1022 results about "Gradient descent" patented technology

The invention discloses a multi-source-domain multi-teacher knowledge distillation method and system based on reinforcement learning, and the method comprises the steps: obtaining target domain sample data, inputting the data into N pre-trained teacher models, and generating the output features of all teacher models; inputting the target domain sample and all teacher model outputs into a reinforcement learning strategy network, generating a dynamic weight of each teacher model, and calculating a knowledge distillation loss function based on the dynamic weights; constructing a total loss function according to the knowledge distillation loss function and the cross entropy loss output by the student model; student model parameters are updated through gradient descent; and calculating a reward value according to student model performance change, and updating reinforcement learning strategy network parameters. According to the method, the reward function based on student model performance improvement is constructed, the strategy network is continuously updated in a strategy gradient optimization mode, the distillation efficiency is effectively improved, knowledge conflicts among teachers are relieved, and the robustness and generalization performance of the student model in a multi-source complex environment are remarkably improved.

The invention relates to the technical field of electronic detection, and discloses an electronic component dispensing detection method. The method comprises the following steps: acquiring dispensing image data of the surface of the electronic component, and generating a standardized dispensing data matrix containing glue position, thickness and uniformity characteristics through standardized preprocessing; constructing a dispensing correction matrix based on an adaptive window frame, and performing spatial reference dynamic correction on the standardized data matrix to obtain a spatial correction dispensing data matrix; inputting the data into a multi-layer sensor fusion network for feature fusion, and outputting a multi-source fusion dispensing data set; constructing a multi-dimensional abnormal feature incidence matrix based on the data set, and identifying abnormal dispensing data nodes by using a dynamic threshold detection algorithm; performing parameter optimization iteration on the multi-source fusion data set by using a gradient descent optimization algorithm to generate an optimized dispensing parameter set; and finally, constructing a three-dimensional visual dispensing quality model, and establishing a dynamic mapping relationship between model parameters and glue physical characteristics. The method can more comprehensively detect the glue quality.

The invention discloses a dynamic self-adaptive recommendation strategy optimization method for a business handling failure scene, and relates to the technical field of business handling recommendation and intelligent decision making, and the method comprises the steps: firstly collecting various types of data of a whole business handling process, and guaranteeing the integrity and real-time performance at a frequency of 100 milliseconds per time; a decision tree and Bayesian network fusion algorithm is used for attribution, and direct and indirect reasons are clarified; integrating data to construct a user portrait, and mining potential and subsequent demands; generating a recommendation scheme set based on attribution and portraits, and adjusting priorities and forms in combination with scene features; feedback data is introduced, a strategy weight is optimized by using a gradient descent algorithm, and the scheme is updated regularly; a multi-dimensional index weighted evaluation effect is set, and emergency optimization is carried out if the evaluation result does not reach the standard; and establishing a distributed strategy library, and reusing the optimal strategy of the similar scene by using a K-nearest neighbor algorithm. According to the method, failure reason accurate positioning and personalized recommendation are realized, the recommendation effect is continuously optimized along with data accumulation, and the method is adaptive to multiple service types and user groups.

The invention provides a slope displacement monitoring data processing system based on an unmanned aerial vehicle laser radar, and relates to the technical field of data processing, and the system comprises the steps: carrying out the spatial interpolation processing of a topographic feature data set, and constructing a digital topographic surface model; the displacement field calculation module is used for performing iterative optimization based on a digital terrain surface model through spatial similarity analysis and fusion with a gradient descent algorithm, calculating a slope surface displacement vector field, identifying a potential sliding surface and a deformation abnormal region, and generating a displacement field calculation result; and the evaluation module is used for inputting a displacement field calculation result into a risk evaluation model and carrying out slope stability quantitative evaluation through a multi-source data fusion analysis platform. According to the invention, the practicability and operability of the monitoring result are improved.

A hybrid neural network architecture is disclosed that integrates matrix multiplication-free (MatMul-free) transformation layers with spiking neural network (SNN) layers for efficient, low-power computation. The system includes an interface module configured to convert intermediate continuous-valued data from MatMul-free layers into a spike-compatible format using encoding techniques such as rate coding, phase coding, or threshold-based conversion. The SNN layers process the spike-encoded data in an event-driven manner, enabling sparse, temporal inference. Training is supported by a hybrid optimization strategy combining backpropagation in MatMul-free components with surrogate gradient descent or spike-timing-dependent plasticity (STDP) in SNN layers. The architecture reduces computational complexity, supports real-time adaptability, and enables deployment in energy-constrained environments such as edge devices and neuromorphic platforms. The system may be implemented in hardware, software, or a co-designed pipeline optimized for dynamic sensor data, control signals, or continuous inference tasks.

The invention discloses a multi-agent combat task cooperation method for a structure entropy guided graph neural network, and the method comprises the steps: S10, each combat agent interacts with an environment according to an action generated by a strategy network, the environment comprises environment information, task parameters and a preset task target, and the strategy of each combat agent is completely executed in a decentralized manner; collecting complete empirical trajectory data; s20, using the collected data for centralized training; performing value evaluation on the global state of each time step by using a value network; s30, calculating strategy loss and value loss by using a multi-agent near-end strategy optimization algorithm in combination with the output of the strategy network and the value estimation of the output of the value network; updating parameters of the strategy network and the value network by using a gradient descent method; and S40, performing loop iteration. The problems that in a traditional method, the battlefield game dynamic structure sensing ability is insufficient, the hierarchical strategy learning and generalization ability is limited, the adaptability of a model in a small sample area is poor, and the migration efficiency is low are solved.

The invention provides a zero-sum game-based distributed elastic consensus optimal control method under denial of service attack of a multi-agent system, and the method specifically comprises the steps: firstly, constructing a multi-agent formation model in which a leader and a plurality of followers cooperatively move through graph theory knowledge and a multi-agent second-order state equation; secondly, in order to reduce the influence of denial of service attack on communication topology, a time-varying weight distributed elastic observer is provided to estimate the state of a leader, and the attacked condition of the leader is considered; then, by constructing an augmentation system, a distributed consistency tracking problem with a leader is converted into a local tracking problem between each follower and a virtual leader thereof; and finally, in order to solve the zero-sum game problem, introducing a Hamiltonian-Jacobian-Ansaxophone equation to realize optimal control input under maximum external disturbance, and realizing algorithm design by using single-evaluation reinforcement learning with experience playback and combining a gradient descent method.

The present invention relates to the technical field of natural ventilation in buildings, and in particular to a computationally assisted decision-making method and system for climate-adaptive building cavity design. The method comprises: using a Delaunay triangulation method to generate an initial mesh, using a Laplace operator-based mesh refinement method to adaptively refine the initial mesh, so as to obtain an adaptive mesh system, wherein the adaptive mesh system is used for dynamically adjusting the mesh density of conditional PINNs; constructing a multi-task learning framework within the conditional PINNs, wherein the multi-task learning framework is used for jointly predicting a plurality of physical field variables within the conditional PINNs; and iteratively training the conditional PINNs, and using a gradient descent algorithm to minimize a loss function until a predetermined number of training iterations or loss convergence is reached, thereby generating a key physical field variable prediction model in building cavity design. The present invention can implement efficient and accurate prediction of key physical quantities in building cavity design, and can be adapted to different building layouts and functional space characteristics.

The invention discloses an automobile part assembly precision intelligent compensation method and a self-adaptive regulation and control system, and relates to the field of intelligent compensation, and the method comprises the steps: synchronously collecting part geometric parameters, tool poses and environment data, and constructing an associated data matrix; analyzing data by using an improved random forest-attention model, and outputting a deviation factor contribution degree sequence; a compensation calculation model is designed accordingly, initial compensation amounts are generated in a segmented mode in combination with a precision margin threshold value, and correction is conducted through historical data similarity matching; selecting an execution path according to the compensation amount and the core deviation type; an actual precision value is obtained through laser detection after assembly, and a compensation error is calculated; based on an error triggering model optimization mechanism, model parameters are iteratively updated by using a gradient descent algorithm, and the deviation identification and compensation precision is improved. The method has the advantages that the model attribution deviation is improved, the precise compensation amount is calculated in combination with historical data, flexible execution, real-time monitoring and model self-optimization are matched, and the assembly precision and the production efficiency are efficiently improved.

The invention relates to the technical field of big data analysis, and discloses a prospecting target area positioning method and system based on big data, and the method comprises the steps: collecting multi-source exploration data in real time through distributed nodes, completing coordinate normalization, semantic alignment and time synchronization through a spatial heterogeneous data flow engine, and generating a standardized incremental data block; performing local feature sensitivity analysis based on the historical model library, identifying a newly added feature dimension, and performing parameter increment updating by adopting a sliding window gradient descent method; inputting the updated model into a target evolution model driven by a Bayesian space-time probability field, and dynamically calculating the metallogenic probability of each space grid in combination with a stress field, an element migration path and historical verification data; and generating high, medium and low three-level target area maps according to probability sorting, and pushing the high, medium and low three-level target area maps to a three-dimensional visual decision terminal. According to the method, minute-level dynamic response of the target region under triggering of newly-added data is realized, computing resource consumption is reduced to be less than 5% of that of an original system, and prospecting efficiency and abnormal region identification timeliness are improved.

The invention relates to the technical field of information, and discloses a radar dynamic anti-interference method and system based on interference source positioning. The method comprises the following steps: acquiring current signal data and a historical signal sequence, and determining an initial deviation value; extracting a historical deviation sequence according to the initial deviation value to obtain a deviation change trend vector; calculating a trend slope and a fluctuation amplitude, and determining an adjustment trigger signal; extracting feature interaction influence according to the adjustment trigger signal, and determining a weight coefficient update increment; iterative optimization is carried out in combination with the convergence rate parameter, and an optimized convergence rate value is obtained; adjusting deviation compensation model parameters according to the convergence speed value, and outputting a deviation compensation result when the compensation residual error is lower than a preset threshold value; and carrying out positioning calculation according to a deviation compensation result, and determining a corrected positioning coordinate. The model is dynamically optimized through technologies such as a sliding window and gradient descent, the problem of positioning deviation caused by complex environment signal interference is solved, and the positioning precision and the response speed are improved.

The invention relates to the field of twitter recognition, in particular to a twitter classification method based on harmonic enhancement and time-frequency semantic joint modeling, which comprises the following steps: collecting twitter samples and carrying out noise reduction and standardized preprocessing, carrying out multi-scale convolution operation on Mel spectrograms by utilizing a layered acoustic encoder, extracting time-frequency features in combination with a channel attention mechanism, and classifying twitter classification results. The method comprises the following steps of: generating adaptive position codes through a dynamic time-frequency joint coding module, carrying out time-frequency mode modeling by combining a global-local interaction mechanism, introducing a semantic fusion module which comprises a frequency band pyramid unit, a harmonic enhancement unit and a time-frequency gating unit, realizing dynamic weighted fusion of multi-layer features, and carrying out time-frequency mode modeling through a global-local interaction mechanism. And inputting the fusion features into a classification layer, training a network by adopting a cross entropy loss function and a gradient descent algorithm, and outputting bird categories through a full connection layer, thereby solving the key problems of insufficient description of a non-stationary time-frequency mode, insufficient modeling of a harmonic structure, reduction of recognition performance in a complex noise environment and the like in the prior art.

The invention discloses a multi-dimensional training method and device for a support vector machine, electronic equipment and a computer readable storage medium, and the method comprises the steps: carrying out the discretization of a training sample data set, and obtaining a discretized data set, the discretized data set comprises a plurality of different attributes, and each attribute corresponds to a plurality of feature vectors; calculating a classification contribution parameter of each attribute feature vector to obtain a plurality of classification contribution parameters; performing data mapping on the plurality of classification contribution degrees by using a kernel function to obtain a target function; and optimizing and training the objective function by using a gradient descent algorithm to obtain a support vector machine model. According to the method, different dimension data are mapped through the kernel function, the data gain weight can be determined, the linear separable effect of the mapped dimension data can be improved, and then the classification and analysis capability of the SVM can be improved.

The invention relates to the field of underwater acoustic communication and detection, in particular to a waveform optimization method and system for an underwater acoustic detection and communication integrated system. According to the method, a constant modulus phase is taken as a constraint, a reserved subcarrier phase is taken as an optimization variable, and a multi-objective function for joint optimization of a peak-to-average power ratio and a non-periodic autocorrelation integral sidelobe ratio is constructed; a population is initialized, an objective function is evaluated, and a parent population is obtained through non-dominated sorting and crowding distance calculation; generating filial generations through selection, crossover and variation, combining the filial generations with the parent generations, and updating sorting and crowding distance to maintain population diversity; introducing a local gradient descent refinement mechanism, carrying out gradient iteration adjustment on an optimized individual under a constant modulus phase condition, and adaptively adjusting a crossover probability, a mutation probability and a phase variation scale according to a diversity evaluation result; and outputting a Pareto optimal solution set after the maximum number of iterations is reached, and obtaining an optimized sounding and communication integrated orthogonal frequency division multiplexing signal, so that the underwater communication and detection comprehensive performance can be effectively improved.

The invention discloses a multi-modal rumor detection method fusing texts, images and social propagation structures, and belongs to the technical field of natural language processing, computer vision and causal reasoning. Specifically, the invention provides a unified causal inference framework, and hybrid deviation in multi-modal data is effectively stripped by integrating text anti-fact causal inference and an image dot product causal intervention mechanism. Under the framework, social propagation structure features are further fused, and a multi-head collaborative attention mechanism is adopted, so that deep alignment and semantic enhancement in cross-modal features are realized. Adversarial samples are generated through projection gradient descent for adversarial training, and model parameters are optimized in combination with anti-fact loss, so that the classification accuracy and generalization ability of the model are improved. According to the rumor detection method, a causal reasoning normal form is introduced into a rumor detection task, the effectiveness of an anti-fact and intervention mechanism in a complex information scene is verified, and a new theoretical support and method path are provided for constructing a credible multi-modal information system.

The invention provides a training and pushing integrated scene-based neural network parameter adaptation method, a medium and equipment, and belongs to the technical field of neural network parameter adaptation. Comprising the following steps: selecting initial parameter configuration, carrying out initial evaluation on a neural network model, and recording the performance of the neural network model; according to an initial evaluation result, positioning the parameters in an optimal parameter region by adopting Bayesian optimization; in the optimal parameter region, local optimization of parameters is carried out by using a gradient descent method; and for the neural network model after parameter optimization, the neural network model is compressed to a smaller version through pruning and quantization. According to the method, the parameter adaptation capability of the super-large-scale model can be effectively improved, the calculation overhead in the adaptation process is reduced, and meanwhile it is guaranteed that the model performance is not affected.

The invention relates to the technical field of antenna control, and discloses a control method for a leaky-wave antenna and a communication device. The method comprises the following steps: measuring the dispersion characteristic of the leaky-wave antenna, establishing a second-order nonlinear mapping relation between a propagation constant and a control voltage, and obtaining a dispersion control parameter group; reversely deducing the target beam directional angle to obtain a target propagation constant, and calculating an initial voltage value of each control unit in combination with the parameter group to form a voltage gradient control sequence; correcting the propagation constant of each unit by adopting a distance compensation algorithm, and recalculating to obtain distance self-adaptive voltage distribution data; and detecting a beam quality factor in real time, updating voltage distribution data through a gradient descent algorithm when the beam quality factor deviates from a target value, and outputting a control voltage sequence to drive each control unit. The leaky-wave antenna control method and device solve the problems that in an existing leaky-wave antenna control technology, the beam quality is reduced and the data rate is sharply attenuated during long-distance transmission, and the beam control precision and the long-distance transmission performance of the leaky-wave antenna in the terahertz frequency band are improved.

The invention discloses an intelligent storage multi-AGV scheduling method and device and a medium, and relates to the technical field of automatic scheduling, and the method comprises the steps: collecting the state and environment perception data of AGVs, and carrying out the standardization processing; constructing a dynamic conflict scheduling model, inputting the standardized AGV state and environment perception data into the dynamic conflict scheduling model for task allocation and path planning, and outputting a preliminary task allocation and path planning scheme; and integrating task execution feedback data with historical task data, optimizing parameters of the dynamic conflict scheduling model, and outputting an optimized task allocation and path planning scheme. According to the method, the task execution feedback data and the historical task data are integrated, and parameter optimization is performed on the dynamic conflict scheduling model based on the scheduling knowledge graph and the meta-gradient descent strategy, so that continuous self-evolution and precision improvement of the scheduling strategy are realized.

The invention discloses a numerical control machine tool dynamic error cooperative compensation control method adaptive to high-speed machining, and relates to the technical field of numerical control machine tool error control. According to the method, a multi-source dynamic error sensing system comprising a grating displacement sensor, a six-dimensional force sensor and the like is constructed to acquire data; after wavelet threshold denoising and Kalman filtering preprocessing, inputting a three-layer LSTM error coupling prediction model combined with an attention mechanism, embedding a servo motor load characteristic curve in the model, and outputting three types of error compensation amounts; through servo-level compensation and machining-level compensation, the position of a feed shaft, the rotating speed of a main shaft, the cutting feed rate and the behavior of a micro-displacement actuator are corrected, and machining errors caused by deflection and vibration conduction of the main shaft are counteracted. And iteratively updating model parameters by using a gradient descent algorithm. According to the method, through multi-source error synchronous sensing, error coupling modeling and hierarchical cooperative compensation, dynamic error cooperative control more adaptive to a high-speed processing scene is realized, and the method has a wide application value.

The invention discloses a landslide image instance segmentation method based on a dual adaptation mechanism, relates to the technical field of image processing, and ensures that a model can have a better effect and numerical stability on data from different sources through a complete process from multi-source data collection to data normalization processing. The designed model is based on a multi-scale state alignment mechanism, in the forward process of the model, exponential moving average fusion is carried out on feature information in the same level, transmission fusion is carried out on feature information of different levels, feature robustness is enhanced, and error accumulation caused by local deviation is reduced. A meta-context incremental learning mechanism is designed, and input data are dynamically converted into a series of key value vector sequences. In the reasoning process of the model, data distribution different from a training domain is dynamically recognized, a gradient descent process is implicitly executed according to the characteristics of data, and model parameters are finely adjusted, so that the characterization capability is greatly improved, and efficient and robust instance segmentation is realized.

The invention relates to the technical field of information processing, and discloses a method for dynamically regulating and controlling production parameters of a plastic film by utilizing program process scheduling. The method comprises the following steps: converging a real-time parameter sequence to a digital twinborn body to establish virtual mapping, and constructing a multi-dimensional data model; analyzing a material state evolution trend in the digital twinborn body, synchronizing with a physical production line state, fusing historical data to predict a potential influence range, and generating a regulation and control demand report; generating an adjustment scheme draft, performing priority ranking on simulation tasks in the adjustment scheme draft by adopting a program process scheduling algorithm, dynamically allocating computing resources, executing the simulation tasks in parallel, and determining an optimization parameter set in combination with a gradient descent algorithm; and iteratively correcting the parameters in the digital twinborn body through feedback circulation to generate a final coordination control instruction, inputting the final coordination control instruction into the digital twinborn body, confirming synchronism and outputting a report. According to the invention, the precision of dynamic regulation and control of the production parameters of the plastic film is improved.

The invention discloses a geometric constraint fitting point cloud filtering method for sea surface three-dimensional reconstruction, and belongs to the technical field of computer vision and three-dimensional reconstruction. The objective of the invention is to solve the problem of insufficient subsequent three-dimensional reconstruction precision caused by interference of reflection noise, mismatching points and the like in sea surface point cloud. The method specifically comprises the following seven steps: firstly, acquiring sea surface original point cloud through three-dimensional data acquisition equipment; a filtering technology is adopted to obtain a to-be-fitted point cloud; fitting a quadric surface through an improved RANSAC (Random Sample Consensus) algorithm to solve an initial parameter; constructing a comprehensive error function, and optimizing the model through gradient descent; effective inner points are screened through quadratic term coefficient constraint and a distance threshold value; and finally, iterating until a termination condition is met, and outputting an optimal effective point cloud. The method is high in noise rejection rate, the point cloud fits the sea surface form, and high-quality data support can be provided for sea surface fitting, sea wave simulation and unmanned ship control.

The invention relates to a chemical production anomaly detection method based on a space-time diagram variational encoder. The method comprises the following steps: selecting public chemical normal working condition data D; an anomaly monitoring model ST-GVAE is constructed, a loss function L (.) is constructed, D serves as input, an Adam optimizer is adopted to train ST-GVAE, model parameters are reversely updated through gradient descent, and trained ST-GVAE'is obtained; a to-be-detected target variable a is selected, normal working condition historical data corresponding to a are input into ST-GVAE ', and an anomaly detection score corresponding to a is obtained and serves as an anomaly detection threshold value of the target variable a; inputting the current chemical working condition data of a into ST-GVAE'to obtain an anomaly detection score corresponding to the current state of a, and if the score is greater than a threshold value, triggering an alarm; and then calculating a reconstruction deviation score B of each node in the PID, taking the node corresponding to the B greater than a deviation threshold as an abnormal node, and outputting the abnormal node. By using the method provided by the invention, the variable abnormal condition of the existing chemical process can be accurately detected and positioned.

The invention provides a flight path optimization method and system based on an improved particle swarm optimization algorithm, and belongs to the technical field of intelligent optimization algorithms and aircraft flight path optimizing.The method comprises the steps that concerned performance indexes in the flight process of an aircraft are obtained to construct a cost function; the cost function is sampled, sampling points of the cost function serve as particles, the improved particle swarm optimization is adopted to optimize the cost function, and a global optimal position is obtained and serves as a final track optimization result; the improved particle swarm algorithm comprises the following steps: carrying out particle initialization by adopting a method for assigning a particle initial value, carrying out random team distribution on each particle by adopting a Monte Carlo method, carrying out first-time updating on a global optimal particle with a minimum adaptive value by using a gradient descent method, and carrying out second-time updating on a global optimal particle with a minimum adaptive value according to the optimal position of each particle in the team and the optimal position of the particle in the team. And the speed and the position of the particle are updated for the second time based on the second-order consistency theory. According to the method, the convergence speed of the algorithm is improved, and falling into a local optimal solution is avoided.

The invention belongs to the field of sensors and signal processing, and particularly relates to a wavelet kernel scale sensitivity oriented abrasive particle induced voltage signal noise reduction method, which comprises the following steps: acquiring an abrasive particle induced voltage signal, and carrying out harmonic elimination on the abrasive particle induced voltage signal to obtain a preprocessed signal; constructing a wavelet kernel function, and calculating the wavelet kernel function and the preprocessed signal to obtain a kernel scale guiding spectrum; constructing a sparse joint noise reduction model based on the kernel scale guiding spectrum; processing the sparse joint noise reduction model to obtain a convex optimization objective function; solving the convex optimization objective function by combining a self-adaptive step gradient descent method and a self-adaptive iterative shrinkage threshold method to obtain a weight vector representing the distribution of the abrasive particle characteristic signals; carrying out binarization processing on the weight vector representing the distribution of the abrasive particle characteristic signals to obtain a characteristic indication vector; carrying out Hadamard product on the feature indication vector and the preprocessed signal, and then carrying out low-pass filtering to obtain a noise reduction signal; according to the method, the abrasive particle characteristic signals can be self-adaptively subjected to non-destructive enhancement and noise reduction processing in a strong interference environment.

The invention discloses a water supply pipe network water supply amount prediction method based on deep learning. The method comprises the following steps: analyzing a convolutional neural network CNN and a long short-term memory network LSTM; constructing a water supply prediction model based on LSTM, analyzing the water supply prediction model, and setting training parameters; further fusing the CNN and the LSTM, and constructing a CNN-LSTM combination model to obtain an optimized water supply prediction model; and carrying out verification and comparative analysis on the optimized water supply prediction model. According to the method, the CNN-LSTM model is constructed, the model adopts an Adam gradient descent algorithm to optimize a traditional algorithm of the model, and the CNN-LSTM model strengthens the time sequence modeling capability of the LSTM through CNN feature extraction, so that the model not only can identify the microscopic fluctuation of water supply amount data, but also can grasp the macroscopic evolution rule of the water supply amount data; the problem that a traditional model is poor in stability and low in reliability is solved.

The invention discloses a method and a system for detecting a jailbreak attack of a large language model, which are applied to discovering potential security risks of the large language model, and the method comprises the following steps: constructing a jailbreak attack-malicious query data set of the large language model; an automatic antagonism suffix generation method fusing cluster search and a gradient descent algorithm is provided; the detection system of the prison break attack large language model is constructed by training, testing and evaluating the validity of the resistant suffixes based on a prison break attack data set, and comprises a malicious query data set display unit, a detection validity verification unit, a comparison and analysis unit before and after an attack and a model defense strategy unit. The method is helpful for discovering defects of a large language model alignment mechanism, so that a more powerful large language security model is designed and constructed.

The invention provides a cross-omics sparse feature selection system and method based on hierarchical causal modeling, and the system comprises a data input and preprocessing module which is used for receiving multi-omics original data of a multivariate sample; the hierarchical causal structure learning module is connected with the data input and adaptive preprocessing module and is used for constructing a cross-omics hierarchical causal topology; the causal-oriented sparse feature selection module is connected with the hierarchical causal structure learning module; and the model retraining and integration module is used for constructing a three-layer weighted integration discrimination model based on the screened markers, optimizing the fusion weight of each layer through a gradient descent algorithm, and outputting a final prediction result. According to the method, the protein-metabolism biological hierarchy relationship and serum-urine complementary information are fully utilized, and the method has good generalization ability and can be widely applied to marker mining and prediction modeling of cancers, metabolic diseases and the like, so that the accuracy and reliability of precise medical treatment are improved.

The invention discloses an ocean engineering structure extended Kalman filter parameter estimation method based on attitude angle virtual observation, and relates to the technical field of ocean engineering, and the method comprises the following steps: S1, initializing a system process noise covariance matrix and an observation noise covariance matrix, and obtaining an extended Kalman filter attitude angle estimation value; s2, establishing a high-precision angular velocity-attitude angle dynamic conversion model, generating attitude angle virtual observed quantity and using the attitude angle virtual observed quantity for online evaluation of a Kalman filtering result; s3, setting a multi-dimensional performance evaluation index system, and quantitatively evaluating the amplitude error and trend stability of the extended Kalman filter estimated attitude angle; s4, adjusting scale factors of a system process noise covariance matrix and an observation noise covariance matrix by using a gradient descent algorithm based on the attitude angle virtual observation quantity and the error measurement of the multi-dimensional performance evaluation index, and carrying out real-time iteration on the scale factors of the system process noise covariance matrix and the observation noise covariance matrix; the problem that attitude parameters cannot be accurately measured and predicted in real time in the prior art is solved.

The invention provides a drought and flood sudden change prediction method and system based on artificial intelligence, and the method comprises the steps: collecting the in-out reservoir runoff observation data of a reservoir in a target region, obtaining a restored natural reservoir runoff series based on a water balance method, calibrating a long-short-term memory model through a minimum batch gradient descent method, and carrying out the prediction of the drought and flood sudden change. Based on the natural reservoir runoff, the actual reservoir runoff and meteorological data, constructing a long-short-term memory model to simulate the influence of water conservancy project regulation and storage on the runoff; based on an earth system mode set and a multivariable deviation correction method, performing spatial downscaling on output data of earth system modes to obtain corrected meteorological variables; driving a multi-member set of an earth system mode, and separating by adopting a detection attribution technology to obtain a contribution rate of man-made climate compulsion to drought and flood sudden turning event evolution; and predicting a daily runoff process under future climate change, and predicting a future drought and flood sudden turning event by adopting deep learning and superposition of regulation and storage influence of a water conservancy project.