487 results about "Data Noise" patented technology

The invention discloses a solar radiation space-time prediction method and system based on physical information constraint and a neural network, and the method comprises the steps: collecting multi-dimensional time sequence meteorological data, extracting high-dimensional time sequence dynamic features, converting geographic space data into a fuzzy set, and carrying out the defuzzification of the fuzzy set through an inference rule, thereby obtaining geographic space features; and a gating mechanism is adopted to realize deep fusion of the space-time features to generate high-dimensional space-time fusion features. In a model training stage, an energy conservation equation is introduced into an optimization process, a physical residual error is constructed by calculating a time derivative and a space derivative of a predicted value, a physical constraint total loss function is formed in combination with a data loss item, and model parameters are updated by using a gradient descent method. According to the method, the accuracy and reliability of a prediction result are remarkably improved while the calculation efficiency is ensured, and the method is particularly suitable for solar radiation prediction under complex meteorological conditions; according to the method, abnormal prediction caused by data noise can be effectively corrected, and a solution with physical rationality and data adaptability is provided for the fields of solar resource evaluation, photovoltaic power generation power prediction and the like.

The invention discloses a multi-dimensional information integrated transformer health state monitoring method, which relates to the technical field of power systems, and comprises the following steps: deploying a multi-source sensor, collecting various signals of a transformer, and carrying out signal conditioning and analog-to-digital conversion on analog signals collected by the sensor; performing timestamp alignment on the received multi-source heterogeneous data, and eliminating data noise by adopting a filtering algorithm; key features which are sensitive to the health state of the transformer and complement each other are selected from the extracted feature values to form a health state evaluation index set; setting a sliding time window, obtaining historical data in the window, performing normalization processing on the data, calculating the information entropy and the variation coefficient of each index, and fusing the information entropy and the variation coefficient to obtain the dynamic weight of each index; obtaining a health state index of the transformer according to the normalized value and the dynamic weight; and displaying the health state index and the change trend thereof in real time, and setting an early warning threshold value and an alarm threshold value of the health state index.

The invention relates to the technical field of transformer substation intelligent management, in particular to a modular prefabricated cabin transformer substation intelligent comprehensive management system with a multi-source data integration and collaborative management function. Comprising a multi-source data acquisition unit; the edge intelligent processing unit is used for carrying out local preprocessing, feature extraction and abnormal early warning on the acquired multi-source heterogeneous data of the transformer substation, and realizing data noise reduction, abnormal recognition and equipment health degree evaluation through a lightweight AI algorithm and a hybrid communication protocol carried by the edge computing terminal module; and a data integration collaboration unit. According to the invention, through an adaptive sampling strategy and a multi-modal feature fusion mechanism of the multi-source data acquisition unit, multi-dimensional data such as electric power parameters, power environment, fire protection and security protection and the like are incorporated into a monitoring system, feature layer association analysis is realized by depending on a Jousseme distance and a Dempster synthesis rule, the assessment limitation of single equipment and single-dimensional data in a traditional scheme is broken through, and the method has the advantages of high reliability and high reliability. And a more comprehensive state basis is provided for equipment health degree research and judgment.

The invention discloses a high-precision real-time positioning system and method for positioning personnel based on multi-mode fusion. The system comprises a multi-source data acquisition module, an intelligent data processing module, a fusion positioning model construction module and a positioning result application module, provides visual monitoring, trajectory analysis and scene customization functions, and supports flexible expansion through modular design. According to the method, satellite positioning, Bluetooth beacon and inertial navigation technologies are integrated, the weight is dynamically adjusted in combination with an adaptive weighted fusion algorithm, and a fusion positioning model supports outdoor (satellite dominant + EKF calibration, the precision being 2-5 meters) and indoor (beacon dominant + fingerprint matching, the precision being lt); according to the invention, intelligent switching between three modes (inertial navigation + ZUPT correction) and signal loss (1 meter) is realized, data noise is optimized by using Kalman filtering, and high-precision real-time positioning in indoor and outdoor complex scenes is realized. According to the invention, the problems of insufficient precision, poor environmental adaptability and weak expansibility of a single positioning technology are solved, and the comprehensive performance of the positioning system is significantly improved.

The invention relates to the technical field of air leakage big data analysis, in particular to a compressed air pipeline air leakage intelligent analysis system and method based on LLM. A plurality of monitoring nodes in a compressed air pipeline are analyzed, and data normal range parameters and adaptive acquisition frequency are preset for each node in the pipeline operation stage; the clear definition standard avoids misjudgment of original data due to fuzzy threshold values, then data noise is effectively reduced by analyzing the data synchronization degree of each monitoring node and intelligently repairing the problems of missing, deviation and the like, the repaired data better fits the actual operation state of the compressed air pipeline, the missed detection and mispositioning risks are reduced, and the reliability of the compressed air pipeline is improved. And finally fusing the data of the gas leakage node and the adjacent node to supplement multi-dimensional information, and optimizing the fusion data quality. The LLM model depends on high-quality fusion data, deep analysis is carried out in combination with compressed air pipeline multi-monitoring-node correlation characteristics and historical experience, deviation caused by data defects is reduced, and the accuracy of an intelligent air leakage analysis result is greatly improved.

The invention discloses a dynamic identification method for unusual cells before young tumors based on multi-omics data, and relates to the technical field of cell unusual identification. A dynamic correlation intensity matrix and a cumulative effect contribution matrix are constructed, a differentiation screening strategy is implemented according to individual response characteristics, and the unusual cells before young tumors are identified. And the abnormal dynamic high-fidelity identification of the young tumor pre-cells is realized. And aiming at individuals of different response types, an instant path, a long-term path or a double-path fusion strategy is respectively adopted, key behavior data is accurately screened, and the input quality is improved. According to the method, redundant interference is effectively eliminated, the simulation capability of the model on key processes such as immunosuppression and DNA damage accumulation is enhanced, the biological rationality and prediction precision of a cell state evolution sequence are remarkably improved, and the problems of model response lag, low calculation efficiency and output distortion caused by data noise in the prior art are solved; and a reliable technical support is provided for early warning and individualized intervention of precancerous lesions.

The present invention is a parameter estimation method for compartment model based on physics-informed neural networks. Starting from a physical model, the method extracts information from an AIF and a small amount of measurement data to obtain kinetic parameters, thereby greatly improving the scanning efficiency of a measuring instrument, and reducing occurrence of inaccurate estimation results due to patient movement. In addition, the present invention has the robustness to AIF noise and measurement data noise, and can flexibly arrange the time of data acquisition, reduce an error of inaccurate estimation caused by long time 10 acquisition and the patient movement, and improve the efficiency of data acquisition of the instrument. Experimental results show that the present invention is more stable and has less errors. Meanwhile, the present invention does not require the setup of training datasets, and is superior to an end-to-end supervised reconstruction method U-net network with fewer samples.

The invention belongs to the technical field of wastewater treatment, and provides a wastewater treatment equipment remote control system based on the Internet of Things, which aims at solving the problems that the traditional fixed DO concentration control cannot adapt to water inlet load fluctuation, the effluent is easy to be substandard or the aeration energy consumption is high, the monitoring data noise is large, and the time sequence is misplaced. According to the scheme, a multi-dimensional real-time sensing network is constructed, flow, COD, BOD, ammonia nitrogen, water temperature, distributed DO and sludge activity sensors are deployed, discrete wavelet transform is adopted for noise reduction, and a data time sequence is aligned; a three-layer load-DO-energy consumption dynamic correlation model is designed, a basic layer predicts a load trend through LSTM, a middle layer quantifies a DO demand through a microbial metabolism model, and an optimization layer outputs an optimal DO set value through a PPO algorithm; and developing a dynamic decision-making system, adaptively generating a DO interval according to a load state, and adjusting fan parameters and number in a linkage manner. According to the invention, load dynamic adaptation is realized, effluent ammonia nitrogen is guaranteed to reach the standard, aeration energy consumption is reduced, and remote control precision and equipment operation efficiency are improved.

The invention discloses a data security sharing method and system, and relates to the technical field of data sharing. The method comprises the steps that a data provider uploads original data, a privacy budget value is calculated through a differential privacy algorithm, noise is added to obtain noisy data, and the noisy data is processed through an anonymous privacy protection algorithm based on maximum dissimilarity degree clustering to obtain desensitized data; encrypting the desensitized data by adopting a block chain decentralization-based ciphertext policy attribute-based encryption method, obtaining an encrypted data ciphertext, uploading the encrypted data ciphertext to a cloud server, and obtaining a content addressing hash value; encrypting the hash value through an elliptic curve encryption algorithm, and storing the encrypted hash value to a block chain account book; and when an access request of a data requester is received, the cloud server verifies the authority by using a non-interactive zero-knowledge proof protocol and returns an encrypted hash value after passing the verification, and the requester decrypts to obtain the hash value and decrypts the encrypted ciphertext to obtain desensitized data, thereby realizing data sharing.

The invention provides an industrial time sequence generation method based on a time sequence decomposition conditional diffusion model. The method comprises the steps that industrial time sequence data are collected and preprocessed to obtain a data set; introducing conditional variables to construct a conditional diffusion model, and injecting noise through forward diffusion; designing a time sequence decomposition and reconstruction UNet module, performing feature extraction on noisy data and conditional variables to obtain an intermediate state, performing time sequence decomposition on the intermediate state, and performing feature reconstruction by using a decoder; the Sinkhorn distance is used as a regularization term to be fused into conditional noise prediction loss to construct a loss function for training; and randomly generating pure Gaussian noise, inputting the pure Gaussian noise into the trained TDA-CDM model, obtaining predicted noise of the current time step, calculating noisy data of the next time step, performing cyclic operation until a time sequence without noise is obtained, and accelerating sampling by using a denoising diffusion implicit model in circulation. According to the method, coexisting multi-scale dynamic features in the complex industrial MTS can be carefully and effectively captured and restored, and the comprehensive quality of generated data is remarkably improved.

The invention discloses a credit risk prediction method based on data and dynamic feature optimization and Bagging integration, and the method comprises the following steps: S1, obtaining an initial data set, carrying out the data preprocessing, balancing the data set through an ATGA algorithm, and reducing the data noise; s2, using LightGBM as an agent model, calculating importance scores of all features, gradually screening key features, adaptively adjusting feature screening standards according to data distribution through a dynamic threshold algorithm, gradually screening feature subsets, and inputting the screened features into a subsequent model; and S3, constructing a TabPFN model by using a Bagging integration algorithm, introducing a dynamic weight distribution mechanism, adaptively adjusting the weight of each base model according to sample features, and finally realizing credit risk prediction through the TabPFN model. According to the method, the credit risk prediction process is comprehensively optimized in three aspects of data set optimization, feature screening optimization and model performance optimization, so that indexes such as the accuracy rate and the rate of return are improved.

The invention relates to the technical field of intelligent water conservancy and automatic control, in particular to a polder area multi-station water conservancy data real-time collection and intelligent fusion processing method and system, and the method comprises the steps: a multi-dimensional collection system construction step: collecting time sequence state, fluid field and environment boundary data, and executing time base unified cleaning; an ideal model construction step: constructing an ideal water tank model based on the law of conservation of mass and generating an ideal water level change curve; a parameter injection simulation step: generating a simulation fault water level curve according to injection efficiency attenuation and medium leakage parameters; a double-track difference calculation step: respectively carrying out difference on actual measurement and simulation data and an ideal curve to generate real and theoretical residual vectors; a similarity judgment and control step: calculating sequence similarity to judge a real physical fault or sensor data noise, and generating a fusion control instruction; according to the invention, the technical problem of distinguishing the noise of the sensor from the real physical fault is effectively solved, and false alarm or missing alarm is avoided.

The invention discloses a data real-time analysis and fault early warning method and system based on a digital electric port box transformer substation, and belongs to the technical field of power equipment monitoring and control systems. The method comprises the following steps: acquiring environmental parameters of each component of the box transformer substation in real time through a monitoring network, and performing data smooth denoising to obtain a parameter sequence; constructing a dynamic storage framework based on the sequence in combination with space-time attributes; extracting historical records of the target component to perform multi-dimensional sorting and change rate calculation, and identifying potential anomalies; when the change rate exceeds the limit and the distribution boundary breaks through, generating an alarm sequence and determining a preliminary abnormal mark; comparing the mark with the historical record, fusing the influence weight analysis verification accuracy, and obtaining a final early warning grading result; and parameter summary information is pushed to a control system according to a grading result, response feedback is obtained, and closed-loop control of the operation state is formed. According to the invention, the problem of control lag caused by data noise and delay is solved, and the timeliness, reliability and automation level of box transformer substation control are improved.

The invention discloses a boat hanging frame mechanical system fault diagnosis method and system, a program product and a computer readable storage medium. The method comprises the following steps: acquiring vibration data of a boat hanging frame mechanical system in a normal-temperature environment and a low-temperature environment; performing noise reduction processing on mechanical vibration data in a normal-temperature environment and a low-temperature environment by a multi-domain fusion self-adaptive fault feature enhancement noise reduction method; dividing the denoised data into a training set, a verification set and a test set; training set data is transmitted to a fault diagnosis model, and normal temperature environment mechanical vibration data features after noise reduction and low temperature environment mechanical vibration data features after noise reduction are extracted; respectively aligning the extracted normal-temperature environment mechanical vibration data characteristics and the extracted low-temperature environment mechanical vibration data characteristics on a plurality of scales by using a multi-layer category perception multi-core adaptive maximum mean difference method; data features are transmitted into a classifier for fault classification, model parameters with the best performance on a verification set are taken, and the effect and performance of the model are checked on a test set.

Embodiments described herein provide systems and methods for noise-robust contrastive learning. In view of the need for a noise-robust learning system, embodiments described herein provides a contrastive learning mechanism that combats noise by learning robust representations of the noisy data samples. Specifically, the training images are projected into a low-dimensional subspace, and the geometric structure of the subspace is regularized with: (1) a consistency contrastive loss that enforces images with perturbations to have similar embeddings; and (2) a prototypical contrastive loss augmented with a predetermined learning principle, which encourages the embedding for a linearly-interpolated input to have the same linear relationship with respect to the class prototypes. The low-dimensional embeddings are also trained to reconstruct the high-dimensional features, which preserves the learned information and regularizes the classifier.

The invention discloses a large language model training-oriented FP8 quantization noise compensation method and system, and relates to the technical field of computer large language model data noise compensation. The method comprises the following steps that: a processor quantizes original data input into a memory according to a designed FP8 format to obtain quantized data representation; and obtaining quantization noise according to the original data and quantization data representation stored in the memory, and constructing a quantization noise training model by taking the quantization noise as a random variable. And designing a noise compensation mechanism by taking the parameters of the quantization noise training model and the compensation model stored in the memory as compensation units. And the processor determines an embedding point of the noise compensation mechanism embedded large language model in a compensation unit training process according to the compensation granularity demand, so that the original data is input into the large language model embedded with the noise compensation mechanism through the processor for iterative learning, and FP8 compensation data is output. By adopting the method, the hardware calculation speed can be increased and the memory access frequency can be reduced in the big language model data processing process.

The invention discloses a reservoir level prediction method based on reservoir capacity curve decoupling. The reservoir level prediction method comprises the following steps: 1, forming a sample set by a historical water level and a reservoir capacity sequence; 2, fitting a water level-reservoir capacity curve by using a polynomial; 3, solving an optimal fitting coefficient through a least square method, and establishing a relation curve; 4, calculating the reservoir capacity change in the rainfall period; 5, obtaining a rainfall net contribution amount; 6, calculating a theoretical response water level; 7, collecting historical data and selecting a core predictive factor; and 8, constructing and calibrating a water level prediction model. According to the method, the model which is clear in physical significance, easy and convenient to calculate and high in prediction precision is constructed, reliable technical support is provided for refined scheduling and flood prevention decision making of the reservoir, and therefore the problems that in an existing reservoir water level prediction model, a physical mechanism model is complex in structure, high in data dependence and low in calculation efficiency are solved; and a data-driven model is poor in interpretability, easy to be interfered by data noise and uncertain in generalization ability.

The invention relates to the technical field of big data processing and artificial intelligence, and discloses an intelligent statistical method and system for innovation and entrepreneurship data, and the method comprises the steps: obtaining heterogeneous data through a multi-modal data access module, and constructing an initial time sequence semantic hypergraph; measuring a semantic drift vector and an innovative trajectory curvature of the entity through a semantic evolution calculation module; calculating an interaction entropy weight of a hyperedge by combining a historical co-occurrence probability and a time decay factor through an entropy weight measurement module; executing hyperedge splitting and fusion operation based on an interaction entropy gradient according to the curvature and the weight through a topology dynamic reconstruction module, and generating a reconstructed time sequence semantic hypergraph; and finally, searching an effective hyperedge in the reconstructed atlas by utilizing a statistical analysis service module and calculating an innovative momentum index. Through time sequence semantic hypergraph evolution and an interaction entropy weight mechanism, data noise caused by conventional operation is effectively eliminated, a cross-dimension substantive innovation chain is identified and aggregated, and the objectivity of innovation evaluation and the interpretability of a result are improved.

The invention provides a large model illusion relieving method and device, a medium and a product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining an input sample which comprises meta-knowledge and dialogue history; screening the meta-knowledge by using a sample filter based on reinforcement learning, and performing model training by using the screened meta-knowledge to obtain a knowledge graph embedding model; inputting the dialogue history into the knowledge graph embedding model, and obtaining a knowledge graph embedding vector output by the knowledge graph embedding model; fusing a local knowledge vector and a global knowledge vector according to the knowledge graph embedded vector to obtain a fused knowledge graph vector; embedding the fused knowledge graph vector into an encoder-decoder model to obtain a large model; according to the method, the interference of data noise on a knowledge graph embedding method can be reduced, so that the illusion problem of a large model is relieved.

The invention relates to a DAS-VSP seismic data noise suppression method based on a double-domain generative adversarial network, and belongs to the field of seismic exploration data denoising and deep learning. The method comprises the following steps: constructing a double-domain generative adversarial network, determining an optimal hyper-parameter combination by Bayesian optimization, adding actual noise to a pure seismic signal obtained by a forward modeling method to construct a complete training set, training the double-domain generative adversarial network, and testing the double-domain generative adversarial network. According to the method, DAS-VSP data which is low in signal-to-noise ratio and contains various kinds of complex noise can be effectively processed, the denoised seismic signals are clearer in structure, better in continuity, higher in signal-to-noise ratio and more thorough in noise suppression, effective signals are reserved to the maximum extent, high-quality basic data are provided for subsequent seismic data processing and explanation, and the method is suitable for large-scale popularization and application. The method meets the high-precision requirement of current seismic exploration, and has a wide application prospect in the field of oil and gas resource exploration and development.

The invention belongs to the technical field of seismic data processing in geophysical exploration, and relates to a Marchenko multiple suppression method for correcting wave field mismatch based on Wasserstein distance, which comprises the following steps: acquiring a pulse reflection sequence through preprocessing and deconvolution; a pulse reflection sequence is input, and Marchenko iteration initialization is carried out; and remodeled Marchenko iteration for correcting the wave field mismatch based on the Wasserstein distance is carried out. According to the method, the optimal transmission theory is systematically introduced into the Marchenko multiple wave suppression field for the first time, the adaptive capacity of the Marchenko method to actual data noise, defect and amplitude distortion is remarkably improved while the advantage that the Marchenko method does not need a speed model is kept, and therefore higher-precision multiple wave suppression and more reliable primary wave recovery are achieved, and the method is suitable for popularization and application. The method is used for high-precision seismic imaging in a complex land exploration environment. The method has remarkable advantages in the aspects of constraint mechanism, error control and global feature protection.

The invention discloses a seismic strong background noise removal method based on a two-channel network, and relates to the field of geophysical exploration data processing, and the method comprises the steps: selecting a noiseless signal and background noise when the noiseless signal and the background noise are not excited from a single-channel seismic record after a seismic source is excited, carrying out the superposition, generating noisy data, and carrying out the normalization processing; constructing a dual-channel constraint denoising network composed of a global constraint sub-network and a denoising sub-network; optimizing network parameters through the training sample set; and performing global constraint denoising and slice local denoising on the noisy seismic data by using the trained model, and finally splicing to obtain a complete denoising result. According to the method, the splicing effect problem caused by traditional blocking processing is effectively solved, the strong background noise removal effect is remarkably improved, and seamless high-quality denoising with the complete edge is achieved.

The invention relates to an intelligent networked automobile heterogeneous sensing fusion method based on a self-adaptive BEV, and belongs to the technical field of mobile communication. According to the method, the problems of reduced global sensing precision, insufficient real-time performance and poor robustness caused by heterogeneity of CAV sensing, communication and computing capabilities in the existing collaborative sensing technology are solved. The method specifically comprises the following steps: dynamically screening credible CAV nodes based on a reputation value, and adaptively allocating BEV resolution and uplink bandwidth through a perception precision-cooperative time delay collaborative optimization model; adopting polar coordinate quantification to construct local BEV features so as to reduce misclassification; smooth alignment of the multi-source heterogeneous BEV features is achieved through coordinate transformation and bilinear interpolation; and applying local and global attention at the same time by using a multi-stage fusion type axial attention module, and deeply aggregating the aligned BEV features. According to the method, the cooperative sensing precision in a complex traffic environment is remarkably improved, the real-time decision-making capability of the system is effectively guaranteed, and the robustness to abnormal nodes and data noise is comprehensively enhanced.

The invention relates to the technical field of electromagnetic fingerprint analysis, in particular to an electromagnetic fingerprint real-time monitoring and abnormity recognition system during operation of industrial equipment. The system comprises a data noise reduction module which is used for obtaining an electromagnetic signal curve of target equipment and carrying out noise reduction to obtain a noise-reduced electromagnetic signal curve; the feature extraction module is used for respectively acquiring a first feature, a second feature and a third feature of the period according to the mean value and the maximum peak value of the data of the previous period of the noise reduction electromagnetic signal curve and the slope between every two adjacent data; the feature difference analysis module is used for acquiring a first feature difference sequence, a second feature difference sequence and a third feature difference sequence; and the abnormity monitoring module is used for respectively acquiring residual terms of the first, second and third characteristic difference sequences, and judging whether the current electromagnetic fingerprint is abnormal or not according to the last residual point in each residual term and other residual points except the last residual point. Whether the electromagnetic fingerprint is abnormal or not can be accurately detected.

The invention provides a social listening data noise reduction method and device based on a large language model, and belongs to the technical field of social media data processing. The method comprises the steps that social media data are collected and preliminarily filtered to obtain preliminarily filtered data; generating a semantic embedding vector by using a pre-trained large language model, and screening semantic related data in combination with cosine similarity and context; identifying and filtering duplicate and variant contents through an embedded model and a generative adversarial network to obtain duplicate-removed data; performing multi-modal feature extraction on the de-duplicated data, and screening credible data in combination with generative AI detection and sentiment analysis; and filtering semantic inconsistency and non-topic continuation texts by adopting a clustering algorithm and semantic relationship analysis to finish noise reduction. According to the method, through a multi-stage and multi-dimensional noise reduction strategy, the purity and credibility of social listening data are effectively improved, and high-quality data support is provided for subsequent topic analysis and decision making.

The invention relates to the field of field groundwater magnetic resonance detection methods, in particular to an augmentation system and method for field groundwater magnetic resonance detection small sample data. Comprising a generation network configured to receive random noise and generate augmented data based on the random noise; the discrimination network comprises a time domain discrimination network and a frequency domain discrimination network; the generative network and the time domain discrimination network form a first discrimination channel, the generative network and the frequency domain discrimination network form a second discrimination channel, and in the second discrimination channel, augmented data generated by the generative network and the noisy data are jointly input into the frequency domain discrimination network; the frequency domain discrimination network is used for discriminating whether the source of input data is a generation network or noisy data in a frequency domain. According to the method, a magnetic resonance detection small sample noisy data set is established, and multi-scale features in an amplitude spectrum and a phase spectrum are captured through the frequency domain discrimination network; the collaborative driving generation network generates a high-quality sample which is close to small sample noisy data in waveform form and spectral characteristics.

The invention discloses a knowledge graph alignment method and system based on a large language model and an agent and oriented to the field of the manufacturing industry. The method comprises the following steps: enhancing a key relation weight by adopting a relation perception graph network, fusing a semantic vector of the large language model and a vector of a domain term library to correct a name conflict, and dynamically adjusting learning parameters; implementing a dynamic bucket dividing strategy, high-confidence scene simplification candidates, low-confidence scene fusion term retrieval and a big language model virtual name generation mechanism according to the embedding quality; based on an agent and large language model hierarchical interaction architecture, precise prediction is realized through coarse-grained screening and domain knowledge enhanced fine-grained matching, and an intelligent iteration termination condition is set; and executing lightweight incremental training to update the embedded representation, combining reinforcement learning to dynamically adjust and optimize the strategy library, and synchronizing and automatically expanding the term library. According to the method, cross-language alignment precision jump, data noise interference suppression, efficiency and accuracy optimization balance and system continuous autonomous evolution capability enhancement are realized.

The invention relates to a safety monitoring method for an irrigation and drainage project operation state and an intelligent system, and belongs to the technical field of artificial intelligence. The method comprises the following steps: collecting and marking irrigation and drainage project operation monitoring data through a sensor, and constructing a training data set; completing data normalization by combining quantile and median robust scaling with adaptive nonlinear transformation, and mining and screening high-order interaction features by combining a mutual information theory and a gradient boosting decision tree; constructing a deep classification network fusing physical prior and adaptive feature interaction, introducing physical constraint and multi-scale feature fusion, and optimizing a model through adaptive marginal classification loss and physical feature manifold alignment loss; real-time data is preprocessed and then input into the model, and operation state grade classification and graded alarm are achieved. According to the method, data noise can be inhibited, a multi-index coupling relationship can be mined, the interpretability and robustness of the model can be improved by integrating a physical rule, irrigation and drainage project abnormity can be accurately identified and early warned, and the method is suitable for intelligent safety monitoring of an irrigation area.

The invention discloses a driving decision model optimization method and electronic equipment, and relates to the technical field of automatic driving, and the method comprises the steps: carrying out the denoising processing through a training diffusion model according to first driving perception data and first noisy data, so as to generate a first driving path point sequence of the first driving perception data at a future moment; therefore, abundant and diversified driving tracks are generated by utilizing the strong complex multi-modal distribution modeling capability of the diffusion model; using a first diffusion model to generate a plurality of second driving path point sequences at future moments according to the second driving perception data so as to construct an evaluator training sample, and training an evaluator model to select an optimal driving path point sequence from the plurality of second driving path point sequences, according to the method, the diffusion model and the evaluator model obtained through training are utilized to construct the driving decision-making model, through joint training of the evaluator model and the diffusion model, the decision-making ability of the driving decision-making model for generating candidate driving tracks and selecting the optimal driving track is enhanced, and the safety of automatic driving is improved.

The invention belongs to the technical field of gravity data noise reduction, discloses a gravity data noise reduction method based on a U-Net network, and provides a U-Net network structure fusing a multi-scale feature fusion module and an attention mechanism aiming at the noise reduction problem of gravity and gravity gradient data. And a physical consistency constraint is introduced in a model training process. A Laplace equation met by the gravitational field potential in geophysics is used as prior information to be fused into a loss function, and a Laplace item is designed. The operation effectively improves the physical interpretability and generalization ability of the noise reduction result of the neural network. Meanwhile, the network structure adopts multi-scale feature fusion and an attention mechanism, and information of different spatial scale features and key spatial positions in complex geological signals is better captured.