US 12,277,519 B2
Systems and methods for maintaining key performance indicator targets of a contact center
Prabhuram Muralikrishnan Vathsala, Chennai (IN); Aiswarya Venkatachalapathy, Chennai (IN); Balakrishnan Palanisamy, Namakkal (IN); and Prashanth Sanjeevi, Chennai (IN)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Jul. 25, 2022, as Appl. No. 17/872,446.
Prior Publication US 2024/0028999 A1, Jan. 25, 2024
Int. Cl. G06Q 10/0637 (2023.01); G06Q 10/0639 (2023.01); H04M 3/51 (2006.01)
CPC G06Q 10/06375 (2013.01) [G06Q 10/06393 (2013.01); H04M 3/5175 (2013.01); H04M 2203/401 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
providing, by a device and as input to a trained machine learning model, input data indicating:
current values corresponding to key performance indicators associated with a plurality of current calls to a contact center,
one or more enterprise events, and
one or more stability events associated with the contact center;
receiving, by the device and as an output from the trained machine learning model, predicted values corresponding to the key performance indicators for a future timeframe;
determining, by the device, predicted rates of change corresponding to the key performance indicators based on a comparison of the current values and the predicted values corresponding to the key performance indicators;
assigning, by the device, severity levels corresponding to the key performance indicators based on the predicted rates of change;
determining, by the device, a service level impact based on the predicted values corresponding to the key performance indicators;
determining, by the device, a performance degradation score associated with the contact center based on the severity levels and the service level impact;
determining, by the device, a strategy based on the performance degradation score;
performing, by the device, an action corresponding to the strategy; and
re-training, by the device, the trained machine learning model based on using the action as an input to update the trained machine learning model.