45 results about "Tree code" patented technology

The invention discloses a tree coding-based long video generation optimization method, which comprises the following steps of: constructing a video frame sequence, and obtaining frame features; clustering the frame features to obtain a correlation score between the key frame and the video query; calculating the number of high-correlation clusters, and outputting a corresponding frame feature set and a correlation score; key frames of all the high-correlation clusters serve as first-layer nodes of a video feature tree, the high-correlation clusters are clustered into w sub-clusters respectively, a second layer is constructed based on the sub-cluster key frames, the correlation score of the second-layer nodes is obtained by subtracting one from the correlation score of the first-layer nodes, each layer is constructed according to the method, and the first-layer nodes and the second-layer nodes are obtained; the relevance score of the last layer of nodes is 1; the large language model outputs an optimization reasoning result based on the speculation sampling principle and the draft model; and inputting the optimized reasoning result and the video frame sequence into a preset video generation model to obtain an answer video. According to the method, the reasoning accuracy and efficiency are improved by inquiring self-adaptive and hierarchical long video understanding.

The invention discloses a sewage high-risk pollutant screening and identification method based on fragmentation tree pre-training, and the method comprises the steps: constructing a fragmentation tree pre-training data set according to the second-level mass spectrum data of known high-risk pollutants, so as to carry out the self-supervision pre-training of a graph neural network encoder, and obtaining a fragmentation tree editor; the method comprises the following steps: acquiring secondary mass spectrum data of suspected high-risk pollutant related compounds in a to-be-detected sewage sample, constructing a fragmentation tree set, constructing a high-risk pollutant screening model based on a fragmentation tree encoder, performing high-risk pollutant signal screening on the fragmentation tree set to obtain a high-risk candidate fragmentation tree set, and performing high-risk pollutant signal screening on the high-risk candidate fragmentation tree set. And generating a candidate molecule set of each high-risk candidate fragmentation tree, and identifying a target molecular structure and a matching score of the high-risk candidate fragmentation tree from the candidate molecule set. According to the invention, rapid screening and priority ranking of high-risk pollutants in sewage are realized, and candidate output of structure identification is further provided on the basis of screening.

The embodiment of the invention belongs to the field of image processing, and relates to a video quality evaluation method and device, computer equipment and a storage medium, and the method comprises the following steps: carrying out the jitter buffering processing of to-be-evaluated video data, and obtaining a standard video data stream; performing fragment analysis on the standard video data stream to obtain video stream fragments; performing coding processing on the video stream segment based on a coding tree coding mode to obtain a video coding unit; judging whether the video coding unit is in a non-skipping mode or not; if the video coding unit is in a non-skipping mode, calculating a unit quantization parameter average value of the video coding unit according to a preset image sequence set parameter, and taking the unit quantization parameter average value as a video quality score; and comparing the video quality score with a preset video quality threshold to obtain a video quality result. According to the invention, the quality of the to-be-evaluated video data can be accurately evaluated without reference, and the evaluation efficiency and accuracy of the to-be-evaluated video data are improved.

A device for decoding a bitstream that includes point cloud data is configured to determine an octree that defines an octree-based splitting of a space containing the point cloud, wherein a leaf node of the octree contains one or more points of the point cloud; and directly decode positions of each of the one or more points in the leaf node, wherein to directly decode the positions of each of the one or more points in the leaf node, the one or more processors are further configured to: generate a prediction of the one or more points; and determine the one or more points based on the prediction.

A point cloud encoding method, performed by an encoding device, includes: obtaining point cloud data, including one or more point cloud groups, wherein the one or more point cloud groups include first points; determining one or more starting points for the one or more point cloud groups; constructing one or more single-chain predictive trees for the one or more point cloud groups based on the one or more starting points; encoding the first points based on the one or more single-chain predictive trees; and transmitting the encoded first points.

An example device includes a memory and one or more processors. The one or more processors are configured to determine whether to use single-tree coding for a first codec tree unit (CTU), determine a first transform unit (TU) based on a first luma sample transform block (TB) and first two corresponding chroma sample TBs based on the first CTU using the single-tree coding. The one or more processors are further configured to determine whether to use dual-tree coding for a second CTU, determine a second TU based on (I) a second luma sample TB or (II) a second set of two chroma sample TBs based on the second CTU using the dual-tree coding. The first TU includes a syntax structure for transforming the first TB samples, and the second TU includes a syntax structure for transforming the second TB samples.

The application discloses a sewage high-risk pollutant screening and identification method based on fragmentation tree pre-training, comprising the following steps: constructing a fragmentation tree pre-training data set according to secondary mass spectrum data of known high-risk pollutants, pre-training a graph neural network encoder in a self-supervised manner to obtain a fragmentation tree editor, obtaining secondary mass spectrum data of suspected high-risk pollutant-related compounds in a sewage sample to be tested, constructing a fragmentation tree set, constructing a high-risk pollutant screening model based on the fragmentation tree editor, screening high-risk pollutant signals from the fragmentation tree set to obtain a high-risk candidate fragmentation tree set, generating a candidate molecule set of each high-risk candidate fragmentation tree, and identifying a target molecular structure and a matching score of the high-risk candidate fragmentation tree from the candidate molecule set. The application realizes rapid screening and priority sorting of high-risk pollutants in sewage, and further provides a candidate output of structure identification on the basis of screening.

The embodiment of the application provides a kind of based on syntax semantic fusion sentiment tuple extraction method and system, it is related to natural language processing technical field.The method can be after obtaining input text, using structure perception syntax encoder calculates the encoding embedding data of input text, again through bidirectional cross attention fusion, obtains the fusion representation of syntax representation and semantic representation depth interaction.Based on double similarity comparison learning framework, the unified representation of fusion representation is calculated, and candidate example is retrieved according to the unified representation.The method can be based on the structure perception graph converter of dependency tree coding to generate encoding embedding data, and through the syntax and semantic fusion realized by bidirectional cross attention mechanism, and carry out double similarity comparison learning, for the structured task of large language model Provide explicit syntax guidance, can simultaneously integrate syntax and semantic information, correctly identify complete sentiment tuple, improve the output precision of sentiment tuple extraction result.

The embodiment of the invention discloses a scene cognition method and device, and the method comprises the steps: obtaining multi-source and multi-mode data samples of services in different scenes, and extracting semantic segmented words in the samples; fusing the semantic segmented words to obtain a feature vector set; encoding semantic segmented words in the semantic segmented word set to obtain a standard semantic segmented word classification tree code; on the basis of the standard semantic word segmentation classification tree code, determining a code mapped by multi-source and multi-modal data of a service in a to-be-recognized target scene; and inputting the mapped code into a model of the configured code calculation rule, and mapping to obtain a final code value so as to determine a cognitive result of the set scene based on the final code value. The code-driven scene data comprehensive analysis is realized, so that people can better obtain more insights from massive and complex multi-source and multi-mode scene data, and various scene services are enabled.

Post training compression of 3DGS data is agnostic to training in a traditional signal compression perspective. Gaussian parameters are treated as signals. Pre-processing and transform coding techniques are used to compress the signals effectively. Firstly, lossless / lossy compression is performed on 3DGS geometry (positions, scales, rotations) using a point cloud coding-based (e.g., G-PCC, GeS) framework. Positions are compressed using occupancy tree coding. Scales and rotations are encoded as attributes using transform coding. The widely used block-based graph Fourier transform (GFT) is used to compress the attributes (base colors, spherical harmonic coefficients and opacities). In addition, a graph construction strategy is used for 3DGS data that computes the edge weights based on similarity (or dissimilarity) between the 3D Gaussian distributions using KL-divergence. Alternatively, positions can be encoded using occupancy tree (e.g., G-PCC, GeS) or AI-based PCC methods, and any subset of Gaussian parameters or the transformed coefficients of Gaussian parameters can be mapped into 2D frames and encoded by video coders.

Adaptive dual tree coding may be optimized, for example, to implement a trade-off between compression efficiency and encoder complexity. For example, adaptive dual tree / single tree representation in inter slices may be conditioned on characteristics of the slice / picture, e.g., slice type, temporal layer id, and / or temporal depth of the slice being coded / decoded. Use of block-vector guided convolutional cross-component model (BVG-CCCM) may be conditioned on disabling adaptive dual tree and / or characteristics of the slice being encoded / decoded. Use of multi-type tree (MTT) split modes early termination may be conditioned on disabling of adaptive dual tree. In examples, a device (e.g., decoder / encoder) may determine a hierarchical parameter associated with a slice. The device may determine whether to enable a dual tree mode for the slice based on the hierarchical parameter for the slice. The device may decode the slice based on the determination of whether to enable the dual tree mode for the slice.

The invention relates to the field of fault tree analysis, in particular to a fault tree cut set solving method based on artificial intelligence. The method comprises the following steps: coding a fault tree into a structure matrix in a similar adjacent matrix form, and expressing an event and a cut set in a binary matrix form; searching the structure matrix to find out an analyzable intermediate event; analyzing each currently analyzable intermediate event through logic gate operation; performing a simplification operation on the analyzed intermediate event cut set, and only reserving a minimum cut set; after all parsable events searched in the round are parsed, rows and columns corresponding to parsed events in the middle event area of the structure matrix are deleted, and the next round of search is continued; and repeating the operation until the top event is analyzed. According to the method, the cut set is solved by adopting the matrix Boolean algebraic method, the fault tree analysis cut set simplification agent model is built based on the neural network, and the cut set is simplified in the solving process, so that the calculation efficiency of the minimum cut set is improved.

A point cloud encoding method, decoding method, encoding device, and decoding device are disclosed. The point cloud encoding method includes calculating a distance from a first point to a parent point of the first point as a first distance; determining a point in un-encoded points closest to the first point as a second point, and calculating residual values on N coordinate components from the second point to the first point; encoding absolute values of the residual values on the N coordinate components from the second point to the first point; encoding signs of the residual values of the second point based on the residual values of the second point and the first distance. The present disclosure utilizes the geometry position relationship between points in a point cloud to encode the absolute values of residual values and the feasible signs of residual values, thereby improving the encoding efficiency of residual values. At the same time, by optimizing the encoding efficiency of residual values, the performance of point cloud prediction tree encoding is improved.

The application provides a data transmission method, device, user equipment, base station and system. The method is applied to user equipment in the coverage of a base station. There are multiple groups of user equipment in the coverage of the base station. The method comprises obtaining uplink resource information corresponding to a group to which the user equipment belongs. The uplink resource information comprises the frequency of L subcarriers used for uplink communication and the position information of n OFDM symbols corresponding to the group on a single subcarrier. The tree code encoder is used to encode the to-be-sent data and the check data, so as to obtain L groups of encoded data. Each group of encoded data in the L groups of encoded data is compressed into a code word with a length of n by using a compression matrix. The L groups of code words are subjected to OFDM modulation. After modulation, each group of code words with the length of n occupies one subcarrier in the L subcarriers, and each code word corresponds to one of the n OFDM symbols on the occupied subcarrier. The modulated data is sent. The uplink communication without random access can be realized.

The invention discloses a general manuscript checking method and device based on a central knowledge base. The general manuscript checking method comprises the following steps: constructing the central knowledge base; obtaining a to-be-examined manuscript, and constructing an abstract syntax tree of the to-be-examined manuscript; extracting key information in the abstract syntax tree through a dynamic syntax tree encoder to obtain key words; determining target knowledge base data of which the key words have core contradictions with a central knowledge base; determining a corresponding target similarity score based on the target knowledge base data and a central knowledge base; if the target similarity score is smaller than a preset threshold value, performing general review on the to-be-reviewed manuscript to obtain a first review result, a second review result and a third review result; and obtaining a target review result based on the first review result, the second review result and the third review result. The method does not need to depend on manpower, and can adapt to diversified context scenes, so that the checking accuracy is improved, and the application range is wide.

The invention discloses a zero-sample Chinese character recognition method based on radical structure tree graph level representation, and belongs to the technical field of Chinese character recognition. The method comprises the following steps: establishing a Chinese character database and constructing a directed radical structure tree of each Chinese character from top to bottom; adding direction position codes to nodes in the tree to distinguish the spatial relationship of brother nodes; inputting the radical structure tree with the direction and position codes into a GraphSAGE-based tree encoder to obtain normalized vector representation of the Chinese characters; extracting vector representation of the sample image by using ResNet; aligning the Chinese character vector and the image vector through comparative learning; and finally, zero sample recognition is realized by calculating the similarity between the to-be-recognized image and all candidate Chinese character vectors, and the highest similarity is selected as a recognition result. According to the method, the structure perception capability is improved through the directed tree, fine-grained spatial differences are perceived through directional coding, and the recognition capability of the model on unseen Chinese characters is effectively improved.

The invention belongs to the technical field of image processing, and provides a brain tumor image segmentation method based on lightweight multi-modality, and the main scheme is as follows: obtaining a multi-modality brain nuclear magnetic resonance image data set, and constructing a multi-modality data fusion feature extraction network based on a binary tree structure; the feature extraction network comprises tree-shaped coding layers with the same number as the modals; constructing a local feature extractor for the brain nuclear magnetic resonance image of each modal, and performing feature extraction; constructing a multi-modal fusion unit for feature extraction results of two adjacent modals, and performing inter-modal feature fusion; generating jump connection parameters for each tree coding layer, performing up-sampling on outputs of all the tree coding layers, and then performing connection fusion operation by using the jump connection parameters; constructing a brain tumor image segmentation network, and obtaining a segmentation result of the brain tumor image; and training, verifying and testing the two networks by using a multi-modal brain nuclear magnetic resonance image data set.

A method of decoding coding units of a coding tree for an image frame from a video bitstream comprising splitting a region of the coding tree into a plurality of coding blocks, each of the coding blocks including a prediction block. Determining matrix intra prediction flags for the prediction block of each of the coding blocks, the determination based upon (i) an area of the region if the region meets a threshold, or (ii) a budget for the region if the area of the region does not meet the threshold. The method further comprises reading matrix coefficients from a memory for each prediction block determined to use matrix intra prediction according to the determined flag; and decoding the coding units using prediction blocks generated for each coding unit in the region using reference samples of each prediction block and the matrix coefficients.

A method for a compression scheme comprising encryption, comprising: receiving, as input, data comprising a plurality of data elements; constructing a Huffman tree coding representation of the input data based on a known encryption key, wherein the Huffman tree comprises nodes that are compression codes having compression code lengths corresponding to respective occurrence probabilities of the data elements, and wherein the encryption key specifies a subset of the nodes to be selected for an encryption process; selecting the subset of nodes in the Huffman tree for the encryption process, based on the encryption key; applying, to each sub-tree of the Huffman tree that is rooted at one of the nodes in the subset, a specified transformation, based on the encryption key; and generating an output data file based, at least in part, on the applying.

A method and apparatus for block partition are disclosed. If a cross-colour component prediction mode is allowed, the luma block and the chroma block are partitioned into one or more luma leaf blocks and chroma leaf blocks. If a cross-colour component prediction mode is allowed, whether to enable an LM (Linear Model) mode for a target chroma leaf block is determined based on a first split type applied to an ancestor chroma node of the target chroma leaf block and a second split type applied to a corresponding ancestor luma node. According to another method, after the luma block and the chroma block are partitioned using different partition tress, determine whether one or more exception conditions to allow an LM for a target chroma leaf block are satisfied when the chroma partition tree uses a different split type, a different partition direction, or both from the luma partition tree.

The invention provides a privacy protection decision tree coding method based on CKKS homomorphic encryption, and the method comprises the steps: reconstructing a mapping mechanism between integer input and a ciphertext polynomial, building an accurate coefficient mapping model on the premise of maintaining the integrity of a CKKS homomorphic operation framework, and effectively solving the problem of function adaptation of a privacy protection decision tree XCMPPDTE; by fully utilizing the plaintext space of CKKS complex field coding, the real / virtual part separation mode of the traditional complex field coding is improved into integer field total space coding, so that the number of plaintext slots corresponds to the polynomial dimension n by 1: 1, and the data coding capacity is improved by 100% compared with the original scheme.

The application discloses a point cloud encoding method, a point cloud decoding method and a terminal, and belongs to the technical field of point cloud processing. The point cloud encoding method comprises the following steps: obtaining a first identification parameter of a first target point cloud to be encoded; and performing an encoding operation on the first target point cloud based on the first identification parameter. The encoding operation comprises at least one of the following: in the case that the first identification parameter is used to represent parallel encoding, performing geometric encoding and attribute prediction encoding on the first target point cloud in parallel to obtain an encoding result of the first target point cloud; and performing geometric prediction encoding on at least part of the to-be-encoded points of the first target point cloud. In the embodiment of the application, the geometric encoding and the attribute prediction encoding are performed on the first target point cloud in parallel based on the first identification parameter of the first target point cloud. By performing the geometric prediction encoding on at least part of the to-be-encoded points of the first target point cloud, the multi-tree encoding on all the to-be-encoded points of the first target point cloud is avoided.

The invention discloses a multi-input gating structure model (TC-MIGSM for short) based on tree coding, which is used for the risk tracing of biological risk factors of codling moths. According to the method, risk source dealers are traced through a multi-input gating structure (MIGSM for short, and the problem of data structural deficiency caused by equipment limitation in a codling moth circulation chain is solved. The traditional interpolation method cannot process the deficiency, so that the invention provides a tree coding algorithm to extract missing data features and effectively cope with the structural deficiency. Besides, internal and mutual characteristics of each dealer in the same circulation link are extracted through an auto encoder model (AE for short) and are input into the MIGSM, so that accurate risk traceability is realized. An experiment proves that TC-MIGSM is superior to other models in accuracy by tracing 208 batches of apples transported from Gansu to Beijing.

The invention discloses a linear multi-threshold classification method based on a Huffman tree, and the method comprises the steps: obtaining a correlation coefficient matrix according to multi-class data in a collected historical data set, and obtaining the average intensity of each class of data in a multi-feature dimension, so as to obtain the probability of each data class; according to the probability, coding is carried out through a Huffman tree, the coding length is inversely proportional to the probability, and classification containers are divided according to the coding length; and according to the divergence matrix of the data in the classification containers, in combination with the divergence matrix between the classification containers, obtaining a feature vector so as to obtain a regression mean value of the classification containers, and determining a classification threshold between the classification containers so as to perform classification by using the data collected in real time. According to the method, classification containers are dynamically divided based on Huffman tree coding, a multi-classification task is optimized into O (logK) subtasks, and in combination with divergence matrix driven feature vector optimization and dynamic threshold selection, the model complexity is reduced, and meanwhile, the recognition precision in a class imbalance scene is improved.

A method of decoding coding units of a coding tree for an image frame from a video bitstream comprising splitting a region of the coding tree into a plurality of coding blocks, each of the coding blocks including a prediction block. Determining matrix intra prediction flags for the prediction block of each of the coding blocks, the determination based upon (i) an area of the region if the region meets a threshold, or (ii) a budget for the region if the area of the region does not meet the threshold. The method further comprises reading matrix coefficients from a memory for each prediction block determined to use matrix intra prediction according to the determined flag; and decoding the coding units using prediction blocks generated for each coding unit in the region using reference samples of each prediction block and the matrix coefficients.

The invention provides a distributed drainage basin model multi-flux parallel computing method. The method comprises the following steps: S1, performing multi-way tree coding on mutually independent computing units according to parallel features of a distributed drainage basin model; s2, creating a parallel computing system according to the total process number, wherein the parallel computing system comprises a master control process which is globally and uniquely responsible for task allocation regulation and control, a plurality of computing processes which are responsible for physical processes and a plurality of transfer processes which are responsible for data transmission among computing units; s3, the main control process sequentially distributes the calculation tasks of all the units to the calculation process according to the multi-way tree codes; s4, the calculation process receives the task and receives upstream data from the transfer process, and calculation is started after unpacking; s5, after the calculation process task is completed, a result is packaged and transmitted to the transfer process; and S6, repeating the steps S3-S5 until all the calculation units are calculated. According to the method, the multi-flux parallel computing method for any distributed drainage basin model discrete in a tree structure is realized.

The present invention discloses an adaptive Huffman coding system and method. The adaptive Huffman coding system includes: a data acquisition module for acquiring data to be encoded and a Huffman binary tree encoding module. The data acquisition module is used to acquire data to be encoded; the Huffman binary tree encoding module is used to construct a Huffman binary tree based on the data to be encoded acquired by the data acquisition module. Each node of the Huffman binary tree is indexed with memory. When constructing the Huffman binary tree, the memory index value of the target node is calculated based on the unique path from the root node to the target node. The adaptive Huffman coding system and method proposed by the present invention can efficiently access the encoding data structure on hardware and optimize the encoding storage space, while providing the flexibility of configurable memory.

The embodiment of the invention provides an emotion tuple extraction method and system based on syntax and semantic fusion, and relates to the technical field of natural language processing. According to the method, after an input text is obtained, coding embedded data of the input text can be calculated by using a structure perception syntactic encoder, and then syntactic representation and semantic representation are deeply interacted through bidirectional cross attention fusion to obtain fusion representation. And calculating a unified representation of the fusion representation based on a dual similarity contrast learning framework, and retrieving candidate examples according to the unified representation. According to the method, coding embedded data can be generated based on a structure perception graph converter of dependency tree coding, explicit syntactic guidance is provided for a structured task of a large language model through syntactic and semantic fusion achieved through a bidirectional cross attention mechanism and double-similarity comparative learning, syntactic and semantic information can be integrated at the same time, and the method has the advantages of being high in practicability and easy to popularize. The complete emotion tuple is correctly recognized, and the output precision of the extraction result of the emotion tuple is improved.

A method of decoding coding units of a coding tree for an image frame from a video bitstream comprising splitting a region of the coding tree into a plurality of coding blocks, each of the coding blocks including a prediction block. Determining matrix intra prediction flags for the prediction block of each of the coding blocks, the determination based upon (i) an area of the region if the region meets a threshold, or (ii) a budget for the region if the area of the region does not meet the threshold. The method further comprises reading matrix coefficients from a memory for each prediction block determined to use matrix intra prediction according to the determined flag; and decoding the coding units using prediction blocks generated for each coding unit in the region using reference samples of each prediction block and the matrix coefficients.