Hierarchical interface for adaptive closed loop communication system

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.

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.