Device, system and method for providing machine learning prompts on a call at a contact center server
A device, system and method for providing machine learning prompts on a call at a contact center server are provided. A contact center (CC) server receives a call. The CC server receives, on the call, an indication of a queue, of a plurality of queues maintained by the CC server, into which to place the call. The CC server places the call into the queue indicated by the indication, the call placed into the queue in a hold state. A machine learning engine generates, based on historical data associated with the queue, one or more prompts for the call. The CC server provides the one or more prompts on the call during the hold state.
1 . A method comprising:
receiving, via a contact center (CC) server, a call;
receiving, via the CC server, on the call, an indication of a queue, of a plurality of queues maintained by the CC server, into which to place the call;
placing, via the CC server, the call into the queue indicated by the indication, the call placed into the queue in a hold state;
generating, via a machine learning engine, based on historical data associated with the queue, one or more prompts for the call; and
providing, via the CC server, the one or more prompts on the call during the hold state, wherein generating one or more prompts for the call comprises:
generating, via the machine learning engine, an initial prompt, of the one or more prompts, that includes one or more estimated reasons for the call based on the historical data associated with the queue;
receiving, on the call, a selection of an estimated reason, of the one or more estimated reasons; and
generating, via the machine learning engine, the one or more prompts that follow the initial prompt, based on the selection of the estimated reason.
2 . The method of claim 1 , wherein the machine learning engine comprises a generative artificial intelligence engine.
3 . The method of claim 1 , wherein the historical data comprises one or more of:
historical caller data associated with previous calls associated with a category of the queue;
respective historical data associated with a caller on the call; news data associated with the category of the queue; and social media data associated with the category of the queue.
4 . The method of claim 1 , wherein the historical data associated with the queue comprises caller data of a given number of previous calls that preceded the call.
5 . The method of claim 1 , wherein the one or more prompts for the call are further based on respective historical data associated with a caller on the call.
6 . The method of claim 1 , further comprising:
generating, via the machine learning engine, a final prompt, of the one or more prompts, that includes one or more of: an indication that the call is to be transferred to a human-operated terminal; and an estimated time until a transfer to the human-operated terminal; and a request for input from a calling device that made the call to indicate whether the call was successful or unsuccessful.
7 . The method of claim 1 , further comprising:
identifying, via the machine learning engine, an event having an aggregate effect on the queue, wherein the historical data associated with the queue comprises historical caller data of a given number of previous calls, including other calls related to the event, that preceded the call;
analyzing, via the machine learning engine, the historical caller data related to the event to determine patterns or trends influencing call volumes or caller behavior resulting from the event;
generating, via the machine learning engine, the one or more prompts specifically tailored to address an impact of the event on the queue and provide relevant information or assistance to callers affected by the event; and
providing, via the CC server, the one or more prompts generated to mitigate the impact of the event on the queue.
8 . The method of claim 1 , further comprising:
determining, based on one or more of a transcript of the call, a length of the call, a respective indication received from a calling device that made the call, whether the call is transferred to a human-operated terminal, whether the call is successful or unsuccessful; and
when the call is successful, training the machine learning engine using the transcript of the call as a positive training set.
9 . The method of claim 1 , further comprising:
determining, based on one or more of a transcript of the call, a length of the call, a respective indication received from a calling device that made the call, whether the call is transferred to a human-operated terminal, whether the call is successful or unsuccessful; and
when the call is unsuccessful, training the machine learning engine using the transcript of the call as a negative training set.
10 . A computing device comprising: a controller; and a computer- readable storage medium having stored thereon program instructions that, when executed by the controller, causes the controller to perform a set of operations comprising:
receiving, via a contact center (CC) server, a call;
receiving, via the CC server, on the call, an indication of a queue, of a plurality of queues maintained by the CC server, into which to place the call;
placing, via the CC server, the call into the queue indicated by the indication, the call placed into the queue in a hold state;
generating, via a machine learning engine, based on historical data associated with the queue, one or more prompts for the call; and
providing, via the CC server, the one or more prompts on the call during the hold state, wherein the set of operations further comprise:
generating, via the machine learning engine, an initial prompt, of the one or more prompts, that includes one or more estimated reasons for the call;
receiving, on the call, a selection of an estimated reason, of the one or more estimated reasons; and
generating, via the machine learning engine, the one or more prompts that follow the initial prompt, based on the selection of the estimated reason.
11 . The computing device of claim 10 , wherein the machine learning engine comprises a generative artificial intelligence engine.
12 . The computing device of claim 10 , wherein the historical data comprises one or more of: historical caller data associated with previous calls associated with a category of the queue; respective historical data associated with a caller on the call; news data associated with the category of the queue; and social media data associated with the category of the queue.
13 . The computing device of claim 10 , wherein the historical data associated with the queue comprises caller data of a given number of previous calls that preceded the call.
14 . The computing device of claim 10 , wherein the one or more prompts for the call are further based on respective historical data associated with a caller on the call.
15 . The computing device of claim 10 , wherein the set of operations further comprise:
generating, via the machine learning engine, a final prompt, of the one or more prompts, that includes one or more of: an indication that the call is to be transferred to a human-operated terminal; and an estimated time until a transfer to the human-operated terminal; and a request for input from a calling device that made the call to indicate whether the call was successful or unsuccessful.
16 . The computing device of claim 10 , wherein the set of operations further comprise:
identifying, via the machine learning engine, an event having an aggregate effect on the queue, wherein the historical data associated with the queue comprises historical caller data of a given number of previous calls, including other calls related to the event, that preceded the call;
analyzing, via the machine learning engine, the historical caller data related to the event to determine patterns or trends influencing call volumes or caller behavior resulting from the event;
generating, via the machine learning engine, the one or more prompts specifically tailored to address an impact of the event on the queue and provide relevant information or assistance to callers affected by the event; and
providing, via the CC server, the one or more prompts generated to mitigate the impact of the event on the queue.
17 . The computing device of claim 10 , wherein the set of operations further comprise:
determining, based on one or more of a transcript of the call, a length of the call, a respective indication received from a calling device that made the call, whether the call is transferred to a human-operated terminal, whether the call is successful or unsuccessful; and
when the call is successful, training the machine learning engine using the transcript of the call as a positive training set.
18 . The computing device of claim 10 , wherein the set of operations further comprise:
determining, based on one or more of a transcript of the call, a length of the call, a respective indication received from a calling device that made the call, whether the call is transferred to a human-operated terminal, whether the call is successful or unsuccessful; and
when the call is unsuccessful, training the machine learning engine using the transcript of the call as a negative training set.