7results about How to "Reduce Feedback Overhead" patented technology

The invention discloses an uplink and downlink combined wireless communication method and system based on channel semantic feature feedback. The method constructs an uplink and downlink closed-loop semantic communication architecture: a terminal side obtains a downlink channel matrix, generates a channel semantic feature vector through a channel semantic feature extraction network, inputs the channel semantic feature vector into a compression coding network to obtain a low-dimensional feedback code word, and sends the low-dimensional feedback code word to a base station side through an uplink limited feedback link; the base station side decodes and restores the low-dimensional feedback code word to obtain a reconstructed channel semantic feature vector, inputs the reconstructed channel semantic feature vector as prior information into a channel sensing sequence coding and modulation network, and generates a complex modulation signal under the condition of meeting the transmission power constraint; and the terminal side is combined with local channel information, and original data is recovered through a channel sensing demodulation network. Through joint optimization of the channel semantic feedback and the transceiver end-to-end transmission process, the channel state information feedback overhead is reduced under the constraint of limited feedback resources, and the transmission reliability and robustness in a complex channel environment are improved.

The application discloses a high-efficiency beam training method, device, medium and product under near field communication, relates to the technical field of communication, and comprises the following steps: selecting code words from the first layer of a stage one codebook according to the index of optimal code words; finding out the optimal code words from the selected code words and updating the index; feeding back the updated index to a base station; determining whether the first cycle parameter is greater than the first maximum cycle parameter, executing the above steps when the first cycle parameter is greater than the first maximum cycle parameter, and setting the second cycle parameter otherwise; selecting code words from the first layer of a stage two codebook according to the index of the current optimal code words; finding out the optimal code words from the selected code words and updating the index; feeding back the updated index to the base station; determining whether the second cycle parameter is greater than the second maximum cycle parameter, outputting the code word at the optimal code word index after updating when the second cycle parameter is greater than the second maximum cycle parameter, and returning to execute the above steps otherwise. The application can effectively improve the reachable rate performance in near field communication and significantly reduce the training and feedback overhead.

A method by a wireless device includes receiving configuration information from a network node, the configuration information enabling hybrid automatic repeat request acknowledgement (HARQ ACK) and / or negative acknowledgement (HARQ NACK) feedback for a first set of HARQ processes and disabling HARQ ACK and / or HARQ NACK for a second set of HARQ processes. The wireless device constructs a first HARQ codebook of a first type based on a first set of HARQ process numbers of the first set of HARQ processes for which HARQ ACK and / or HARQ NACK feedback is enabled and sends HARQ ACK and / or HARQ NACK feedback based on the first HARQ codebook to the network node.

This application discloses a channel state information (CSI) feedback method, system, electronic device, and readable storage medium. The method includes: measuring initial channel state information with a network device and converting the initial channel state information into a two-dimensional grid representing positions in a target dimension; the target dimension includes angular and temporal domains; extracting sparse semantic feature information from the two-dimensional grid, the sparse semantic feature information including at least the position information of the main propagation path in the two-dimensional grid, the main propagation path including several propagation paths determined based on the most energetic propagation path; and sending the sparse semantic feature information to the network device, so that the network device reconstructs the initial channel state information based on the sparse semantic feature information. This technical solution can reduce the occupation of uplink channel resources, ensure good reconstruction results in different types of scenarios, and enhance the generalization ability of the CSI feedback process.

The application discloses a channel information compression feedback method of an asymmetric network structure. First, a two-dimensional Fourier transform is used to convert a channel state information (CSI) matrix in a space-frequency domain to an angle-delay domain, then a complex matrix is split into two real number sub-matrices and spliced, and the value range of the CSI matrix is adjusted; a coding network extracts a feature map and a position map of the CSI through an amplitude pooling module, and fuses the feature map and the position map into a feedback code word through a position embedding module; a decoding network extracts a feature map and a position map from the received code word, restores a rough CSI through an inverse pooling layer, and finally further improves the accuracy of CSI reconstruction through a feature fine-tuning network. The application introduces a pooling structure at an encoder end, introduces trainable network parameters only at a decoder end, removes the network trainable parameters at the encoder end through the asymmetric network structure, and introduces a residual compression excitation network, so that the CSI recovery accuracy can be effectively improved.

This application provides a method, apparatus, electronic device, storage medium, and product for data retransmission. The method includes: receiving control information and service data sent by each wireless mesh network node, wherein each node is a neighbor node of a target node; detecting the service data of each node based on the control information of each node; generating Hybrid Automatic Repeat Request (HARQ) feedback information for each node, wherein the HARQ feedback information is ACK or NACK; and then the target node sends the HARQ feedback information of each node through the Physical Downlink Control Channel (PFSC), so that each node determines whether to retransmit the corresponding control information and service data based on the corresponding HARQ feedback information. This method reduces the feedback overhead caused by transmission via the PSFCH.

The invention discloses a channel information compression feedback method and system based on a large language model. The method comprises the steps that firstly, a channel state information compression feedback task is reconstructed into a mask lexical element prediction task aligned with the function of the large language model; then, an information theory mask selection strategy based on self-information is designed, channel state information elements with the highest self-information are recognized and screened out at a user side to serve as visible lexical elements to be fed back, elements with the low self-information serve as masked lexical elements, and therefore the prediction accuracy of the large language model is maximized; and the base station end reconstructs complete channel state information representation according to feedback visible lexical elements through context reasoning by utilizing the strong modeling capability of a large language model. According to the method, the user side only needs to deploy a lightweight network, the calculation complexity is mainly concentrated on the base station side, the limitation of a traditional small model on the channel state information reconstruction precision is effectively broken through, and the communication rate in a multi-user multi-input multi-output scene is remarkably improved.