472 results about "Temporal correlation" patented technology

The invention belongs to the technical field of earthquake disaster scene recognition, and discloses an earthquake disaster scene recognition method based on deep learning. The method comprises the following specific steps: S1, data acquisition and preprocessing; S1.1, multi-source heterogeneous data acquisition and establishment of a comprehensive database containing seismic waveform data, surface deformation data, building structure data, geographic information data and historical disaster record data; through fusion of a 3D convolutional network, a graph attention mechanism, a space-time LSTM and an adaptive cross-modal attention fusion technology, combined modeling of a seismic waveform space-time evolution law, an earth surface deformation space distribution characteristic, a building group topology vulnerability and disaster chain time sequence association is realized, the characterization capability of a complex nonlinear disaster mode is effectively improved, and the method has the advantages of high adaptability and high reliability. And disaster assessment response time is shortened to a sub-second level through mixed precision quantification and edge computing deployment, and high recognition accuracy is still kept in a scene with strong noise and data missing in combination with a multi-task classifier and a physical constraint verification mechanism.

A system and method for multi-scale temporal attention processing in multimodal technology deep learning systems. This system processes time-series, textual, sentiment, and structured tabular data across three hierarchically-organized temporal streams—quarterly, weekly, and intraday levels—with bidirectional cross-temporal information flow. Scale-specific attention mechanisms are optimized for respective temporal granularities, while an adaptive controller dynamically weights each temporal level based on real-time market volatility indicators. A multi-scale fusion processor integrates attention-weighted representations to generate temporally unified representations preserving both short-term market dynamics and long-term trends. This approach enables superior forecasting and risk assessment by leveraging temporal correlations across multiple time scales while automatically adapting to changing market conditions. The system facilitates interpretable AI analysis through attention visualization and enables synthetic scenario generation for model testing.

This invention relates to a gait emotion recognition method, system, storage medium, and computer device based on spatiotemporal graph convolution. The method includes the following steps: S1, data augmentation by reversing the temporal direction of gait; S2, obtaining deep emotion features and prior emotion features respectively through a spatiotemporal graph convolutional network and prior feature statistical methods; S3, performing nonlinear mapping on the prior emotion features using a feature mapping layer; S4, inputting the fused features of the deep emotion features and prior emotion features into an emotion classifier to obtain the emotion category. The feature mapping layer of this invention achieves more effective feature fusion by performing nonlinear mapping on prior features; it also introduces causal temporal convolution to replace general temporal convolution, effectively extracting fine-grained temporal features by enhancing temporal correlation and cross-period feature fusion. Furthermore, a walking direction recognition auxiliary task is designed to accelerate the training and convergence speed of the model, enhancing the ability to extract temporal-dependent features and the performance of emotion recognition.

The invention provides a color steel plate coating thickness dynamic monitoring method and system based on artificial intelligence. According to the method, the temperature distribution data of the surface of the color steel plate coating is obtained, the thermal response map is generated in a pulsed eddy current excitation mode, then the temperature distribution data and the thermal response map are subjected to time sequence correlation processing, the heat conduction characteristics are extracted, and then the heat conduction characteristics are synchronously analyzed; color steel plate coating defect types and thickness abnormal grades are distinguished through a dynamic weight distribution mechanism, a detection result containing defect positions, sizes and thickness deviation values is generated, and finally a coating thickness dynamic compensation instruction is generated according to the detection result; according to the technical scheme provided by the invention, the online control precision and the production efficiency of the coating quality are remarkably improved, and a closed-loop feedback system from detection to control is formed.

The embodiment of the invention discloses a park load prediction method and device based on multi-modal data and a medium, and relates to the technical field of micro-grids, and the method comprises the steps: collecting multi-modal micro-grid data through a multi-source heterogeneous sensor network disposed at a power distribution node, the multi-mode micro-grid data comprises electrical measurement data, environment monitoring data and equipment state data; constructing a dynamic space-time incidence matrix according to the multi-modal micro-grid data, and performing feature extraction based on the dynamic space-time incidence matrix through a space-time diagram convolutional network deployed at an edge calculation node to determine a space-time feature vector; and inputting the spatio-temporal feature vector into a time sequence fusion prediction model, outputting a load prediction result, and generating an optical storage cooperative scheduling instruction according to the load prediction result, the load prediction result including a load prediction value and a confidence interval.

The invention relates to the technical field of data processing, and discloses a comprehensive evaluation method and system for the health degree of a distribution network cable. The method comprises the following steps: collecting cable joint multi-source monitoring signals, normalizing the monitoring signals to obtain a degradation degree feature vector, correcting multi-physics field coupling model parameters, obtaining a recessive degradation index through finite element calculation to obtain an enhanced feature vector, and performing time-frequency domain decomposition to extract multi-scale feature parameters to obtain a comprehensive feature matrix; a double attention mechanism calculates a feature weight and a time sequence correlation degree to obtain a deterioration trend prediction value, and fuzzy integral is fused with a multi-classifier output probability to obtain a health degree evaluation grade and an early warning result. According to the invention, the early defect identification accuracy and the degradation trend prediction precision are improved.

The invention provides a user behavior data mining method and system applied to digital enterprise management, and the method comprises the steps: collecting the multi-dimensional behavior data of a target user in a business operation interface, carrying out the multi-modal data analysis of the multi-dimensional behavior data, generating a behavior track feature set with time sequence relevance, and carrying out the mining of the behavior track feature set; training an adaptive time sequence analysis model based on the behavior trajectory feature set, capturing a long and short term dependency relationship in a user behavior mode by the time sequence analysis model through a dynamic window division strategy, generating a potential loss risk prediction index, and constructing an interaction process parameter matrix according to the potential loss risk prediction index; and calling the optimized interaction process parameter matrix to drive a service operation interface to reconstruct, generating an interaction interface adaptive to the current user behavior mode, and iteratively updating the time sequence analysis model through an incremental feedback mechanism in a preset verification period. According to the invention, the comprehensiveness and accuracy of user behavior pattern mining can be improved.

The invention relates to a hydrological flow prediction method and system based on multi-site time-space association. The prediction method comprises the following steps: carrying out dimension reduction and feature reconstruction on original multi-site hydrological data through an auto-encoder; space-time correlation modeling and adjacency matrix dynamic construction are carried out, a multi-dimensional Euclidean distance matrix between stations is calculated based on a multivariable dynamic time warping (MDTW) algorithm, a similarity matrix is generated in combination with dynamic programming, and a dynamic adjacency matrix is constructed by fusing a geographic space adjacency relation; extracting spatial features of a GCN (Graphics Convolutional Network); carrying out adaptive time sequence decomposition and trend-period modeling; and carrying out multi-stage fusion prediction and result output, and generating a final prediction result through a decoder in combination with the decomposed trend item and periodic item. According to the method, accurate extraction and dynamic correlation modeling of spatial-temporal characteristics of multi-site hydrological data are realized, the accuracy and robustness of single-site flow prediction are improved, and the problems that multi-site spatial-temporal correlation modeling is insufficient, non-linear time sequence alignment is difficult, and single-site prediction precision is limited are solved.

The invention relates to the technical field of data acquisition and processing, and provides a real-time data acquisition and processing method and system for a distributed control system, and the method comprises the steps: collecting a data flow in real time through a terminal sensor, analyzing the probability distribution of a data change rate through a sliding window, and obtaining a data change rate; and a sensitivity threshold is intelligently generated by combining dynamic factors such as equipment electric quantity and network load. When data mutation exceeds a threshold value, the system automatically extracts a key change section and generates time, period and variable quantity three-dimensional features, and meanwhile, the frequency domain analysis result is fused to enhance the anti-interference performance. And the event emergency degree is calculated based on the time-space correlation of the spectrum energy entropy and the characteristic parameters, and finally a processing queue sorted according to priorities is formed and the bandwidth is dynamically allocated. According to the method, through multi-dimensional data fusion and resource adaptive adjustment, the response speed of the system to emergencies, the data discrimination precision and the stability in a complex environment are improved.

The invention provides a big-data-combined bus system full-data comprehensive management analysis method and system, and the method comprises the steps: collecting a real-time operation data set uploaded by a plurality of bus terminals in a target region, carrying out the multi-dimensional feature extraction, generating a bus operation feature set, carrying out the abnormality recognition based on a preset abnormality detection model, and obtaining a bus operation feature set; determining an abnormal operation event set; performing time-space association mapping on the bus operation feature set and the historical operation data set, constructing a bus operation knowledge graph, performing dynamic path planning and resource allocation analysis on the graph, generating a target scheduling strategy set, and performing priority adjustment on the abnormal operation event set based on the target scheduling strategy set. Generating a bus scheduling optimization instruction set and issuing the bus scheduling optimization instruction set to a corresponding bus terminal; and updating a weight parameter and a historical operation data set of the multi-task optimization model based on the execution feedback data. According to the method, multi-source real-time data can be integrated, and a scheduling strategy is dynamically optimized, so that the problems of data islands and strategy stiffness are solved.

The invention discloses a multi-modal content understanding method and system based on a knowledge graph, and belongs to the technical field of multi-modal content understanding, the method comprises the steps of obtaining multi-modal input data and conducting feature decoupling, semantic information in the multi-modal data and noise and redundant information peculiar to modals can be effectively separated through the feature decoupling technology, and the multi-modal content understanding efficiency is improved. The method comprises the following steps of: establishing a space-time perception graph attention network, improving the purity and semantic expression capability of features, bridging semantic gaps among different modals through the space-time perception graph attention network, realizing cross-modal semantic alignment, enhancing the generalization capability of a model, deeply mining space-time modes, relationships and anomalies in data through space-time association reasoning, and improving the accuracy of the data. The method provides support for multi-modal data analysis in a complex scene, and combines a graph neural network and a recurrent neural network to capture semantic association and spatial-temporal dynamics and optimize the performance of an inference model.

A predictive incident management system, consisting of: a sensor input module configured to receive heterogeneous telemetry data streams from mechanical, thermal, electrical and cyber sources; a temporal correlation control unit operationally coupled to the sensor input module, wherein the temporal correlation control unit is configured to normalize received data into a uniform time series envelope that includes identifiers, microsecond-precision timestamps, metric names, values, and context markers, and is further configured to compute sliding window-cross-sensor correlation matrices, event motifs, and lead-lag dependencies across multiple time granularities; a scalable rule processor that is communicatively linked to the control unit for temporal correlation, wherein the rule engine includes an in-memory runtime environment for processing complex events and a domain-specific declarative language, and is configured to apply rules that reference primitive sensor metrics, derived correlation features, and motive-based early warning vectors to classify, escalate, or resolve predicted incidents; A historical repository that is communicatively connected to both the temporal correlation control unit and the rule engine. The repository is configured to store tagged event histories, correlation motif dictionaries, rule versions, and rule origin metadata to ensure the verifiability and explainability of predictions; and An incident response interface is operationally connected to the rule engine. The incident response interface is configured to trigger automated workflows, including the generation of tickets for IT service management, chat ops notifications, the execution of orchestration playbooks, and direct machine control via industrial protocols. the system is configured to perform predictive analyses based on temporal correlations between sensors and to execute context-aware, rule-based incident management in real time.

The invention provides a three-dimensional simulation and infection scene decision optimization system and method based on digital twinning, and relates to the technical field of intelligent medical treatment and digital twinning crossing technologies. The three-dimensional simulation and infection scene decision optimization system and method based on digital twinborn comprises the following modules: a data acquisition module, a path optimization module, a risk analysis module, a disinfection scheduling module and a collaborative prevention and control module, by arranging an air microorganism sampler, ultra-wideband positioning equipment and a temperature and humidity sensor, pathogen concentration, personnel trajectory and environmental parameters are collected in real time. Through a multi-source sensor fusion algorithm and a space-time attention mechanism, weight fusion and noise filtering are carried out on pathogen concentration, personnel tracks and environmental parameters in a hospital environment, the problems of information isolation and noise interference in traditional data collection are solved, and the space-time relevance of multi-modal data is remarkably enhanced.

The invention relates to the technical field of power system measurement, and discloses a current transformer error dynamic monitoring method and system.The current transformer error dynamic monitoring method comprises the steps that current transformer time sequence data and a system event log are obtained; constructing a time sequence causal graph to represent the time correlation between the event and the error change; identifying potential causal links by applying a counter causal model; designing a multi-world simulation engine to generate an anti-fact scene; quantifying a causal effect by comparing actual observation with an anti-fact simulation result; establishing a monitoring mechanism to track key trigger events in real time; generating a dynamic causal interpretation report and adjusting a compensation strategy; according to the method, the limitation of traditional correlation analysis is broken through, the causal relationship and the correlation can be accurately distinguished, the real triggering factor of the error change of the current transformer can be accurately identified, the false alarm rate and the missing report rate are reduced, and the accurate dynamic monitoring of the error of the current transformer is realized.

The invention relates to the technical field of compartment remnant real-time detection systems, and discloses a real-time visual identification and detection system for remnant in a compartment of a subway last station. In the system, an image acquisition module acquires a monitoring video stream and generates a carriage image sequence set; the feature extraction module processes the image to obtain a time sequence association partition labeling set; the time sequence association module analyzes the time sequence stable section image frame and generates a feature matching overlay analysis result; the abnormity judgment module identifies abnormal points to form a remnant abnormal point set; and the risk output module is used for marking the point locations with the left risks and generating a real-time detection and risk early warning result. The system can adapt to the dynamic environment of subway carriages, the efficiency and accuracy of remnant detection are improved, and real-time identification and risk early warning are achieved.

The invention provides a vibration signal space-time reconstruction method based on a multi-modal condition diffusion model, and relates to the technical field of vibration signal reconstruction, and the method comprises the steps: firstly collecting structure vibration response through multiple sensors, constructing a multi-dimensional vibration signal matrix, and automatically recognizing a space continuous missing region and a time random missing region; performing coarse reconstruction on the missing region by adopting self-adaptive multi-scale interpolation so as to recover the basic trend and frequency band characteristics of the signal; a pseudo-missing mask is further applied to complete data, a training sample is constructed through a self-supervision strategy, and the model is guided to learn spatio-temporal correlation features and missing modes; in a training stage, a diffusion model is used as a generation framework, Gaussian noise disturbance is applied to a missing region, four types of condition embedding of time, space, trend and frequency domain are introduced in a denoising inversion process, signal periodicity, multi-sensor space coupling, low-frequency change and a physical frequency spectrum structure are respectively described, and the noise is reduced; and high-fidelity signal reconstruction under multi-modal information joint constraint is realized.

The invention discloses an artificial intelligence abnormity early warning diagnosis method for industrial equipment operation state monitoring, and belongs to the technical field of industrial equipment intelligent monitoring, and the method comprises the steps: collecting a multi-source heterogeneous signal of industrial equipment, and carrying out the time-frequency dual-domain feature extraction; constructing a multi-scale time window based on the time-frequency features, and executing self-supervised contrast learning by injecting a preset abnormal mode to obtain cross-scale contrast feature representation; constructing a dynamic adjacency matrix according to the comparison features, extracting space-time correlation features through a graph attention network, and determining an abnormal score based on joint evaluation; according to the method, a deep coupling closed-loop cooperative system is formed, multi-dimensional state characterization, adaptive anomaly detection and root cause diagnosis are realized, and the problems of single data source and lack of fault analysis capability in the prior art are effectively solved.

Systems and methods disclosed herein are enabled to dynamically generate structured documents using one or more artificial intelligence models. A computing device receives an output generation request and uses a first AI model to retrieve data chunks from source documents and applicable templates. A second AI model ranks the retrieved chunks based on one or more metrics, such as vector similarity, keyword density, and temporal relevance. A third AI model subsequently generates a response using the ranked chunks, templates, and predefined operational boundaries for each chunk. The generated response is tagged with source identifiers to enable the traceability of the response back to corresponding chunks. The system transmits, via the computing device, the response, the retrieved chunks, and / or the source identifiers.

The invention discloses a machine room monitoring method and system based on a multi-source data fusion intelligent inspection robot, and belongs to the technical field of machine room automatic monitoring, and the method comprises the steps: applying adversarial transfer learning on a four-dimensional fault semantic feature field, and generating a cross-modal causal atlas representing a fault evolution path through a graph neural network; according to the method, a loss function is combined to align feature distribution of a standard machine room and a current machine room, a gradient inversion layer is utilized to force feature distribution alignment of a source domain and a target domain, meanwhile, an attention mechanism and a causal strength weight are combined to generate a cross-modal causal atlas, and a graph neural network further models physical connection, functional dependence and time sequence association between nodes, so that the cross-modal causal atlas is obtained. A causal relationship is coded into an edge weight, noise correlation is filtered through a causal mask, the stability of the causal atlas is improved, and the cross-modal causal atlas can accurately capture a fault propagation path.

The invention belongs to the technical field of tunnel engineering, and provides a multi-physics field real-time assimilation simulation and regulation method and system in a tunnel grouting process in order to solve the problem that real-time dynamic simulation and automatic regulation are lacked in existing tunnel construction, and the real-time assimilation simulation and regulation method and system in the tunnel grouting process are provided by utilizing ensemble Kalman filtering and combining real-time monitoring data in the tunnel grouting process. Dynamically correcting parameters of the multi-physical model; time correlation in the slurry condensation process is considered, a time-varying condensation model depicting physical property changes of slurry evolving along with time is integrated, the time-varying condensation model serves as an external function in the time step length to be embedded into the multi-physical field model in correction, and the slurry flowing state is adjusted in a self-adaptive mode through numerical simulation; and generating control parameters of tunnel grouting according to a dynamic simulation result, and realizing closed-loop regulation and control of tunnel grouting. Synchronous linkage of numerical simulation and on-site working conditions is realized.

The invention provides a signal blind separation and intelligent reconstruction method and system in a complex scene, and relates to the technical field of signal processing, and the method comprises the steps: receiving an aliasing signal, and converting the aliasing signal into a multi-channel signal observation matrix; performing decomposition in a wavelet domain to obtain a wavelet coefficient, matching the wavelet coefficient with the sparse dictionary, and reconstructing a target signal source after optimization; estimating the number of signal sources based on covariance matrix eigenvalue distribution; mapping a signal source to a graph structure domain, extracting space and time sequence correlation through a mixed graph convolutional network, and obtaining a target separation signal through variational reasoning optimization; and finally, carrying out quality evaluation and post-processing to obtain a final reconstruction signal. According to the invention, the signal separation precision and robustness in a complex scene are improved.

The invention relates to a bridge modal parameter automatic identification method and system considering multi-channel information, and the method comprises the following steps: S1, directly analyzing a multi-channel monitoring signal through COV-SSI, generating a stability diagram, and automatically extracting a stability axis in combination with a DBSCAN clustering algorithm, thereby achieving the automatic identification of a modal frequency; s2, performing signal decomposition on the multi-channel monitoring data by adopting MvFIF to generate an intrinsic mode function (IMF) group with a mode alignment characteristic; s3, the instantaneous frequency and bandwidth of the IMF in the step S2 are calculated through HHT, IMF components containing target modal frequency are screened out, and linear reconstruction is carried out; s4, taking the multi-channel monitoring data reconstructed in the step S3 as system input of a COV-SSI algorithm, calculating a system matrix and an output matrix, and calculating a modal damping ratio by utilizing eigenvalue decomposition; according to the method, the spatial-temporal correlation among multi-channel data can be considered, and synchronous decomposition of multi-channel monitoring data is realized; and automatic and accurate identification of the structural modal parameters under different noise levels can be realized.

The invention provides a multi-modal collaborative delivery scheduling method, which comprises the following steps of: constructing a dynamic environment model according to topographic data and traffic condition data, extracting delivery demand characteristics from real-time order information, and splitting a complex order into a plurality of sub-task units by adopting a task decomposition technology to obtain a decomposed sub-task set; extracting sub-task features of adjacent areas and similar time windows from the optimized sub-task sequence, performing clustering analysis on the sub-tasks by adopting an intelligent combination technology, determining space-time relevance among the sub-tasks, and generating a preliminary sub-task aggregation group; and calculating the path cost and the time cost of each delivery batch according to the final resource allocation scheme and the sub-task aggregation grouping, and carrying out optimization iteration on the batch path by adopting a genetic algorithm to obtain a time table and a route plan of the efficient delivery batch.

The invention relates to a numerical control machining dynamic error compensation method and system based on a space-time attention mechanism, and the method comprises the steps: synchronously collecting multi-source signals through a 9-axis MEMS vibration sensor, an infrared thermal imager and an acoustic emission sensor which are disposed at key parts of a machine tool, and constructing a space-time feature tensor fusing vibration energy, temperature gradient and acoustic emission features; inputting the tensor into a space-time attention network, extracting space correlation characteristics by using a graph convolution network, capturing time sequence correlation in combination with causal convolution, and generating a coupling weight matrix of thermal deformation, vibration and tool deflection; and the compensation amount is dynamically calculated based on a multi-physics field coupling formula, three-axis linkage compensation instruction generation is completed within 5ms through an FPGA hardware accelerator, and closed-loop writing is performed in a CNC system. The system comprises a multi-source sensing module, an edge computing unit and a cloud platform. According to the method, submicron real-time error compensation is achieved, the vibration suppression rate is 65%, and the machining efficiency is effectively improved.

The invention discloses a multi-source heterogeneous anomaly detection method based on time correlation, and belongs to the technical field of water diversion engineering, and the method comprises the steps: S1, obtaining multi-source sensor time sequence data in multi-source heterogeneous data, carrying out the preprocessing of the multi-source sensor time sequence data, and dividing a training set and a test set; s2, constructing a double-branch depth feature extraction network model, training by adopting the training set, and testing through the test set to obtain a trained double-branch depth feature extraction network model; the double-branch depth feature extraction network model comprises a double-branch unit, an attention feature fusion unit, a classifier unit and an output layer unit which are connected in sequence; and S3, inputting to-be-detected data into the trained double-branch depth feature extraction network model, and finally outputting an anomaly diagnosis result. A double-branch depth feature extraction network is constructed, adaptive fusion is realized through an attention mechanism, and the problem of poor modal adaptability of heterogeneous data is solved.

The invention discloses a motor bearing remaining service life prediction method and system using health indexes, and belongs to the technical field of automation. According to the method, time domain, frequency domain and time-frequency domain characteristic extraction is carried out on a vibration signal sequence, and sensitive characteristics of a degradation process can be accurately reflected through monotonicity and time correlation screening. And performing principal component analysis and dimension reduction on the screened features, and selecting the maximum principal component as a health index. And calculating an initial degradation point of the health index and dividing the data set. When residual service life prediction is carried out, an input signal is decomposed into a trend part and a residual error part, different models are used for feature extraction, and finally a residual service life prediction result is output. Through the steps of health index construction, signal decomposition, feature extraction, residual service life prediction and the like, the degradation stage can be accurately divided, meanwhile, accurate feature extraction and service life prediction can be carried out on data of the degradation stage, and the service life prediction accuracy is improved.

The invention relates to the technical field of hydraulic engineering monitoring, and discloses a hydraulic engineering intelligent monitoring system and method. The method comprises the following steps: acquiring multi-source monitoring data such as a water level fluctuation sequence, a flow velocity change sequence and a gate opening change sequence of a water conservancy project monitoring point; spatial-temporal feature extraction processing is carried out on the multi-source monitoring data, and a hydraulic engineering operation state feature matrix containing spatial-temporal correlation data of water level fluctuation features, flow velocity change features and gate opening change features is generated; inputting the feature matrix into an anomaly detection model, and generating a water conservancy project abnormal operation state identifier containing anomaly type, anomaly level and anomaly position information; and finally, based on the abnormal operation state identifier, generating a water conservancy project regulation and control instruction set comprising a water level regulation scheme, a flow speed control scheme and a gate opening degree regulation scheme. According to the method, the engineering operation state can be comprehensively monitored, the abnormity can be accurately identified, the regulation and control scheme can be rapidly generated, and the intelligence and efficiency of hydraulic engineering monitoring can be improved.