Systems and methods for providing coachable events for agents
A method for providing coachable events for agents within a call center is provided. Behavior score waveforms for interactions and behaviors can be determined. Events can be identified in the behavior score waveforms within identified durations, and a relevancy of one or more events to one or more behaviors can be determined.
1. A method for providing coachable events for agents within a call center, the method comprising:
receiving, by a computing device, a plurality of interactions that are based on recordings of interactions between customers and agents in the call center;
determining, by the computing device, for each agent behavior in a plurality of agent behaviors and each interaction in the plurality of interactions, a behavior score waveform based on the respective interaction to create a plurality of behavior score waveforms;
identifying, by the computing device, for each behavior score waveform, one or more durations of the behavior score waveform;
identifying, by the computing device, for each event in a plurality of events, the particular interaction within the plurality of interactions that the particular event occurred within and associating the particular event with the particular interaction, wherein each event comprises properties that describe the event;
determining, by the computing device, for each behavior score waveform, for each duration of the one or more durations, a number of times each of the one or more events exist within each duration;
determining, by the computing device, for each behavior and each event that exists in each behavior, a behavior-event score that indicates relevancy of a current event to the behavior based on the corresponding number of times the current event occurs within the duration; and
displaying, by the computing device, for each behavior a ranked list of events with the behavior-event score scores.
2. The method of claim 1 further comprising for each behavior score waveform, for each duration of the one or more durations, determining, by the computing device, a number of times each of the one or more events exist outside each duration.
3. The method of claim 1 wherein determining the behavior-event score is further based on the number of times each of the one or more events exists outside each duration.
4. The method of claim 1 , further comprising:
determining, by the computing device, for each agent of a plurality of agents and each behavior, an average score based on all behavior-event scores for the particular agent.
5. The method of claim 1 , wherein identifying the one or more durations further comprises identifying portions of the respective behaviors score waveform that have a value above a predetermined threshold.
6. The method of claim 1 , wherein identifying the one or more durations further comprises identifying portions of the respective behaviors score waveform that have a value below a predetermined threshold.
7. The method of claim 1 further comprising:
receiving, by the computing device, a request for event information for a particular agent of the plurality of agents for a particular behavior of the plurality of behaviors.
8. The method of claim 1 wherein the plurality of interactions are a phonetic index, a transcript or both of the recording of the interactions.
9. The method of claim 1 wherein the behavior score waveform is generated based on machine learned behavior models.
10. The method of claim 1 wherein the behavior score waveform is further based on sentiment scores for the plurality of interactions, wherein the sentiment scores are based on phrases within the plurality of interactions.
11. The method of claim 1 wherein determining a number of times each of the one or more events exists within each duration further comprises dilating each duration by a predetermined time.
12. The method of claim 1 wherein determining each behavior-event score is further based on a number of interactions in the plurality of interactions that have interactions or are absent interactions.
13. A non-transitory computer program product comprising instructions which, when the program is executed cause the computer to:
receive a plurality of interactions that are based on recordings of interactions between customers and agents in the call center;
determine for each agent behavior in a plurality of agent behaviors and each interaction in the plurality of interactions a behavior score waveform based on the respective interaction to create a plurality of behavior score waveforms;
identify for each behavior score waveform, one or more durations of the behavior score waveform;
identify for each event in a plurality of events, the particular interaction within the plurality of interactions that the particular event occurred within and associating the particular event with the particular interaction, wherein each event comprises properties that describes the event;
determine for each behavior score waveform, for each duration of the one or more durations, a number of times each of the one or more events exist within each duration;
determine each behavior and each event that exists in each behavior, a behavior-event score that indicates relevancy of a current event to the behavior based on the corresponding number of times the current event occurs within the duration; and
display for each behavior a ranked list of events with the behavior-event score scores.
14. The non-transitory computer program product of claim 13 comprising instructions which, when the program is executed cause the computer to:
for each behavior score waveform, for each duration of the one or more durations, determine a number of times each of the one or more events exist outside each duration.
15. The non-transitory computer program product of claim 13 wherein determining the behavior-event score is further based on the number of times each of the one or more events exists outside each duration.
16. The non-transitory computer program product of claim 13 comprising instructions which, when the program is executed cause the computer to:
determine for each agent of a plurality of agents and each behavior, an average score based on all behavior-event scores for the particular agent.
17. The non-transitory computer program product of claim 13 wherein identifying the one or more durations further comprises identifying portions of the respective behaviors score waveform that have a value above a predetermined threshold.
18. The non-transitory computer program product of claim 13 wherein identifying the one or more durations further comprises identifying portions of the respective behaviors score waveform that have a value below a predetermined threshold.
19. The non-transitory computer program product of claim 13 comprising instructions which, when the program is executed cause the computer to:
receive a request for event information for a particular agent of the plurality of agents for a particular behavior of the plurality of behaviors.
20. The non-transitory computer program product of claim 13 wherein the behavior score waveform is generated based on machine learned behavior models.
21. The non-transitory computer program product of claim 13 wherein determining a number of times each of the one or more events exists within each duration further comprises dilating each duration by a predetermined time.