20 results about "Network code" patented technology

The application discloses a kind of based on graph coding's diagnosis and surgical matching check method and system, the method includes: obtaining the diagnosis data and surgical plan data of target object;Based on feature extraction algorithm, extract the diagnosis change feature and surgical step feature in the diagnosis data and the surgical plan data;Based on graph network coding algorithm, the diagnosis change feature and surgical step feature are encoded into corresponding node relationship graph;The node relationship graph is input into trained graph neural network to obtain the matching degree parameter of output diagnosis and surgical plan.It can be seen that the present application can realize accurate medical diagnosis and surgery matching evaluation based on graph structure feature association, improve the scientificity and adaptability of surgical plan selection, reduce the surgical risk and treatment deviation caused by mismatch between scheme and diagnosis.

This invention relates to network coding technology and discloses a network coding method based on maximum rank distance code. The method includes: performing network coding on transmitted data to obtain coded data; performing linear addition and multiplication on the coded data to obtain coded data packets; using a preset parity check matrix to perform error detection and location on the coded data packets to obtain an error matrix; and performing rank error correction on the coded data packets based on the error matrix to obtain the original source data. This invention also provides a network coding apparatus, device, and medium based on maximum rank distance code. This invention can reduce the amount of redundant data transmitted in the transmission network and maintain low latency and high data recovery success rate even in complex network environments.

The application discloses a code segment processing method and device, a storage medium and equipment. The method comprises the following steps: setting an interactive control associated with a code editing area in a network code editor; in response to a triggering operation on the interactive control, determining a target code segment to which a cursor belongs, and acquiring a starting line and an ending line of the target code segment in the network code editor; and based on the network code editor, visually highlighting and displaying the target code in the starting line to the ending line. By associating the interactive control with the code editing area in the network code editor and determining the target code segment in response to the triggering operation on the interactive control, the target code segment is visually highlighted and displayed, which significantly improves the convenience, accuracy, response speed and fault tolerance of the user in locating and identifying the code segment.

The application provides a face image privacy protection recognition method based on optical coding and reverse feature enhancement, and relates to the technical field of computer vision recognition, and the method comprises the following steps: S1, acquiring a face data set, performing data enhancement, and constructing a face enhanced data set; S2, constructing a binary neural network convolution coding layer based on a straight-through estimator quantization, and performing optical coding on the face enhanced data set; S3, constructing a CNN and Transformer dual-channel multiplexing reverse feature enhancement neural network model, and performing feature dimension enhancement; S4, using a hybrid constraint, and jointly optimizing the neural network coding layer and the dual-channel multiplexing reverse feature enhancement neural network model; and S5, constructing a face embedding database, comparing a high-dimensional coding value of a single-pixel detection value with features in the face embedding database, and realizing face recognition. The application jointly optimizes the neural network binary convolution coding layer for spatial light modulator optical coding and the dual-channel multiplexing reverse feature enhancement model, so that the recognition precision is improved.

A communication device may comprise: a processor configured to carry out a method comprising: receiving a first consensus verification code from a first communication device; receiving a second consensus verification code from a second communication device; generating a combination code by network coding the first consensus verification code and the second consensus verification code; and instructing the transmission of the combination code to the first communication device and to the second communication device.

Network coding in automatic receipt request (ARQ) functionality is disclosed. A compatible transmitter configures a new transmission period, in which the set of data for transmission is transmitted, and a retransmission period, after the new transmission period, in which a number of network coded data is retransmitted based on the acknowledgement feedback received from the receivers receiving the transmitted set of data. The acknowledgement feedback identifies one or more data requested for retransmission by one or more of the receivers. The transmitter determines a number of network coded data that could be transmitted to accommodate each of the requesting receivers and the data requested by such receivers for retransmission. These network coded data would then be retransmitted by the transmitter during the retransmission period.

The invention discloses a prediction-based Internet of Vehicles code retransmission method and system and electronic equipment, and is applied to the field of Internet of Vehicles network transmission. The method comprises the following steps: collecting network states and vehicle motion characteristics of a plurality of transmission paths, and constructing a multi-modal tensor; constructing a prediction model by using a time sequence convolution encoder and an attention mechanism, and predicting a link state; a main path and an auxiliary path are screened according to the prediction result, the main path sends an original data packet, and the auxiliary path sends a polarization adjustment convolutional coding check packet generated based on the predicted packet loss rate; and the edge server carries out decoding by using the verification packet during packet loss, and feeds back a transmission result to update prediction model parameters. According to the method, the problems of high packet loss rate and retransmission delay jitter of the Internet of Vehicles in a high dynamic scene can be relieved by utilizing heterogeneous path cooperative transmission and a prediction-based polarization adjustment convolutional code coding retransmission mechanism, and technical support is provided for Internet of Vehicles services such as automatic driving.

Aspects presented herein may improve the latency and power consumption for communications by enabling a wireless device to apply outer coding (OC) (with forward error correction (FEC)) to transmission(s). In one aspect, a wireless device segments each packet data convergence protocol (PDCP) packet in a plurality of PDCP packets into a set of OC symbols, where the plurality of PDCP packets corresponds to a packet data unit (PDU) set. The wireless device assembles multiple sets of OC symbols into an OC block. The wireless device applies an FEC encoding to the OC block. The wireless device outputs the OC block based on the FEC encoding. In some examples, the wireless device also adds an OC header to the OC block, where the OC header includes a symbol size, a set of source symbols, and / or a symbol index associated with the FEC encoding.

The application discloses a kind of satellite-borne four-channel Ka frequency band data transmission channel systems, it is related to satellite communication technical field, including, the original spectrum data of acquisition Ka frequency band inner frequency point, synchronous reception interference hot area database, construct original spectrum matrix, and mark interference area, generate spectrum map with interference mark;With interference mark spectrum map input pre-trained convolutional neural network, output each frequency band interference probability, and identify safe frequency band, and safe frequency band is segmented into micro sub-band, and the optimization allocation scheme is optimized by Q-learning algorithm, and the optimized spectrum configuration table is generated;According to bandwidth parameter in the optimized spectrum configuration table, dynamically adjust modulation mode, and high-speed AOS data is blocked according to frame, and network coding check package is generated in combination with channel allocation strategy in the optimized spectrum configuration table.The application improves the spectrum utilization, communication reliability and overall performance of satellite-borne Ka frequency band data transmission system under dynamic environment.

The application relates to the communication technical field, discloses a communication method, device and system, and is used for solving the problem of large network coding resource consumption in the prior art. The method comprises the following steps: a first node performs network coding on a plurality of carried data packets to obtain coded data packets, wherein the target node of the plurality of carried data packets is a second node; and the first node sends the coded data packets to the second node.

The application discloses a variable working condition industrial process monitoring method and device based on abnormal sensitivity feature coding and knowledge distillation, and relates to the technical field of industrial process fault detection and intelligent monitoring. The method comprises the following steps: collecting variable working condition physical state parameters to obtain time series data, and decoupling the time series data through stationary subspace analysis to obtain stationary features; inputting the abnormal sensitivity long short-term memory network coding to extract abnormal sensitivity high-dimensional features; updating the dynamic memory bank based on the features, and utilizing the cross-attention mechanism to fuse the historical memory features to form cross-working condition fusion features; reconstructing the global time and feature dimension weight through the cross-attention time series distillation mechanism, aligning the current and historical fault sensitive features to obtain target features; inputting the target features into the fault classification head to map the positive abnormal probability, and determining the state and triggering the equipment control according to the positive abnormal probability. The application can accurately perceive the hidden subtle faults in the variable working condition non-stationary industrial process, and realize the continuous inheritance of monitoring knowledge among different production states.

Provided in the embodiments of the present application are a processing method for a neural network model, and a secure element and a computing apparatus. The computing apparatus comprises: a storage element, which is used for storing a first neural network code for the first model inference of a neural network model and at least some first network parameters for the first model inference; a secure element, which is used for storing the remaining first network parameters for the first model inference, and / or storing a second neural network code and second network parameters for the second model inference of the neural network model, and executing the second model inference on the basis of the second network parameters and the second neural network code; and a general-purpose computing element, which is used for executing the first model inference on the basis of the first neural network code and the first network parameters. The embodiments of the present application can prevent a neural network model from being physically attacked, thereby improving the security of the neural network model.

Methods, systems, and devices for wireless communications are described. A wireless device may receive a set of sidelink messages via one or more sidelink channels, where a group of sidelink messages of the set of sidelink messages is associated with feedback information requesting retransmission for each sidelink message. The wireless device may generate one or more network coded combined messages corresponding to one or more subsets of sidelink messages of the group of sidelink messages based on the feedback information. For example, the wireless device may perform an exclusive or operation on two or more sidelink messages of the group of sidelink messages to obtain a network coded combined message corresponding to a subset of sidelink messages. The wireless device may transmit, via the one or more sidelink channels, the one or more network coded combined messages and an indication of the one or more subsets of sidelink messages.

This invention discloses a physical layer security method for RSMA communication combining artificial noise and network coding. In the first time slot, based on the channel state information from the source node to the relay node and from the relay node to the trusted user, an optimal full-duplex relay is selected using the maximum-minimum relay selection method to receive the RSMA signal transmitted by the source node. The selected relay simultaneously transmits artificial noise to weaken the untrusted user, and the full-duplex trusted user also transmits artificial noise to interfere with the untrusted user. In the second time slot, the optimal relay decodes the received signal according to the RSMA mechanism, uses network coding to encode the artificial noise generated by the relay in the first time slot and the signal sent to the trusted user, and then uses RSMA technology to encode the resulting network-coded signal, the public signal, and the signal sent to the untrusted user into an RSMA signal, which is then forwarded. This invention improves the security of legitimate users while ensuring the transmission reliability of untrusted users.

A configuration method for a network coding function and related apparatus are disclosed in this application. A terminal sends capability information to an access network device wherein the capability information indicates a network coding capability supported by the terminal. The capability information may be at least one of: a network coding type, a size of a code block, a quantity of original data packets, a quantity of redundancy packets, a bit rate of network coding, a convolution depth, a size of a finite field for a coding operation, or a maximum data volume capable of being processed by the terminal. The terminal receives configuration information from the access network device, wherein the configuration information indicates the terminal to configure a network coding function, and the configuration information is determined by the access network device based on the capability information.

This application relates to a method, system, and computer equipment for supply chain resilience analysis and optimization. It includes: constructing an initial tensor based on the supply chain's on-site situation and objective constraints, encompassing information such as logistics subgraphs, task requirements, vehicle capacity, and primary / backup road networks; generating a context vector by fusing graph features, numerical features, and constraint features through network coding; performing sequence decoding on the context vector and combining it with objective constraints to generate lower-level scheduling decisions; and finally mapping the decision results to obtain a comprehensive level of supply chain resilience. Therefore, it achieves a closed-loop process from situational awareness and optimization decision-making to resilience level evaluation, providing decision support and quantitative basis for supply chain resilience analysis.

This invention discloses a dynamic spectrum allocation and multi-path collaborative transmission communication method and system for unmanned platforms. The method involves: first, real-time scanning of the operating frequency band, synchronously collecting signal strength and interference types of the target frequency band, generating a spectrum occupancy heatmap, and classifying interference signals; then, generating an availability probability map of each sub-channel within a future time window to predict the spatiotemporal distribution of interference sources; next, constructing a deep reinforcement learning (DRL) model to achieve dynamic allocation of transmission resources; finally, when the detected interference intensity exceeds a preset threshold, activating a multi-band, multi-path concurrent transmission and network coding mechanism, with the main path using a low-frequency band to ensure coverage, and the backup path using a high-frequency band to ensure rate. The receiving end processes the received data using a confidence-weighted fusion algorithm. The system includes a spectrum sensing module, a decision engine, and a multi-path transmission module. This invention improves communication efficiency and anti-interference performance, is highly adaptable, flexible in deployment, and has good scalability.

The application discloses a SPAD depth optical flow estimation and reconstruction method based on a counter overflow interval, belongs to the technical field of neuromorphic visual perception and image processing, and effectively improves the timing stability under a low photon counting condition through short-time statistical modeling and overlapping time window coding, so that the structural representation of a dynamic area is more reliable; a shared weight pulse neural network coding structure is adopted to reduce the parameter scale and enhance the consistency of cross-time window modeling, and the characteristics of passive SPAD sparse pulse data are adapted; an alternating update mechanism of image reconstruction and optical flow is introduced in the decoding stage, so that the optical flow can perform timing alignment and constraint on the reconstruction process, and the reconstruction feature can inversely refine the optical flow, thereby obtaining higher reconstruction robustness in a high-speed dynamic scene; through joint optimization of image reconstruction loss and optical flow loss, the structural recovery capability of an image at a key moment is improved, and the finally reconstructed image has higher clarity and stability.

Embodiments of the present application provide a data processing method for a network communication system, and a related device. The data processing method comprises: obtaining, from a plurality of batches of encoded packets subjected to network coding and transmitted by a data sending end, a data vector sequence to be decoded and a matrix sequence to be decoded, said matrix sequence comprising a plurality of matrices to be decoded; performing row reduction on all matrices to be decoded in said matrix sequence to obtain a reduced matrix sequence, and recording a corresponding row transformation operation sequence; and performing reduction iteration on the reduced matrix sequence until variable columns of all said matrices are solved or no decodable variable columns exist, the row transformation operation sequence being used for performing a transformation operation on said data vector sequence to obtain decoded data. The efficiency of solving data vectors to be decoded is improved, and the decoding efficiency and decoding reliability of a matrix sequence to be decoded are improved.