1095 results about "Codebook" patented technology

A correlation-aware adaptive codebook compaction system for multi-modal data compression that preserves cross-modal relationships while providing enhanced reconstruction quality. The system analyzes temporal and spatial relationships between different data modalities to generate correlation maps that guide compression decisions. A virtual management layer performs stream characterization and adaptive routing, while a processing pipeline implements primary codebook compression with mismatch handling for novel data blocks. High-entropy data segments receive pre-compression processing before codebook compression. Sequential registration data is processed through matrix factorization and dedicated matrix codebooks. The system continuously monitors data distribution characteristics and automatically retrains codebooks when drift thresholds are exceeded. A neural upsampling subsystem uses correlation information to guide cross-modal enhancement processes through modality-specific networks and attention mechanisms. The unified output includes compressed data streams, correlation maps, synchronization metadata, neural model parameters, and updated codebooks, enabling synchronized reconstruction with preserved cross-modal relationships and enhanced quality through correlation-guided neural upsampling.

An adaptive random access system and method with learned query optimization for compacted data files that enhances random access performance through machine learning and pattern recognition. The system incorporates a query pattern learning module that analyzes historical access patterns and user behavior to build statistical models of data usage. An adaptive estimator module improves location estimation accuracy by incorporating learned patterns rather than relying solely on mathematical calculations. A predictive boundary detector uses learned codeword patterns to more accurately identify boundaries in compacted data, reducing misalignment errors. An intelligent search engine coordinates optimization strategies including context-aware search string parsing and encoding strategy selection based on learned performance data. A dynamic codebook optimizer reorganizes sourceblock layout based on access frequencies and co-occurrence patterns to improve retrieval speed. An enhanced search cache implements predictive caching algorithms that anticipate user queries and proactively load relevant data.

A federated system and method for data compression optimization in distributed device networks. The system comprises multiple edge devices that analyze local data patterns to generate device characteristic profiles while performing local compression optimization and maintaining data privacy. Edge devices contribute to collaborative learning by generating privacy-preserved updates without transmitting raw data. A central coordination system aggregates encrypted contributions using secure multi-party computation protocols, identifies device groups based on data pattern similarities, and generates optimized compression parameters for each group. The system coordinates collaborative training of data reconstruction models across device groups and deploys group-optimized reconstruction capabilities. Device grouping is performed by calculating similarity scores between device characteristic profiles and clustering devices with scores above predetermined thresholds. The system dynamically adapts compression and reconstruction parameters through federated learning while preserving individual device data privacy, enabling efficient data compression and near-lossless recovery across heterogeneous Internet-of-Things networks.

Methods, systems, and devices for wireless communications are described. Feedback based codebooks for reducing or eliminating interference between orbital angular momentum (OAM) based backhaul communications between a first network node and a second network node and access communications between the first network node and a user equipment (UE) are described. The first network node may transmit a message to a UE indicating a feedback codebook for a set of reference signals associated with OAM modes. The first network node may transmit the reference signals, where each reference signals may be associated with a respective OAM mode. The UE may generate and indicate in a feedback report to the first network node codewords corresponding to UE feedback for the received reference signals. The first network node may communicate with the UE via an access link and with the second network node via a backhaul link based on the feedback report.

A computer-implemented method includes converting by a pose tokenizer, based on a learned codebook, pose parameters of a body into a sequence of discrete pose tokens; randomly masking a portion of the sequence of discrete pose tokens; predicting the randomly masked sequence of discrete pose tokens based on multi-scale features extracted from a monocular image by an image conditioned masked transformer; optimizing the sequence of discrete pose tokens by aligning a re-projected three-dimensional (3D) pose with an estimated two-dimensional (2D) pose; directly regressing, from the multi-scale features, a shape parameter of the body and a weak perspective camera parameter; and generating a 3D mesh reconstruction of the body based on the shape parameter and the weak perspective camera parameter.

A system and method for data compaction and encryption of anonymized data records. A dataset may be pre-processed by dividing into sourceblocks at reasonable intervals and tallying each sourceblock's frequency, creating a tally record of tokens and count values. This tally record may then be anonymized and transmitted to a data deconstruction engine which combined with a library manager creates a codebook and performs optimization techniques on the codebook. The data deconstruction engine and library manager may be distributed across multiple nodes or devices. The received anonymized tally record may be parsed into individual tokens by identifying the tokens with the highest count value. The tokens may then be sent descending order of count value to the library manger where each token may be assigned a codeword. A half-backed codebook is then created using the tokens and each token's unique codeword, before sending the half-backed codebook to a system user.

The invention discloses a semantic-driven intelligent agent capability discovery method and device oriented to the intelligent agent Internet, and the method comprises the steps: firstly generating an intelligent agent structured portrait which covers the three-dimensional information of skills, roles and states; semantic coding is carried out on the portrait, and the portrait is converted into a high-dimensional semantic vector; then, the vector is partitioned, a codebook is generated in each subspace in a clustering mode, and the codebook comprises representative vectors and serial numbers of the representative vectors; and quantizing the sub-vectors into numbers based on a codebook, and splicing the numbers to form discrete identification codes of the agent index. And when the index is updated, incremental maintenance is executed according to the distance between the new agent sub-vector and the vector in the codebook. Meanwhile, a generative retrieval model is trained, task query is directly mapped into discrete identification codes, historical and new task samples are mixed for continuous learning in training, and stability constraints are introduced. According to the method, through semantic portraits, a quantitative index mechanism and memory enhancement continuous learning, an end-to-end retrieval and rapid updating capability discovery scheme is constructed.

The embodiment of the invention provides a self-supervised emotion recognition method based on a heart and brain combined codebook and related equipment, and belongs to the technical field of physiological signal processing and artificial intelligence. The method comprises the following steps: respectively defining heart beats of electrocardiosignals and electroencephalogram signal segments with equal lengths as words, and constructing sentences; a shared heart and brain joint codebook is created and trained, and electrocardio and electroencephalogram words are mapped to a unified discrete semantic space through vector quantization so as to learn cross-subject general characterization; then, discretizing a signal sentence by using the codebook, and combining space and position embedding and inputting a Transform encoder to carry out mask pre-training so as to learn context semantics of the signal; and finally, finely tuning the pre-training model for an emotion recognition task. According to the method, deep semantic fusion of heart and brain signals is realized through signal structuring and codebook sharing, dependence on labeled data is effectively overcome, and emotion recognition accuracy and cross-subject generalization ability are remarkably improved.

The invention provides a weak supervision video anomaly detection method and system based on prototype orthogonality, and the method comprises the steps: inputting a visual feature sequence into a selective state space model, so as to filter redundant information in a time sequence, capture a key dynamic state, and output a high-value time sequence feature; then, a learnable prototype codebook containing a normal category prototype codebook and an abnormal category prototype codebook is given, end-to-end training is carried out by adopting a multi-instance learning framework of a video-level label, prototype orthogonality constraint is applied in the training process, and after training is completed, the normal category prototype codebook and the abnormal category prototype codebook are subjected to end-to-end training; according to the method, only the distance between the high-value time sequence feature and the nearest prototype in the abnormal category prototype codebook is needed, and the video anomaly score is obtained according to the distance, so that video anomaly detection is realized. According to the method, the global geometric constraint of prototype orthogonality is introduced, and the selective state space model (S3M) with efficient calculation is combined, so that the extremely light weight of the model is realized while the high detection precision is ensured.

A system and method for a wireless device to derive a channel state information (CSI) codebook based on a decoder and a vector quantization codebook, receive a reference signal from a base station, derive an estimated channel from the reference signal, select an entry from the CSI codebook based on the estimated channel and a selection criterion, and report an index of the selected entry to the base station. The wireless device may receive a subset indication, derive therefrom a second CSI codebook, and select the CSI codebook entry from the second CSI codebook. A CSI compression machine learning (ML) system and vector quantization codebook may be obtained by a network controller. The decoder may be a part of the CSI compression ML system, the vector quantization codebook may be based on an encoder of the CSI compression ML system, and they may be sent to the wireless device.

Apparatuses and methods for channel state information (CSI) and calibration reporting. A method performed by a user equipment (UE) includes receiving information related to first and second CSI reports. The information for the first CSI report indicates NTRP CSI reference signal (CSI-RS) resource sets, NTRP>1, and a report quantity set to ‘cjtc-Dd’. The information for the second CSI report indicates NTRP CSI-RS resources, a report quantity set to ‘cri-RI-PMI-CQI’, and a codebook type set to ‘typeII-CJT-r18’. The first CSI report is linked to the second CSI report via a radio resource control (RRC) parameter. The method further includes determining, based on the information, a CSI for the second CSI report and transmitting the second CSI report including the CSI.

A system and method for cross-stream asymmetric enhancement combines machine learning-driven asymmetric codebook generation with dyadic distribution algorithms to enable simultaneous optimization of compression efficiency, cryptographic security, and error correction capability. The system analyzes input data characteristics and initializes multiple specialized ML models to generate stream-specific asymmetric codebooks optimized for different objectives. Enhanced dyadic distribution processing creates three pre-conditioned data streams that are processed through parallel asymmetric transformation pipelines: compression-optimized for maximum data reduction, security-optimized for cryptographic strength, and error-correction-optimized for robust recovery capability. Cross-stream optimization coordinates the multiple processing paths to ensure overall system coherence while maintaining individual stream objectives. The system supports multiple operating modes including ultra-high compression using only the primary stream, broadcast quality using primary and secondary streams, and archival mode using all streams for lossless reconstruction. The system supports graduated access control that enables different reconstruction quality levels based on available stream combinations.

A method of detecting superimposed SCMA signals from multiple user equipment in a receiver of an OTFS communication system includes initializing an executing an iteration loop, in which a mean of all a posteriori estimates of the transmitted signal determined so far is calculated, which a posteriori estimates are based on the OTFS-demodulated received signal, the corresponding channel matrix, and the mean vectors and variances determined for each UE. The mean of all a posteriori estimates determined so far is used for determining vectors and variances for each UE, further using the probabilities of the non-zero elements of the respective UEs codebooks. The iteration is repeated until a termination criterion is met.

The invention provides a semi-supervised signal modulation identification method based on multi-codebook discrete virtual adversarial training, and the method comprises the steps: carrying out the high-dimensional potential representation coding of input labeled and unlabeled sample signals through employing a vector quantization generative adversarial network, so as to obtain a continuous potential representation; mapping the continuous potential representation into a discrete vector sequence through a quantizer; virtual confrontation disturbance meeting the condition that the L2 norm does not exceed epsilon is applied to the unlabeled sample at the input end, and a disturbance sample is generated; respectively inputting a labeled sample, a label-free sample and a disturbance sample into a classifier, calculating cross entropy loss and KL divergence consistency loss, and jointly optimizing parameters of an encoder, a codebook and the classifier in a weighted sum form; therefore, the discrete potential representation is obtained through the vector quantization generative adversarial network, disturbance is constructed for the unlabeled sample at the input end, and joint optimization is performed in combination with the cross entropy and the KL divergence loss, so that the recognition accuracy and robustness under the conditions of few labels and low signal-to-noise ratio are improved.

A UE-associated entity may train an encoder to encode uplink control information. The UE-associated entity may determine a quantization codebook to be applied to the encoded uplink control information. The UE-associated entity may share a sequential training dataset with a base station-associated entity, the sequential training dataset including: one of an input vector set or an output vector set; and one of an encoded and unquantized intermediate vector set or an encoded and quantized intermediate vector set. The base station-associated entity may train a decoder based on a quantization codebook and at least the sequential training dataset from the UE-associated entity. When the base station-associated entity receives multiple sequential training datasets for different vendors, the base station-associated entity may train a multi-vendor decoder based on the multiple sequential training datasets.

An information transmission method and device, and a HARQ-ACK codebook generation and transmission method and device, are provided. The information transmission method includes transmitting downlink control information DCI used for triggering a one-shot hybrid automatic repeat request acknowledgement HARQ-ACK codebook to report, where the DCI carries assistance information instructing a terminal to perform one-shot HARQ-ACK codebook reporting.

Methods, systems, and devices for wireless communications are described. A UE may receive one or more control messages that indicate a quantity of a set of sounding reference signal (SRS) resource sets configured for codebook usage and at least one maximum rank value associated with uplink shared channel transmissions by the UE. The UE may receive downlink control information (DCI) with an SRS resource indicator (SRI) field and a transmit precoding matrix indicator (TPMI) field. The UE may then interpret the SRI and TPMI fields according to a mapping that is based on the maximum rank value and a maximum quantity of ports the UE is capable of supporting. Then, the UE may transmit the uplink shared channel message in accordance with the mapping.

The invention discloses a physical feature perception large language model construction method for flow field understanding and generation, and belongs to the technical field of intelligent aerodynamics, multi-modal deep learning and computer vision crossing. High-level aerodynamic semantics and bottom-level physical feature learning of a flow field are decoupled through a double-codebook sharing mapping mechanism, and alignment of the high-level aerodynamic semantics and the bottom-level physical feature learning is kept at the same time. The discrete unified representation obtained through the token device is combined with a large language model, high-precision physical reconstruction and deep aerodynamic semantic understanding of the flow field image can be achieved at the same time under a single model framework, and the core problems that in the prior art, perception and generation tasks are split, and the fidelity of physical characteristics is low are effectively solved.

A terminal is disclosed that includes a receiver that receives beamforming information relating to one or more beamformed Channel State Information—Reference Signals (CSI-RSs), the CSI-RSs corresponding to one or more Spatial Domains (SDs) or Frequency Domains (FDs). The terminal also includes a processor that determines a type of the one or more CSI-RSs, and when the type of the one or more CSI-RS is a Type II, performs a Type II port selection codebook with a beamformed CSI-RS of the one or more CSI-RSs in the SD and FD domains.

A method of wireless communication includes determining a first precoding matrix indicator (PMI) value and a second PMI value, the first PMI value indicating a first matrix W1 of a first codebook C1, the second PMI value indicating a second matrix W2 of a second codebook C2, wherein the first matrix W1 and the second matrix W2 together define a precoding matrix W for multi-antenna transmission. The method also includes transmitting the first PMI value at a first periodicity, and transmitting the second PMI value at a second periodicity shorter than the first periodicity. In some examples, the method also includes transmitting a rank indicator (RI) value, where the first PMI value and the second PMI value are determined based on the RI value.

A method for wireless communication, the method comprising: selecting a set of orthogonal spatial bases of an antenna array for supporting up to eight orthogonal layers for up to 128 ports, wherein each spatial basis of the set can support up to two orthogonal layers based on a first horizontal phase compensation factor value that is associated with a first layer of the two orthogonal layers for a first spatial basis and based on a second, opposite horizontal phase compensation factor value that is associated with a second layer of the two orthogonal layers for the first spatial basis; and causing transmission of a radio signal using the set of spatial bases, or preparing, for transmission, feedback specifying the preferred spatial bases as part of CSI (Channel State Information).

The invention discloses a monitoring image multi-target tracking method based on deep learning, and relates to the technical field of digital image processing, and the method comprises the following steps: S1, generating a multi-scale feature pyramid; s2, extracting causal feature vectors; s3, generating a discrete codebook index; s4, constructing a dynamic graph; s5, inputting the dynamic graph into an improved ASTGCN network, iteratively fusing space-time attention weights and Hamilton dynamics evolution characteristics between nodes through cascaded Hamilton space-time blocks, and generating a final prediction state of each historical track node; s6, solving an optimal correlation matching matrix by using a Hungary algorithm; and S7, extracting all active track information. According to the method, the limitations of identity drift caused by variable appearance characteristics and inaccurate prediction caused by lack of physical priori in a traditional multi-target tracking method are overcome, and an efficient, accurate and robust solution is provided for intelligent video monitoring.

Provided in the embodiments of the present application are communication methods and communication apparatuses, which can send first carriers on the basis of configurations of the first carriers. A method comprises: on the basis of a configuration of a first carrier, a first node sending the first carrier to an ambient Internet-of-Things (AIoT) device, wherein the configuration of the first carrier comprises one or more of the following: a power configuration of the first carrier, a carrier spacing configuration of the first carrier, a guard band configuration of an AIoT system, a frequency hopping configuration of the first carrier, a codebook configuration of the first carrier, or a waveform configuration of the first carrier, and the first carrier is used for carrying modulation information of the AIoT device in the AIoT system.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, in a control resource set (CORESET) associated with a first CORESET pool index or a second CORESET pool index, downlink control information (DCI) including an indication that a hybrid automatic repeat request acknowledgement (HARQ-ACK) codebook scheduled in a first slot is to be retransmitted in a second slot. The UE may transmit, in the second slot and in connection with receiving the DCI, a first HARQ-ACK codebook associated with the first CORESET pool index or a second HARQ-ACK codebook associated with the second CORESET pool index. Numerous other aspects are described.

A distributed system and method uses a virtual management layer to classify incoming heterogeneous data streams by type, attach association flags to related streams, and route each stream to a selected compression or decompression subsystem executing on available computing devices. The virtual layer allocates tasks using live resource conditions to enable parallel processing across devices and per-type optimization (e.g., statistical, codebook, or neural techniques). Outputs returned from disparate devices are collected and deterministically regrouped using the association flags so related streams are preserved regardless of where processing occurred. The architecture supports both compression and decompression workflows, load-balanced scheduling, and scalable operation across multiple devices, improving throughput while maintaining relationships among multi-type data.

A base station may identify a first antenna configuration of the base station and a second antenna configuration of a wireless device. The base station may select one or more codebook-based precoders for communication with the wireless device with LOS MIMO. The one or more codebook-based precoders may include at least one of a Legendre precoder, a block-DFT precoder, a DFT precoder, a block-Walsh precoder, a Walsh precoder, a block-Legendre precoder, a Kronecker Legendre precoder, a Kronecker block-DFT precoder, or a Kronecker block-Walsh precoder. The base station may transmit, to a wireless device, an indication of a second codebook-based precoder for transmission from the wireless device to the base station with LOS MIMO. The base station and the wireless device may communicate with each other with LOS MIMO based on one or more codebook-based precoders.

Methods and apparatus are provided for configuring a dynamic hybrid automatic repeat request acknowledgement (HARQ-ACK) codebook for a network-controlled repeater (NCR). A first HARQ-ACK group is configured for physical downlink control channel (PDCCH) transmissions from a base station to the NCR. The PDCCH transmissions include first side control information. A second HARQ-ACK group is configured for scheduled physical downlink shared channel (PDSCH) transmissions from the base station to the NCR. The scheduled PDSCH transmissions include second side control information. A third HARQ-ACK group is configured for downlink (DL) channels or signals from the base station for the NCR to forward to a user equipment (UE). The dynamic HARQ-ACK codebook includes a combination of the first HARQ-ACK group, the second HARQ-ACK group, and the third HARQ-ACK group.

The disclosed method for generating virtual objects includes generating, based on object data, compressed object data, performing, based on the object data and scales, operations to train a first untrained machine learning model to generate a first trained machine learning model comprising a trained codebook and a trained decoder, wherein the first trained machine learning model is trained to generate a reconstruction of the compressed object data, generating, based on the compressed object data and the scales and using the first trained machine learning model, token maps data, performing, based on the token maps data and conditions, operations to train a second untrained machine learning model to generate a second trained machine learning model comprising a trained autoregressive model, wherein the second trained machine learning model is trained to generate predicted token maps, and generating, based on the scales, conditions, and using both trained models, a virtual object.

Aspects relate to mechanisms for a UE to dynamically update and re-calibrate beamforming codebooks based on a current foldable state of the UE. The UE may include a first tile including a first antenna array and a second tile including a second antenna array. The UE may be capable of being configured in a plurality of different foldable states, each defined by a respective angular separation between the first tile and the second tile. The UE can further maintain a plurality of beamforming codebooks, each associated with a respective configured foldable state of the UE, and update a beamforming codebook of the plurality of beamforming codebooks based on the current foldable state.

A user equipment receives downlink control information (DCI) for releasing a plurality of semi-persistent scheduling (SPS) resources, and transmits a HARQ-ACK codebook including HARQ-ACK information for releasing the plurality of SPS resources. The HARQ-ACK codebook includes the HARQ-ACK information for releasing the plurality of SPS resources at the position of a HARQ-ACK bit corresponding to an SPS resource having the lowest SPS setting index among the plurality of SPS resources.