3342 results about "Codebook" patented technology

A method is provided for mapping the latent space of a Vector Quantized Variational AutoEncoder (VQ-VAE) to polynomial basis vectors. The method includes training a VQ-VAE model on a dataset to obtain a set of codebook vectors representing the latent space; defining a polynomial basis for the latent space, the polynomial basis containing terms up to a predetermined order; mapping each codebook vector to the polynomial basis by determining polynomial coefficients that represent each codebook vector in terms of the polynomial basis; and using the polynomial coefficients to reconstruct and manipulate latent space representations.

Systems, apparatuses, methods, and computer-readable media are provided for dynamic hybrid automatic repeat request (HARQ)-acknowledgement (ACK) feedback for multi-cell scheduling (e.g., a downlink control information (DCI) that schedules physical downlink shared channels (PDSCHs) and / or physical uplink shared channels (PUSCHs) on multiple cells). Embodiments may include techniques to determine a downlink assignment index (DAI) and / or a HARQ-ACK codebook, e.g., a Type-1. Type-2, and / or Type-3 codebook, for multi-cell scheduling. Other embodiments may be described and claimed.

A system for adaptively caching network communication protocols provides improved efficiency and performance through a multi-level cache architecture. The system monitors performance metrics and synchronizes cache contents across distributed nodes using a hierarchical structure. Protocol cache requirements are predicted based on usage patterns, enabling proactive cache management. The system compresses cached protocols using existing codebooks to optimize storage and transmission efficiency. Integration with event-driven data communication systems enables seamless protocol selection and translation. The caching system works in conjunction with transaction managers and protocol predictors to enhance network communication performance. The system maintains cache coherency across local, regional, and global cache levels while minimizing network overhead and optimizing protocol availability. By predicting and pre-caching likely needed protocols, the system reduces protocol negotiation latency and improves overall network communication efficiency.

The codebook-based homomorphic compression system is a novel approach that combines data compression and homomorphic encryption to enable efficient and secure computation on compressed data. It involves quantizing the input data, generating an optimized codebook using techniques like Huffman coding or deep learning, and compressing the data by replacing each value with its corresponding codeword. The compressed data is then encrypted using a homomorphic encryption scheme, allowing computations to be performed directly on the encrypted compressed data without decryption. The system includes a deep learning architecture trained on and operating on the homomorphically compressed and encrypted data, enabling inference and decision-making while maintaining data privacy. This approach combines the benefits of data compression, homomorphic encryption, and deep learning, enabling efficient storage, transmission, and secure computation on compressed data streams.

According to some embodiments, a method performed by a wireless device comprises obtaining a sounding reference signal (SRS) resource configuration for 6 or 8 SRS ports and transmitting SRS according to the SRS resource configuration. In particular embodiments, the SRS resource configuration comprises an SRS resource for 6 or 8 SRS ports wherein the SRS resource is divided into at least two subsets, wherein each subset is associated with a different comb offset. In particular embodiments, the SRS resource configuration comprises two SRS resources. Each SRS resource supports up to 4 SRS ports. Transmitting SRS according to the SRS configuration comprises transmitting SRS using an 8 port codebook.

A system and method for deep learning using a large codeword model with homomorphically compressed and dyadically encrypted data is disclosed. The system preprocesses input data, applies homomorphic-dyadic compression and encryption, tokenizes the compressed data into sourceblocks, and assigns codewords using a codebook. These codewords are processed through a machine learning core, which can be either a conventional transformer-based architecture or a latent transformer core utilizing a variational autoencoder. The system enables secure operations on encrypted data, preserving privacy while allowing complex computations. The processed output is decrypted, decompressed, and translated to match the input modality. A neural upsampler may further enhance the output. The machine learning core is continuously trained using the processed data and additional training data, improving performance over time.

A system and method for implementing multilayer security in documents using multiple codebooks. The system encodes different sections of a document using codebooks associated with specific security clearance levels. Users can only access sections of the document for which they have appropriate clearance, with unauthorized sections appearing redacted. The system provides granular, section-level security while also offering data compression benefits. Additional features include dynamic reclassification, hierarchical codebooks, expiring access, multi-factor authentication, and user-specific watermarking.

The invention relates to the technical field of speech synthesis, can be applied to business scenes such as financial science and technology, medical health and the like, and discloses a speech generation method, device, equipment and medium. And inputting a text speech language model to generate an intermediate code in combination with a speech code extracted based on a codebook generation mode, extracting a speaker feature vector in the prompt speech, decoding the intermediate code and the speaker feature vector by a generative adversarial decoder, and outputting a target speech. According to the method, fine-grained text representation is established by fusing character semantics and pinyin pronunciation information, and voice cloning is completed through unified voice language modeling and an adversarial generation mechanism in combination with codebook-driven acoustic coding and speaker personality characteristics, so that the naturalness, similarity and pronunciation accuracy of generated voices are improved.

The invention discloses a semantic communication method based on a semantic perception mask and a vector quantization codebook, and belongs to the technical field of wireless communication. Specifically, the invention provides a semantic perception compression strategy, semantic perception masking is performed on an input image according to the semantic importance size represented by the attention vector of the last self-attention layer of an image encoder of a CLIP model, image blocks with relatively low semantic importance can be selectively masked instead of random masking, and therefore, the semantic perception compression strategy can be applied to image processing. Therefore, the semantic information learning capability of the model is enhanced, and the training efficiency is improved. In addition, an improved robust vector quantization codebook shared at a transmitting end and a receiving end is designed. According to the codebook, coding features are represented by orthogonal and trainable base vector indexes in transmission, so that the robustness of a system is enhanced, and the transmission data volume is reduced. According to the method provided by the invention, the semantic information processing efficiency can be remarkably improved, and better performance is shown under the challenging low signal-to-noise ratio condition.

A system and method for accelerating applications in closed networks through intelligent compression and routing. The system includes a flow analysis system that classifies network traffic as latency-critical or bandwidth-critical, enabling optimized handling of different flow types. Latency-critical flows are transmitted directly to minimize delay, while bandwidth-critical flows undergo compression using dynamically selected methods including Huffman, alphabetic, and Tunstall coding. The system maintains synchronized codebooks across network nodes while enabling node-specific optimizations based on local traffic patterns. A network topology manager maintains comprehensive network state awareness, enabling intelligent route selection based on flow classification and current conditions. The system continuously monitors performance and adapts compression and routing strategies in real-time. This approach enables significant performance improvements in closed network environments where all compression-accelerated applications are developed by the same team.

A neural network audio codec system and related methods are provided. In one example, a method is provided comprising: obtaining speech audio to be encoded; applying the speech audio to an audio encoder that is part of a neural network audio codec system that includes the audio encoder and an audio decoder. The audio encoder and the audio decoder have been trained in an end-to-end manner. The speech audio is encoded with the audio encoder to generate embedding vectors that represent a snapshot of speech audio attributes over successive timeframes of the raw speech audio, and from the embedding vectors, codeword indices are generated to entries in a codebook. The codeword indices are then transmitted or stored for later retrieval and processing by the audio decoder. Further aspects include converting the speech audio to text based on decoding the codeword indices, translating the speech audio from a first language into a second language by mapping codeword indices from a first language to a second language, converting the speech audio prosody by mapping the codeword indices, text generation and discrimination tasks.Yet another aspect includes converting text to speech audio with a different prosody.

A method and apparatus for determining uplink scheduling information. The method includes a user equipment (UE) reports full power transmission capability and / or coherence transmission capability to a base station, determining a codebook subset of a codebook-based PUSCH and / or second information according to first information, the first information comprising at least one of the following information: the full power transmission capability, the coherence transmission capability, codebook subset restriction information of the codebook-based PUSCH, and first instruction, and the second information comprising an overhead indicated by a precoded matrix and the number of transport layers of the codebook-based PUSCH and / or an encoding mode indicated by the precoded matrix and the number of transport layers of the codebook-based PUSCH, and receiving uplink scheduling information of the codebook-based PUSCH, and determining the precoded matrix and the number of transport layers of the codebook-based PUSCH according to the uplink scheduling information of the codebook-based PUSCH.

Methods, apparatus, and systems are disclosed. One method includes the WTRU receiving a first Physical Downlink Shared Channel (PDSCH) associated with a first type of service or priority level in a first slot or mini slot and a second PDSCH associated with a second type of service or priority level in a second slot or mini-slot and determining a first HARQ codebook acknowledgment index (HCAI) based on a property of the first PDSCH or control information associated with the first PDSCH and a second HCAI based on a property of the second PDSCH or control information associated with the second PDSCH. The method includes generating for a subsequent slot or mini-slot, a first Physical Uplink Control Channel (PUCCH) including first HARQ-ACK information in accordance with the first HCAI and a second PUCCH including second HARQ-ACK information in accordance with the second HCAI and transmitting the first and second PUCCHs.

A neural network audio codec system and related methods are provided. In one example, a method is provided comprising: obtaining speech audio to be encoded; applying the speech audio to an audio encoder that is part of a neural network audio codec system that includes the audio encoder and an audio decoder. The audio encoder and the audio decoder have been trained in an end-to-end manner. The speech audio is encoded with the audio encoder to generate embedding vectors that represent a snapshot of speech audio attributes over successive timeframes of the raw speech audio, and from the embedding vectors, codeword indices are generated to entries in a codebook. The codeword indices are then transmitted or stored for later retrieval and processing by the audio decoder.

The invention discloses a reconfigurable intelligent metasurface beam tracking device, and belongs to the technical field of wireless communication. Specifically, the reconfigurable intelligent metasurface module integrates a large number of metasurface units, a tunable element is embedded to achieve reconfiguration of electromagnetic characteristics, a receiving end of the communication receiving and transmitting module receives reflected signals of the metasurfaces and feeds back the quality of the received signals in the moving process, and the positioning sensing module senses the position of the receiving end in real time. And the codebook calculation module calculates a phase regulation codebook based on the signal quality and the position feedback information, converts the phase regulation codebook into a control voltage value, transmits a corresponding digital control signal to the voltage regulation module, and outputs multiple paths of analog voltages, so that the reflection coefficient of the metasurface array is regulated and controlled, and real-time dynamic wave beam tracking is realized. According to the invention, the coverage range, the transmission rate and the service quality of the communication network are obviously improved.

A system and method for efficient data storage, transfer, synchronization, and security using automated model monitoring and training. The system analyzes test datasets to detect data drift, retraining encoding and decoding algorithms as needed. New data sourceblocks are created and assigned codewords, compiling an updated codebook for distribution to connected devices. A novel dyadic distribution subsystem simultaneously compresses and encrypts data by transforming input streams into a dyadic distribution. This process generates a compressed main data stream and a secondary stream of transformation information, which are combined into a secure output. The system includes a network device manager for optimizing codebook distribution based on device resource usage. Operating in both lossless and lossy modes, the system offers flexible, efficient, and secure data handling across various network configurations.

Apparatuses, methods, and systems are disclosed for configuring a codebook corresponding to TPMI. One method includes receiving a codebook configuration from a network. The codebook configuration corresponds to an enhanced UL codebook-based transmission, the codebook corresponds to a TPMI, the TPMI corresponds to uplink transmission, and the TPMI corresponds to at least one layer. The method includes transmitting a set of SRSs. The method includes receiving the TPMI via a DCI for scheduling a PUSCH transmission. The DCI is received on a PDCCH, a PDSCH, or a combination thereof, and the DCI is decomposed into a first stage DCI and a second stage DCI. The method includes receiving a subset of codebook parameters corresponding to the TPMI in a second stage DCI. The second stage DCI is received in the PDCCH, the PDSCH, or a combination thereof.

The invention provides an audio watermark generation method, audio watermark generation equipment and a computer storage medium. The audio watermark generation method comprises the following steps: acquiring target audio data; extracting amplitude spectrum features and phase spectrum features of the target audio data; acquiring watermark adding frame information of the amplitude spectrum features; selecting one watermark information code from a watermark codebook library, and performing frame-level copying according to the frame number of the amplitude spectrum characteristics to obtain first watermark data; performing frame selection on the first watermark data according to the watermark adding frame information to obtain second watermark data; fusing the amplitude spectrum feature with the second watermark data to obtain a watermark amplitude spectrum feature; and fusing the watermark amplitude spectrum feature and the phase spectrum feature to obtain watermark audio data. According to the audio watermark generation method, the watermark adding selector is designed, the frame number and the frame number needing to be added with the watermark are selected through the frame selection logic, and it is guaranteed that after the audio watermark is generated, the audio listening feeling is not affected.

A system and method for real-time time series forecasting using a compound large codeword model with integrated supervisory neurons. The system processes diverse inputs through adaptive codebook generation and codeword allocation. A projection network fuses different data types, creating unified representations for a latent transformer-based machine learning core. The core contains local neural network regions of interconnected operational neurons, monitored by supervisory neurons. These supervisory neurons receive activation data from operational neurons, perform real-time statistical analysis, determine necessary structural modifications, and initiate their implementation during operation. This architecture enables efficient handling of multi-modal data, capturing complex relationships between different input types. The combination of adaptive codebook generation and the supervisory neuron system ensures responsiveness to evolving data patterns and task requirements. This approach provides more accurate and timely forecasts by leveraging diverse data types in a sophisticated, integrated manner, while continuously adapting its structure to maintain optimal performance.

Procedures, methods, architectures, apparatuses, systems, devices, and computer program products directed, in part, to WTRU-specific codebooks generated based on channel state information (CSI) measurements and channel and / or transmission details, parameters and / or requirements. As an example, a WTRU may receive information indicating any of metrics and requirements for configuring a codebook; generate a codebook, comprising first parameters, based on the metrics and CSI related measurements associated with at least a first set of subbands, wherein the first parameters comprise a cluster of subbands having a CSI correlation satisfying a threshold and comprising at least one subband from any of the first set of subbands and a second set of subbands that is based on the first set of subbands; and transmit feedback information associated with CSI, the feedback information indicating at least some of the first parameters and second parameters associated with the at least some of the first parameters.

The invention relates to the technical field of picture generation, in particular to a picture generation method based on multi-scale features. The method comprises the following steps: firstly, collecting medical images, patient data and lesion stage information under different equipment and acquisition parameters, after screening preprocessing, constructing and training a multi-scale VQ-VAE model, introducing an attention mechanism, and adopting adaptive codebook updating and multi-codebook fusion quantification; then, a hierarchical autoregression model based on a Transform decoder is constructed and trained, and lesion stage information is fused into the hierarchical autoregression model; and finally, inputting specific lesion stage information, generating a multi-scale discrete index sequence through a hierarchical autoregression model, converting the multi-scale discrete index sequence into a codeword vector through a multi-scale VQ-VAE model, and finally generating a simulated medical image. According to the scheme, the multi-scale VQ-VAE model is utilized to encode the input image into the multi-scale discrete feature representation, and meanwhile, the autoregression model is applied to the discrete hidden space of the VQ-VAE, so that the distribution of the discrete representation sequence can be effectively modeled, and the medical image with higher quality and more realistic sense can be generated.

Vector-scaled hierarchical codebook quantization reduces precision (bitwidth) vectors of parameters and may enable energy-efficient acceleration of deep neural networks. A vector (block array) comprises one or more parameters within a single dimension of a multi-dimensional tensor (or kernel). For example, block array comprises 4 sub-vectors (blocks) and each sub-vector comprises 8 parameters. The parameters may be represented in integer, floating-point, or any other suitable format. A vector cluster quantization technique is used to quantize blocks of parameters in real-time. Hardware circuitry within a datapath identifies an optimal codebook of a plurality of codebooks for quantizing each block of parameters and the block is encoded using the identified codebook. During processing, the identified codebook is used to obtain the quantized parameter and perform computations at the reduced precision.

A wireless input / output (I / O) device wirelessly coupled to a wireless dongle of an information handling system to encrypt and transmit a data packet frame in response to a transmitted polling packet from a wireless dongle requesting a selected number of packets of a selected packet length. The microcontroller executing code instructions to sign and encrypt the selected number of data packets generating a signature and generating an LFSR distributed signature and an LFSR distributed payload. An encryption algorithm used with an initial or dynamic key and shifting state machine output of another pair of LFSRs generates a data packet encryption output value that is applied via an exclusive OR operator to the LFSR distributed signature and payload to encrypt the data packet and the data packet encryption output value is used for encryption of the next data packet until the selected number of packets of the frame are encrypted.

The present disclosure is generally related to wireless communications technologies, network topologies, and communication device implementations, and in particular, to multipletransmission reception point (multi-TRP) uplink (UL) transmission schemes. The multi-TRP UL transmission schemes include timing advance (TA) associations for multi-TRP operation, channel state information (CSI) enhancements, and codebook structural enhancements. To enhance the performance of Rel-16 codebook, a new codebook structure is constructed by preserving the Rel-16 codebook structure in the spatial dimension (SD) and frequency dimension (FD) while extending the Rel-16 codebook in the time dimension (TD) using a mutually orthogonal Discrete Fourier Transform (DFT) basis.

A terminal according to one aspect of the present disclosure includes a control section that determines a precoder, based on a codebook for transmission using more than four antenna ports, when a codebook subset indicating “non coherent” or “partial coherent” is configured, and a transmitting section that performs uplink full power transmission, based on the precoder. According to one aspect of the present disclosure, UL full power transmission using more than four antenna ports can be appropriately controlled.

The invention discloses a dynamic beam adaptive optimization method for the Internet of Vehicles, and the method comprises the steps: firstly obtaining the current position, speed and driving direction of a vehicle, and carrying out the prediction of a future trajectory through combining historical trajectory information and employing a Kalman filtering technology and the like; and selecting a candidate beam direction from the predefined beam codebook. The system receives channel quality feedback information of a communication link in real time, and dynamically updates a beam forming weight based on an improved recursive least square algorithm. According to the algorithm, a composite adaptive adjustment mechanism of an error size and an error change trend is introduced, a multi-objective optimization function is constructed, and performance indexes such as link quality maximization, interference power minimization and beam switching frequency minimization are effectively balanced in a dynamic environment, so that an optimal beam direction is obtained. Finally, the real-time switching of the antenna array beams is realized through a low-overhead and low-delay control protocol. According to the method, track perception and a self-adaptive feedback mechanism are fused, and good real-time performance, stability and expandability are achieved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a visual token generation method, device, equipment and medium based on a shared index, and the method comprises the steps: obtaining an input image, and extracting semantic features and pixel features through a semantic encoder and a pixel encoder; calculating the distance between each feature and a codebook thereof, and carrying out weighted summation to determine a shared index; retrieving quantitative features from the codebook using a shared index; respectively generating a reconstructed image and a reconstructed semantic feature by using a pixel decoder and a semantic decoder; jointly optimizing an encoder, a codebook and a decoder based on a reconstruction result; and generating a unified visual token sequence for the target task image by using the optimized component. Through double-flow feature extraction, shared mapping quantization and joint loss optimization, global semantic information and local pixel details can be reserved in the visual token at the same time, so that the model has accurate understanding ability, high-fidelity images can be generated, and the performance of understanding and generating tasks is improved.

A precoder index is derived from a precoder codebook using a low computationally complex process. A plurality of uplink channel matrix estimates are received at a Base Station (BS) from a User Equipment (UE). The plurality of uplink channel matrix estimates are processed to determine an indicator of the precoder having a highest spectral efficiency estimate. The indicator of the precoder having the highest spectral efficiency estimate is selected for transmission by the BS.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a network node may receive, from a network entity, a configuration of a codebook associated with a reconfigurable intelligent surface (RIS) pattern. The network node may receive, from the network entity, an indication of a codeword in the codebook that is potentially associated with RIS element failure based at least in part on one or more RIS attributes. The network node may perform an RIS failure mitigation based at least in part on the indication. Numerous other aspects are described.

A method and device for transmitting or receiving improved codebook-based channel state information in a wireless communication system are disclosed. A method performed by a terminal in a wireless communication system, according to one embodiment of the present disclosure, comprises the steps of: receiving one or more channel state information (CSI)-reference signals (RS) from a network; and transmitting, to the network, one or more CSI reports including information indicating a first precoding matrix based on the one or more CSI-RSs and a channel quality indicator (CQI) based on a second precoding matrix, wherein the first precoding matrix is included in a set of precoding matrices defined on the basis of one or more predetermined codebooks, and the second precoding matrix can be determined on the basis of the first precoding matrix and one or more pieces of artificial intelligence (AI) / machine learning (ML) model-related information.