Hierarchical interface for adaptive closed loop communication system
A communication system for processing a call includes control logic and at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor operated on the call. Heuristic logic transforms the call classifiers into weighted sub-metrics for the call, and aggregate normalized Gaussian logic transforms the weighted sub-metrics into a metric control that may be applied as a feedback signal to adapt the operation of the control logic. The control logic in turn may adapt the behavior of an agent, automated voice attendant, or a template utilized in a call flow. The system includes a scorecard interface operable to select a target and an indication of the metric control to apply for the target, and to apply the metric control to generate and display a historical performance visualization and a performance feed of the metric for the target.
1. A communication system for processing a call, the communication system comprising:
a scorecard user interface display;
at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor configured to operate on the call;
heuristic logic configured to transform the call classifiers into a plurality of weighted sub-metrics for the call;
aggregate normalized Gaussian logic to transform the weighted sub-metrics into a metric control, the metric control applied as feedback to adapt control logic of the communication system; and
the scorecard interface operable to select a target and an indication of the metric control to apply for the target, and to apply the metric control to generate and display a historical performance visualization and a performance feed of the metric for the target.
2. The communication system of claim 1 , wherein the historical performance visualization comprises a selection control for either a time series visualization or a histogram visualization.
3. The communication system of claim 2 , wherein the historical performance visualization comprises:
a composite comparative visualization for the target and comparable target.
4. The communication system of claim 1 , wherein the performance feed comprises:
a time series visualization of a selectable event for the target.
5. The communication system of claim 1 , wherein the target comprises one of an agent, a team, and a site.
6. The communication system of claim 1 , the scorecard interface further comprising a control to select a time interval to apply to generation of the historical performance visualization and the performance feed.
7. A method comprising:
operating at least one machine learning model to generate call classifiers from outputs of an audio signal processor and a natural language processor to operate on the call;
transforming the call classifiers with heuristic logic into a plurality of weighted sub-metrics for the call;
applying an aggregate normalized Gaussian transform on the weighted sub-metrics to generate a metric control, the metric control applied as feedback to adapt control logic of a communication system; and
operating a scorecard interface to select a target and an indication of the metric control to apply for the target, and to apply the metric control to generate and display a historical performance visualization and a performance feed of the metric for the target.
8. The method of claim 7 , wherein the historical performance visualization comprises a selection control for either a time series visualization or a histogram visualization.
9. The method of claim 8 , wherein the historical performance visualization comprises:
a composite comparative visualization for the target and comparable target.
10. The method of claim 7 , wherein the performance feed comprises:
a time series visualization of a selectable event for the target.
11. The method of claim 7 , wherein the target comprises one of an agent, a team, and a site.
12. The method of claim 7 , further comprising:
operating the scorecard interface further to select a time interval to apply to generation of the historical performance visualization and the performance feed.
13. The method of claim 7 , further comprising:
operating the scorecard interface to generate coaching examples for the target for improving the metric control.
14. The method of claim 13 , the coaching examples comprising a best call and a worst call for the metric control.
15. A computing apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the apparatus to:
operate at least one machine learning model to generate call classifiers from outputs of an audio signal processor and a natural language processor to operate on the call;
transform the call classifiers with heuristic logic into a plurality of weighted sub-metrics for the call;
apply an aggregate normalized Gaussian transform on the weighted sub-metrics to generate a metric control, the metric control applied as feedback to adapt control logic of a communication system; and
operate a scorecard interface to select a target and an indication of the metric control to apply for the target, and to apply the metric control to generate and display a historical performance visualization and a performance feed of the metric for the target.
16. The computing apparatus of claim 15 , wherein the historical performance visualization comprises a selection control for either a time series visualization or a histogram visualization.
17. The computing apparatus of claim 16 , wherein the historical performance visualization comprises:
a composite comparative visualization for the target and comparable target.
18. The computing apparatus of claim 15 , wherein the performance feed comprises:
a time series visualization of a selectable event for the target.
19. The computing apparatus of claim 15 , wherein the target comprises one of an agent, a team, and a site.
20. The computing apparatus of claim 15 , wherein the instructions further configure the apparatus to:
operate the scorecard interface further to select a time interval to apply to generation of the historical performance visualization and the performance feed.