Abstract:
A federated learning method and a federated learning system based on mediation process are provided. The federated learning method includes: dividing a plurality of client devices into a plurality of mediator groups, and generate a plurality of mediator modules; configuring a server device to broadcast initial model weight data to the plurality of mediator modules; configuring the plurality of mediator modules to execute a sequential training process for the plurality of mediator groups to train a target model and generate trained model weight data; configuring the server device to execute a weighted federated averaging algorithm to generate global model weight data; and configuring the server device to set the target model with the global model weight data to generate a global target model.
Abstract:
The present disclosure provides an event stream processing system, comprises a gateway device and an external module. The gateway device comprises an event processing engine, and the external module comprises external processor. The event processing engine comprises an event grouping unit, a catch-collector, a processor and an event generator. The event processing engine processes a plurality events of the event stream corresponded to a rule. The event grouping unit groups the events corresponded to the rule. The catch-collector couples to the event group unit, configured for storing a first group event. The processor couples to the event group unit, configured for processing a second group event. The external module calculates the first group event and generates a first processing result. The event generator integrates the first processing result of the first group event and a second processing result of the second group event and generates a derived event.