expiry of the timer.
20. The non-transitory computer readable medium of claim 15 , wherein the call is a debt collection call and the first keyword comprises one from a group of “bankruptcy”, “attorney”, and “lawyer”.