1927 results about "Decodes" patented technology

The invention relates to the technical field of artificial intelligence, and discloses a large language model high concurrency reasoning method and system, and the method comprises the steps: calculating the size of a video memory block through an actuator, and distributing a video memory space; the scheduler is used for converting the request sequence and putting the request sequence into a waiting queue of the scheduler; the scheduler allocates a corresponding video memory block to each request sequence until each request sequence can perform next reasoning; the scheduler calculates the video memory requirement of the request sequence in the waiting queue according to the priority sequence, and transfers the request sequence in the waiting queue to the running queue; according to the number of pre-filling types and the number of decoding types of the request sequence, distributing the number of video memory blocks used for executing pre-filling reasoning or decoding reasoning; therefore, according to the method, continuous batch processing, a dynamic space allocation mechanism and a task scheduling framework are adopted, the parallel reasoning capability of continuous batch processing is fully utilized, the concurrency and throughput of large model reasoning are improved, and the limitation that traditional continuous batch processing needs space pre-allocation is solved.

The invention provides a satellite image and actually measured RSRP fused ground radio map generation system, and the system comprises a satellite image feature extraction module which is used for converting a high-resolution satellite image of a target region into high-dimensional image features reflecting the ground feature type distribution of the region; the base station physical characteristic input module is used for converting the physical parameters of the communication base station in the target area into characteristic vectors reflecting electromagnetic propagation characteristics; the multi-modal fusion module is used for fusing the high-dimensional image features and the feature vectors to generate joint feature representation; the radio map decoder is used for generating a radio signal power plane distribution diagram of the target area through a decoding network based on the joint feature representation; and the ground RSRP correction module is used for correcting the radio signal power plane distribution diagram output by the radio map decoder so as to output a final radio signal power distribution result. According to the invention, the space-ground collaborative data source fusion is realized to improve the mapping precision.

The invention provides a lightweight wavelet convolution guide wire segmentation network model and a double guide wire generation method, and the construction of the model comprises the steps: obtaining an input image, carrying out the feature extraction of the input image through a Stem module, obtaining a bottom-layer feature, carrying out the processing of the bottom-layer feature through five wavelet encoders in an iteration manner, and carrying out the recognition of the processed bottom-layer feature through the five wavelet encoders. And inputting the features output by the wavelet encoders into a decoder in an iteration form to carry out decoding processing so as to obtain a segmented prediction map. The method comprises the following steps of: inputting the features output by the wavelet encoders into the decoder in an iteration form to carry out decoding processing on the features output by the wavelet encoders; the wavelet transform attention convolution provided by the invention is specially used for capturing complex edge and texture nuisance features of the guide wire. A channel attention mechanism is introduced after a wavelet decomposition process to enhance feature representation. The combination of channel attention can selectively emphasize key frequency components, significantly improve the ability of the network to capture complex texture modes, and improve the precision of guide wire segmentation.

The embodiment of the invention discloses an intelligent downhole operation state monitoring system and method, and relates to the technical field of monitoring data processing. The method comprises the following steps: acquiring multi-modal monitoring data for reflecting an underground operation state; performing fluctuation analysis on each piece of time sequence data in the multi-modal monitoring data to obtain a corresponding fluctuation analysis result; the correlation degree between the fluctuation analysis results corresponding to the different time series data is calculated based on a grey correlation analysis method, and fluctuation correlation information is obtained; performing information fusion on the fluctuation analysis result and corresponding time sequence data through a time window alignment mode to obtain target monitoring data; taking the fluctuation associated information as a weight parameter of an attention mechanism, performing multi-modal feature coding on the target monitoring data through a coding network, and outputting a corresponding operation state representation vector; and inputting the operation state representation vector into a decoding network to carry out downhole operation state anomaly analysis to obtain intelligent downhole operation state monitoring data.

A system and method for handling acknowledgments in a wireless system. In some embodiments, the method includes, receiving, by a User Equipment (UE), one or more first transmissions; decoding, by the UE, the first transmissions, to generate a first sub-codebook including one or more corresponding Hybrid Automatic Repeat Request Acknowledgement (HARQ ACK) bit strings each having a first length; receiving, by the UE, one or more second transmissions; decoding, by the UE, the second transmissions, to generate a second sub-codebook including one or more corresponding HARQ ACK bit strings each having a second length, greater than the first length; receiving, by the UE, one or more third transmissions; and decoding, by the UE, the third transmissions, to generate a third sub-codebook including one or more corresponding HARQ ACK bit strings each having a third length, greater than the second length.

A video dynamic mesh coding (v-DMC) decoding system, includes a de-multiplexer that receives and demultiplexes an encoded v-DMC bitstream into: a parameter set and mesh data, geometry, atlas data, and attribute video substreams. The decoding system also includes: a mesh data substream decoder; a video decoder that decodes the geometry data substream; an atlas data substream decoder; a mesh subdivision component that subdivides the one or more base meshes into one or more resampled base meshes based upon the decoded atlas data; a displacement decoder that outputs one or more displacements to verticies of the one or more resampled base meshes; a mesh position refinement component that applies the one or more displacements to the one or more resampled base meshes and outputs one or more resultant meshes; and a video decoder that decodes the attribute video substream into one or more texture images.

Embodiments of the present application provide an encoding method, a decoding method, an encoder, a decoder, and a storage medium. The decoding method comprises: determining a prediction parameter of a current block, wherein the prediction parameter of the current block comprises a first indication parameter; if the first indication parameter indicates using a DIMD merge mode to decode the current block, on the basis of one or more candidate positions, determining direction parameters to be merged, wherein the one or more candidate positions are located in a reconstructed area of an image where the current block is located; and determining a predicted value of the current block on the basis of the direction parameters to be merged.

The invention discloses a soft decoding method and device, a medium and a product, and relates to the technical field of error correction coding, and the method is applied to a low-density parity check code, and comprises the steps: obtaining a target low-density parity check code with an information node and a check node containing an erasure bit; and allocating a preset non-zero log-likelihood ratio to the erasure bit on the check node, and executing first soft decoding. And if the first soft decoding fails, judging whether to carry out second soft decoding or not based on the weight of the syndrome generated by the first soft decoding and the number of the erasure bits on the information node. If it is judged that the second soft decoding needs to be carried out, a preset non-zero log likelihood ratio is distributed to the erasure bit located on the information node, and the second soft decoding is carried out. According to the method and the device, the erasing bits on different nodes are conditionally processed in stages, so that the success rate and the efficiency of decoding are effectively improved.

The embodiment of the invention relates to the technical field of exploration and development, and provides a well logging curve reconstruction method, device and equipment, a storage medium and a product, the method comprises the steps that an original well logging curve in a specified time period is obtained, the original well logging curve comprises a to-be-reconstructed well logging curve and a plurality of basic well logging curves, carrying out representation learning on the original logging curve to obtain an initial feature vector matrix; the initial feature vector matrix is input into a pre-trained curve reconstruction model, a reconstruction curve of the to-be-reconstructed logging curve is obtained, the curve reconstruction model comprises at least one decoding layer, and the decoding layer comprises an asymmetric causal attention layer, a first normalization layer, a feedforward network layer and a second normalization layer; the asymmetric causal attention layer is used for extracting the space-time correlation weight of the initial feature vector matrix. According to the embodiment of the invention, the reconstruction precision of the logging curve can be improved, so that accurate and reliable data support is provided for exploration and development decisions of oil and gas fields.

Disclosed in embodiments of the present application are an encoding method, a decoding method, a code stream, an encoder, a decoder, and a storage medium. The decoding method includes: decoding a relevant syntax element of a current block; according to the relevant syntax element, determining to use an intra-template matching prediction (TMP) (IntraTMP) merged intra prediction mode to perform prediction on the current block; determining a matching block of the current block on the basis of a TMP mode, and determining a first predicted block of the current block according to the matching block; determining a second predicted block of the current block on the basis of a non-template matching intra prediction mode; and merging the first predicted block and the second predicted block to determine a final predicted block of the current block.

An encoding method includes: decoding a bitstream to determine prediction parameters of a current block; determining a first prediction block of the current block according to the prediction parameters; determining model parameters according to a first color component value and a second color component value of the first prediction block; determining a reference sample value of a first color component sample of the current block; determining a prediction value of a second color component sample of the current block according to the reference sample value of the first color component sample of the current block and the model parameters; and determining a reconstructed value of the second color component sample of the current block according to the prediction value of the second color component sample of the current block.

The embodiment of the invention provides a model training method, an information recommendation method, equipment, a storage medium and a program product. According to the embodiment of the invention, a multi-encoder-multi-sub-decoder-total decoder hybrid model architecture is provided, sample data of different information modes correspond to different encoders-sub-decoders, and a mode of processing all training sample data by a single model is converted into a divide-and-conquer mode. The internal complexity of each encoder-sub-decoder is relatively low, the complexity of model training can be reduced, resource consumption can be saved, and different encoder-sub-decoders can be trained in parallel, so that the model training time can be shortened; and furthermore, by utilizing a dual decoding mechanism of the sub-decoder and the global decoder, parameters of the encoder can be continuously adjusted through local optimization and global optimization, the performance of the model is optimized, the accuracy of a reasoning result is improved, the convergence speed of the model is accelerated, the model training efficiency is further improved, and the model training time is saved.

The embodiment of the invention discloses a video encoding and decoding method and device, equipment and a medium. The method comprises the following steps: a coding end determines a mode identifier corresponding to a sub-block according to a coding mode of a target transformation block for representing binarization coding distribution of a non-zero transformation coefficient at an internal position of the sub-block, and codes the mode identifier to obtain coding information of the target transformation block, so that the coding end or a decoding end carries out decoding according to the coding information of the target transformation block, and the target transformation block is decoded. And obtaining a coding mode for representing the binarization coding distribution of the non-zero transformation coefficients at the internal positions of the sub-blocks, thereby realizing the determination of the positions of the non-zero transformation coefficients corresponding to the target transformation block. According to the technical scheme, the coding and decoding efficiency of the transform block is improved, and the video coding and decoding reliability is high.

Disclosed herein are a decoding method and apparatus and an encoding method and apparatus for deriving an intra-prediction mode. An intra-prediction mode may be derived using a method for deriving an intra-prediction mode based on a neighbor block of the target block, a method for deriving an intra-prediction mode using signaling of the intra-prediction mode of the target block, or a method for deriving an adaptive intra-prediction mode based on the type of a target slice. An MPM list may be used to derive the intra-prediction mode, and a temporal neighbor block or the like may be used to configure the MPM list.

The invention discloses a time sequence prediction method and system based on adaptive period segmentation and parallel decoding, and the method comprises the following steps: judging the period length of time sequence data, segmenting the time sequence data according to the period length, and obtaining time sequence segmentation data; adaptively adjusting the hiding dimension of the embedded layer according to the period length, and mapping the time sequence segmentation data into the hiding dimension to obtain a time sequence representation; the obtained time sequence representation is input into a Transform encoder to carry out feature extraction; the decoder input is initialized according to the Transform encoder output, the initialized decoder input and the encoder output are subjected to feature interaction in the decoder based on a cross attention mechanism, and finally prediction output is obtained. According to the method, a more flexible period segmentation scheme and a decoding mechanism are adopted, the reasoning efficiency is improved, accumulative errors are reduced, and the time sequence basic model can achieve a better prediction effect with fewer parameters.

The method includes: A transmitter obtains a first bit sequence, and then performs LDPC encoding on the first bit sequence based on a check matrix, to obtain a second bit sequence. Correspondingly, a receiver receives the second bit sequence, and then performs LDPC decoding on the second bit sequence based on the check matrix, to obtain K information bits. The first bit sequence includes the K information bits, the second bit sequence includes M check bits, and both K and M are positive integers. The check matrix is obtained based on a first base matrix, the first base matrix corresponds to a second base matrix, the second base matrix includes the following elements: 0, 1, and 2.

The invention relates to a Manchester coded signal decoding method and a Manchester coded signal decoding system, and belongs to the field of electronic information, communication and power system automation. A plurality of clocks with the same frequency and different phases are generated according to Manchester encoding signals, the clocks are used for sampling the signals, a phase-shifting clock sampling method is used, dependence on a high-frequency clock is reduced, most interference in communication signals is determined to be eliminated according to a majority voting strategy for sampling results, and the accuracy of the signals is improved. And the seriously distorted signals are corrected according to special value enumeration, so that the interference of signal duty ratio distortion and burrs is reduced, and the decoding reliability is further improved. And finally, determining an original data stream of the signal according to the two level states of each code element. The method is used for decoding high-speed and ultra-high-speed Manchester encoding signals under the conditions of no high-frequency clock, poor data signal quality or unstable clock, and simultaneously realizing self-adaptive communication of different encoding formats.

The invention provides a decoding device and method. The method is suitable for the condition that periodic repeated code elements exist in original information code elements. The method comprises the steps that scrambled information code elements k0, k1, k2,..., kt-1, kt,..., km-1 with the length of m, the initial state M (0) of a long code generator and a state transition matrix B are received; constructing auxiliary data k0 ', k1', k2 ',..., k' 82 according to the scrambled information code elements k0, k1, k2,..., kt-1, kt,..., km-1; wherein ki '= ki + kt-1 + i, and i = 0, 1,..., 82; according to the auxiliary data k0 ', k1', k2 ',..., k' 82, the initial state M (0) and the state transition matrix B, a 42 * 42 full-rank matrix D is obtained through calculation; wherein the first behavior of the D is CBn, and then a scrambling code # imgabs0 # with the length of m is obtained through sequential analysis, the scrambling code obtained through analysis and scrambled information code elements k0, k1, k2,..., km-1 are subjected to modulo 2 addition operation, and an original information code element with the length of m is obtained.

The invention provides a coding method, a decoding method, a device and a system. In the method, a strategy for code block coding of a training frame is defined, so that content obtained after code block coding of the training frame comprises a control code block, and the control code block can be used for determining a boundary code block between a code block set corresponding to a sub-frame included in the training frame after code block coding and an adjacent code block set. The boundary code block corresponds to the boundary of the sub-frame and the adjacent sub-frame in the training frame, so that the boundary of the sub-frame in the obtained training sequence can be determined through the control code block in the decoding process.

The invention provides a coding method and system of a Transform class model for channel state information prediction. The coding method comprises the following steps: S1, acquiring and processing channel state time sequence data; s2, inputting the processed data into an encoder to extract features; s3, CFR data needing to be predicted are embedded, and position codes of the model are added; decoding the relevant parameters using a decoder; s4, processing the output of the decoder, and predicting channel state information; and S5, taking the CFR data and the CSI data obtained in the actual scene as the input of the model, and predicting channel frequency response information. According to the method, the time sequence characteristics of the channel state information are calculated and coded, and the time information is brought into the model, so that the relative stability time of the channel at the future moment is considered, the problem of weak time sequence information embedding capability in a Transform model is solved, and the accuracy of channel state prediction is improved.

The invention relates to a coding method, a decoding method and a device, in the coding method, first equipment can determine a second bit sequence and a third bit sequence based on a first bit sequence, and the third bit sequence comprises a bit sequence of which the weight is higher than a first threshold in a base graph corresponding to the first bit sequence. That is, the weight corresponding to the second bit sequence is lower than the weight corresponding to the third bit sequence. Furthermore, the first device can perform polar code coding on the second bit sequence, which is equivalent to providing additional protection for the second bit sequence with lower weight in a polar code coding mode, so as to improve the error correction performance. And for the third bit sequence with relatively high weight, LDPC coding can be performed on the third bit sequence and a polarization code coding result (namely, a fourth bit sequence obtained by performing polarization code coding on the second bit sequence). The error floor of LDPC decoding is reduced, and the error correction performance of LDPC codes is improved.

The video encoding / decoding method and apparatus according to the present invention can: determine a reference area for intra-frame prediction of a current block; derive an intra-frame prediction mode of the current block; and decode the current block based on the reference area and the intra-frame prediction mode.

In a video encoding / decoding method and device according to the present invention, a merge candidate of a current block may be determined, a merge candidate list may be configured on the basis of the merge candidate, motion information of the current block may be derived from the merge candidate list, and the motion information may be used to perform inter prediction of the current block.

This invention discloses a method for camouflaged target detection, belonging to the field of camouflaged target detection. This method constructs a BiSAM based on the SAM network. The SAM encoder, CNN encoder, and dual-domain cascaded attention module BCAM work collaboratively to enrich multi-scale feature information and extract multi-source features from the input image. Specifically, BCAM operates collaboratively in the spatial and spectral domains, selectively recovering and enhancing high-frequency object boundaries while suppressing irrelevant background noise. The multi-source features are fused using AKM to guide the SAM decoder in decoding the ViT image embedding. The method replaces the original position encoding of the cross-attention key vector in the SAM decoder, injecting task-specific knowledge into the frozen SAM decoder. By replacing the original position encoding, the general attention key vector is transformed into a task-aware attention key vector, specifically adapted to camouflaged target detection scenarios, thereby improving the accuracy of camouflaged target detection while maintaining generalization ability.

The invention discloses a multi-dimensional time sequence anomaly detection method based on correlation characteristics and multi-scale integrated decoding. The method comprises a coding stage, a decoding stage and an anomaly detection stage. In the encoding stage, by investigating the correlation between dimensions and the dependency of time, calculating a correlation feature matrix between the dimensions, and mining effective implicit features by using a convolution encoder; in the decoding stage, decoders with different scales are used for decoding the output of the coding layer, the outputs of the decoders are fused, and finally a reconstructed feature matrix is obtained; in the anomaly detection stage, the anomaly is identified by using errors of the reconstruction matrix and the original feature matrix; the method effectively solves the problems that in the prior art, correlation between the sequences is not considered, and a decoder is prone to error accumulation in the decoding process, and has the advantage that the correlation between the sequences and the time dependence of data can be effectively modeled.