Communication session interruption and dynamic learning system
Arrangements for machine learning-based dynamic learning are provided. In some examples, audio data associated with a plurality of calls may be received and analyzed to identify a topic and sub-topic of each call and metadata of each call. Feedback data may also be received. A machine learning model may be executed by inputting, to the model, the identified topic and sub-topic and metadata of each call, and the feedback data, to output one or more topics or sub-topics of concern. A plurality of ongoing calls may be monitored to identify an ongoing call related to one of: a topic or sub-topic of concern. A plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern and are available may be identified and joined, via respective computing devices, to the ongoing call in a dynamic learning session.
1. A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
a memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive, from a plurality of communication sessions each communication session of the plurality of communication sessions being between a first computing device associated with an agent and a second computing device associated with a user, audio data associated with each communication session of the plurality of communication sessions;
identify, from the audio data associated with each communication session of the plurality of communication sessions, a topic and a sub-topic of each communication session of the plurality of communication sessions;
extract, from the audio data associated with each communication session of the plurality of communication sessions, metadata associated with each communication session of the plurality of communication sessions;
receive, from a plurality of different communication channels, feedback data associated with the plurality of communication sessions;
execute a dynamic learning machine learning model, wherein executing the dynamic learning machine learning model includes inputting, to the dynamic learning machine learning model, the identified topic and sub topic of each communication session, the extracted metadata from each communication session, and the feedback data to output one or more topics or sub-topics of concern;
monitor a plurality of ongoing communication sessions to identify an ongoing communication session related to one of: a topic or a sub-topic of concern;
identify, based on an agent mapping graph, a first plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern;
identify, from the first plurality of agents, a second plurality of agents who have an available status; and
join, to the identified ongoing communication session related to one of:
the topic or sub-topic of concern, computing devices of the second plurality of agents in a dynamic learning session.
2. The computing platform of claim 1 , wherein monitoring the plurality of ongoing communication sessions to identify an ongoing communication session related to one of: the topic or sub-topic of concern includes identifying the ongoing communication session related to one of: the topic or sub-topic of concern that includes an agent identified, by the agent mapping graph, as a subject matter expert in the one of: the topic or sub-topic of concern.
3. The computing platform of claim 1 , further including instructions that, when executed, cause the computing platform to:
generate a notification that the second plurality of agents will be joined to the dynamic learning session; and
send, to the computing devices of the second plurality of agents, the notification, wherein sending the notification causes the notification to be displayed by displays of the computing devices of the second plurality of agents.
4. The computing platform of claim 1 , wherein the second plurality of agents is a subset of the first plurality of agents.
5. The computing platform of claim 1 , wherein identifying, from the first plurality of agents, the second plurality of agents who have an available status is based on current computing device activity of each agent of the second plurality of agents.
6. The computing platform of claim 5 , wherein the computing device activity includes mouse activity and keyboard activity.
7. The computing platform of claim 1 , further including instructions that, when executed, cause the computing platform to:
update the agent mapping graph based on the dynamic learning session.
8. The computing platform of claim 1 , further including instructions that, when executed, cause the computing platform to:
update the dynamic learning machine learning model based on the dynamic learning session.
9. A method, comprising:
receiving, by a computing platform, the computing platform having at least one processor and memory, and from a plurality of communication sessions each communication session of the plurality of communication sessions being between a first computing device associated with an agent and a second computing device associated with a user, audio data associated with each communication session of the plurality of communication sessions;
identifying, by the at least one processor and from the audio data associated with each communication session of the plurality of communication sessions, a topic and a sub-topic of each communication session of the plurality of communication sessions;
extracting, by the at least one processor and from the audio data associated with each communication session of the plurality of communication sessions, metadata associated with each communication session of the plurality of communication sessions;
receiving, by the at least one processor and from a plurality of different communication channels, feedback data associated with the plurality of communication sessions;
executing, by the at least one processor, a dynamic learning machine learning model, wherein executing the dynamic learning machine learning model includes inputting, to the dynamic learning machine learning model, the identified topic and sub topic of each communication session, the extracted metadata from each communication session, and the feedback data to output one or more topics or sub-topics of concern;
monitoring, by the at least one processor, a plurality of ongoing communication sessions to identify an ongoing communication session related to one of: a topic or a sub-topic of concern;
identifying, by the at least one processor and based on an agent mapping graph, a first plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern;
identifying, by the at least one processor and from the first plurality of agents, a second plurality of agents who have an available status; and
joining, by the at least one processor and to the identified ongoing communication session related to one of: the topic or sub-topic of concern, computing devices of the second plurality of agents in a dynamic learning session.
10. The method of claim 9 , wherein monitoring the plurality of ongoing communication sessions to identify an ongoing communication session related to one of: the topic or sub-topic of concern includes identifying the ongoing communication session related to one of: the topic or sub-topic of concern that includes an agent identified, by the agent mapping graph, as a subject matter expert in the one of: the topic or sub-topic of concern.
11. The method of claim 9 , further including:
generating, by the at least one processor, a notification that the second plurality of agents will be joined to the dynamic learning session; and
sending, by the at least one processor and to the computing devices of the second plurality of agents, the notification, wherein sending the notification causes the notification to be displayed by displays of the computing devices of the second plurality of agents.
12. The method of claim 9 , wherein the second plurality of agents is a subset of the first plurality of agents.
13. The method of claim 9 , wherein identifying, from the first plurality of agents, the second plurality of agents who have an available status is based on current computing device activity of each agent of the second plurality of agents.
14. The method of claim 13 , wherein the computing device activity includes mouse activity and keyboard activity.
15. The method of claim 9 , further including:
updating, by the at least one processor, the agent mapping graph based on the dynamic learning session.
16. The method of claim 9 , further including:
updating, by the at least one processor, the dynamic learning machine learning model based on the dynamic learning session.
17. One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:
receive, from a plurality of communication sessions each communication session of the plurality of communication sessions being between a first computing device associated with an agent and a second computing device associated with a user, audio data associated with each communication session of the plurality of communication sessions;
identify, from the audio data associated with each communication session of the plurality of communication sessions, a topic and a sub-topic of each communication session of the plurality of communication sessions;
extract, from the audio data associated with each communication session of the plurality of communication sessions, metadata associated with each communication session of the plurality of communication sessions;
receive, from a plurality of different communication channels, feedback data associated with the plurality of communication sessions;
execute a dynamic learning machine learning model, wherein executing the dynamic learning machine learning model includes inputting, to the dynamic learning machine learning model, the identified topic and sub topic of each communication session, the extracted metadata from each communication session, and the feedback data to output one or more topics or sub-topics of concern;
monitor a plurality of ongoing communication sessions to identify an ongoing communication session related to one of: a topic or a sub-topic of concern;
identify, based on an agent mapping graph, a first plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern;
identify, from the first plurality of agents, a second plurality of agents who have an available status; and
join, to the identified ongoing communication session related to one of: the topic or sub-topic of concern, computing devices of the second plurality of agents in a dynamic learning session.
18. The one or more non-transitory computer-readable media of claim 17 , wherein monitoring the plurality of ongoing communication sessions to identify an ongoing communication session related to one of: the topic or sub-topic of concern includes identifying the ongoing communication session related to one of: the topic or sub-topic of concern that includes an agent identified, by the agent mapping graph, as a subject matter expert in the one of: the topic or sub-topic of concern.
19. The one or more non-transitory computer-readable media of claim 17 , further including instructions that, when executed, cause the computing platform to:
generate a notification that the second plurality of agents will be joined to the dynamic learning session; and
send, to the computing devices of the second plurality of agents, the notification, wherein sending the notification causes the notification to be displayed by displays of the computing devices of the second plurality of agents.
20. The one or more non-transitory computer-readable media of claim 17 , wherein identifying, from the first plurality of agents, the second plurality of agents who have an available status is based on current computing device activity of each agent of the second plurality of agents.