2 results about "Task sharing" patented technology

This invention discloses an intelligent control method for collaborative autonomous linkage inspection of unmanned equipment in a dedicated power grid. The method includes: opening a task sharing channel for each inspection party, through which the inspection parties share shared inspection tasks in real time; marking the shared inspection tasks in a power grid visualization information model; sharing the power grid visualization information model with each inspection party; identifying the inspection tasks dispatched by the inspection parties and marking them accordingly in the power grid visualization information model; determining the timeliness requirements of each inspection task and the shared inspection task in the power grid visualization information model; marking the inspection tasks and the shared inspection tasks with corresponding classification tags according to the timeliness requirements; performing real-time collaborative inspection analysis of the unmanned inspection equipment based on the classification tags to obtain the inspection control mode, and sharing task completion data in real time with each unmanned inspection equipment of the inspection parties during the inspection process.

The application provides a model initialization method based on cross-task shared expert inheritance, constructs a multi-task mixed expert ancestor model and trains; each task data is input into the ancestor model, and the selection probability of each expert is counted according to layers; the importance score is constructed based on the cross-task average selection probability and the entropy of the expert, and the shared expert is selected according to layers to form a learning gene; each layer of the shared expert is used as a basic expert, a derived expert set is generated through linear expansion to initialize the mixed expert module of the corresponding layer of the offspring model; in the training or fine-tuning of the offspring model, Top-K sparse routing is used to activate the expert and output; when the multi-task training is performed, the task-expert mutual information loss and the task loss are introduced to form a total loss and update the model parameters, and the convergence speed and the generalization performance of the application in unknown downstream tasks can be improved.