System and methods for dynamically routing and rating customer service communications
A system may receive an indication that a user is accessing an ATM, receive, from the ATM, average session duration data over a predetermined period, generate, using a machine learning model, a busyness score for the ATM based on the average session duration data over the predetermined period, and determine whether the busyness score for the ATM exceeds a busyness score threshold. When the busyness score for the ATM does not exceed the busyness score threshold, the system may cause the ATM to present, via a first graphical user interface, a default ATM experience. When the busyness score for the ATM exceeds the busyness score threshold, the system may cause the ATM to present via, a second graphical user interface, a busy ATM experience.
1. A system comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive a phone call from the first user using a first phone number;
identify the first user via the first phone number;
receive one or more utterances via the phone call;
identify one or more issues from the one or more utterances;
determine, using a first machine learning model, whether the first user has a first emotion type based on one or more emotion metrics;
when the first user does not have the first emotion type, route the phone call to any call center representative;
when the first user has the first emotion type, route the phone call to a call center representative associated with an average call score that is above a predetermined threshold;
generate a call score for an assigned call center representative based the one or more issues and the determination of whether the first user had the first emotion type;
update the average call score associated with the assigned call center representative based on the call score.
2. The system of claim 1 , further comprising receiving the one or more emotion metrics, wherein the one or more emotion metrics comprise user interaction data, a tone of voice associated with the one or more utterances, word choice associated with the one or more utterances, talking speed associated with the one or more utterances, or combinations thereof, and wherein the user interaction data comprises chat data associated with the first user and via a textual chat session.
3. The system of claim 2 , wherein:
the user interaction data comprises global positioning system (GPS) data associated with the first user device, and
determining whether the first user has the first emotion type is based in part on the GPS data.
4. The system of claim 1 , wherein:
the instructions are further configured to cause the system to receive one or more audio signals from the first user via the phone call, and
determining whether the first user has the first emotion type is based in part on the one or more audio signals.
5. The system of claim 4 , wherein:
the one or more audio signals comprise background noise;
the instructions are further configured to cause the system to determine whether the background noise in the one or more audio signals exceeds a predetermined threshold level; and
determining whether the first user has the first emotion type is based on the determination of whether the background noise exceeds the predetermined threshold level.
6. A system, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive user interaction data associated with a first user using a first user device;
receive a phone call from a user using a first phone number;
receive one or more utterances from the first user via the phone call;
identify the user via the first phone number;
track a call duration for the phone call;
identify one or more issues from the one or more utterances;
determine, using a first machine learning model, whether the first user has a first emotion type based on the user interaction data;
when the first user has the first emotion type, route the first user to a call center representative associated with an average call score that is above a predetermined threshold; and
prompt the first user for first feedback after the issue is resolved or the phone call ends.
7. The system of claim 6 , wherein determining whether the first user has the first emotion type is based on a tone of voice associated with the one or more utterances, word choice associated with the one or more utterances, talking speed associated with the one or more utterances, or combinations thereof.
8. The system of claim 6 , wherein the memory stores further instructions that are further configured to cause the system to:
receive the first feedback from the first user;
generate a call score for an assigned call center representative based the one or more issues, the call duration, the first feedback, and the determination of whether the first user had the first emotion type; and
update the average call score associated with the assigned call center representative,
wherein the user interaction data comprises chat data associated with the user and via a textual chat session.
9. The system of claim 6 , wherein:
the user interaction data comprises global positioning system (GPS) data associated with the first user device, and
determining whether the first user has the first emotion type is based in part on the GPS data.
10. The system of claim 6 , wherein the memory stores further instructions that are further configured to cause the system to receive one or more audio signals from the user via the phone call.
11. The system of claim 10 , wherein the one or more audio signals comprises background noise determining whether the first user has a first emotion type is based on whether the background noise exceeds a threshold amount.
12. The system of claim 6 , wherein the memory stores further instructions that are further configured to cause the system to:
prompt the assigned call center representative to provide second feedback on whether the first user had the first emotion type;
receive the second feedback from the assigned call center representative; and
update the first machine learning model based on the first feedback, the second feedback, or both.
13. A system, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive user interaction data associated with a first user using a first user device;
receive a phone call from a user using a first phone number;
identify the user via the first phone number;
determine, using a first machine learning model, whether the first user has a first emotion type based on the user interaction data; and
when the first user has the first emotion type, route the first user to a first call center representative among one or more first call center representatives.
14. The system of claim 13 , wherein the user interaction data comprises chat data associated with the user and via a textual chat session.
15. The system of claim 13 , wherein:
the user interaction data comprises global positioning system (GPS) data associated with the first user device, and
determining whether the first user has the first emotion type is based in part on the GPS data.
16. The system of claim 13 , the instructions are further configured to cause the
system to receive one or more audio signals from the first user via the phone call, and determining whether the first user has the first emotion type is based in part on the one or more audio signals.
17. The system of claim 16 , wherein the audio signals comprise background noise and determining whether the first user has a first emotion is based on whether the background noise exceeds a threshold amount.
18. The system of claim 13 , wherein the memory stores further instructions that are further configured to cause the system to receive one or more utterances from the first user via the phone call.
19. The system of claim 18 , wherein determining whether the first user has a first emotion type is based on a tone of voice associated with the one or more utterances, word choice associated with the one or more utterances, talking speed associated with the one or more utterances, or combinations thereof.
20. The system of claim 19 , wherein the memory stores further instructions that are further configured to cause the system to:
identify one or more issues from the one or more utterances;
track a call duration for the phone call;
prompt the first user for first feedback after the issue is resolved or the phone call ends;
receive the first feedback from the first user;
generate a call score for an assigned call center representative based the one or more issues, the call duration, the first feedback, and the determination on whether the first user has the first emotion type;
update an average call score associated with the assigned call center representative;
prompt the assigned call center representative to provide second feedback on whether the first user was angry or frustrated;
receive the second feedback from the assigned call center representative; and
update the first machine learning model based on the first feedback, the second feedback, or both, and
wherein the one or more first call center representatives have average call scores above a predetermined threshold.