Distributed trusted sensing method and system for integrated communication, sensing and computation network

A distributed trusted sensing system for an integrated communication, sensing, and computation network, comprising multiple edge nodes and multiple miners, wherein each edge node corresponds to one miner;

• the edge nodes each comprises a processor and a memory storing program codes, wherein the processor performs the stored codes to:
• obtain a global model and an initial global parameter, substitute the initial global parameter into the global model, and locally train the global model by using local data, to obtain a local model parameter;
• upload the local model parameter to a corresponding miner;
• assign a weight to each of received local model parameters and the local model parameter of the edge node based on validity of the local model parameters;
• perform, based on the weight, weighted aggregation on all the received local model parameters and the local model parameter of the edge node, to obtain an iterative global parameter;
• determine whether the iterative global parameter meets a preset condition;
• and if yes, use the iterative global parameter as a final global parameter;
• or if not, substitute the iterative global parameter into the global model, and return to the step of locally training the global model by using local data, to obtain a local model parameter;
• and
• the miners each comprises a processor and a memory storing program codes, wherein the processor performs the stored program codes to:
• save and broadcast the received local model parameter;
• store the received local model parameter in a memory pool;
• send local model parameters in the memory pool to the corresponding edge node when a number of the local model parameters in the memory pool exceeds a specified threshold;
• and
• add the iterative global parameter to a generated block, and broadcast and perform digital signature verification on the iterative global parameter.