7results about How to "Save communication bandwidth" patented technology

The invention relates to an unmanned aerial vehicle route planning method and system based on lightweight artificial intelligence, and the method comprises the following steps: S1, obtaining the environment data of a distribution line, and fusing the data of multiple sensors in real time; s2, constructing an environment map based on the fused multi-sensor data; s3, key points are extracted from the environment map to serve as path nodes, the number of the nodes is reduced through a clustering algorithm, and a three-dimensional environment map with the key path nodes is obtained; s4, optimizing path calculation by adopting an improved A * algorithm and utilizing a heuristic search strategy according to the electric power line inspection plan, and constructing a path plan; and S5, deploying an edge terminal at the key node, and triggering real-time data storage and transmission only when necessary by adopting an event-based detection algorithm. Through the lightweight artificial intelligence algorithm design, the method can efficiently operate on an unmanned aerial vehicle platform with limited computing resources, and can effectively execute the inspection task in a complex distribution line environment at the same time.

The invention provides a theoretical security analysis method of a lattice-based PKE / KEM scheme based on compressed public key design. The method comprises the following steps: obtaining a key packaging scheme; the method comprises the following steps: splitting e into two parts e1 and e2 by utilizing the property of discrete Gaussian distribution, and then re-representing parameters as # imgabs0 #, representing # imgabs1 # imgabs2 # as # imgabs3 #, wherein # imgabs4 # is selected from proper distribution; secondly, splitting a secret # imgabs5 # by utilizing the property of discrete Gaussian distribution, decomposing the secret # imgabs5 # into a secret # imgabs6 # and a redundant part # imgabs7 # of a standard model LWE problem, further rewriting a sample form into # imgabs8 #, evaluating a theoretical difficulty lower bound of a corresponding problem by utilizing the standard model LWE problem corresponding to # imgabs9 #, and further evaluating a safety intensity lower bound of a KEM scheme; and for the required security strength lambda, selecting specific parameters of a key packaging scheme according to the calculation complexity of a standard module LWE problem corresponding to # imgabs10 #.

The invention provides a method and system for switching an emergency command and dispatch interface, and relates to the technical field of management systems. The method comprises: using the top-level container of the interface as a root function module and the function modules required by the interface as sub-function modules to construct an interface tree structure; using the root function module as a basic coordinate system and using a layered mounting technology to mount other sub-function modules on the root function module with relative coordinates; obtaining a switching instruction for an emergency command and dispatch scene interface; loading a target root function module corresponding to a target scene interface of the emergency command and dispatch, and updating a reference path of the target root function module; using a dynamic detail level strategy to dynamically adjust the data sampling frequency of each sensor in each sub-function module according to the distance from the place where the emergency event occurs; loading the underlying data required by each sub-function module in real time according to the data sampling frequency of each sensor; and displaying each sub-function module in the target scene interface of the emergency command and dispatch.

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.

The embodiment of the present invention discloses a method and system for safe driving, which relates to the field of computer technology. The method includes: a control console dispatches multiple driving tasks to multiple automatic guided transport vehicles; multiple automatic guided transport vehicles automatically adjust safe driving areas respectively; according to the safe driving areas, the multiple automatic guided transport vehicles drive safely. According to the method for safe driving of an embodiment of the present invention, multiple automatic guided transport vehicles automatically adjust safe driving areas respectively; according to the safe driving areas, the multiple automatic guided transport vehicles drive safely. This reduces the frequent communication between the automatic guided transport vehicles and the control console, saving communication bandwidth.

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.