Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

11results about How to "Reduce bandwidth overhead" patented technology

System for marine ecological monitoring information compression and data transmission

The invention discloses a system for marine ecological monitoring information compression and data transmission. Comprising a plurality of unmanned aerial vehicles, a plurality of buoys deployed in different sea areas, a target marine organism video acquisition module, a deep learning model training module, a marine organism attribute acquisition module, a marine organism attribute coding module, a roaring bitmap compression coding module, a roaring bitmap compression coding sending module and an unmanned aerial vehicle alternating module. According to the system, a deep learning model distributed training scheme based on federal learning is proposed, and deep learning models carried on all unmanned aerial vehicles are asynchronously updated; and characteristic dynamic differential compression coding and roaring map compression coding are designed to compress the monitoring data, so that the coding length and the sending frequency of the monitoring data are reduced, the bandwidth occupancy rate is reduced, and the communication efficiency is improved.
Owner:NAVAL UNIV OF ENG PLA

An online website defense method based on adversarial patches

The present invention discloses an online Web site defense method based on an adversarial patch. The method first calculates the key area of ​​network traffic data; then generates the adversarial patch: firstly, the difference between online and offline defense scenarios is analyzed, and the adversarial patch generation process is restricted, and then a non-targeted adversarial patch generation algorithm for the key area is proposed, and an adversarial patch corresponding to each site is generated; finally, the adversarial patch is injected: the injection process designs a Tor plug-in based on the WFPadTools framework, firstly the plug-in is deployed on the user end and the bridge end of Tor, and then a control message is designed for the communication between the user end and the bridge end, and finally the adversarial patch is injected online according to a predetermined strategy. The present invention improves the practicality of Web site fingerprint defense by utilizing the adversarial patch technology and designing a patch injection scheme.
Owner:SOUTHEAST UNIV

AI-driven game violation image recognition and data transmission system

PendingCN122273124AReduce computing powerReduce bandwidth overheadAlgorithmAttack
This invention relates to the field of game anti-cheating technology, specifically to an AI-driven system for identifying and transmitting images of game violations. The system first aggregates authoritative game data on the server side, calculates the balance deviation score of attack attempts, filters high-risk triggering events, and limits the evidence collection time window and pixel acquisition area. Next, it extracts legitimate semantic summaries from the game engine rendering chain, generates a predictive structure mask, and identifies semantically uninterpretable illegal overlays by comparing pixel-level differences. Finally, it integrates risk-graded transmitted evidence, and the server completes consistency verification through a homogeneous process. This invention does not rely on the appearance characteristics of cheats, significantly reduces computing power and bandwidth consumption, and provides a complete and auditable evidence chain.
Owner:GUANGZHOU YOUWANG INTERACTIVE NETWORK TECH CO LTD

Data storage method and apparatus based on erasure code

ActiveCN115577399BAvoid the problem of large bandwidth overheadReduce bandwidth overhead
The embodiment of the application provides a data storage method and device based on an erasure code, which comprises the following steps: a network card unit acquires first data to be stored, and divides the first data into a plurality of original data blocks. The network card unit performs erasure code processing on the plurality of original data blocks, and obtains at least one check data block corresponding to the plurality of original data blocks. The network card unit sends the plurality of original data blocks and the at least one check data block to a second storage server, so that the second storage server stores the original data blocks and the check data blocks. After the network card unit receives the first data to be stored, the network card unit directly performs data segmentation, erasure code encoding, and data transmission after the erasure code encoding is completed, so that the bandwidth cost of the storage server in the erasure code processing process can be effectively reduced.
Owner:ALIBABA (CHINA) CO LTD

A value burst flow detection method based on P4 and sketch

ActiveCN117811976BReduce the burden onReduce bandwidth overheadStreaming dataData pack
The present application relates to a kind of value burst flow detection method based on P4 and Sketch.Break through the detection scheme of traditional based on successive burst, propose value burst flow definition, observe the burst of traffic on the flow level, process the input data packet under the limited memory overhead by the data structure design based on Sketch, detect burst data packet according to the time interval between data packet, and then detect value burst flow. When data packet arrives, each data packet is mapped to a bucket set, but at most to one bucket is operated, under appropriate conditions, can vote according to the voting mechanism based on burst; when each measurement period ends, traverse all buckets, obtain the value burst flow detected by query operation and feedback to control plane. The present application reduces bandwidth overhead and user burden in burst detection process, while only limited memory occupation and low time complexity are generated.
Owner:FUZHOU UNIV

Robust multi-label website fingerprint defense method based on hybrid deep learning

The invention discloses a robust multi-label website fingerprint defense method based on hybrid deep learning, and belongs to the technical field of network security. The method comprises two stages of reconstructing an input sequence and constructing an anonymous sequence model, in the first stage, some overlapped virtual data packet traces are generated for an opponent of a trainee, so that the opponent of the trainee is familiar with the overlapped flow and the website identity of the multi-tab, and the accuracy of the opponent is reduced; secondly, designing an LSTM (Long Short-Term Memory) automatic encoder technology, effectively reconstructing overlapped input sequences in a multi-tab interface, and separating overlapped regions; in the second stage, bidirectional long-short term memory (Bi-LSTM) is used for anonymizing a traffic sequence to fuzzy a sequence mode of user interaction, and meanwhile, an adversarial example is added in a training process, so that the robustness of the method is further improved.
Owner:TIANJIN UNIV

Self-adaptive forward error correction method for real-time audio and video stream transmission process

The invention provides a self-adaptive forward error correction method for a real-time audio and video stream transmission process, which can dynamically adjust error correction redundancy configuration according to the change of network packet loss characteristics so as to improve the data transmission reliability in a complex network environment. Specifically, in a real-time transmission process, a sending end carries out long-term trend estimation and short-time burst estimation on network packet loss by respectively adopting a Kalman filtering algorithm and an exponential weighted moving average algorithm based on a packet loss rate measurement value fed back by a receiving end, and a dual-time-scale packet loss prediction model is constructed. Meanwhile, the statistical fluctuation characteristics of the historical packet loss rate are calculated, a dynamic safety redundancy boundary is introduced, and the redundancy adjustment process is smoothed in combination with a hysteresis state control mechanism, so that frequent fluctuation is avoided. The method can reduce the redundancy overhead, improve the error correction capability and reduce the packet loss rate in a complex and changeable network environment, is suitable for real-time audio and video stream transmission under various network conditions, and has good practicability and robustness.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Block chain communication method, related equipment, storage medium and computer program product

Provided in an embodiment of the present application are a block chain communication method, related device, storage medium and computer program product, the method being applied to a first node, the method comprising: the first node receiving first information sent by a second node, the first information comprising a first Internet Protocol (IP) multicast address; wherein the second node is used for managing at least one chain identifier and an accounting node group address and an IP multicast address corresponding to a channel identifier under the chain identifier; after the first block sent by the first sorting node is received, converting the first block into a second block; the second block is sent to all the first accounting nodes in the multicast tree corresponding to the first IP multicast address in a first preset mode, the first preset mode comprises an IP multicast mode, that is, the first node only needs to send the second block once, and all the related accounting nodes can receive the second block, so that the network communication bandwidth overhead and the communication time delay can be reduced, and the network communication efficiency is improved. And thus, the block chain service deployment and operation cost is reduced.
Owner:CHINA MOBILE COMM LTD RES INST +1

A personalized federated graph learning method and system based on dynamic structure perception and elastic alignment

PendingCN122655918AImprove robustnessInhibit cascading spreadPersonalizationMolecular analysis
The application discloses a kind of personalized federated graph learning method and system based on dynamic structure perception and elastic alignment, belongs to federated graph learning technical field.The method introduces self-supervised enhancement dynamic structure learning mechanism in client, relies on variational information bottleneck and graph contrast learning to realize topological denoising and multi-scale feature fusion;Design elastic parameter alignment mechanism and curvature perception weighted aggregation strategy based on Fisher information on the server side, accurately quantify parameter importance and impose anisotropic constraints, effectively alleviate the model drift and catastrophic forgetting caused by non-independent and identically distributed data.The application can inhibit topological noise propagation, protect local personalized knowledge, improve federated training stability and model accuracy, suitable for noisy graph data and distributed heterogeneous scene, with good generalization in biochemistry molecular analysis, encrypted traffic classification and other fields.
Owner:TIANJIN UNIVERSITY OF TECHNOLOGY

Coarse-grained reconfigurable processor convolution operator bandwidth optimization design method

The invention relates to a coarse-grained reconfigurable processor convolution operator bandwidth optimization design method. The method comprises the following steps: performing matrix conversion processing on target original data to obtain matrix data of the target original data; the target original data is obtained by the computing unit from a shared memory; the target original data in the shared memory is carried from the dynamic random access memory; and performing matrix multiplication operation on the matrix data to obtain a convolution calculation result of the target original data. The method comprises the following steps: carrying out matrix conversion processing on target original data carried in from a shared memory to obtain matrix data, carrying out matrix multiplication operation on the matrix data of the target original data to obtain a convolution calculation result of the target original data, and carrying out convolution calculation on the target original data to obtain a convolution calculation result of the target original data, the data is not expanded data after the target original data matrix is converted, so that the data carrying amount from the dynamic random access memory to the shared memory is reduced, and the bandwidth overhead of carrying the data from the dynamic random access memory to the shared memory is reduced.
Owner:INTERNATIONAL INNOVATION CENTER OF TSINGHUA UNIVERSITY SHANGHAI +1

Data processing method and system of block chain and electronic equipment

The invention provides a data processing method and system of a block chain and electronic equipment. The method comprises the following steps: initiating a target transaction; determining a target fragment according to the target transaction input, generating a target transaction witness according to the target transaction and the target fragment, and broadcasting the target transaction and the target transaction witness to the block chain; when the target fragment receives a target transaction and a target transaction witness, a target block chain node in the target fragment verifies the target transaction witness to extract a corresponding target subset witness, updates a corresponding target state commitment value according to the target subset witness, and packages the target transaction into a new block; and receiving the new block and verifying the updated target state commitment value. Through the stateless verification technology, under the condition that the fragmentation block chain does not need to store other fragmentation state data, transaction verification and witness extraction are carried out at the same time, communication between all the fragments except broadcast transaction does not need to be carried out, communication between the fragments is reduced, and the bandwidth overhead and the storage overhead of the system are reduced.
Owner:BEIJING UNIV OF POSTS & TELECOMM