Hybrid computing landscape event characterization

A system comprising:

• at least one programmable data processor;
• and
• memory storing instructions which, when executed by the at least one programmable data processor, implement operations comprising:
• receiving messaging device data from each of a plurality of computing nodes characterizing at least one operational aspect of such computing node, the computing nodes being used to manage and characterize a supply chain across multiple physical sites;
• processing the received messaging data to identify events within such messaging device data;
• aggregating additional contextual information for the identified events relating to at least one supplier or potential supplier in the supply chain, the additional contextual information comprising:
• data characterizing a supplier chosen when a certain event condition occurred or data characterizing a supplier rejected for a certain event condition;
• generating, using the aggregated additional contextual information, messaging event data characterizing the identified events;
• executing a plurality of rules implicated by the messaging event data;
• and
• providing, using at least one machine learning model, action recommendations based on the actions, the at least one machine learning model being trained on data sets comprising one or more of attributes relating to event data, suggested actions from rules, actions taken, context data from other systems on which a rule ran, or historic aggregated data from other systems, the action recommendations being recommendations to solve operational anomalies within the supply chain.

A non-transitory computer program product storing instructions which, when executed by at least one programmable data processor forming part of at least one computing system, implement operations comprising:

• receiving messaging device data from each of a plurality of computing nodes characterizing at least one operational aspect of such computing node, the computing nodes being used to manage and characterize a supply chain across multiple physical sites;
• processing the received messaging data to identify events within such messaging device data;
• aggregating additional contextual information for the identified events relating to at least one supplier or potential supplier in the supply chain;
• generating, using the aggregated additional contextual information, messaging event data characterizing the identified events;
• executing a plurality of rules implicated by the messaging event data to result in actions specified by the executed rules;
• and
• providing, using at least one machine learning model, action recommendations based on the actions, the at least one machine learning model being trained on data sets comprising attributes relating to event data, suggested actions from rules, actions taken, context data from other systems on which a rule ran, and historic aggregated data from other systems, the action recommendations being recommendations to solve operational anomalies within the supply chain.