71 results about "Result vector" patented technology

The application discloses an edge computing platform and system based on FPGA real-time target recognition detection, and relates to the field of microelectronic chips.The edge computing platform comprises an interconnected FPGA and DDR, and an ISP module, a pre-processing module, a VDMA module, an inference accelerator, a CPU and a character superposition module are arranged on the FPGA.The inference accelerator is used for deploying a preset convolutional neural network model, reading any frame of second image and weight parameter data about convolution kernels in the convolutional neural network model from the DDR, accelerating the execution of the algorithm of the convolutional neural network model by using a sphygmic array cluster module, and generating an inference result vector output to the DDR;the sphygmic array cluster module is integrated with a Winograd fast convolution algorithm and a multi-channel sphygmic array.Compared with the prior art, the application realizes the accelerated operation of the convolutional neural network model, and thus improves the inference efficiency.

The application provides an automatic disk IO method based on structural mechanics CAE simulation software, comprising the following steps: S1, constructing a memory-disk cooperative computing framework, and dynamically monitoring a data access state in a simulation solving process; S2, automatically exchanging non-active core data structures to a high-performance disk according to a data access frequency, a life cycle and a memory pressure; S3, loading back to the memory on demand when subsequent calculation needs to access the data exchanged to the high-performance disk; wherein the core data structures comprise a stiffness matrix, shape function data, an intermediate result vector and derivative physical quantities, and the exchange process is transparent to the solver. According to the application, the exchange process is highly transparent to the core computing logic of the solver, is automatically managed by the system, and does not need user intervention, so that efficient utilization of memory resources and stable operation of super-large-scale model simulation are realized.

This application provides an address comparison and checking method, scalar processor, and device for a compressed issue queue. The method acquires a first instruction and a second instruction from the compressed issue queue; and obtains an address comparison and checking result based on the address correlation between the first instruction and each second instruction. Furthermore, a comparison and checking result vector is formed, and this vector is updated in advance based on the instruction status in the compressed issue queue in the next cycle. This method, by obtaining the address comparison and checking result based on the address correlation between the first instruction and each second instruction, can flexibly support diverse memory access granularities with a small hardware area overhead while ensuring processor performance (timing). Additionally, by calculating the next state of the comparison and checking result in advance based on the enqueue / dequeue status of the issue queue determined in the current cycle, and updating it directly in the next cycle, it ensures a one-to-one correspondence between the address comparison and checking result and the new instruction position in the issue queue, while also optimizing timing.

The invention discloses a high-precision coordinate calculation method based on Matlab, and belongs to the field of coordinate calculation technology and data processing, and the method comprises the steps: firstly, obtaining the combination of all points and vectors through a specific combination generation function, and then initializing a result vector; aiming at each combination, calculating intersection point coordinates and parameters by virtue of an accurate geometric intersection point calculation function, storing the intersection point coordinates and parameters in a result vector, and distributing the intersection point coordinates and parameters to a working area according to a rule by virtue of a working area assignment function; then, a midpoint coordinate matrix is obtained by applying a midpoint calculation function based on the coordinates of the intersection points, the distance between the points is calculated, a clustering center is determined by adopting a clustering algorithm, points of an intersection point concentrated area are screened out according to distance characteristics in a cluster, and finally, high-precision coordinates are calculated through a weighted average calculation function in combination with priori knowledge and weights. According to the method, the coordinate calculation precision can be effectively improved, good noise immunity is achieved, priori knowledge can be fully fused, and the method is suitable for numerous fields with high coordinate precision requirements.

The invention relates to the technical field of power equipment state monitoring and intelligent operation and maintenance, and discloses a high-voltage cable operation state reliability evaluation method and system. The method at least comprises the following steps: converting a standardized multi-modal data set into a standardized evaluation data set by referring to a pre-constructed integrity evaluation system, and generating a training sample set and a verification sample set based on the standardized evaluation data set; constructing a composite neural network architecture comprising a feature extraction layer, a nonlinear transformation layer and a parameter optimization layer, and training the composite neural network architecture based on the training sample set to obtain an evaluation result vector comprising a plurality of reliability dimensions; and comparing the evaluation result vector with a verification sample set from a plurality of dimensions including numerical value consistency check, trend goodness of fit analysis and anomaly detection capability evaluation to obtain a structured evaluation report reflecting the reliability of the running state of the high-voltage cable. The intelligent operation and maintenance response efficiency of the high-voltage cable is remarkably improved.

The application discloses an AI scoring report intelligent generation and analysis method based on cloud cooperation, which comprises the following steps: step one, obtaining original scoring data of an object to be evaluated; step two, performing data preprocessing on the original scoring data; step three, obtaining a scoring feature tensor and a collaborative scoring feature sub-tensor set through decryption verification and feature construction; step four, generating a scoring prediction result vector through an improved Crossformer network based on the scoring feature tensor and the collaborative scoring feature sub-tensor set; step five, generating a structured AI scoring report text through template matching and field semantic mapping based on the scoring prediction result vector; step six, performing semantic consistency detection and logical conflict detection on the structured AI scoring report text; and step seven, updating the improved Crossformer network. The Crossformer network is used, and the credibility of AI scoring report intelligent generation is improved.

This invention relates to an improved spatially smoothed source angle estimation method and apparatus based on a coprime linear array. The method includes: acquiring a signal from a source under test using an augmented coprime array to obtain a received signal; vectorizing the covariance matrix of the received signal, sorting the resulting vectors according to the element positions of the uniform linear array, and processing them according to a data processing strategy to obtain a virtual signal received by a virtual array; uniformly dividing the virtual array into overlapping virtual subarrays based on a pre-constructed spatial smoothing rule, and calculating the spatial smoothing covariance matrix of the received signals from the virtual subarrays; performing eigenvalue decomposition on the spatial smoothing covariance matrix using a predefined spatial spectrum estimation method to obtain a spatial spectrum function; and performing spectral peak search on the spatial spectrum function to determine the source angle of the source under test. The method provided by this invention improves the array degrees of freedom and the accuracy of source angle estimation by constructing a larger number of virtual array elements.

A method, system, device and medium for evaluating the contribution of participants in federated learning, the method evaluates the contribution of participant updates to the convergence of the global model from the perspective of model update similarity, uses the projection size and the included angle relationship of the local model update of the participant in the convergence direction of the global model to calculate the contribution value of a participant at a certain training round; the contribution is an evaluation of the uploaded model of the participant, including the data contribution and model training contribution of the participant, obtaining the contribution percentage normalization result of each participant in this federated learning, and forming a result vector evaluation result to provide a basis for constructing an incentive mechanism to ensure the fairness of federated learning; the system, device and medium based on the projection for evaluating the contribution of participants in federated learning, realize reasonable evaluation of the contribution of participants, and do not need test data set, have the advantages of simple and efficient evaluation, high precision.

The invention discloses a sparse matrix vector multiplication-oriented hardware accelerator, sparse matrix vector multiplication-oriented hardware accelerator equipment and an application method, and the hardware accelerator comprises an off-chip storage system, an on-chip network used for carrying out data exchange routing, and an on-chip processing system used for executing access and multiplication calculation and matrix in-row element merging, the off-chip storage system comprises HBM channels used for storing five types of data of a column index, a row index, a vector value, a matrix value and a result vector, each HBM channel comprises an HBM stack and a memory controller, and the HBM channels used for storing the vector values are connected with an on-chip network through second-level caches. And the other HBM channels are directly connected with the on-chip processing system. The method aims at improving on-chip data reuse of the hardware accelerator for sparse matrix vector multiplication, reducing off-chip memory access times and improving performance and energy efficiency performance of the hardware accelerator.

The embodiment of the invention provides a reasoning result obtaining method, electronic equipment and a computer readable storage medium, in the reasoning result obtaining method, after the electronic equipment obtains a query text, the query text is converted into a mark sequence, and the mark sequence is sent to the electronic equipment; then obtaining a first query matrix, a first key matrix and a first value matrix in a pre-filling stage according to the mark sequence, and executing dot product operation, normalization operation and weighted summation operation among the first query matrix, the first key matrix and the first value matrix in parallel; next, in a decoding stage, the matrix vector operation, the normalization operation and the weighted summation operation of the current result vector, the second key matrix and the second value matrix are subjected to parallel calculation, and finally, the next mark of the reasoning result is obtained according to the result of the weighted summation operation in the decoding stage, so that the next mark of the reasoning result can be obtained through parallel calculation in the pre-filling stage. The calculation delay is reduced, and the calculation bottleneck is relieved; in the decoding stage, through parallel computing, the bandwidth utilization rate is improved, and the memory access bottleneck is relieved.

According to the continuous sign language recognition method based on visual text prompt guidance, frame-level semantic conditional fusion is carried out before fusion, and on the premise that an external sensor and a skeleton pipeline are not introduced, the frame-level semantic conditional fusion is carried out; frame-level visual feature sequences extracted by a video encoder are constructed in parallel, and are averagely pooled to obtain a video-level visual prompt vector and a frame-level text prompt vector obtained by a text prompt extraction module. Unified linear projection and splicing are completed in the prompt guide fusion module, visual-text prompt vectors are generated through a multi-layer perceptron, broadcast copying is carried out along the time dimension, layer normalization is carried out to complete frame-by-frame fusion after the visual-text prompt vectors are added with feature residuals output by a main model of each frame, and then the visual-text prompt vectors are input into an encoder and a CTC to be subjected to end-to-end training; the discriminability and the time sequence consistency of feature expression are improved, so that the synchronous improvement of identification optimization and feature optimization is realized, and the robustness and the identification performance of the model are enhanced.

Embodiments of the present disclosure provide a method, apparatus, computing device and storage medium for calculating matrix-vector multiplication, where the matrix is an M*K matrix and the vector is a K*1 vector, M and K are positive integers. The method comprises: converting the M*K matrix into an M*(K / N)*N first tensor, where N is a positive integer, N>1, and K is a multiple of N; converting the K*1 vector into an N*(K / N) second tensor; using a tensor computing core to batch-process the general matrix multiplication of the M*(K / N)*N first tensor and the N*(K / N) second tensor to obtain M result matrices; and adding the elements on the diagonal of each of the M result matrices to obtain each element on the M*1 result vector of the M*K matrix multiplied by the K*1 vector. The above scheme uses a tensor computing core to implement high-throughput, low-latency high-speed matrix-vector multiplication (MMV) operation.

The application provides an optical computing device, method, equipment and storage medium. The device comprises a processor configured to obtain a target vector and a target matrix to be subjected to multiplication calculation; the processor is further configured to decompose the target matrix to obtain at least one sub-matrix and a weight vector; a modulator configured to configure a phase difference of an optical computing unit in a corresponding optical computing array based on an element attribute of a matrix element in the sub-matrix; a laser configured to generate an optical signal; the modulator is further configured to configure a phase of the optical computing unit in the corresponding optical computing array based on an element attribute of a vector element in the target vector; an optical computing array configured to receive the optical signal and output a corresponding optical computing result; and the processor is further configured to perform weighted calculation on the optical computing result based on the weight vector to obtain a calculation result vector of the target vector and the target matrix. The application can reduce the complexity of the configuration of the optical computing unit and avoid information loss.

The invention discloses a fault decision-making method for a fault diagnosis system, and the method comprises the following steps: S1, carrying out the feature extraction of multi-modal data: enabling the multi-modal data to enter a neural network operator (100) in a tensor form, and carrying out the hierarchical feature extraction, thereby obtaining a feature graph F; s2, calculation of a weight vector G: inputting the feature map F into a gating network (210) to generate the weight vector G, inputting the feature map F into an expert network (220) to generate a diagnosis result vector E, and obtaining an output result Y by an internal hybrid expert layer (200) according to the weight vector G and the diagnosis result vector E; and S3, generation of a structured fault result: the local expert system (300) performs reasoning on the output result Y in combination with a preset rule base to generate the structured fault result. According to the fault decision-making method for the fault diagnosis system provided by the invention, the calculation efficiency and the interpretability of the model can be improved while high precision is ensured.

A data processing device comprises a round mask generator, a controller configured to control values and a processor configured to iteratively process a vector of values, where each iteration comprises receiving a respective input vector, generating a processing result vector by applying a predefined processing algorithm to the input vector, and, in reaction to that the control value associated with the iteration indicates that the iteration is a dummy iteration, outputting the input vector re-masked with the round mask associated with the next iteration of the sequence of iterations and, in reaction to that the control value associated with the iteration indicates that the iteration is a real iteration, generating a masked processing result vector by masking the processing result vector with the round mask associated with the next iteration and outputting the masked processing result vector.

The invention discloses a random binarization Softmax layer and a forward propagation method and a backward propagation method thereof, and relates to the technical field of neural networks, and the method comprises the steps: carrying out the single class sampling of an analog current signal outputted by a memristor cross array, and obtaining a forward propagation result vector of the analog current signal; sending the forward propagation result vector of the analog current signal to a post-processing module, and obtaining error gradient data obtained by the post-processing module based on the forward propagation result vector; carrying out two times of independent category sampling on the error gradient data to respectively obtain a first forward propagation result vector and a second forward propagation result vector of the error gradient data; and simplifying the error gradient data based on the first forward propagation result vector and the second forward propagation result vector of the error gradient data to obtain a back propagation result gradient. Through the method, random binaryzation is realized, meanwhile, the calculation complexity of back propagation is greatly reduced, and the calculation efficiency is remarkably improved.

This invention discloses a hardware accelerator, device, and application method for sparse matrix-vector multiplication. The hardware accelerator includes an off-chip storage system, an on-chip network for data exchange routing, and an on-chip processing system for performing data fetching, multiplication calculations, and matrix row element merging. The off-chip storage system includes HBM channels for storing five types of data: column indices, row indices, vector values, matrix values, and result vectors. Each HBM channel includes an HBM stack and a memory controller. The HBM channels for storing vector values ​​are connected to the on-chip network via a L2 cache, while the remaining HBM channels are directly connected to the on-chip processing system. This invention aims to improve on-chip data reuse in hardware accelerators for sparse matrix-vector multiplication, reduce off-chip memory accesses, and improve the performance and energy efficiency of the hardware accelerator.

Embodiments of this specification provide methods and apparatuses for data privacy protection. An embodiment of the methods comprises receiving, by a first party from a second party, an encrypted integrated vector, determining an encrypted result vector based on the original matrix and the encrypted integrated vector, determining a data processing result based on the encrypted result vector, and sending the data processing result to the second party for the second party to obtain a multiplication calculation result of the original matrix and the n original vectors based on the data processing result.

The embodiment of the invention provides a service method and device, equipment, a storage medium and a program product, and relates to the field of big data. The method comprises the steps of obtaining a query text of a user and determining a corresponding first query vector; corresponding query result information is determined in a multi-modal database according to the first query vector, the multi-modal database comprises a vector database constructed according to vectors corresponding to the unstructured data and a knowledge fragment library constructed according to the structured data, and the query result information comprises result vectors and result knowledge fragments; according to the query result information and historical query information, corresponding first reply information is generated through a natural language generation model, and the historical query information comprises a query text. According to the method, the capability of processing complex interaction is improved.

A computing device (100) is provided that includes a processor (104) and a storage device (102) holding instructions executed by the processor (104) to implement a base artificial intelligence (AI) model (106) and two or more incremental AI models (108A to 108C), each incremental AI model (108) having a lower dimension than the base AI model (106). Comprising an input hint (112) is received, the inference request (110) specifying a selected incremental AI model (108A) of the two or more incremental AI models (108A to 108C). An input hint (110) is input to the base AI model (106), thereby generating a base model result vector (116). An input hint (112) is input to the selected incremental AI model (108A), thereby generating an incremental model result vector (118). The output vector (122) is generated by combining the base model result vector (116) and the incremental model result vector (118) via a combination operation (120). An output vector (122) is output.

The embodiment of the invention provides a data processing method, a vector processor, a chip and electronic equipment. The vector processor comprises an instruction analysis layer, a data scheduling layer and a calculation acceleration layer, the instruction analysis layer is used for decoding the vector instruction to obtain decoding information of the vector instruction; wherein the vector instruction comprises one of the following: a vector operation instruction and a vector configuration instruction, and the vector operation instruction comprises an instruction obtained by converting single-instruction multi-data; the calculation acceleration layer is used for carrying out operation on data of a vector operation instruction according to decoding information of the vector operation instruction by utilizing a calculation array under the condition that the vector instruction is the vector operation instruction, so as to obtain an operation result of the vector operation instruction, and the data of the vector operation instruction is obtained from the data scheduling layer; and under the condition that the vector instruction is a vector configuration instruction, reconstructing the computing array based on decoding information of the vector configuration instruction to obtain a reconstructed computing array.

In a method, audio data and a first complex number array is acquired. The first complex number array includes a filter parameter set of a filter, and is converted into a second complex number array. A real part and an imaginary part of each complex number in the first complex number array are extracted to obtain a first complex number vector. A real part and an imaginary part of each complex number in the second complex number array are extracted to obtain a second complex number vector. A plurality of first operation vectors is obtained based on the first complex number vector. A plurality of second operation vectors is obtained based on the second complex number vector. A set of vector operations is performed on the first and second operation vectors to obtain a plurality of result vectors. Filtered audio data is determined based on the plurality of result vectors.

The invention provides a cross-language information retrieval method and device based on a vectorization model. The method comprises the steps that a retrieval request input by a user in a target language is received; converting the retrieval request into a semantic vector to be retrieved based on a multi-language embedding model; in the vector knowledge base, M retrieval result vectors with the highest similarity with the semantic vector to be retrieved are determined, and information entry original texts corresponding to the retrieval result vectors are fed back to the user. According to the method, the positive and negative sample pair set of the target language is constructed to finish learning fine tuning of the multi-language embedding model, so that the multi-language embedding model constructs a semantic space irrelevant to a language, and the purpose that the target language used by a user is the language can be achieved. And the converted semantic vectors can be compared and matched with entries in the vector knowledge base in the same semantic space, so that the semantic consistency of cross-language query is ensured, and the cross-language information retrieval accuracy is remarkably improved.

The present disclosure provides a statistical analysis-oriented cross-language code generation method and device, equipment and medium, by acquiring sample data set, initial statistical requirement information and initial semantic hub model; the sample data set and the initial statistical requirement information are input to the initial semantic hub model, and a plurality of sets of initial statistical analysis execution codes corresponding to a preset programming language are mapped; each set of initial statistical analysis execution code is run respectively to obtain a result vector corresponding to each set of initial statistical analysis execution code; each result vector is subjected to consistency check to obtain a consistency check result; if the consistency check result is abnormal, a first model repair instruction is generated to update the initial semantic hub model to obtain a target semantic hub model; statistical requirement information with a target programming language is input to the target semantic hub model, and reliable statistical analysis execution code can be flexibly generated according to user requirements.

The invention discloses a cooking robot automatic cooking method based on artificial intelligence, and the method comprises the steps: collecting image, temperature and humidity data in a pot, carrying out the preprocessing and dynamic weight fusion of the data, and generating a multi-modal fusion matrix; analyzing the visual state of the food material and the thermodynamic state in the pot, and fusing to generate a comprehensive state vector of a decision; inputting to a decision-making model, and generating a control instruction sequence containing the heating degree adjustment amount and the stir-frying action; executing the control instruction sequence, monitoring an execution process, collecting data after execution, and generating a feedback result vector containing an execution deviation and a state after execution; updating parameters of the decision model and an internal optimization target state; receiving preference input and evaluation feedback of a user, and using preference and feedback information to drive personalized adjustment of a decision model and an optimization target state; the sensing precision and robustness of the comprehensive state in a complex cooking environment are greatly improved, and multi-modal data fusion is closer to a real change process.

The present disclosure discloses a lane attribute production system, a production method and a computer program product. The lane attribute production system comprises: a map element encoder and a large language model; an output layer of the map element encoder is connected to an input layer of the large language model, the map element encoder is used for processing a vectorized map to output a vector encoding result, the vectorized map uses a vector feature to represent a map element, and the map element comprises a lane; the input layer of the large language model also receives at least one of an image encoding result and a text encoding result, and the large language model is configured to generate lane attribute data according to at least one of the image encoding result and the text encoding result and the vector encoding result. The scheme of the embodiment of the present disclosure can process data of multiple modalities including a vector modality, so as to match driving rules to corresponding lanes, so as to provide accurate and detailed lane attribute data for constructing a traffic rule layer.

The invention relates to the technical field of software testing, in particular to an automatic software test case generation method and system based on machine learning, and the method comprises the steps: S1, generating an initial population matrix; s2, calculating an action selection probability and selecting an action operator; s3, generating an action result vector; s4, forming a comprehensive index vector; s5, calculating the fitness score of the current iteration round; s6, under the condition of local convergence or insufficient coverage, dynamic step length updating is carried out on the strategy parameters; s7, step length updating is carried out on the coverage initial excitation weight and the diversity initial excitation weight; and step S8, outputting a test data set with an optimal coverage rate and removing structural repeated test samples. According to the method, the test case coverage rate is optimized by dynamically adjusting strategy parameters, diverse incentive weights and removing coverage structures, the local convergence problem is solved, and the automatic test efficiency and comprehensiveness are improved.

This invention discloses a privacy-preserving vector database query method, comprising: each server obtaining a query vector secret share and performing a linear transformation to obtain a transformed query vector secret share; sending the locally held transformed vector data secret share and the transformed query vector secret share to semi-trusted hardware; the semi-trusted hardware performing a nearest neighbor search to obtain the nearest neighbor vector and its corresponding index; sharing the nearest neighbor vector and the one-hot vector corresponding to the index with each server; each server performing a dot product calculation between the one-hot vector secret share and the locally held label secret share to obtain a query result label secret share; performing an inverse linear transformation on the nearest neighbor vector secret share to obtain a query result vector secret share; and sending the query result label secret share and the query result vector secret share to the user terminal; the user terminal reconstructing the query result vector and the query result label.

Mechanisms are provided for fault-tolerant computing. The mechanisms solve, by a controller computing device in a controller-worker computer architecture, a sparse algebraic linear system of equations with incomplete matrix-vector products. The solving includes: A set of worker computing devices computing matrix-vector products Ax=b, wherein A is a sparse matrix, x is a vector being multiplied, and b is a resultant vector; a controller determining that a worker has not returned a result of its computation within a threshold length of time; and in response to the determination, assuming, by the controller computing device, that the result of the worker computing device computation is zero and continuing the computing of a solution to the sparse algebraic linear system. The controller computing device provides, to a subsequent computing operation, the solution to the sparse algebraic linear system of equations as a basis for performing the subsequent computing operation.

The application relates to the technical field of data processing, in particular to a code reordering processing method and system. A plurality of candidate codes are generated based on requirements; a plurality of indexes are set for each candidate code; each index is tested based on an execution channel to generate an execution result vector of each candidate code; each index is tested for deviation to set a deviation value of each index; an equivalent cluster of each candidate code is constructed; an execution score of each candidate code is calculated based on the deviation value and the execution result vector; each candidate code is tested based on an inference channel to output an inference score of each candidate code; a mixed score is calculated, and each candidate code is reordered based on the mixed score and the equivalent cluster. The application overcomes the inference illusion problem of a large language model when generating codes through a double-channel scoring system, and improves the quality of code generation.