116results about How to "Reduce dimensionality" patented technology

The invention discloses a network security active defense method and system for detecting abnormal network behaviors. The method comprises the following steps: S1, constructing a virtualized isolation network environment through a software defined network technology; s2, deploying intelligent dynamic camouflage nodes in the virtualized isolation environment; s3, acquiring a disguised node attack behavior, and identifying a network abnormal behavior through a deep learning technology; s4, extracting network abnormal behavior features, and identifying potential threats through a deep learning technology; s5, a defense mechanism is automatically triggered, a honeynet is started, and abnormal behaviors and potential threats are isolated; and S6, tracing an attack path, and carrying out source positioning. The network security active defense system comprises a network construction module, a deployment module, an identification module, a honeynet, an isolation module and a tracing module. The disguised nodes are deployed through the deployment module to detect abnormal network behaviors, active defense of network security is realized through the honeynet, the isolation module and the tracing module, and the network security is improved.

The invention relates to the technical field of spectral analysis, and discloses a spectral analysis-based gas component detection method, device and equipment and a medium, the method comprises the following steps: carrying out axial scanning on a gas storage device to obtain hyperspectral image data; performing preprocessing and spectrum standardization on the hyperspectral image data to obtain preprocessed spectrum data; carrying out waveband selection on the preprocessed spectral data to obtain a characteristic waveband; performing abundance estimation on the characteristic wave band to obtain initial gas component content data; optimizing the initial gas component content data to obtain target gas component content data; and performing gas component anomaly detection on the target gas component content data to obtain a gas component anomaly detection report, thereby improving the accuracy of gas component anomaly detection.

The invention relates to an enterprise park meteorological fire risk assessment method based on an adaptive random forest model, and the method comprises the steps: building a risk assessment model and a visual early warning platform, enabling the risk assessment model to collect alarm data, meteorological data, enterprise data and park division data, and forming a risk assessment data set, and integrating internal characteristics and external data of the park into a data set, inputting new data into the self-adaptive random forest model by means of a real-time data flow technology, updating and evaluating a fire risk index value of the park in real time, and optimizing a model decision tree to automatically adjust a risk evaluation model and adapt to changes of environment and operation. Accurate early warning information is provided for a visual early warning platform, the risk level of the park is displayed in real time, and a risk alarm is given out in time.

The invention discloses a water quality prediction method based on double decomposition and a hybrid model and a related device, and relates to the technical field of water quality monitoring, and the method comprises the following steps: preprocessing obtained original water quality time sequence data; determining to-be-processed data based on a Pearson's correlation coefficient method and the preprocessed data; performing complete ensemble empirical mode decomposition on the to-be-processed data to obtain a plurality of intrinsic mode functions; k-means clustering is carried out on the plurality of intrinsic mode functions; the clustered intrinsic mode function comprises a high-frequency mode, an intermediate-frequency mode and a low-frequency mode; variational mode decomposition is carried out on a high-frequency mode in the clustered intrinsic mode function, and a plurality of high-frequency sub-modes are obtained; and respectively inputting the plurality of high-frequency sub-modes, the plurality of intermediate-frequency modes and the plurality of low-frequency modes into the Parallel Transform-LSTM model to obtain a final prediction result. The precision and stability of water quality parameter prediction can be improved.

The invention provides a power distribution network dynamic network reconstruction method based on constraint enhanced safety reinforcement learning, and the method comprises the steps: describing a DDNR task of a power distribution network as a constraint type Markov decision process (CMDP); then, soft constraints (node voltage and line current constraints) and hard constraints (radial topology constraints) in the DDNR process are processed by adopting an interior point strategy optimization (IPO) algorithm and a mode of adding a safety layer based on a branch switching method respectively; meanwhile, the invention provides a space-time perception neural network model to increase the dynamic space-time change characteristics of the reinforcement learning agent to the power flow of the power distribution network in the DDNR process. The method plays an important role in reducing the energy loss of the power distribution network, optimizing the voltage distribution and increasing the bearing capacity of new energy.

The invention relates to an intelligent industrial data clustering and grouping method, system and device and a medium, and the method comprises the steps: carrying out the standardization preprocessing of collected original industrial data, obtaining standard industrial data, and constructing a high-dimensional feature space according to the standard industrial data; performing industrial feature extraction and dimension reduction on the high-dimensional feature space to obtain a low-dimensional feature vector; performing preliminary grouping on the low-dimensional feature vectors according to a preset clustering algorithm to obtain a first clustering result; performing secondary adjustment on the first clustering result to obtain a second clustering result; and performing industrial scene simulation verification on the second clustering result to obtain a verification result, and performing optimization adjustment on the second clustering result according to the verification result to obtain a target clustering combination. According to the method, a more reasonable clustering result can be obtained, and the accuracy and applicability of the clustering effect are improved.

The invention discloses a black box confrontation attack method based on local region disturbance, which can be applied to digital image attack and physical attack, and comprises the following steps: (1) positioning a salient region in an image by adopting a CAM type activation graph, and determining a local region highly sensitive to disturbance in an original image; (2) further grouping the salient regions to obtain sub-regions; (3) designing an objective function of local confrontation disturbance; (4) adding disturbance to the sub-regions; (5) calculating the size of a loss function of the sub-regions after the disturbance is added, and sorting the sub-regions; and (6) selecting an optimal sub-region, and carrying out disturbance of random search according to a target function. And (7) when an iteration stopping condition is satisfied, outputting the generated confrontation sample.

The invention discloses a data migration method and device, a storage medium and a computer program product. The method comprises the following steps: acquiring an initial data set of a plurality of service modules in a service system to be migrated, the plurality of service modules being function modules obtained by splitting according to a plurality of functions provided by the service system; determining the similarity among the service modules according to the initial data set of each service module, and clustering the plurality of service modules according to the similarity to obtain a plurality of clusters; and for each clustering cluster, performing dimension reduction processing on the initial data set of each service module in the clustering cluster to obtain a target data set of each service module, and migrating the target data set of each service module in the clustering cluster. According to the method and the device, the technical problem of data missing and inconsistency of dimension-reduced data due to the fact that the dependency relationship between the business modules to which the data belong is not considered when dimension-reduced migration is carried out on a large-scale data set in the prior art is solved.

The invention provides an electrical equipment fault diagnosis method and device based on artificial intelligence, and relates to the technical field of fault recognition, and the method comprises the steps: obtaining historical operation data collected by a sensor installed in a power system, and enabling the historical operation data to serve as an original data set; expanding the original data set; inputting the expanded original data set into a feature extraction model to train the feature extraction model; training a feature dimension reduction model, and training a classifier model; and inputting real-time operation data collected by a sensor installed in the power system into the trained feature extraction model, the feature dimension reduction model and the classifier model in sequence, and outputting corresponding fault categories. The diversity of a data set is enhanced through a data expansion technology, the generalization ability of a model is improved, feature extraction, feature dimension reduction and classification processing are carried out, deep analysis and processing of data are achieved, and therefore the operation state and the possible fault type of the electrical equipment can be judged more accurately.

The invention discloses a reverberation suppression method based on a self-adaptive meshless dictionary, and the method comprises the steps: precisely selecting space-time atoms of a reverberation subspace in a continuous space-time plane through employing a particle swarm optimization algorithm, and constructing a self-adaptive space-time dictionary; sparse decomposition is carried out on sonar array observation data on a designed dictionary in combination with a sparse Bayesian learning algorithm, so that high-precision reverberation covariance matrix estimation is obtained, grid mismatch errors are eliminated, and the reverberation suppression effect and the target detection performance are improved.

The invention discloses an oil reservoir history fitting method based on graph lasso and set smooth multi-data assimilation, and relates to the technical field of oil and gas field development. The method comprises the following steps: firstly, acquiring to-be-optimized model parameters and observation data of a target oil reservoir, constructing an observation error covariance matrix and initializing a model parameter set, performing numerical simulation by utilizing an oil reservoir numerical simulator to obtain prediction data, constructing a joint state matrix, performing dimensionless standardization processing on the joint state matrix to obtain an empirical correlation coefficient matrix, and then, performing optimization on the joint state matrix. And executing a graph lasso algorithm combined with an extended Bayesian information criterion to obtain an optimal dimensionless sparse precision matrix, extracting correlation coefficient sub-blocks required by Kalman updating from the optimal dimensionless sparse precision matrix based on a Scherr's theorem, obtaining a robust data auto-covariance matrix through a reverse reduction physical quantity outline, calculating Kalman gain in combination with an observation error covariance matrix, and calculating a Kalman filter. And the model parameter set is updated until the preset condition is met, the reservoir history fitting model parameter set is output, and the stability and precision of reservoir automatic history fitting are improved.

The invention relates to an industrial production monitoring method and system based on a large model, a terminal and a storage medium, and relates to the technical field of industrial safety production monitoring, and the method comprises the steps: obtaining production multi-modal data of a preset production region; controlling a preset industrial safety monitoring model according to the production multi-modal data to generate an industrial safety production state through reasoning; judging whether the industrial safety production state meets the requirements of a preset normal production state or not; if yes, continuously obtaining the production multi-modal data of the production area for cyclic judgment; if not, analyzing the industrial safety production state to determine a production assessment risk; determining real-time alarm data according to the production assessment risk, the industrial safety production state and a preset risk alarm relationship; and performing alarm prompt according to the real-time alarm data. The method has the effect of improving the accuracy of industrial safety production monitoring.

The invention relates to the technical field of battery management, in particular to a similar lithium ion battery health state estimation method, system and device and a storage medium. Comprising the following steps: acquiring voltage, current, capacity and corresponding sampling time data of the lithium ion battery in a charge-discharge cycle constant-current charging stage; obtaining a capacity increment curve and a constant-current charging curve based on the voltage, the current, the capacity and the corresponding sampling time data; performing dimension reduction processing on the capacity increment curve and the constant current charging curve based on a segmented aggregation approximation algorithm to obtain a low-dimensional capacity increment curve and a low-dimensional constant current charging curve; fusing the low-dimensional capacity increment curve and the low-dimensional constant-current charging curve to obtain fusion features; according to the method, the low-dimensional capacity increment curve and the low-dimensional constant-current charging curve are fused to serve as the characteristics for evaluating the health of the battery, the data dimension is reduced, information reflecting the health state of the battery is reserved, and therefore the efficiency and accuracy of characteristic extraction are improved.

The invention provides a digital quantum simulation method, which comprises the following steps of: performing symmetry analysis and subspace decomposition on a target Hamiltonian to obtain an effective Hamiltonian and a symmetry constraint condition; constructing a target unitary operator according to the effective Hamiltonian, and initializing a quantum circuit population of the target unitary operator; calculating entanglement characteristics of each quantum line in the quantum line population, performing structure variation on the quantum line population based on the entanglement characteristics, and performing line fragment crossing in combination with a symmetry constraint condition to obtain a candidate line set; performing line parameter optimization on the candidate line set based on the fidelity gradient to obtain an optimized line set, and extracting gate distribution structure features of the optimized line set; and non-uniform sampling is carried out on the optimized line set based on gate distribution structure characteristics to obtain a sampling line subset, an optimal quantum line is screened out from the sampling line subset based on the deviation between an experimental observation value and a theoretical expected value, and quantum simulation is carried out based on the optimal quantum line.

The invention discloses a power distribution network bearing capacity evaluation method and system for large-scale automobile charging loads, and the method comprises the steps: firstly, achieving the efficient expansion of data through combining a variational auto-encoder and a polynomial fitting method, effectively increasing the number of training samples, reducing the risk of over-fitting, and improving the reliability of the power distribution network bearing capacity evaluation. Then, the stability in a complex training environment is improved by adopting a self-adaptive biological influence optimization method, the accuracy of feature extraction and the training efficiency are improved, then, data are carefully captured and reconstructed by adopting a self-encoding neural network with self-adaptive refined features, the information flow is optimized, the dimensionality is reduced, important information is reserved, and the accuracy of feature extraction is improved. Then, an adaptive error compensation mechanism of a kernel extreme learning machine is adopted to adjust an error learning rate and weight update in real time, and the accuracy and robustness of the model are improved; through the above optimization training, the model can fully master the characteristics of the charging load data, and achieves the precise evaluation of the bearing capacity of the power distribution network through the output final category. Therefore, the method is high in accuracy.

The invention discloses a fractured-vuggy reservoir rock facies fine division method. The method comprises the steps that single well data of a to-be-measured area is acquired and preprocessed; carrying out depth homing on the required core physical property data; performing principal component analysis on the single well data to obtain dimension reduction and noise reduction fusion representation data; the data set is divided into a clustering data set and an inspection data set; carrying out optimal classification cluster selection on the clustering data set by adopting an elbow rule; classifying the data by adopting a fuzzy C-means improved clustering algorithm, and establishing an identification model of the fractured-vuggy reservoir rock facies; evaluating the identification model of the fractured-vuggy reservoir rock facies by adopting the contour coefficient; the identification model of the fractured-vuggy reservoir rock facies is inspected in combination with the inspection data set; outputting a test clustering result by using the test identification model of the fractured-vuggy reservoir rock facies, and performing sensitivity analysis by using a rank correlation matrix; and intersection is carried out by adopting the sensitive curves to obtain an identification chart of the fracture-vuggy reservoir rock facies.

This specification pertains to the field of refining and chemical production processing technology, and particularly relates to a method and apparatus for optimizing refining and chemical production plans for a target secondary processing unit. The method includes: obtaining parameters of the secondary processing unit under a refining and chemical production optimization scenario; constructing a nonlinear constraint equation for product output based on the parameters of the secondary processing unit; performing an equivalent transformation on the nonlinear constraint equation to obtain an equivalent transformation equation; extracting the nonlinear constraint terms and performing a Taylor expansion; transforming the Taylor expansion formula into a linear approximation equation based on the proportion of the feed material to the output material of the blending tank, the feed material quantity to the blending tank, and the feed property values ​​of the blending tank, according to the property balance constraints of the blending tank; and then substituting these into the nonlinear constraint equation for product output, thereby transforming the nonlinear constraint equation for product output into a linear approximation equation containing only material information variables. This method effectively ensures model convergence and shortens the solution time.

The application relates to the field of flight control technology, in particular to a hovering control method and device for a short take-off and vertical landing aircraft of a tilt-rotor type, wherein the method comprises the following steps: constructing a hovering nonlinear dynamics model of the short take-off and vertical landing aircraft containing a tilt-rotor power system; converting the hovering nonlinear dynamics model of the short take-off and vertical landing aircraft into a high-order full-drive system model to design a state tracking controller; designing an adaptive law based on a neural network to estimate nonlinear terms in the hovering nonlinear dynamics model of the short take-off and vertical landing aircraft; and feeding back the nonlinear terms to the state tracking controller to perform hovering mode stable control. Thus, the problems that the hovering control method based on dynamic inversion needs a large amount of linearization processing, the actuator dynamic characteristics are significantly different, the controller needs to verify the closed-loop performance through repeated simulation and experiment, and the multi-actuator decoupling efficiency of the aircraft is low and the robust control performance is poor are solved.

The invention relates to a demand control method, system and equipment based on an energy storage system, and a medium. The method comprises the following steps: collecting power load characteristics and related influence factor data thereof; analyzing the collected power load characteristics and related influence factor data by using a principal component-weighted grey relational analysis method to extract key input variables for load prediction; inputting the key input variable into a long and short term memory load prediction model based on an Attention mechanism, and training the long and short term memory load prediction model to output load prediction data in a period of time in the future; according to the predicted load prediction data, constructing a pre-month energy storage optimization model to determine a predicted maximum demand value; and according to the maximum demand value, carrying out rolling optimization on an intra-day scheduling scheme so as to carry out optimal charging and discharging operation of energy storage. According to the method, through optimal scheduling of the energy storage system, the accuracy of power load prediction and the efficiency of power cost control are improved.

The application belongs to the technical field of simulation analysis, and particularly relates to a switch cabinet condensation margin evaluation method based on simulation analysis and order reduction reconstruction, steps of which comprise: establishing a simulation analysis model of the switch cabinet, adding a physical field and performing physical field coupling and mesh partitioning; solving the simulation analysis model to obtain the temperature and humidity distribution inside the switch cabinet; optimizing the simulation analysis model; replacing electromagnetic heat with loss data as a heat source input into a non-isothermal flow field; constructing a physical field snapshot library for order reduction model training; processing the physical field snapshot library based on a POD method to construct an order reduction model; training a Kriging model to reconstruct the temperature and humidity field of the switch cabinet; constructing a condensation margin evaluation cloud map; in the actual operation process of the switch cabinet, calculating an actual dynamic dew point temperature to generate an actual operation condensation margin cloud map, and completing online real-time evaluation. The application can realize efficient and accurate reconstruction of the temperature and humidity field inside the switch cabinet and efficient evaluation of the condensation margin of the switch cabinet.

The invention is applicable to the technical field of unmanned aerial vehicle scheduling, and particularly relates to a regional route collaborative scheduling method and system for logistics unmanned aerial vehicles. Judging whether flight interference exists based on a preset minimum interference distance, acquiring flight information of the unmanned aerial vehicle participating in the flight interference, and sending the flight information to the corresponding unmanned aerial vehicle; yaw information calculation is carried out through the unmanned aerial vehicles according to the flight information and a built-in force field simulation obstacle avoidance model, and the unmanned aerial vehicles are controlled to fly based on the yaw information; and when the distance between the unmanned aerial vehicles is greater than the minimum interference distance, outputting return flight information based on the force field simulation obstacle avoidance model, and controlling the unmanned aerial vehicles to return to the flight route. According to the regional route co-scheduling method for the logistics unmanned aerial vehicles, each unmanned aerial vehicle is regarded as an agent which autonomously moves in a three-dimensional force field, complex global path planning and real-time obstacle avoidance are decoupled, and the dimensionality and complexity of distributed calculation are greatly reduced.

The present invention discloses a two-stage key area semantic map construction method based on Hough transform. Aiming at the problem that existing UAV environment modeling involves a large amount of calculation and cannot always guarantee the real-time processing of actual ranging images on currently available airborne computing devices, a two-stage linear plane extraction method is proposed. In the first stage, the three-dimensional space of the original point cloud is decomposed into a two-dimensional plane subspace, and the search problem of the plane object in the three-dimensional space is converted into the search problem of the straight line segment in the two-dimensional subspace (scanning plane), thereby significantly reducing the amount of calculation by reducing the dimensions of the search object and the search space; the second stage also does not involve a large amount of calculation, because the search for the plane object is not based on the original point cloud, but on the straight line segments extracted in the first stage, and the number of these straight line segments is much less than the number of points in the original image, which further reduces the amount of calculation, thereby improving the autonomous task execution efficiency of the UAV in the industrial city environment.

The present invention discloses a hyperspectral image compression and reconstruction method, device and equipment based on an autoencoder, which comprises: obtaining a Houston image data set and performing preprocessing including random cropping to generate an image block of a preset size as an original hyperspectral image; inputting the original hyperspectral image into an autoencoder model including an encoder and a decoder and training based on a preset loss function to obtain a trained hyperspectral compression model, wherein the network structure of the encoder includes a thumbnail generation branch and a potential encoding branch, and the network structure of the decoder includes a thumbnail decoding branch and a potential representation decoding branch; inputting a hyperspectral image to be compressed into the hyperspectral compression model, encoding the hyperspectral image to be compressed by the encoder to obtain compressed data, and decoding the compressed data by the decoder to obtain a reconstructed hyperspectral image.

The present invention relates to the technical field of depression recognition, and in particular to a method and system for speech recognition of depression based on deep learning. The present invention clusters speech data of a training individual to obtain speech clusters, adjusts the elements in the characteristic sequence of speech attributes of the speech data based on the number of speech data in the speech cluster, and obtains the characteristic speech value of each speech attribute; constructs a characteristic word segmentation set of the training individual according to the number of occurrences of the same word segmentation in the speech cluster to which it belongs in the word cluster set of the training individual, and the number of speech clusters in which each word segmentation exists; trains a neural network in combination with the characteristic speech value and the characteristic word segmentation set of the speech attribute of the training individual, and uses the trained neural network to detect depression in the individual to be tested. The present invention trains a neural network by combining the speech features and semantic features of the language of the training individual to improve the accuracy of depression detection.

The present invention discloses a low-complexity multi-user communication signal recovery and perception positioning estimation method, which generates and transmits an integrated waveform of superimposed pilot and data at the transmitting end, so that the communication signal and the perception signal are linearly superimposed in the symbol domain using a power allocation method in the same time-frequency resource block, and the receiving end uses a designed low-complexity algorithm to process the received signal to realize the function of simultaneous communication and positioning of multiple users; including: using SCMA technology to design an encoder for superimposed symbols at the transmitting end and a decoder for detection and demodulation at the receiving end, and using the UAMP-SBL algorithm at the receiving end to process the received signal to separate the positioning coordinates of the communication signals of multiple users. The present invention is based on the original RIS-assisted communication system, and can use a low-complexity algorithm to simultaneously obtain the communication data of multiple users and accurate user positioning coordinates without adding additional hardware equipment.

The application is suitable for the field of artificial intelligence technology, and provides a word vector representation method and device based on language processing and a terminal device, the method comprising: constructing an input word table; setting word frequency information of each word in the input word table; classifying the words into N clusters according to the word frequency information, words with the same word frequency information being classified into the same set to obtain a clustering set with N subsets; defining a first word vector dimension of the words in the first cluster through an experience factor, and obtaining a second word vector dimension of the words in each subset according to the subset where the words are located and the first word vector dimension; defining an nth linear mapping matrix for the nth cluster; and processing a target word vector through parameters shared by the input word table as an input of a natural language processing model. Through the application, the problem that the calculation amount is large, the efficiency is low and the word distribution features cannot be considered when converting words into word vectors in natural language processing can be solved.

This invention provides a method for identifying the authenticity of wheat flour based on the fusion of Raman and near-infrared spectroscopy, belonging to the field of wheat flour authenticity identification technology. The method includes: acquiring Raman and near-infrared spectral data of the wheat flour sample to be tested, and preprocessing them separately; constructing and training a fusion detection model, which includes a data-level fusion module, a feature-level fusion module, and a decision-level fusion module; the data-level fusion module generates full-spectrum fusion data; the feature-level fusion module concatenates core features into a comprehensive feature set; the decision-level fusion module inputs the comprehensive feature set into a hybrid model; and the trained fusion detection model processes the comprehensive feature set to output the authenticity identification result of the wheat flour sample to be tested. This invention, through a three-level spectral fusion architecture and a dynamic adaptive adversarial mechanism, can effectively achieve high-precision and high-robust identification of wheat flour authenticity.

The application discloses a fast robust monocular vision inertial positioning method and system, comprising the following steps: configuring IMU and monocular camera sensor parameters; IMU data preprocessing; IMU attitude initialization; extracting image features of a monocular camera, removing abnormal matching points and performing IMU pre-integration; monocular vision initialization; odometer attitude optimization, comprising the following steps: judging whether a feature point is mis-matched based on an IMU pre-integration result, constructing a feature point re-projection error Jacobian matrix, and optimizing inverse depth of the feature point and image frame attitude through block and diagonalization processing of the re-projection error Jacobian matrix; after completing current frame attitude updating, selecting a key frame based on a key frame identification rule; and judging according to a current frame, removing a certain frame in a sliding window to reserve a sliding window space for adding a latest frame. The application optimizes inverse depth of a feature point and image frame attitude through block and diagonalization processing of a re-projection error Jacobian matrix, and reduces computational complexity.

The application provides a lightweight identity recognition method combining voiceprint and earprint features. The method comprises the following steps: obtaining voice and ear canal echo signals of a known registered person and a person to be verified; extracting and fusing 13-dimensional mel-frequency cepstral coefficients (MFCC) of the voice and ear canal echo signals, i.e., obtaining voiceprint and earprint fusion features; inputting the fusion features into a lightweight identity recognition model to extract 128-dimensional embedding features of the known registered person and the person to be verified; calculating the similarity of the embedding features of the two types of persons by using a probabilistic linear discriminant analysis (PLDA) method; and determining whether the person to be verified is the known registered person according to the similarity. In the application, the fusion of earprint and voiceprint features improves the recognition performance of the classification model. The lightweight identity recognition model is obtained through a pre-training process, which reduces the equal error rate (EER) and greatly reduces the parameter quantity of the identity recognition model.

The present invention relates to a method, system, computer device and storage medium for assessing the risk of breast cancer, which obtains original data based on breast cancer including gene sequencing data and medical imaging data. Then, feature extraction is performed on the original data, mutation site features and gene expression level features are obtained from the gene sequencing data, and shape and texture features of the tumor area are extracted from the medical imaging data. A breast cancer risk assessment model based on a Transformer neural network model is constructed using the extracted features. Finally, the initial model is trained to obtain a trained assessment model. The method achieves efficient and accurate assessment of the risk of breast cancer by fusing gene sequencing data and medical imaging data and combining the feature extraction and learning capabilities of the Transformer neural network.