Using real-time speech analytics to navigate a call that has reached a machine or service
View Patent ↗Various embodiments of the invention provide methods, systems, and computer program products for using real-time speech analytics to navigate a call that has reached a machine or service. In various embodiments, a call leg is established from a call handler handling the call to a speech analytics system configured to analyze the call to detect keywords. As the speech analytics system monitors the call, the speech analytics system sends an event to the call handler upon detecting a keyword. In turn, the call handler carries out some action based on the event that is configured to advance the progress of the call. Accordingly, if the call handler determines a live party has been reached on the call as result of the action, the call handler connects the call with a second live party to converse with the live party reached on the call.
1. A method for handling a call that has reached an answering machine or a voice mail service, comprising:
establishing a call leg from a call handler handling the call to a speech analytics system configured to analyze audio of the call over the call leg to detect one or more keywords being spoken on the call;
receiving a first event at the call handler from the speech analytics system as a result of the speech analytics system detecting a first particular keyword being spoken in the audio of the call during a progress of the call, the first event indicating the call has reached the answering machine or the voice mail service; and
after receiving the first event:
determining a content of a message to provide over the call to the answering machine and the voice mail service based on the progress of the call;
receiving a second event at the call handler from the speech analytics system as a result of the speech analytics system detecting a second particular keyword being spoken in the audio of the call, the second event indicating an instance when a message can be left on the answering machine or the voice mail service; and
after receiving the second event, playing the message over the call to be recorded by the answering machine or the voice mail service.
2. The method of claim 1 , wherein the progress of the call indicates an extension to reach a particular party was entered and the content of the message references the particular party.
3. The method of claim 1 further comprising:
upon receiving the first event, setting a timer by the call handler; and
upon the timer expiring prior to receiving the second event:
terminating the call leg to the speech analytics system by the call handler; and
disconnecting the call by the call handler.
4. The method of claim 2 further comprising recording an outcome to the call by the call handler upon receiving the second event or upon the timer expiring.
5. The method of claim 1 further comprising selecting a library of keywords by the call handler upon receiving the first event that is to be used by the speech analytics system in analyzing the audio of the call upon reaching the answering machine or the voice mail service.
6. The method of claim 1 further comprising terminating the call leg to the speech analytics system by the call handler upon receiving the second event.
7. A non-transitory, computer-readable medium comprising computer-executable instructions for handling a call that has reached an answering machine or a voice mail service, that when executed, cause a call handler to:
establish a call leg to a speech analytics system configured to analyze audio of the call over the call leg to detect one or more keywords being spoken on the call;
receive a first event from the speech analytics system as a result of the speech analytics system detecting a first particular keyword being spoken in the audio of the call during a progress of the call, the first event indicating the call has reached the answering machine or the voice mail service; and
after receiving the first event:
determine a content of a message to provide over the call to the answering machine and the voice mail service based on the progress of the call;
receive a second event from the speech analytics system as a result of the speech analytics system detecting a second particular keyword being spoken in the audio of the call, the second event indicating an instance when a message can be left on the answering machine or the voice mail service; and
after receiving the second event, have the message played over the call to be recorded by the answering machine or the voice mail service.
8. The non-transitory, computer-readable medium of claim 7 , wherein the progress of the call indicates an extension to reach a particular party was entered and the content of the message references the particular party.
9. The non-transitory, computer-readable medium of claim 7 , wherein the computer-executable instructions are configured to cause the call handler to:
upon receiving the first event, set a timer; and
upon the timer expiring prior to receiving the second event:
terminate the call leg to the speech analytics system; and
disconnect the call.
10. The non-transitory, computer-readable medium of claim 9 , wherein the computer-executable instructions are configured to cause the call handler to record an outcome to the call upon receiving the second event or upon the timer expiring.
11. The non-transitory, computer-readable medium of claim 7 , wherein the computer-executable instructions are configured to cause the call handler to select a library of keywords upon receiving the first event that is to be used by the speech analytics system in analyzing the audio of the call upon reaching the answering machine or the voice mail service.
12. The non-transitory, computer-readable medium of claim 7 , wherein the computer-executable instructions are configured to cause the call handler to terminate the call leg to the speech analytics system upon receiving the second event.
13. A system for handling a call that has reached an answering machine or a voice mail service, comprising:
a call handler configured to:
establish a call leg to a speech analytics system configured to analyze audio of the call over the call leg to detect one or more keywords being spoken on the call;
receive a first event from the speech analytics system as a result of the speech analytics system detecting a first particular keyword being spoken in the audio of the call during a progress of the call, the first event indicating the call has reached the answering machine or the voice mail service; and
after receiving the first event:
determine a content of a message to provide over the call to the answering machine and the voice mail service based on the progress of the call;
receive a second event from the speech analytics system as a result of the speech analytics system detecting a second particular keyword being spoken in the audio of the call, the second event indicating an instance when a message can be left on the answering machine or the voice mail service; and
after receiving the second event, have the message played over the call to be recorded by the answering machine or the voice mail service.
14. The system of claim 13 , wherein the progress of the call indicates an extension to reach a particular party was entered and the content of the message references the particular party.
15. The system of claim 13 , wherein the call handler is further configured to:
upon receiving the first event, set a timer; and
upon the timer expiring prior to receiving the second event:
terminate the call leg to the speech analytics system; and
disconnect the call.
16. The system of claim 15 , wherein the call handler is further configured to record an outcome to the call upon receiving the second event or upon the timer expiring.
17. The system of claim 13 , wherein the call handler is further configured to select a library of keywords upon receiving the first event that is to be used by the speech analytics system in analyzing the audio of the call upon reaching the answering machine or the voice mail service.
18. The system of claim 13 , wherein the call handler is further configured to terminate the call leg to the speech analytics system upon receiving the second event.