Method, device, and computer program product for processing data

A method for processing data, comprising:

• sending, at a terminal device, a model loading request to a switch, a data processing model to be loaded by the switch being specified in the model loading request;
• sending model parameters of the data processing model to the switch;
• and
• sending to-be-processed data to the switch, such that the to-be-processed data is processed at the switch based on the data processing model;
• wherein the switch comprises a programmable switch and is implemented in a network separate from the terminal device;
• wherein the programmable switch is programmed to (i) select the data processing model based on the model parameters acquired from the terminal device, and (ii) process the data received from the terminal device using the selected data processing model;
• wherein the terminal device comprises an Internet of Things (IoT) device that provides both the model parameters and the to-be-processed data to the programmable switch, the model parameters and the to-be-processed data being provided by the IoT device to the programmable switch responsive to receipt of a service list in the IoT device from the programmable switch, the service list identifying a plurality of different neural network models that are executable in the programmable switch, the model parameters provided by the IoT device to the programmable switch comprising one or more characteristics of each of one or more network layers of a given one of the neural network models;
• and
• wherein an output generated by the programmable switch utilizing the selected data processing model is returned to the same IoT device that provided both the model parameters and the to-be-processed data to the programmable switch.

A switch, comprising:

• a processor;
• and
• a memory storing computer program instructions, wherein the processor runs the computer program instructions in the memory to control the switch to perform actions comprising:
• loading, in response to receipt of a model loading request from a terminal device, a data processing model specified in the model loading request;
• acquiring model parameters of the data processing model from the terminal device;
• and
• processing, in response to receipt of to-be-processed data from the terminal device, the data using the data processing model based on the model parameters;
• wherein the switch comprises a programmable switch and is implemented in a network separate from the terminal device;
• wherein the programmable switch is programmed to (i) select the data processing model based on the model parameters acquired from the terminal device, and (ii) process the data received from the terminal device using the selected data processing model;
• wherein the terminal device comprises an Internet of Things (IoT) device that provides both the model parameters and the to-be-processed data to the programmable switch, the model parameters and the to-be-processed data being provided by the IoT device to the programmable switch responsive to receipt of a service list in the IoT device from the programmable switch, the service list identifying a plurality of different neural network models that are executable in the programmable switch, the model parameters provided by the IoT device to the programmable switch comprising one or more characteristics of each of one or more network layers of a given one of the neural network models;
• and
• wherein an output generated by the programmable switch utilizing the selected data processing model is returned to the same IoT device that provided both the model parameters and the to-be-processed data to the programmable switch.