Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

449results about How to "Reduce time complexity" patented technology

Power grid main equipment fault diagnosis method and system based on voiceprint cloud edge cooperation

The invention belongs to the technical field of power grid main equipment diagnosis, and provides a power grid main equipment fault diagnosis method and system based on voiceprint cloud edge collaboration, which adopts a new cloud edge collaboration method and divides the analysis of voiceprint monitoring data into two stages. According to the method, the exception detection model is deployed on the edge side, exception analysis of mass voiceprint data is achieved, concurrent requests of a large number of concurrent signals at the cloud side are avoided, and the timeliness of voiceprint monitoring and analysis is improved. In the cloud, a multi-modal defect identification method fusing voiceprint, visible light, infrared and other multi-source data is deployed, secondary classification of sound abnormal signals is realized, and the reliability of equipment operation, maintenance and management is improved.
Owner:STATE GRID INTELLIGENCE TECHNOLOGY CO LTD

Large language model joint reasoning method for enhancing thinking chain prompt based on knowledge graph

The invention belongs to the related technical field of natural language reasoning, and discloses a big language model joint reasoning method based on knowledge graph enhanced thinking chain prompt, which comprises the following steps: constructing a local knowledge sub-graph, decomposing an original problem text into S sub-problem texts, and splicing the original problem text and the S sub-problem texts, and inputting the spliced question text into a graph reasoning model to obtain weighted entity distribution, extracting first G answer entities with the highest confidence from the weighted entity distribution, backtracking the reasoning process of each answer entity by utilizing a reasoning transfer matrix, generating a reasoning path from the question entity to the corresponding answer entity, and obtaining a final reasoning path from the question entity to the corresponding answer entity. And predicting the answer of the original question text by using the reasoning path to assist the large language model. Through the method, the big language model can quickly and accurately find the answer of the question text.
Owner:HUAZHONG UNIV OF SCI & TECH

Power prediction method considering photovoltaic power clustering

The invention discloses a power prediction method considering photovoltaic power clustering, which comprises the following steps of: firstly, acquiring historical data of a photovoltaic power station, decomposing a photovoltaic power time sequence by using an STL time sequence decomposition method, performing DBSCAN clustering on the decomposed photovoltaic power data, identifying a low-power cluster and a high-power cluster, and predicting the power of the photovoltaic power station according to the low-power cluster and the high-power cluster; establishing a photovoltaic power prediction model based on a time convolutional network and Times Net for low power and high power respectively; secondly, a badger algorithm is improved, Chebyshev chaotic mapping is adopted to improve initialization of a badger population, and a Gaussian mutation strategy and a lens imaging reverse learning strategy are introduced to obtain MHBA; and optimizing hyper-parameters of the TCN photovoltaic low-power prediction model and the TimesNet photovoltaic high-power prediction model by using an improved badger algorithm, and predicting photovoltaic power by using the optimized models to obtain a final prediction value. Compared with the prior art, the precision and effectiveness of the photovoltaic power prediction model can be improved.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY

Infrared weak and small target detection self-supervised learning method based on image degradation

The invention belongs to the technical field of target detection, and particularly relates to an infrared weak and small target detection self-supervised learning method based on image degradation, and the method specifically comprises the following steps: S1, preparing data sets: preparing six data sets: a data set 1, a data set 2, a data set 3 and a data set 6 for pseudo sample generation; according to the infrared weak and small target detection self-supervised learning method based on image degradation, a novel degradation model fusing fuzzy degradation, brightness / contrast degradation and scale degradation modes is constructed, and an online gridding high-order constraint pseudo sample generation model combining global target constraint, local target constraint and local gray level constraint is designed. A new position-confidence # imgabs0 # evaluation index is provided, a simple and efficient neural network is designed, a complete network self-supervised training framework is closed to enable the network to converge successfully, the detection precision and the detection speed of a weak and small target are improved, and the problems that calculation complexity is too high and data are difficult to obtain are solved.
Owner:CHANGCHUN UNIV OF SCI & TECH

Welding implicit anomaly detection and identification method based on multi-source data

The invention discloses a welding implicit anomaly detection and identification method based on multi-source data, and belongs to the field of welding quality detection. The implementation method comprises the following steps of: acquiring multi-modal data information of welding quality of each object in real time, wherein the multi-modal data information comprises sound, current, voltage, spectrum, temperature information and image information; each information source is collected by a corresponding sensor, and the characteristics of the information sources are extracted. And carrying out normalization processing on the extracted feature values, and carrying out dimensionality reduction on the data based on abnormal categories by adopting an LDA method. And detecting abnormal points by using a local outlier factor (LOF) method. Abnormal points are identified on the whole by using an isolated forest, a detection region is segmented, and a new neighborhood search space is defined in the segmented region. And adopting a PNN (probabilistic neural network) method to identify abnormal types. And optimizing a smoothing factor of the PNN by using an artificial bee colony algorithm ABC to obtain an optimal smoothing factor and establish an optimal PNN model, and realizing welding recessive anomaly detection and identification according to the optimal PNN network optimization model.
Owner:BEIJING INST OF TECH

EC debugging method based on serial port instruction

The invention discloses an EC debugging method based on a serial port instruction, and the method comprises the steps: connecting debugging equipment and an EC end, and setting serial port parameters of the EC end and the debugging equipment; the debugging equipment sends instruction data to the EC end through a serial port; the EC end judges whether the instruction data is received or not through a serial port interruption mechanism; after the EC end obtains the received complete instruction data, matching the obtained instruction data with a predefined instruction name in the instruction set array by adopting a KMP algorithm; aiming at poor EC debugging expandability in the prior art, communication connection is established between the EC end and the debugging equipment through the serial port, and the debugging equipment generates a debugging instruction according to a preset frame format and sends the debugging instruction to the EC end through the serial port controller. And the EC end receives and judges whether instruction data is complete or not through a serial port interruption mechanism, and then an optimized KMP algorithm and a hash algorithm are adopted to quickly match and analyze the instruction to adapt to different EC debugging requirements.
Owner:SHENZHEN ARBOO TECH

Method for predicting node pressure of urban water supply network

ActiveCN119129798Areduce time complexityEnhanced Generalization Prediction AbilityForecastingPipeline systemsWater useUrban water supply
The invention provides a method for predicting node pressure of an urban water supply pipe network, which comprises the following steps of: constructing a corresponding water supply pipe network topological structure by taking water use nodes in the urban water supply pipe network as nodes and taking connected pipelines as edges; acquiring node pressure data of each sensor in the urban water supply network to construct a data set; constructing a prediction model based on a transform model framework and a water supply pipe network topological structure; training the prediction model by using the data set to obtain a node pressure prediction model for predicting the pressure of the sensorless water use node; and inputting the position information of the target water consumption node and the prediction time point into the node pressure prediction model to obtain node pressure data of the target water consumption node. According to the method provided by the invention, a water supply pressure data prediction model which does not depend on a hydraulic model can be constructed, the water demand pressure of a water demand node in the future is predicted, and good prediction precision is shown in a flat water supply area.
Owner:ZHEJIANG UNIV +2

Photovoltaic power short-term probability prediction system and method

The invention discloses a photovoltaic power short-term probability prediction system and method. The system comprises a convolutional neural network, a sequential network and a probability density estimation module. The time sequence network is composed of a self-organizing mapping neural network, a time sequence encoder and a time sequence decoder; each of the time sequence encoder and the time sequence decoder is formed by alternately connecting an autocorrelation mechanism unit, a time sequence decomposition unit and a feed-forward layer; the time sequence decoder is composed of an upper branch sub-layer and a lower branch sub-layer; the convolutional neural network screens meteorological factors to obtain a high-dimensional mapping relation between meteorological characteristics and optical power; the sequential network performs progressive decomposition and autocorrelation extraction on an optical power sequential sequence to obtain periodicity and tendency characteristics of the optical power sequence; the probability density estimation module optimizes and combines the high-dimensional mapping relation with periodicity and tendency characteristics of the optical power sequence to obtain optical power probability distribution parameter output; according to the method, the numerical weather forecast information and the weather type forecast published by the meteorological observatory are integrated to realize optical power probability prediction, so that the risk of misinformation of a single meteorological source is effectively reduced.
Owner:TIANJIN UNIV

Image clustering method and device based on particle multi-kernel k-mean value, and electronic equipment

The invention relates to the field of image clustering analysis, in particular to an image clustering method and device based on a particle multi-kernel k-mean value and electronic equipment. The method comprises the following steps: acquiring a discrete data point set of a plurality of to-be-clustered images; performing granular ball division on the image data to obtain an image granular ball set; calculating to obtain an image pellet center, an image pellet distance matrix and an average distance between image pellets; calculating to obtain an image pellet kernel matrix; according to the image pellet kernel matrix and a preset clustering division matrix, constructing a multi-kernel k-means clustering objective function based on pellets; calculating to obtain a corresponding target clustering division matrix when the target function value is minimum; discretizing the target clustering division matrix according to a multi-kernel k-mean algorithm to obtain a clustering result of image pellets; and distributing the clustering result of the image pellets to all discrete data points contained in the image pellets to obtain the clustering result of the image data. According to the invention, the efficiency and accuracy of image clustering are improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Traffic flow prediction method and system of adaptive graph learning space-time neural network

The invention discloses a traffic flow prediction method and system of an adaptive graph learning space-time neural network. The invention provides a self-adaptive graph structure learning module, which comprises the following steps of: firstly, constructing a graph adjacency matrix consisting of a predefined adjacency matrix and an adjacency matrix which can be directly learned by training parameters; thirdly, a space-time attention module is designed to learn a space-time attention matrix, the traffic condition is predicted by stacking a plurality of space-time layers, and each space-time layer is subjected to convolution in the space dimension and the time dimension; meanwhile, a two-stage training strategy is provided to improve the performance of the model. According to the method, the space-time dependence of the traffic network can be adaptively learned from the data, and the utilization of a predefined structure is reserved at the same time, so that the prediction accuracy and generalization ability are enhanced. The application of the method in a traffic flow prediction system shows that the method can accurately predict the traffic flow in real time, so that traffic control and optimization strategy formulation are effectively guided.
Owner:YANGZHOU UNIV

Matrix data transposition method, matrix data transposition device and chip

The embodiment of the invention discloses a matrix data transposing method, a matrix data transposing device and a chip, the matrix data transposing method comprises the following steps: performing first cyclic shift on initial matrix data to obtain shift matrix data, taking every at least two adjacent matrix elements as an element set, and further writing the element set into a cache unit; according to the method, the instantiation number of cache units in an artificial intelligence chip can be effectively reduced, so that the area of the artificial intelligence chip is reduced, a target element set is read from each cache unit and combined to obtain target row data, and then the transposed initial matrix data is obtained through simple matrix element recombination, so that the transposed initial matrix data is obtained. Therefore, the time complexity can be effectively reduced, the transposition performance is improved, the area-effect ratio is effectively improved, the transposition performance is effectively improved while the area of an artificial intelligence chip is reduced, and the method can be widely applied to the technical fields of artificial intelligence, cloud technology and the like.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Optical fiber terahertz communication system optimization method based on artificial intelligence

The invention discloses an optical fiber terahertz communication system optimization method based on artificial intelligence, and belongs to the technical field of communication. According to the method, four-dimensional constellation shaping is constructed by utilizing additional dimensions provided by two independent sidebands, and an end-to-end optimization framework is divided into a training stage and a deployment stage; in the training stage, firstly, an equalizer based on a pruning neural network and an equalized channel model based on a mixed density network are trained in sequence through receiving and transmitting of a random training sequence; then connecting a constellation shaper at a transmitting end with a demapper at a receiving end through an equalized channel model with fixed parameters, thereby considering full-link residual distortion and noise after equalization, and carrying out back propagation gradient to learn a globally optimal four-dimensional joint geometric probability constellation diagram to further approach the Shannon limit; and in the deployment stage, transmission of the bit stream is realized through coordination of the four-dimensional geometric shaping constellation table and the probability distribution obtained in the training stage and an equalizer at the receiving end and a demapper.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Video generation acceleration method for large model buffer optimization

The invention relates to the technical field of computers, and provides a video generation acceleration method for large model buffer optimization. Comprising the following steps: constructing and initializing a data structure for storing a cluster and a corresponding token value; performing real-time clustering processing on the tokens extracted from the video stream, and distributing the tokens to corresponding clustering clusters according to features of the tokens; the key tokens in the clustering clusters are reserved and sampled based on a preset rule; and performing approximate calculation of a matrix vector product and a partition function based on the obtained data information to reduce the calculation burden during large model buffer optimization, and adjusting a clustering cluster and a corresponding token value in the data structure according to the approximate calculation result. According to the method, an online clustering method is adopted to compress a data structure, storage of redundant data is reduced, large-scale data flow processing is more efficient, and on the basis of an online clustering and sampling technology of key tokens, the time complexity of calculation is reduced, and the operation speed of an attention mechanism is increased.
Owner:PIO CLOUD COMPUTING (SHANGHAI) CO LTD

Hyperspectral image classification method based on element pseudo-label multi-scale image convolutional network

The invention relates to a hyperspectral image classification method based on a meta-pseudo-label multi-scale image convolution network, and the method comprises the steps: building a meta-pseudo-label multi-scale feature search image convolution network (MPL-MFSGCN), dividing the HSI into superpixel images of different scales through employing an SLIC superpixel segmentation technology, and converting the superpixel images into image structures; secondly, constructing a multi-scale feature search graph convolutional network MFSGCN architecture, optimizing a superpixel feature weight combination by using a neural network search algorithm, and enhancing the discrimination of feature expression; a semi-supervised teacher-student model sharing the same graph convolutional network is adopted to generate meta-pseudo tags, and a student network is finely adjusted to improve the robustness of the network; the key features can be automatically captured under the small sample condition, the classification precision higher than that of an advanced method is obtained compared with a common HSI data set, and the classification accuracy is effectively improved.
Owner:ZHEJIANG COLLEGE OF SECURITY TECH +2

Reliability parameter assisted low-complexity polarization code rate matching method

The invention discloses a reliability parameter assisted low-complexity polarization code rate matching method, and belongs to the technical field of wireless communication. Aiming at the problem that a proper punching site is difficult to select during rate matching due to a recursive structure of a polar code, the invention provides a polar code punching site selection algorithm based on a reliability parameter. An information bit reliability parameter is defined to calculate the reliability of candidate punching bits, and the optimal punching position is selected by traversing and solving the minimum value of the maximum reliability parameter. In order to solve the problem of high complexity of the existing polar code rate matching method, an interleaving algorithm and a pruning serial offset list decoding algorithm based on rate matching parameter mapping are provided, secondary sorting calculation of an interleaver is avoided, and a calculation unit updating strategy of a decoder is simplified. The polarization code rate matching method provided by the invention not only can improve the rate matching coding gain, but also can effectively reduce the calculation complexity.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Federal learning contribution degree evaluation method and device, electronic equipment, medium and product

The invention discloses a federated learning contribution degree evaluation method and device, electronic equipment, a medium and a product, and relates to the technical field of federated learning, and the federated learning contribution degree evaluation method comprises the steps: obtaining an initial global model, and sending the initial global model to each client in a preset client set; performing federal iteration training on the initial global model based on a received local model uploaded by each client in a preset client set, and determining an overall global model; performing federal iteration training on the initial global model based on received local models uploaded by clients except the to-be-evaluated client in a preset client set, and determining partial global models; and determining the contribution degree of the to-be-evaluated client according to a performance difference value between the overall global model and the partial global model. According to the federal learning contribution degree evaluation method provided by the invention, the calculation complexity of the contribution degree is reduced, and the time consumption and the calculation resource demand are reduced.
Owner:WEBANK (CHINA)

Method for solving task-platform optimization configuration problem based on QGA quantum enhancement

The invention discloses a method for solving a task-platform optimization configuration problem based on QGA quantum enhancement, and the method comprises the steps: firstly, employing the true randomness and entanglement of quantum, achieving the coding of a corresponding relation between a task and a platform through a quantum state, and determining an optimal individual in a population through a fitness function; secondly, a quantum logic gate is used for achieving selection operation in the algorithm, and the rotation angle and direction of the quantum logic gate are determined through the fitness difference value between each chromosome and the optimal chromosome; then, a quantum logic gate X and a quantum logic gate SWAP are used for achieving mutation operation and crossover operation in the algorithm respectively; the method provided by the invention has high accuracy and timeliness, the number of algorithm iterations and the time complexity are greatly reduced, and the method can be effectively used for solving the task-platform optimization configuration problem in the military C2 organization.
Owner:NAT UNIV OF DEFENSE TECH

3D human body action generation method and device, storage medium, electronic equipment and product

The invention relates to the technical field of 3D action generation, and particularly provides a 3D human body action generation method and device, a storage medium, electronic equipment and a product, and the method can comprise the steps: obtaining a text feature vector corresponding to the text description of a human body action; layering and quantifying the text feature vector to obtain a basic action mark sequence and a residual action mark; acquiring a basic action sequence corresponding to the basic action mark sequence, and acquiring a residual action sequence corresponding to the residual action mark; and generating a 3D human body action sequence based on the basic action sequence and the residual action sequence. Some embodiments of the present application can improve the accuracy of 3D human motion generation.
Owner:BEIJING VIRTUAL DYNAMIC POINT TECH CO LTD

Vehicle moving track data compression method and system and electronic equipment

The invention discloses a vehicle moving track data compression method, which comprises the following steps of: acquiring vehicle driving data which comprises vehicle original track data; performing first analysis processing on the vehicle driving data to obtain vehicle travel information; performing first impurity removal processing on the vehicle original trajectory data to obtain first trajectory impurity removal data; performing track redundant point merging processing on the first track impurity-removed data to obtain first track compressed data; and performing similar track merging processing on the first track compressed data to output second track compressed data. According to the technical scheme, compared with the prior art, the compression rate of the vehicle form track can be increased, and the pressure of data processing and transmission can be reduced. In addition, the invention also relates to a vehicle movement track data compression system and electronic equipment, which also have the above beneficial effects.
Owner:SHENZHEN LANYOU TECHNOLOGY CO LTD

Hierarchical power electronic circuit layout method based on reinforcement learning

The invention discloses a hierarchical power electronic circuit layout method based on reinforcement learning, which belongs to the field of integrated circuits and mainly comprises three levels of element sequence generation, layout optimization and wiring optimization. The method comprises the following steps: firstly, analyzing the power flow direction of a power electronic circuit, and reasonably arranging an element layout sequence, so as to realize basic optimization from a top layer; then, on the basis of the element sequence, a convolutional neural network is used for extracting layout features, a graph convolutional neural network is used for extracting graph features of a circuit connection relation, specific design rules of the power electronic circuit are embedded into a reinforcement learning reward system, and a deep Q network (DQN) is used for achieving layout of elements; through reinforcement learning, the intelligent agent can summarize experience in trial and error without human intervention, and finally a reward maximized layout result is generated.
Owner:HUAZHONG UNIV OF SCI & TECH

Unmanned aerial vehicle route planning method, electronic equipment and computer readable medium

The embodiment of the invention discloses an unmanned aerial vehicle route planning method, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the steps of obtaining unmanned aerial vehicle task demand information of a to-be-executed task; environment information between the flight start point and the flight end point is collected, and the environment information comprises the terrain and at least one obstacle information; according to the unmanned aerial vehicle task demand information and the environment information, generating a flight starting point and a flight ending point, and obtaining an initial flight route path; performing path optimization on node paths among the flight nodes in the initial flight route path to generate an optimized flight route path; generating a target flight route path according to the optimized flight route path; and controlling the unmanned aerial vehicle to execute the task to execute the task according to the target flight route path. According to the embodiment, the route path generation efficiency can be improved on the premise of ensuring that the optimal flight path for the unmanned aerial vehicle is accurately generated.
Owner:STATE GRID INFORMATION & TELECOMM GRP CO LTD +1

Regional new energy output and load prediction method based on source-load common mode

The invention discloses a regional new energy output and load prediction method based on a source-load common mode, and the method comprises the following steps: 1), collecting a source-load end historical sequence and same-time-period meteorological data, 2), obtaining a multi-mode feature sequence of an electrical load and a new energy output sequence at different frequencies through an original sequence of variational mode decomposition; 3) fusing the multi-modal feature sequence, the meteorological feature sequence and the time coding feature sequence to obtain a multi-dimensional feature fusion sequence group; 4) constructing a model containing a pyramid attention module based on a multi-way tree structure; and 5) collecting features given by the last node of all scales in the pyramid attention module, mapping the features to all future time steps in the batch, and obtaining final prediction through a full connection layer of a cross-channel dimension. The method has the beneficial effect that the common mode effect of a complex coupling relation under the influence of multiple factors such as a supply side and a demand side is improved.
Owner:STATE GRID JIANGSU ECONOMIC RES INST +2

Single-photon laser ranging method based on laser pulse frequency modulation deblurring

The invention discloses a single-photon laser ranging method based on laser pulse frequency modulation deblurring, and belongs to the field of laser ranging. In the ranging process, two different pulse frequency references are firstly set to correspond to two coding code elements respectively, n-bit random codes are generated according to n-time non-fuzzy distance expansion requirements, it is guaranteed that the n-bit random codes do not have displacement symmetry, then a laser source is made to repeatedly emit corresponding pulse signals according to a sequence represented by the random codes, then echo signal sequences are received, and the pulse frequency references correspond to the two coding code elements respectively. And performing cross-correlation operation on the single photon accumulation histogram and a pulse sequence represented by a known random code to obtain an operation result, determining one of the single photon accumulation histograms with the maximum amplitude, and calculating a histogram time position corresponding to the result, namely, calculating a distance measurement result of de-blurring. According to the method, the problem of range ambiguity of pulse radar ranging can be solved, the time sliding sequence matching method proposed in cross-correlation operation has the advantages of being efficient and flexible, and the time complexity of cross-correlation operation is effectively reduced.
Owner:BEIJING CHANGCHENG INST OF METROLOGY & MEASUREMENT AVIATION IND CORP OF CHINA

Long-time sequence power load prediction method based on improved Informer model

ActiveCN119106350AEnrich input feature representationSolve the problem of insufficient sparsityLoad forecast in ac networkBiological modelsTemporal informationLoad forecasting
The invention provides a long-time sequence power load prediction method based on an improved Informer model, and particularly relates to the technical field of power load prediction, and the method comprises the steps: carrying out the feature coding and embedding of meteorological features, scalar information, position information, time information and trend information through a feature embedding layer and an SSI model, and carrying out the feature coding and embedding of the meteorological features, scalar information, position information, time information and trend information; the method comprises the following steps of: providing richer input feature representation for a model, carrying out secondary sparsity on probability sparse attention by adopting a method for carrying out sparsity evaluation on a key value matrix, reducing the time complexity of an attention mechanism from O (LlnL) to O ((lnL) 2), and finally outputting a final predicted value through a decoder and an encoder; according to the method, the problems that when an original Informer model is applied to power load prediction, feature richness is insufficient and a probability sparse attention module still has insufficient sparsity are solved, so that the effect of improving the precision and efficiency of long-time sequence power load prediction is achieved.
Owner:TRAINING CENT OF STATE GRID SHAANXI ELECTRIC POWER CO LTD +1

Cold-rolled material quality performance interval forecasting method based on multi-objective evolutionary learning

The invention provides a cold-rolled material quality performance interval forecasting method based on multi-objective evolutionary learning, and relates to the technical field of cold-rolled material quality performance forecasting. The method comprises the following steps: firstly, collecting chemical components, process parameters and corresponding quality performance data in the production process of the cold-rolled material to obtain an original sample data set, preprocessing the sample data and dividing the sample data into a training set and a test set; then, a multi-target differential evolution algorithm is adopted to obtain a hyper-parameter set required for constructing a quality performance forecasting model, and an optimal hyper-parameter combination is selected from Pareto frontier based on a preference knee solution to serve as a parameter combination for constructing a Gaussian regression model; and finally, constructing a final cold-rolled material quality performance interval forecasting model based on a Gaussian process regression model framework and the selected kernel function. According to the method, the obtained multi-objective evolutionary learning model has relatively high prediction accuracy and relatively low time complexity.
Owner:NORTHEASTERN UNIV CHINA

Wireless charging method and system based on disturbance detection-golden section

The invention provides a wireless charging method and system based on disturbance detection-golden section, and solves the defects of high time complexity, low solving speed and low maximum tracking speed of an existing maximum efficiency tracking control method. According to the invention, the improved disturbance detection-golden section method is adopted to realize rapid maximum efficiency tracking. Firstly, a current solution not only needs to be compared with a previous solution, but also needs to be compared with a next solution, and if the current solution is superior to the previous solution and the next solution at the same time, an interval where an optimal solution is located can be determined; secondly, maximum efficiency tracking is carried out through a golden section search algorithm; the time complexity of the golden section search algorithm is generally O (log n), and n is the dimension of a solution space. Therefore, the maximum efficiency tracking speed can be improved to a certain extent by adopting the disturbance detection-golden section method.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Underdetermined blind source separation method based on improved single source point detection

The invention discloses an underdetermined blind source separation method based on improved single source point detection, and the method comprises the steps: firstly, carrying out the initial single source point extraction of a mixed signal through employing the cosine angle criterion of a real part and an imaginary part of a time-frequency matrix column vector; then, abnormal points are removed according to whether the linear relation between the single source points and the abnormal points exists or not, the influence of the abnormal points on single source point detection is reduced, and therefore the estimation precision of a hybrid matrix is improved; then, clustering is carried out on the obtained single source points by using a K-means algorithm, so that an estimated hybrid matrix is obtained; and finally, recovering a source signal by using a least square method. The method provided by the invention not only considers the absolute direction of the real part and the imaginary part in the single source point, but also considers the linear relation between different single source points to remove the abnormal points, so that the estimation precision of the hybrid matrix can be improved, the noise immunity of the method is enhanced, and finally, a high-quality recovery signal is obtained.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Living body detection method and system based on language guide picture feature extraction

The invention discloses a living body detection method and system based on language guide picture feature extraction, and the method comprises the following steps: carrying out the preprocessing of a video data set for face fraud detection, and constructing a picture encoder and a text encoder; constructing a picture-picture projector and a text-picture projector, constructing a contrast learning module to shorten the distance of corresponding projection features, and generating a plurality of groups of text cue words by a text design module; the method comprises the following steps: constructing a text screening module, constructing a frozen text encoder module, freezing a pre-training weight of a text encoder, calculating a text cue word which is most matched with a human face through cosine similarity calculation and binary cross entropy, and judging whether the human face is true or false by a classifier according to whether the text cue word is described. And supervising and training three output results of the comparison learning module, the picture text feature alignment module and the classifier, and obtaining a face true and false prediction result based on the trained model. The method is higher in face authenticity judgment accuracy and better in generalization performance.
Owner:SOUTH CHINA UNIV OF TECH

Medicinal material replenishment method and device, electronic equipment and computer readable medium

The embodiment of the invention discloses a medicinal material replenishment method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: for each medicinal material in a target clinic, executing the following processing steps: acquiring a medicinal material ex-warehouse information sequence of the medicinal material in a preset time period; inputting the medicinal material ex-warehouse information sequence into a medicinal material replenishment information prediction model to obtain medicinal material replenishment predicted quantity information corresponding to a preset future time period; obtaining current stock value information of the medicinal materials and a preset warehousing replenishment total value; according to the inventory value information, generating current medicinal material unit value information of the medicinal material; determining actual medicinal material replenishment information corresponding to the medicinal materials according to the medicinal material unit value information, the medicinal material replenishment predicted quantity information and the warehousing replenishment total value; and according to the actual medicinal material replenishment information, the associated medicinal material transport vehicle is controlled to execute replenishment operation. According to the embodiment, the replenishment quantity of the medicinal materials can be accurately determined, repeated vehicle dispatching for medicinal material replenishment is not needed, and waste of transportation resources is avoided.
Owner:海南榕树家信息科技有限公司

Metasurface multi-beam rapid generation method based on semi-supervision

The invention discloses a metasurface multi-beam rapid generation method based on semi-supervision, and the operation process of the method comprises the following steps: 1, introducing an attention mechanism based on a convolutional neural network, and designing a cross entropy loss function; step 2, training the model by using a large number of samples obtained by caliber field superposition, migrating trained model parameters to a new model, and training based on the samples optimized by a traditional algorithm; step 3, semi-supervised learning is introduced, a model obtained through initial training is utilized to label unlabeled data samples, labeled sample data is added to label data samples, then the network model is retrained, the process is continuously repeated, and the number of the samples is iteratively increased; and 4, inputting required directional diagram data to obtain a corresponding coding matrix. Based on the method, a multi-beam coding problem is converted into a multi-label classification problem, the condition of repeated traversal in a codebook set in a traditional algorithm is avoided, and the time complexity is reduced.
Owner:BEIJING UNIV OF POSTS & TELECOMM