3results about How to "Save communication bandwidth" patented technology

The application discloses a low-throughput real-time voice transmission system and method. The system comprises multiple sending ends and a receiving end. Each sending end is used for collecting voice data of a current speaker and converting the voice data into incremental recognition text, and then assigning a corresponding unique identifier to the current speaker, and sending the incremental recognition text and the corresponding unique identifier of the current speaker to the receiving end. The receiving end is used for storing the received incremental recognition text according to the unique identifier corresponding to the speaker, and then synthesizing the incremental recognition text into audio. The application effectively reduces the data transmission amount, saves the communication bandwidth, removes the voiceprint features in the original voice, protects the privacy of the speaker, reduces the end-to-end transmission delay, and meets the real-time communication demand.

The application discloses a kind of unmanned aerial vehicle interference methods based on distributed beam synthesis, first, with the weakest interference power in the whole no-fly zone as the goal, establish the mathematical model of node deployment and beam synthesis joint optimization, construct a maximum-minimum optimization problem;Second, to improve the calculation efficiency, the non-convex optimization problem is decomposed into node deployment subproblem and beam synthesis subproblem to support distributed solution;Finally, through the low complexity iterative calculation of alternating optimization framework, the node deployment strategy and beam synthesis scheme with interference robustness are obtained, the unmanned aerial vehicle interference method based on distributed beam synthesis described in the application can effectively suppress all potential unmanned aerial vehicle targets in the region by maximizing the weakest interference power in the no-fly zone, overcome the shortcomings of traditional centralized interference method, such as poor robustness and high computational complexity, thereby improving the interference performance and practical value of anti-unmanned aerial vehicle system.

This invention belongs to the field of machine learning and discloses a method for updating model parameters in distributed federated learning. It addresses the problems of accuracy loss and reduced convergence rate caused by discarding the local correlation information implicit in gradient values ​​in existing communication compression schemes used during model parameter updates. In this invention, edge nodes use locally stored training samples to calculate the gradient matrix of the model parameters for the current round using the backpropagation algorithm. Then, a pooling operator is used to compress the gradient matrix to obtain the sparse gradient matrix for the current round, which is then uploaded to the central server. The central server, based on the received sparse gradient matrices of each designated edge node for the current round, updates the model parameters for the current round using a distributed gradient descent algorithm. If the updated model parameters meet the required preset accuracy, they are output as the final model parameters; otherwise, the updated model parameters are redistributed to the edge nodes for the next iteration.