Predictive scoring based on key performance indicators in telecommunications system
AssigneeRibbon Communications Operating Company, Inc.
InventorsCharles W. Boyle, Surya Kumar Kovvali, Nizar K. Purayil
Life of this patent
Estimating the term…
Abstract
A method includes: receiving protocol event data from a plurality of probes within the telecommunication system; determining a most probable cause of a call event from the protocol event data; applying the most probable cause to a trained machine learning algorithm that includes the most probable cause as its input and a telecommunication system score as its output; and in response to an output score from the trained machine learning algorithm, performing a corrective action for a plurality of network users that are expected to be affected by the most probable cause.
Claims20
A non-transitory machine readable medium having stored thereon instructions for performing a method comprising machine executable code which when executed by at least one machine, causes the machine to:
- receive protocol event data from a plurality of probes within a telecommunication system;
- determine a multi-protocol Key Performance Indicator (KPI) of a call event from the protocol event data;
- apply the multi-protocol KPI to a trained machine learning algorithm that includes the multi-protocol KPI as its input and a telecommunication system score as its output;
- and
- in response to an output score from the trained machine learning algorithm, perform a corrective action for a plurality of network users that are expected to be affected by the multi-protocol KPI.
A method performed by a computing system that collects information in a telecommunication system, the method comprising:
- receiving protocol event data, including data relating to a multitude of different protocol processes within the telecommunication system;
- determining a Key Performance Indicator (KPI) of a call failure from the protocol event data, the KPI including metrics from a plurality of different protocols;
- applying the KPI to a trained machine learning algorithm that includes a telecommunication system score as its output;
- predicting telecommunication system scores for a plurality of users affected by the KPI;
- and
- performing a corrective action for the plurality of users.
A method comprising:
- receiving call event data relating to a multitude of different protocol processes within a telecommunication system;
- determining a performance indicator of a call failure from the call event data, the performance indicator including metrics from a plurality of different protocols;
- applying the performance indicator to a trained machine learning algorithm that includes a telecommunication system score as its output;
- predicting telecommunication system scores for a plurality of users affected by the performance indicator;
- and
- performing a corrective action for the plurality of users.
Dependencies are inferred from the claim text.