Abstract: Disclosed are a resource scheduling method, an electronic device and a storage medium. The resource scheduling method may include: acquiring an intelligent application processing request acquiring current resource usage information; matching an intelligent application instance according to the intelligent application processing request and creating a task according to the resource usage information and the intelligent application instance, to process the intelligent application processing request.

Abstract: A resource scheduling method, a resource scheduling system, a device, and a computer-readable storage medium are disclosed. The resource scheduling method may include: obtaining a scheduling object from a scheduling queue (S100); and when the scheduling object is a customized resource, splitting the customized resource according to the current resource state to obtain a scheduling unit list (S200), the scheduling unit list including first scheduling units configured to form the customized resource; and sequentially scheduling the first scheduling units in the scheduling unit list (S300).

Abstract: A model training method and apparatus, a system, a prediction method, an apparatus, and a non-transitory computer-readable storage medium are disclosed. The model training method may include: determining, by a first device, a second device participating in model training, and sending a part of or the overall model training operation to the second device (100); and executing, by the first device, a first model training code to, for a jth training step, deliver by the first device a model parameter corresponding to the jth training step to the second device in response to the model training being not finished; and receiving a model parameter increment corresponding to the jth training step uploaded by the second device, and calculating a model parameter corresponding to a (j+1)th training step according to the model parameter increment corresponding to the jth training step uploaded by the second device (101).

Abstract: Provided are a method and device for training data, a storage medium and an electronic device. The method includes determining sample data and an available cluster resource; splitting an overall training model into sub-models; and training the sample data concurrently on the sub-models by using the cluster resource.