1319 results about "Mutual information" patented technology

The invention discloses an industrial data analysis and mining system based on a knowledge graph, relates to the technical field of data mining, and aims to solve the problems of difficulty in cross-process parameter association and low abnormal traceability precision. The system calculates the correlation strength of the oven temperature in the coating process and the direct-current internal resistance of the battery cell in the formation and capacity grading process through a time-lag mutual information algorithm, generates an influence relation edge with a time-varying weight in combination with a temperature-internal resistance negative correlation process rule, and constructs an industrial knowledge graph; taking a direct-current internal resistance abnormal batch as a starting point, reversely traversing the knowledge graph along a process path, fusing a parameter Z-score deviation degree and a dynamic weight to generate a root cause parameter list, and realizing quality root cause positioning; instantiating abnormal parameters into event nodes, identifying star-type and chain-type propagation topologies through subgraph isomorphism detection, and extracting a standardized fault mode; based on an FCI causal discovery algorithm, a real causal structure is identified, the weight of the knowledge graph is dynamically adjusted, adaptive evolution of the graph is realized, and the accuracy and the intelligent level of complex process quality analysis are improved.

The invention discloses a deep well rock burst early warning system and method based on multi-dimensional monitoring, and belongs to the technical field of deep well rock burst early warning. According to the method, multi-dimensional data such as stress, strain and microseism are collected through a monitoring network, and an aligned multi-source data set is obtained through space-time registration; after dynamic noise suppression processing matched with physical characteristics is adopted, strong correlation characteristics are screened through mutual information entropy; frequency domain, time domain and time-frequency domain features are extracted through principal component extraction and phase-space reconstruction, and a multi-dimensional state space data set is formed; and inputting the prediction model to obtain a danger level and trigger a corresponding early warning signal, and finally dynamically adjusting the monitoring network layout and prevention and control measures based on the early warning signal. According to the method, the early warning accuracy and real-time performance are improved, and effective technical support is provided for deep well rock burst prevention and control.

The invention relates to the technical field of power distribution operation and maintenance management, and discloses an intelligent power distribution operation and maintenance management system based on 5G transmission. The system comprises a 5G real-time acquisition module, a multi-dimensional feature fusion module, a dynamic topology generation module, an anomaly propagation analysis module and a strategy optimization feedback module. The 5G real-time acquisition module acquires operation state data streams such as current and voltage waveforms, an equipment temperature sequence and environment monitoring indexes of the power distribution equipment through a 5G network; the multi-dimensional feature fusion module is used for separating equipment state features, calculating mutual information amount and generating equipment state feature tensors; the dynamic topology generation module constructs an association intensity matrix according to the feature tensor, and generates a hierarchical connection path and a dynamic equipment topological graph; the abnormal propagation analysis module extracts a state fluctuation sequence, identifies an abnormal transmission path and marks a core propagation node; and a strategy optimization feedback module generates a maintenance strategy priority queue according to the dynamic topology map, and feeds back an execution result to update the dynamic topology map, so that the intelligence and accuracy of power distribution operation and maintenance management are improved.

The invention relates to the technical field of biomedical engineering, in particular to a multi-mode brain anomaly detection method and system based on machine learning. The method comprises the following steps: acquiring brain medical image data of different modalities, and realizing spatial registration and alignment through a multi-modal registration algorithm based on mutual information; a multi-branch feature extraction model including a convolutional neural network, a converter and a state space model is utilized to perform feature embedding on the original image of each modal; performing frequency decoupling on the features of each mode through adaptive approximate wavelet transform, and decomposing the features into high-frequency detail information and low-frequency global information; a frequency band fusion strategy based on an attention mechanism is implemented on high and low frequency features of different modal images, and fused frequency sub-band features are input into a space-frequency Mama module. Through the adaptive frequency domain decomposition and cross-modal fusion mechanism, the multi-modal brain image information is effectively integrated, and the accuracy and robustness of brain anomaly detection are remarkably improved.

The invention discloses a power Internet of Things terminal attack tracing method based on lightweight dynamic causal reasoning, relates to the technical field of network security, and solves the problems of sample unevenness, graph scale expansion and calculation delay in power Internet of Things terminal attack tracing in the prior art. The method comprises the following steps: processing a log text to obtain vector data; a residual error generation network is adopted, and the time sequence and logic relevance between attack events is introduced in the GAN training process; then, constructing a preliminary attack traceability graph, designing a graph neural network and attention mechanism combination method to calculate weights among nodes, and introducing a mutual information technology to dynamically adjust causal confidence among the nodes; and finally, generating high-quality embedding by utilizing the GAT teacher model, and migrating traceability knowledge of the teacher model to the lightweight GIN student model through knowledge distillation. In conclusion, the method can systematically construct an efficient attack traceability technical framework oriented to the power Internet of Things terminal from three key stages.

The invention discloses a multi-modal remote sensing semantic segmentation method and system for learning frequency domain fusion. The method comprises the following steps: respectively extracting multi-scale features of two modal input images by adopting a double-branch encoder; sequentially executing frequency domain decoupling and fusion, mutual information constraint-based feature optimization and low-frequency guided cross-modal fusion processing on each scale feature to generate a fused semantic feature; and performing up-sampling and feature refining on the fused features through a decoder, and outputting a full-resolution segmentation prediction map. According to the multi-modal remote sensing image semantic segmentation method, modal sharing information and specific details are effectively separated through frequency domain decoupling, feature representation is optimized through mutual information constraint, adaptive feature fusion is achieved in combination with an attention mechanism, and the accuracy and robustness of multi-modal remote sensing image semantic segmentation are remarkably improved.

The invention relates to a gated multi-graph convolution perception modeling method for traffic flow prediction. The method integrates multi-graph structure construction, gating graph convolution and time feature extraction, and aims to solve the problems of strong time fluctuation and heterogeneous spatial relationship in traffic data. The method comprises the following steps of: firstly, respectively constructing a geographic map and a semantic map according to the maximum mutual information measurement between the spatial distribution information of a sensor and historical traffic data; and then, designing a dual-adaptive gating graph convolution module, and dynamically adjusting an information propagation path of a multi-graph structure by introducing an attention mechanism and a gating factor, thereby improving the modeling performance of the model on spatial isomerism dependence. On the time dimension, a time sequence interactive sensing module is constructed in combination with multi-scale causal convolution and an attention mechanism, time dependence characteristics of a short period and a long period are captured, and fusion and expression of time characteristics are completed. According to the method, the modeling precision and stability of the traffic prediction model in a complex traffic scene can be effectively enhanced, and the method has relatively high practical application value.

The invention relates to a multi-sensor fault feature fusion diagnosis method for electrical equipment, which comprises the following steps: synchronously acquiring operation data of the electrical equipment through a vibration sensor, a temperature sensor, a current sensor and an ultrasonic sensor, dynamically adjusting the sampling frequency according to the physical characteristics of each sensor, and the sampling rate of the temperature signal is not lower than 1Hz. Through a multi-source sensor data synchronous acquisition and time sequence alignment technology and a signal alignment method combining a dynamic time warping (DTW) algorithm and Hilbert-Huang transformation, the problem of time asynchronization of heterogeneous sensor data such as vibration and temperature is solved, so that the time alignment precision of multi-source data is improved, the feature extraction accuracy is improved, and the accuracy of feature extraction is improved. Through hierarchical feature extraction and graph convolutional network fusion, a feature incidence matrix based on mutual information is constructed, deep correlation between vibration signal TKEO features and cross-modal features such as current harmonics is mined by using GCN, the feature dimension is reduced, and the fault feature separability index is improved.

The invention discloses a PCB mainboard defect detection method and system based on multi-sensor fusion, and the method comprises the steps: synchronously collecting multi-modal data through optical, ray and thermal imaging sensors, and achieving the feature fusion through a multi-branch feature extraction network in combination with a cross-modal attention mechanism (a mutual information algorithm dynamically distributes weights). Defect detection is completed through a feature pyramid network and sub-pixel positioning, and finally sensor parameters, models and production processes are adjusted in a closed-loop mode based on detection results. The problems of detection blind areas of a single sensor, insufficient fixed weight fusion precision, missing detection of small defects and the like are solved, all-directional detection from the surface to the inner layer and from the form to thermal anomaly is realized, the detection precision is improved, the defect occurrence rate is reduced through process linkage, and the method is suitable for a high-density PCB mainboard.

The invention relates to a water quality prediction method and system based on gating residual enhancement and feature fusion, and belongs to the technical field of water environment intelligent analysis and deep learning. Taking each water quality index as a node of the graph, and constructing two complementary variable relation graph structures by utilizing a Pearson's correlation coefficient and mutual information; respectively inputting the two graph structures into a graph convolutional network, extracting deep dependency features among indexes, and splicing and fusing the deep dependency features. A multi-head attention mechanism is used as a trunk to extract global time dependence, a GRU network is introduced to extract local time sequence features, GRU output is used as an adjustable residual term to be injected into the attention trunk through a residual gating mechanism, self-adaptive enhancement of local dynamic features is achieved, and finally a self-adaptive fusion mechanism is introduced to generate comprehensive representation. According to the method, the complex dependency relationship between the water quality indexes and the time dynamic evolution process can be modeled in a collaborative manner, the response capability to key local change and sudden change events is remarkably enhanced, and the accuracy and robustness of water quality prediction are improved.

The invention relates to the technical field of safety monitoring, and particularly discloses an embankment danger rapid identification method and system, and the method comprises the steps: collecting multi-modal data in real time through arranging a multi-source sensor network; according to the phase space trajectory, extracting a Lyapunov exponent spectrum, correlating the dimension and the Kolmogorov entropy, and forming a structure response chaos degree index; calculating a hydrogeological coupling coefficient in combination with multi-scale decomposition and mutual information analysis; and fusing the two into a three-dimensional dangerous case feature tensor, inputting the three-dimensional dangerous case feature tensor into a pre-training model based on a deep convolutional neural network and a long-short-term memory network, realizing intelligent discrimination of high, medium and low risk levels, generating an adaptive monitoring instruction for a low-risk working condition, outputting a risk evolution trend map, and supporting closed-loop management and control.

The invention discloses a gradient welding strength control method and system for a welded galvanized steel pipe for fire fighting, particularly relates to the technical field of welding automation control, and aims to solve the problem of abnormal welding seam strength gradient caused by instantaneous unbalance of an electric field and a thermal field during dynamic parameter switching in the prior art. Electromagnetic distortion characteristic quantity is extracted through frequency domain energy analysis, and thermodynamic offset state quantity is deduced in combination with a thermal diffusion trend; on the basis of frequency band correlation mapping of electromagnetic and thermodynamic parameters, thermoelectric cooperative imbalance levels are divided through mutual information entropy evolution, and a self-adaptive harmonic attenuation weight tuning instruction is generated; analyzing a mismatching relation between transient disturbance of an environment magnetic field and arc voltage modulation distortion in real time, dynamically generating a magnetic field compensation factor and reversely superposing the magnetic field compensation factor to a control instruction; and in combination with the matching degree of molten pool oscillation energy and a harmonic frequency spectrum, correcting wire feeding rate calibration, reconstructing a multi-band harmonic energy proportion spectrum, outputting an anti-interference welding control signal, and realizing dynamic balance between arc stability and molten pool heat input.

The invention relates to a multivariate time series data abnormal root cause identification method based on a space-time cause and effect diagram, and belongs to the technical field of anomaly detection. According to the method, multi-window expansion causal convolution is adopted for multivariate time series data, mutual information screening is combined, and time embedding covering short-term mutation and long-time dependence at the same time is extracted; non-local space correlation is learned through multi-head self-attention, the directional causal intensity is measured through conditional entropy, and a sparse and interpretable space-time causal graph is generated through normalization-pruning; introducing a causal enhancement graph attention network on the space-time causal graph, and performing multiple rounds of causal propagation updating on node embedding; and calculating a root cause score by integrating the abnormal degree and the causal influence, identifying a key source node in an abnormal propagation path, and realizing accurate root cause positioning of the system abnormality. According to the method, the adaptability to the dynamic behavior mode and the capturing capability to the abnormal driving factor are enhanced, and the modeling precision and the root cause identification capability of the abnormal propagation process are improved.

The invention provides a circuit board electrical performance test and diagnosis method, which comprises the following steps of: constructing a structured process-electrical data set by collecting process parameters such as etching time, pressing temperature, drilling precision, copper foil thickness and the like and electrical test indexes such as impedance deviation, leakage current, signal attenuation and the like; screening key process variables by adopting mutual information analysis and a maximum correlation-minimum redundancy criterion; through modeling of a three-layer causal diagram and a structural equation, quantitative influence evaluation of process parameters on electrical performance and fault types is realized; when a fault is detected, the system can automatically perform reverse reasoning, identify a main manufacturing deviation item and generate attribution diagnosis and process optimization suggestions, so that the accuracy of fault diagnosis and the pertinence of process adjustment are improved, and the fault occurrence rate is reduced and the product quality is improved.

The invention discloses a multi-modal offshore wind power ultra-short-term prediction method in the field of offshore wind power plant cluster power prediction, and aims to solve the technical problems of spatial-temporal feature splitting and insufficient dynamic dependency relationship modeling. The method comprises the steps of performing anomaly detection and restoration on fan data, and generating a corrected wind power cluster data set; extracting a mean value, a standard deviation and a latest value of core operation data of each fan through a dynamic time window, and constructing a multi-dimensional node feature; a static geographic similarity matrix is generated based on geographic coordinates, a basic wake effect matrix is generated in combination with real-time wind direction data, correction is carried out through the maximum mutual information quantization time-delay effect, and then a dynamic adjacency matrix is obtained through self-adaptive fusion; and integrating the multi-dimensional node features and the dynamic adjacency matrix into a space-time diagram sequence data architecture, inputting the space-time diagram sequence data architecture into a multi-scale wake flow perception diagram space-time prediction model, and outputting a multi-fan power prediction value. According to the invention, high-precision multi-fan power prediction can be realized.

The invention relates to the technical field of temperature control, in particular to a mass concrete water cooling water temperature control method and system. The method comprises the following steps: collecting concrete key parameters through a multi-source sensor, constructing a microenvironment model based on information geometry, and generating a thermosensitive characteristic spectrum; forming a distributed thermodynamic model by utilizing a mutual information routing algorithm and heat-fluid-solid coupling analysis, and calculating an optimal cooling strategy; water flow path and flow optimization is realized in combination with fractional order particle swarm optimization; a pump set and a valve are adjusted through fuzzy self-adaptive control; and a potential instability region is identified through the spectrum energy gradient, and risk early warning is triggered. The precision and reliability of mass concrete cooling temperature control are remarkably improved, and intelligent, efficient and safe temperature control adjustment in the whole process is achieved.

The invention discloses a cross-modal heterogeneous data processing method and system. The method comprises the following steps: acquiring multi-source heterogeneous data including a vibration signal, a temperature signal, an oil spectral signal and the like, and forming a cross-modal alignment index sequence through event detection and time alignment processing; constructing a heterogeneous graph structure based on the aligned index sequence, and determining an edge weight according to correlation between modal fragments to obtain a cross-modal heterogeneous graph; performing representation decoupling on the heterogeneous graph, generating a cross-modal shared semantic subspace and a modal specific subspace, and reducing redundancy and noise interference through mutual information minimization constraint; establishing a prototype library, dynamically generating positive and negative sample pairs by adopting cross-modal contrast learning to enhance the discrimination ability, and obtaining an optimized cross-modal fusion result; and finally, outputting a diagnosis result including the fault type and severity, generating a diagnosis evidence track, and binding the key cross-modal fragment with the semantic centroid of the prototype library to realize interpretable traceability and self-correction of the result.

The invention discloses a networking intelligent key dynamic key management system supporting multi-device binding, particularly relates to the technical field of Internet of Things security, and is used for solving the problem that a cryptographic attack path is exposed due to key residue of an existing dynamic key management system. According to the system, an instruction analysis module receives an equipment unbinding instruction and extracts an equipment identifier; the residual positioning module marks residual nodes based on the identification deep search key tree; the fragment confusion module divides the key fragments into length non-geometric progression fragments and generates confusion fragments through elliptic curve encryption; the pollution evaluation module calculates a mutual information value of the confusion fragments and a parent key, and determines a hierarchical pollution coefficient in combination with a key entropy attenuation curve; the path decision module segments or recombines a key path according to a pollution coefficient threshold; and the key updating module constructs a new key tree, distributes updated sub-keys to the binding equipment, clears key residual relevance and blocks generation of a cryptographic attack path.

The invention discloses an intelligent data management system, and relates to the field of intelligent data management. The system comprises a data acquisition module for acquiring and preprocessing multi-source data and extracting field information; the decoupling analysis module is used for calculating a mutual information index and an information cementation degree according to the field information; the map generation module is used for constructing an attribute fusion map according to the field information and generating risk mapping skewness and a risk control map; the behavior analysis module is used for collecting action execution logs, extracting field behavior sequences and calculating field behavior interference factors; and the quality evaluation module is used for extracting a key field missing proportion and information entropy based on the field information to calculate an information completeness index, and fusing multiple indexes to generate a comprehensive quality score. Through graph structure construction, behavior sequence analysis and quality scoring fusion, the multi-source data field fusion accuracy and risk identification precision are improved, and intelligent assessment and compression abstract generation of high-quality data are realized.

The invention relates to the crossing field of hydraulic engineering hydrological monitoring technology and machine learning prediction technology, discloses a sediment concentration prediction method based on deep learning, and aims to solve the problems that in existing sediment concentration prediction, hyper-parameter manual tuning is low in efficiency, key feature attention is insufficient, local and time sequence information is difficult to consider by a single model and the like. Accurate prediction is realized through five core modules: a data preprocessing module performs missing value filling, abnormal value processing and derivative feature generation on hydrological data; the feature selection module screens key features based on mutual information; the time sequence construction module generates time sequence data through a sliding window; the hyper-parameter automatic optimization module adopts Bayesian optimization iteration to obtain an optimal hyper-parameter; the CNN-LSTM-attention prediction module fuses CNN local feature extraction, bidirectional LSTM time sequence dependence capture and multi-head self-attention mechanism key feature focusing capability, is suitable for scenes such as river channels and channels, and provides efficient decision support for hydrological regulation and control.

The invention discloses a multi-mode equipment maintenance and inspection knowledge intelligent recommendation system combined with digital twinning, and belongs to the technical field of equipment maintenance and inspection. The method is used for solving the technical problem that in an existing scheme, recommendation strategy staticizing and edge cloud collaborative global optimization are difficult to consider at the same time. According to the method, multi-modal data synchronous acquisition driven by digital twinning is carried out, a long-short-term memory network model of an attention mechanism is fused, a loss function is weighted through an attenuation rate deviation, strong correlation feature screening and dynamic weighting based on mutual information entropy are carried out, and a time-varying feature matrix is utilized to capture an evolution rule of an equipment state along with time; a knowledge graph with physical entity association precision and causal reasoning ability is constructed, and a three-layer architecture including full-link interpretability of data, features, entities, causals and decisions, edge-end high-frequency response-cloud global optimization-federated learning parameter synchronization is realized. The contradiction between high-frequency data real-time processing requirements and global knowledge graph dependence in industrial equipment maintenance can be solved.

The invention discloses a farmland precise fertilization control method based on multi-source data fusion and deep learning, and the method comprises the steps: obtaining the multi-dimensional heterogeneous data of a target farmland in real time, including the crop spectrum time series data of a satellite image, the ion concentration data collected by a soil sensor network, and the microenvironment time series monitored by a meteorological station; and constructing a Delaune triangulation network spatial index, and re-sampling satellite image data to be matched with a soil sensor network space. Calculating a time-varying mutual information entropy, extracting related microenvironment parameters as coupling factors, combining the coupling factors with soil basic parameters to form a three-dimensional feature matrix, and converting the three-dimensional feature matrix into a growth period feature vector fused with time-space correlation; the collaborative decision model is input, the main branch predicts the basic fertilization amount, the auxiliary branch detects the ion concentration space mutation area and corrects the fertilization amount, a fertilization control instruction is output, and the fertilization device is controlled to conduct precise fertilization. The problem that fertilization control cannot be accurately and efficiently performed on farmland in the prior art is effectively solved.

The invention discloses a power transmission line icing intelligent early warning method, system and device and a medium, and the method comprises the steps: obtaining icing state data and meteorological data, and dynamically adjusting the collection frequency and a dormancy strategy; performing data preprocessing and cleaning on the acquired data; extracting time-frequency features through wavelet packet transformation and a self-attention mechanism, and fusing the spatial dependency relationship and cross-modal interaction information of multiple monitoring points by using a graph neural network to obtain enhanced icing state characterization; performing icing risk prediction by adopting a gradient boosting decision tree model to obtain an icing risk prediction result; and analyzing an icing risk prediction result by using an interpretable tool, identifying a key factor which has the greatest influence on icing risk prediction, dynamically adjusting an early warning level according to the key factor, and generating an early warning and maintenance suggestion. Therefore, the monitoring real-time performance and the early warning timeliness are improved.

The invention relates to the technical field of computer vision, in particular to a high-rise facility operation risk monitoring method based on deep learning and point cloud detection, and the method comprises the steps: collecting a three-dimensional point cloud in real time, and extracting a target point cloud through dynamic threshold denoising and template registration; performing joint coding on space geometry and time sequence motion by using a pre-trained space-time diagram network in combination with an attention mechanism; high-reflectivity beacon points are identified, and the change rate of displacement and angular velocity is calculated; constructing a gating fusion model, dynamically weighting and coupling semantic features and measurement data, and generating risk probability distribution through mutual information consistency check; a fuzzy logic classifier with membership degree optimization is used for mapping to four-level early warning, and grading response is triggered; after early warning, a key frame incremental learning fine tuning model is extracted, and preprocessing parameters are reversely optimized to form a closed loop. According to the method, through multi-source heterogeneous data fusion, dynamic adaptive weighting and a self-evolution mechanism, the real-time performance, accuracy and robustness of risk monitoring in a complex construction environment are remarkably improved.

The invention discloses a target multi-attribute identification method based on feature decoupling and cross-task collaboration, and belongs to the technical field of computers of specific calculation models, and the method comprises the following steps: firstly, extracting the initial features of each task through a lightweight backbone network, carrying out feature decoupling in a subspace, and according to the cross-task feature similarity, carrying out feature extraction; according to the target multi-attribute identification method based on feature decoupling and cross-task collaboration, an orthogonal constraint weight is dynamically adjusted, then mutual information confrontation minimization is adopted to further suppress statistical dependence between tasks, task residual errors are injected in a cross-task feature aggregation stage, differentiation enhancement is achieved, and finally unified joint feature representation is formed. According to the method, subspace statistical independence is realized, independence and necessary collaborative information are considered, a stable basis is provided for subsequent fusion, statistical dependence between tasks is further suppressed through mutual information confrontation minimization, complementation information is reserved while independence is ensured, and feature discrimination and robustness are improved.

The invention discloses a data security risk assessment method based on a big data model, and relates to the technical field of data security, and the method comprises the steps: collecting and preprocessing multi-source data, collecting security-related data from network equipment, a server and an application system, carrying out the preprocessing, carrying out the adaptive feature extraction, and carrying out the data security risk assessment. The feature importance is evaluated by calculating the mutual information amount of features and risk tags, a standardized feature vector set is constructed, multi-model collaborative analysis is performed, feature vectors are input into a cascade collaborative network composed of an anomaly detection model, a threat recognition model, a correlation analysis model and a prediction model, and a risk risk is obtained. Through cross-model feature transmission and a bidirectional information feedback mechanism, deep collaborative analysis and multi-model deep fusion decision making are carried out, a weight is calculated according to historical accuracy of each model, a comprehensive risk score is calculated by adopting dynamic gating deep fusion, and a dynamic threshold value is calculated based on a sliding time window. And the risk is divided into three levels of high risk, medium risk and low risk.

The invention discloses a remote sensing image multi-source heterogeneous data fusion processing method and system, and the method comprises the steps: extracting global information from remote sensing image data through employing a convolutional neural network, extracting image local features through cutting operation, and capturing local feature information in the remote sensing image data; constructing a cross-time-domain attention mechanism for the local feature information through a cyclic matrix to extract mutual information among different modal variables, and screening highly-associated cross-time-domain key information; establishing a cross-time-domain sensing hierarchical aggregation module for the cross-time-domain key information, and obtaining detail information and edge information of the remote sensing image; acquiring global fusion data by adopting an asymptotic fusion strategy, and introducing a loss function to reduce a semantic gap; according to the method, missing information is repaired by adopting an interactive network model of mixed contrast learning, complete real-time remote sensing image multi-source heterogeneous fusion data is obtained, and efficient and high-precision fusion processing of the multi-source remote sensing data is realized by constructing a multi-collaborative deep fusion framework.

The invention discloses an anti-illusion training method and device for a multi-modal model, equipment and a medium, and the method comprises the steps: firstly introducing a time delay mutual information causal discovery algorithm in a data preprocessing stage, and building a cross-modal causal atlas between modal data; and dynamically adjusting the fusion weight of each modal data according to the dynamic gating mechanism of the second stage and the causal relationship between the modal data corresponding to the cross-modal causal atlas so as to solve the cross-modal conflict resolution capability and solve the problem of data fusion distortion caused by traditional static weight distribution. And on the basis of the causal relationship between the modal data corresponding to the cross-modal causal atlas, constructing an adversarial multi-modal sample on the basis of the original multi-modal data, and carrying out constrained adversarial training on the multi-modal model on the basis of causal regularization to obtain an anti-illusion multi-modal model, so that the reasoning precision of the multi-modal model is improved. The method can be applied to the financial risk prediction field and the medical diagnosis field so as to improve the risk prediction accuracy and the diagnosis accuracy.

The invention discloses a neural network-driven battery acoustic pressure monitoring and early warning method and system, and aims to realize omnibearing analysis and fault early warning of battery pressure signals by constructing a multi-stage deep learning framework. According to the method, a neural network coding technology is adopted, and causal features of pressure data are extracted through reverse time evolution and chaotic attractor projection; identifying a pressure periodic rhythm by using a time convolutional network, establishing a rhythm reference model and generating an abnormal index; a mutual information resonance mechanism is introduced, and the information correlation degree between data is determined through phase slip analysis; a structured feature map is generated through variational echo reconstruction, and the evolutionary process of the features is captured through a diffusion model; predicting a phase change critical point based on a reformed group theory, converting early warning parameters into an oscillator network, and analyzing synchronization characteristics; and finally, graded early warning is realized through singular value decomposition and activation intensity calculation, so that early abnormal symptoms of the battery can be accurately identified, and reliable technical support is provided for safety management of the battery.

Provided is a day-ahead electricity price prediction method based on a parallel multi-dimensional attention mechanism, which method belongs to the technical field of day-ahead electricity price prediction in a power market. The maximum mutual information coefficient is used to select variables having a certain relevance with an electricity price, so as to assist in predicting future electricity price data; next, a decomposition algorithm is used to decompose an original electricity price signal; and then, electricity price sub-components obtained by means of decomposition and the electricity-price-related variables are inputted into an MBI-IPMDA-PBISA deep learning model, so as to predict a future electricity price. In this way, an MBI-IPMDA-PBISA deep learning model can fully learn a complex association relationship between electricity price sub-components and electricity-price-related variables and a future electricity price, the problem of error superimposition caused by separately predicting the electricity price sub-components and then superimposing same to obtain the future electricity price is also avoided, and the problem of the accuracy of existing attention mechanisms during prediction being low is solved, thereby improving the prediction accuracy.