97 results about "Quantization matrix" patented technology

The invention provides a model training method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of neural network models and model training. The specific implementation scheme is as follows: a calculation unit executes quantization matrix multiplication based on Hadamard pre-transformation on an activation tensor and a weight tensor of a target model stored in a memory so as to generate an output tensor of a linear layer based on a low-precision tensor with smaller data bit width; using the output tensor and a subsequent network layer of the target model to complete forward propagation so as to obtain a loss value; and according to the loss value, updating model parameters of the target model stored in a memory through a back propagation algorithm. By means of the technical scheme, on the premise that the model training precision is guaranteed, memory resource occupation and the calculation amount in the calculation process can be remarkably reduced, and the training cost is reduced.

The invention discloses a network security situation awareness method based on artificial intelligence, and the method comprises the following steps: collecting multi-source heterogeneous data, and generating a standardized data set; spatial-temporal feature decoupling is carried out, and spatial-temporal dimension features are separated; fusing the time-space cross attention, and outputting a fused time-space feature vector; constructing a causal inference engine, and outputting a dynamic causal graph and an anti-fact inference result set; constructing a dynamic risk propagation model, and outputting a whole asset risk value matrix and a risk propagation path diagram; generating a situation quantization matrix, constructing an adversarial training decision network, and outputting a defense strategy set verified by adversarial training; automatically generating a strategy; and a man-machine cooperative verification closed loop is realized. According to the method, dynamic reconstruction of a threat propagation path is realized through spatial-temporal feature decoupling and a causal reasoning engine, and a risk positioning error is reduced; and the adversarial training decision network is combined, so that the misjudgment rate of the defense strategy in the simulation APT attack test is reduced.

The invention provides a model quantification method and device, a model reasoning method and device, equipment, a medium and a product. Performing sensitivity evaluation on each network channel based on the weight matrix to obtain the channel sensitivity of each network channel; based on the channel sensitivity of the network channel corresponding to each element in the weight matrix, rearranging and dividing each element in the weight matrix to obtain a plurality of weight sub-matrixes; based on the channel sensitivity of the network channel corresponding to each element in each weight sub-matrix, allocating quantitative resources to each weight sub-matrix; performing quantization processing on the weight sub-matrixes based on the quantization resources to obtain a plurality of quantization sub-matrixes; and correcting the plurality of quantization sub-matrixes to obtain a target quantization matrix. Elements in a weight matrix can be accurately and orderly gathered according to channel sensitivity, different weight parameters are finely classified, different weight sub-matrixes are compatible for quantification, the problem of weight heterogeneity caused by multiple modes is solved, and the accuracy of model quantification is improved.

The invention relates to the field of image encryption, in particular to a chaos image encryption method based on DNA coding, which comprises the following steps: S1, calculating a hash value of a plaintext grayscale image by using a hash algorithm, and generating an initial key based on the hash value, S2, iterating a chaos sequence by using the initial key as an initial value and a control parameter of an iteration variable of two-dimensional chaos mapping 2D-CSMM, performing segmentation and quantization processing on the chaotic sequence to obtain a quantization matrix; performing reduction XOR operation on the quantization matrix to obtain a bit matrix; performing scrambling processing on a plaintext grayscale image based on the quantization matrix and the bit matrix to obtain a ciphertext image; s5, performing DNA diffusion processing on the ciphertext image based on the quantization matrix and the bit matrix to obtain an encrypted image; s6, decrypting the encrypted image according to the inverse process of image encryption to obtain a decrypted image; according to the encryption method provided by the invention, the security of image encryption is greatly improved, and the security performance and the encryption effect are good.

The invention discloses an image compression method and system based on edge gradient self-adaption, and the method comprises the steps: converting an input image into a YCbCr color space, calculating an edge gradient value of a brightness component, and employing iteration processing including a feedback mechanism: dividing an edge region and a non-edge region based on a current self-adaption edge gradient threshold value, the blocks are divided according to different sizes; dynamically updating an edge gradient threshold according to a block statistics result, and adaptively optimizing region division through multiple iterations; and finally, based on the optimized blocking result, processing the edge region and the non-edge region by adopting different quantization strategies, generating a quantization matrix, and then carrying out entropy coding to output a compressed code stream. According to the method, adaptive adjustment of compression parameters is realized through an iterative optimization mechanism, image edge and texture details are effectively reserved while a high compression rate is ensured, and the subjective visual quality of a compressed image is remarkably improved.

The invention belongs to the technical field of vehicle-road cloud integrated systems, and discloses a method for analyzing functional requirements of a vehicle-road cloud integrated system based on LLM, and the method comprises the following steps: S1, collecting and preprocessing basic data; s2, structured extraction of VRCIS requirements: semantic analysis is performed on the design requirement document based on LLM, a data structure is converted, and functional requirements and non-functional requirements are extracted; s3, constructing a VRCIS demand and benefit-critical person matrix: based on the output of the S2, mapping the function demand of each VRCIS benefit-critical person and the system design key dimension, and generating a standardized quantization matrix which can be identified by a machine; s4, quantitative analysis of demand priorities: identifying the demand priorities through quantitative analysis by utilizing the benefit-critical person matrix constructed in the S3 and fusing cost-benefit analysis; and S5, outputting a demand analysis result. The method is high in analysis efficiency, and the problems that in the analysis process, demand decomposition is not in place, the demand priority is not clear, and a general demand template cannot fully express VRCIS complexity are solved.

An encoder, includes: memory; and circuitry coupled to the memory, in which in a first encoding process, the circuitry quantizes a current block using a first quantization matrix in both of a first case where the circuitry performs primary transform and the circuitry does not perform secondary transform and a second case where the circuitry performs both the primary transform and the secondary transform, in a second encoding process, the circuitry quantizes the current block using a second quantization matrix in a third case where the circuitry performs primary transform and the circuitry does not perform secondary transform, and in a third encoding process, the circuitry quantizes the current block without using a quantization matrix in both of a fourth case where both the primary transform and the secondary transform are skipped and a fifth case where both the primary transform and the secondary transform are performed.

A system and method for energy-efficient approximate digital JPEG and MJPEG-compression. The system includes a controller unit to control a processing loop for processing image blocks based on a comparison of a current image block to a previous image block. The system includes a quantization unit configured to quantize the frequency domain representation using an approximate quantization process and a quantization (Q) matrix. The quantization unit is configured to: identify, a nearest power of two value for each element of the quantization matrix; generate an updated Q matrix by assigning each element of the quantization matrix with the identified nearest power of two value; and shift each element of the updated Q matrix by a number of bits to generate a quantized frequency domain representation. The number of bits corresponds to the identified nearest power of two for the corresponding element of the updated Q matrix.

Disclosed is an operation method for executing an addition operation on quantized matrices. This operation method comprises the steps in which: an NPU matrix multiplication unit executes a matrix multiplication operation on a first matrix and a second matrix, wherein the first matrix has a size of R0*2C0 and is obtained by concatenating a first input tensor and a second input tensor, each of which is composed of quantized values and has a size of R0*C0, and the second matrix is obtained by concatenating a first diagonal matrix having a size of C0*C0 and having all main diagonal element values equal to integer N1 and a second diagonal matrix having a size of C0*C0 and having all main diagonal element values equal to integer N2; and an NPU vector processing unit calculates elements of a non-quantized tensor obtainable by adding the second input tensor to the first input tensor, by adding real number B to a product of real number R and a third matrix calculated by the matrix multiplication operation.

The invention relates to the technical field of artificial intelligence model optimization, in particular to a large model reasoning acceleration method and device for packet sensing quantization and residual correction, and the method comprises the steps: carrying out the statistical analysis of the weight and activation of each layer of a large model, and generating a channel feature matrix; constructing a learnable grouping mapping matrix, dividing channels into different groups, and dynamically distributing quantized bit width to obtain a grouping weight matrix; on the basis of the channel weight-activation joint sensitivity, calculating each grouping error contribution on line by using a small prediction model, and adjusting a grouping weight matrix to generate an optimized weight matrix; constructing an error control matrix to dynamically adjust the quantization error along the propagation path, and generating a correction matrix; dynamically adjusting the sparse rate and the quantization precision according to the channel feature matrix and the hardware constraint by combining a structured sparse strategy, and generating a sparse quantization matrix; in the reasoning process, model reasoning is carried out according to the correction matrix and the sparse quantization matrix, and the weight matrix and the correction matrix are updated and optimized in a closed-loop mode.

The application discloses a network security situation awareness method based on artificial intelligence, comprising the following steps: collecting multi-source heterogeneous data to generate a standardized data set; decoupling space-time characteristics to separate space-time dimension characteristics; fusing space-time cross attention to output fused space-time characteristic vectors; constructing a causal reasoning engine to output a dynamic causal diagram and a counterfactual reasoning result set; constructing a dynamic risk propagation model to output a full asset risk value matrix and a risk propagation path diagram; generating a situation quantization matrix, constructing an adversarial training decision network, and outputting a defense strategy set verified by adversarial training; automatically generating a strategy; and man-machine collaborative verification closed loop. Through space-time characteristic decoupling and the causal reasoning engine, the application realizes dynamic reconstruction of a threat propagation path, reduces risk positioning error; in combination with the adversarial training decision network, the application makes the defense strategy have a reduced misjudgment rate in the simulation APT attack test.

The invention discloses an image compression method and device, and the method comprises the steps: comparing a threshold matrix with a frequency domain coefficient matrix, so as to calculate the number of effective coefficients of each frequency point in each frequency domain coefficient matrix, forming an effective coefficient matrix, and achieving the independent calculation of the scaling of each frequency point based on the effective coefficient matrix and a scaling calculation formula. According to the method, a frequency domain coefficient matrix is obtained, a corresponding scaling matrix is formed, a corresponding optimized quantization matrix is generated according to the scaling matrix, the frequency domain coefficient matrix is quantized by using the optimized quantization matrix, scanning, data rearrangement and entropy coding operation are executed, and image compression is completed.

Disclosed herein is a video decoding method including determining one or more adaptation parameter sets including a quantization matrix set including a plurality of quantization matrices, determining an adaptation parameter set including a quantization matrix set applied to a current picture or a current slice from among the one or more adaptation parameter sets, dequantizing transform coefficients of a current block of a current picture or a current slice based on the quantization matrix set of the determined adaptation parameter set, and reconstructing the current block based on the dequantized transform coefficients, wherein the adaptation parameter set includes coding information applied to one or more pictures or slices.

The invention relates to an electromagnetic component performance analysis method and device, equipment, a medium and a product, and the method comprises the steps: constructing a judgment matrix according to the relative importance degree of a plurality of quantitative indexes affecting the performance of a to-be-analyzed electromagnetic component; the to-be-analyzed electromagnetic components comprise a plurality of electromagnetic components in the target substation; determining a weight matrix corresponding to each quantitative index according to the value of each element in the judgment matrix; determining a membership matrix corresponding to each quantitative index according to the membership between each quantitative index and a preset quantitative level; determining a comprehensive quantization matrix according to the weight matrix and the membership matrix; each element value in the comprehensive quantization matrix represents an electromagnetic protection level quantization value corresponding to the to-be-analyzed electromagnetic component. By adopting the method, the accuracy and reliability of a final electromagnetic component performance analysis result can be improved, and a scientific basis is provided for operation management, equipment type selection and the like of a transformer substation.

The present disclosure provides a network training method and device, a network optimization method and a data processing method. The network training method comprises: quantizing a sample neural network to obtain a sample quantization matrix in a first state, the matrix being used to indicate the type of an operator in the network and the connection relationship between the operators; performing optimization function prediction on the sample quantization matrix in the mth state through a reinforcement network in the mth state to determine a sample optimization function in the mth state; optimizing the sample neural network in the mth state through the sample optimization function in the mth state to obtain a sample neural network in the m+1th state; training the reinforcement network in the mth state according to the reward values of the sample neural networks in the mth state and the m+1th state to obtain a reinforcement network in the m+1th state; and determining the trained reinforcement network under the condition that a training condition is met. The embodiments of the present disclosure can improve the training effect of the reinforcement network.

The invention discloses a dust monitoring method and monitoring system for an out-of-service wind power blade, and relates to the technical field of dust monitoring. The method comprises the following steps: marking a tracing material on an ex-service wind power blade, establishing a mapping relation between spectral characteristics and blade information, transmitting a coaxial composite light detection light field to a to-be-monitored ex-service wind power blade processing area through a multi-frequency laser synergistic excitation source, receiving a returned multi-mode light response mixed signal, and determining the ex-service wind power blade to be monitored according to the received multi-mode light response mixed signal. The method comprises the following steps: performing multi-spectral feature calculation on a multi-modal light response mixed signal through a sub-channel spectral decoupling mechanism to obtain a component-form-traceability three-dimensional feature set, generating a dust hazard level dynamic quantization matrix through a cross-spatio-temporal data coupling knitting algorithm, and constructing a global dust situation monitoring panoramic map through a virtual-real mapping visualization technology. And a directional traceability regulation and control instruction is generated. The dust risk management and control efficiency and precision in the decommissioning wind power blade treatment process can be improved, and harm of dust to personnel health and the environment is reduced.

A system and method for energy-efficient approximate digital JPEG and MJPEG-compression. The system includes a controller unit to control a processing loop for processing image blocks based on a comparison of a current image block to a previous image block. The system includes a quantization unit configured to quantize the frequency domain representation using an approximate quantization process and a quantization (Q) matrix. The quantization unit is configured to: identify, a nearest power of two value for each element of the quantization matrix; generate an updated Q matrix by assigning each element of the quantization matrix with the identified nearest power of two value; and shift each element of the updated Q matrix by a number of bits to generate a quantized frequency domain representation. The number of bits corresponds to the identified nearest power of two for the corresponding element of the updated Q matrix.

An orthogonal transform unit orthogonally transforms prediction residuals in a block of a P×Q array of pixels, thereby generating an N×M (N is an integer satisfying N<P, and M is an integer satisfying M<Q) array of orthogonal transform coefficients. A quantization unit quantizes the N×M array of the orthogonal transform coefficients using at least a quantization matrix of an N×M array of elements, and thereby generates an N×M array of quantized coefficients.

The present disclosure relates to the technical field of computer system, and provides a fine-grained quantization matrix multiplication device and method based on systolic array, which comprises: an input scheduling module, configured to receive input matrix data and corresponding quantization factor data, and to attach type identifiers to the input matrix data and the quantization factor data; a systolic array, connected by multiple processing units in a two-dimensional mesh structure, and each processing unit is configured to select to perform a multiply-accumulate operation or a dequantization operation according to the data received from an upstream and the type identifier of the data; wherein the input scheduling module is configured to schedule the data with the attached type identifiers to the systolic array by rows and by columns; and an output module, configured to receive and output the calculation results calculated by the systolic array. The problems of low efficiency of quantization factor insertion, fragmentation of dequantization and calculation pipeline, and large task switching overhead are solved, and the data multiplexing rate, calculation efficiency and overall energy efficiency ratio of the systolic array in the fine-grained quantization scenario are significantly improved.

The present application provides an image decoding apparatus and method, an image encoding apparatus and method, and a storage medium. A decoding unit decodes data corresponding to a first array of quantized coefficients including an N x M array of quantized coefficients corresponding to a first block and data corresponding to a second array of quantized coefficients including an N x M array of quantized coefficients corresponding to a second block. An inverse quantization unit derives a first array of orthogonal transform coefficients from the first array of quantized coefficients using at least a first quantization matrix of elements of the N x M array and derives a second array of orthogonal transform coefficients from the second array of quantized coefficients using at least a second quantization matrix of elements of the N x M array. An inverse orthogonal transform unit inverse orthogonally transforms the first array of orthogonal transform coefficients to generate a first prediction residual of pixels of a P x Q array and inverse orthogonally transforms the second array of orthogonal transform coefficients to generate a second prediction residual of pixels of the N x M array.

The application discloses an adversarial sample generation method based on AdvDrop, relates to the technical field of machine learning security, and processes two different branches of an image input space domain and a frequency domain; for the frequency domain attack AdvDrop, first, the input image is segmented into N*N blocks, and discrete cosine transform (DCT) is used on each block to convert them to the frequency domain; a quantization matrix M is introduced to reduce some specific frequencies of the transformed image; a tangent function is introduced in the quantization process to gradually approach the quantization function, and then the quantization matrix M is accurately adjusted through the new quantization function; then, the image is converted from the frequency domain to the space domain through inverse discrete cosine transform (IDCT) operation; finally, the space domain attack and the frequency domain attack fusion module are used to iteratively update the adversarial perturbation by using the gradients from different fields, and the adversarial sample is generated; the quality of the generated adversarial sample is improved, the difference between the distribution characteristics of the adversarial sample and the distribution characteristics of the real sample is reduced, and the attack success rate is improved.

Decoding corresponding to a first array of quantized coefficients including an N×M array corresponding to a first block and data corresponding to a second array including an N×M array corresponding to a second block. Deriving a first array of orthogonal transform coefficients from the first array of quantized coefficients by using at least a first quantization matrix of an N×M array of elements, and derives a second array of orthogonal transform coefficients from the second array of by using at least a second quantization matrix of an N×M array of elements. Performing inverse orthogonal transform on the first array of orthogonal transform coefficients to generate a P×Q array of pixels of first prediction residuals, and performs inverse orthogonal transform on the second array of orthogonal transform coefficients to generate an N×M array of pixels of second prediction residuals.

The application relates to the technical field of network security, and discloses a data processing method and system for network security monitoring.The method comprises the following steps: acquiring network entity connection relationship data and historical attack event data; constructing graph structure data and obtaining an initial representation vector by embedding the graph structure data in a preset graph neural network; weighting the initial representation vector according to a network entity importance index to obtain a quantization matrix; extracting risk nodes from the quantization matrix, and obtaining potential transmission paths by random walk when the number of the risk nodes exceeds a preset number threshold; processing the potential transmission paths in segments to confirm a risk core mode; marking a propagation chain set based on the risk core mode; extracting node risk values from the propagation chain set and preprocessing the node risk values to obtain a risk state vector, inputting the risk state vector into a preset time sequence prediction model to obtain a predicted diffusion distribution probability; determining an enhanced monitoring target based on a preset probability threshold and the predicted probability; and obtaining a monitoring enhancement scheme after solving a target function.

The application discloses a kind of power network container migration methods based on probability language and resource similarity, belong to the field of power network, including: according to container resource average demand quantity calculation container demand semantic probability, according to resource actual demand and declaration demand, construct multidimensional resource judgment matrix and calculate container demand semantic vector, calculate container resource demand probability language quantization vector.Power node resource semantic probability matrix is calculated, and the probability language matrix of the available resource of power node is constructed, and the probability language quantization matrix of the available resource of power node is calculated.According to container resource demand probability language quantization vector and the probability language quantization matrix of the available resource of power node, resource similarity vector is calculated, and the most similar power node is selected to migrate container.The application effectively quantizes the similarity of multidimensional data between container resource demand and power node resource condition, ensures migration result, meets the demand of user container and improves the stability and efficiency of power network operation.

The invention relates to the technical field of computer systems, and provides a fine-grained quantization matrix multiplication device and method based on systolic arrays, and the device comprises a first systolic array which is used for receiving element streams of a first quantization factor matrix and a second quantization factor matrix, and carrying out the fusion calculation of quantization factors according to the element streams of the quantization factors, generating a quantization factor product; the second systolic array is used for receiving element streams of the first data matrix and the second data matrix, and performing multiplication and accumulation calculation according to the element streams of the matrixes; each first processing unit in the first systolic array is configured to send a quantization factor product obtained by calculation to a corresponding anchor processing unit in the second systolic array according to a mapping proportion; and the anchor processing unit is configured to receive the quantization factor product and serve as a propagation source point, the quantization factor product is propagated in the second systolic array in the row direction and the column direction within the quantization block size range corresponding to the quantization factor product, and the calculation efficiency is improved.

The invention relates to the technical field of computer systems, and provides a fine-grained quantization matrix multiplication device and method based on a systolic array, and the device comprises an input scheduling module which is used for receiving input matrix data and corresponding quantization factor data, and adding type identifiers to the input matrix data and the quantization factor data; the systolic array is formed by connecting a plurality of processing units in a two-dimensional net structure, and each processing unit is used for selectively executing multiply-accumulate operation or inverse quantization operation according to the data received at the upstream and the type identifier of the data; wherein the input scheduling module is used for scheduling data added with a type identifier to a systolic array according to rows and columns; and the output module is used for receiving and outputting a calculation result calculated by the systolic array. The problems that quantization factor insertion is low in efficiency, inverse quantization is separated from calculation flow and task switching overhead is large are solved, and the data reuse rate, the calculation efficiency and the overall energy efficiency ratio of the systolic array in a fine-grained quantization scene are remarkably improved.

The present application provides an encoding device, a decoding device and a storage medium. The encoding device performs up-conversion and down-conversion on a first quantization matrix to generate a second quantization matrix, the first quantization matrix has a first number of rows and a first number of columns equal to the first number of rows to form a square matrix, the second quantization matrix has a second number of rows and a second number of columns different from the second number of rows to form a rectangular matrix; and, using the second quantization matrix to quantize the transform coefficients of the current block, wherein, in the up-conversion, the circuit generates the second quantization matrix by performing up-conversion in a first direction in such a way that one of the second number of rows and the second number of columns is greater than the first number of rows, the first direction is the horizontal direction; and, in the down-conversion, the circuit generates the second quantization matrix by performing down-conversion in a second direction in such a way that the other of the second number of rows and the second number of columns is less than the first number of rows, the second direction is different from the first direction, and the second direction is the vertical direction.

The invention relates to a matrix quantization operation method and device based on an analog storage and calculation integrated circuit, and the method comprises the steps: enabling a preset quantization coefficient memory, an intermediate vector memory and a controller to be connected with a preset splicing unit, a vector number multiplication unit and a matrix multiplication unit, a preset analog-to-digital converter and a digital-to-analog converter are combined to construct a target simulation, storage and calculation integrated circuit; obtaining current working demand information of the target simulation storage and calculation integrated circuit, and determining a current working state type of the target simulation storage and calculation integrated circuit according to the current working demand information; and based on the current working state type, controlling the target simulation storage and calculation integrated circuit to execute a corresponding quantization matrix multiplication operation so as to obtain a final matrix multiplication result. Therefore, the problem that an application scene is seriously limited due to the fact that an existing simulation storage and calculation integrated circuit lacks support for grouping quantization matrix multiplication is solved.

The invention relates to the technical field of silicon carbide defect detection, and discloses a silicon carbide product defect detection method and system based on an intelligent sensor, and the method comprises the steps: obtaining initial time sequence data; executing spatial feature mapping according to the data, extracting a preliminary boundary of a purity non-uniform region, and obtaining a purity deviation feature vector of the preliminary boundary; performing multi-time-domain evolution analysis based on the vector to obtain an optimized defect transition trajectory sequence; carrying out time domain differential analysis on the sequence, and extracting a dynamic evolution path index; the purity is judged, and an evolution influence quantization matrix is generated; further fusing the associated information to obtain a defect evolution influence factor; and generating a defect detection report based on the factor to obtain a final detection result. According to the method, defect dynamic evolution tracking under the high-temperature working condition can be achieved.

The embodiment of the invention provides an effective asset verification-based power transmission and distribution price calculation method, which is applied to the technical field of power systems, and comprises the following steps of: acquiring environment data, equipment health data and operation data of a power transmission line, calculating an environment adaptability coefficient and a space redundancy parameter, and performing multi-dimensional fusion on the environment adaptability coefficient and the space redundancy parameter to form an effective asset quantification matrix; further mapping into an effective asset score and an effective asset value of each power transmission line; and calculating an effective asset reduction proportion according to a comparison result of the effective asset score and a preset trigger threshold value, inputting the effective asset value and the reduction proportion into a power transmission and distribution price calculation model, determining the power transmission and distribution price of each power transmission line, and realizing accurate matching of the asset value and the price allocation.