35370 results about "Feature extraction" patented technology

An AI-based Cybersecurity System and Method enable real-time detection, analysis, and mitigation of cyber threats within computing networks using adaptive artificial intelligence. The system continuously monitors network traffic, extracts behavioral and contextual attributes, and applies deep learning-based inference to identify anomalous activities indicating security breaches. The method integrates several computational units, including a network monitoring unit, feature extraction unit, artificial intelligence processor, contextual reasoning processor, and decision synthesis unit, to compute a composite risk index quantifying threat likelihood and severity. A classification processor categorizes detected threats into types such as ransomware, phishing, or unauthorized access, while a mitigation control processor initiates automated response actions to isolate compromised nodes and restore network integrity. An adaptive learning processor updates AI models using feedback from confirmed incidents. This provides a scalable, self-evolving cybersecurity framework that minimizes human intervention and enhances resilience against dynamic and zero-day threats.

Systems and methods are disclosed for classifying objects using electro-optical and synthetic aperture radar images through multi-modal feature alignment and fusion. A computing system acquires and preprocesses image data, then aligns features across modalities using a multi-modal alignment engine. A cross-modal attention fusion network extracts and integrates complementary information using transformer-based attention mechanisms. A modality-specific feature extraction framework processes EO and SAR images through specialized branches, ensuring optimal feature representation. An adaptive fusion decision system dynamically determines the best fusion strategy based on image quality and confidence scores. A self-supervised consistency controller enforces alignment between EO and SAR features using contrastive learning. The fused representations are processed by a neural network to generate object classifications. This system improves accuracy and robustness in environments where one modality may be degraded or missing, enhancing applications such as remote sensing, surveillance, and autonomous navigation.

A computing system for adaptive electronic message classification employs a multi-agent architecture comprising a media feature analysis system, a user context refinement system, and a response synthesis system. The media feature analysis system generates pillar scores including message type, intent, and link risk scores with associated confidence values using trained classification models. When pillar scores and confidence values do not satisfy predetermined threshold conditions, the user context refinement system dynamically constructs contextual prompts using the pillar scores and confidence values as input parameters. User responses generate score modification data that refines the pillar scores and contextual response data for recommendation generation. The response synthesis system generates refined classifications and personalized recommendations using the refined pillar scores and contextual response data. An orchestration system coordinates agent interactions using learned uncertainty points and implements asymmetric influence algorithms with variable weighting based on content and URL analysis concordance.

The invention belongs to the technical field of bridge monitoring, and relates to a system and a method for fusing multi-source data of a bridge structure. Comprising a heterogeneous topological graph construction and manifold embedding technology module, a multi-scale space-time cognitive convolutional neural network module, a continuous manifold space-time alignment and Bayesian fusion module and a structure health index calculation and state evaluation module. The heterogeneous topological graph construction and manifold embedding technology module is used for obtaining a heterogeneous topological graph, a node embedding vector and a manifold model parameter; the multi-scale space-time cognitive convolutional neural network module is used for performing deep feature extraction on the heterogeneous topological graph to obtain multi-scale fusion features; the continuous manifold space-time alignment and Bayesian fusion module is used for obtaining space-time alignment parameters and fusion state vectors; the structure health index calculation and state evaluation module is used for carrying out structure health monitoring and state evaluation on the bridge to obtain a final health evaluation result; therefore, the intelligence, automation and reliability levels of the structure monitoring system are improved.

The invention relates to the technical field of bearing fault detection, and discloses a bearing fault detection method and system based on a health state index. The method comprises the following steps: collecting multi-source sensing signals at least comprising a vibration signal, a temperature signal and an acoustic signal during bearing operation; respectively performing time domain feature extraction and frequency domain feature extraction on the multi-source sensing signals, and performing normalized fusion on the extracted time domain features and frequency domain features to generate a multi-dimensional health state index sequence; constructing a long-short-term memory network model based on an attention mechanism, inputting the multi-dimensional health state index sequence into the model for training, and outputting a bearing health state prediction sequence; and calculating a dynamic early warning threshold according to the historical health state prediction sequence, comparing the current prediction value with the dynamic early warning threshold in real time, and generating a fault early warning signal. The method can improve the accuracy of bearing health state evaluation and fault early warning, and is suitable for complex operation conditions.

The invention relates to the technical field of intelligent power grids, in particular to a power distribution network battery digital dynamic management system based on digital twinning. Comprising a data acquisition unit; the digital twinborn modeling unit is used for constructing a battery-power grid-environment multi-dimensional dynamic twinborn body and realizing virtual-real bidirectional mapping and adaptive updating by combining a multi-physics field coupling model and a long-short-term memory network time sequence prediction algorithm; a dynamic optimization unit; and executing the feedback unit. Through a distributed heterogeneous sensing network of a data acquisition unit, multi-dimensional operation data of a battery pack and a key node of a power distribution network are acquired, and a high-fidelity data set containing four-dimensional labels of a battery state, a power grid parameter, time and a position is generated in combination with a spatial-temporal feature extraction technology; the deep fusion of the full life cycle state of the battery and the global operation data of the power distribution network is realized, and the comprehensive data support covering the global is provided for the optimization decision.

Disclosed in the present invention is an improved deep learning model-based refrigeration unit fault detection method. The method uses an LOF algorithm to remove outliers from a fault dataset, and then uses ADASYN technology to solve the problem of data imbalance. In addition, in respect of the problems that existing refrigeration unit fault diagnosis deep learning models are prone to network degradation, and refrigeration unit fault diagnosis models generally lack weighting critical features, the present invention first alleviate, on the basis of ResNet, the problem of network performance degradation which is prone to occur in deep neural network training processes, and then integrates a CBAM for capturing critical features in fault data, so as to improve the feature extraction capability of a network. Experimental results show that the LOF-ADASYN-ResNet-CBAM method provided by the present invention effectively diagnoses refrigeration unit faults.

A multimodal intelligent agent system for dynamic environmental monitoring and user-centered support, consisting of: a multimodal sensor module configured to continuously acquire environmental and behavioral data from multiple input modalities, including at least one visual sensor, at least one acoustic sensor, at least one environmental conditions sensor, and at least one proximity or motion detection sensor, each generating modality-specific data streams representing visual images, audio waveforms, physical environmental parameters, and motion signatures within a monitored environment; a data preprocessing and fusion subsystem that is operationally coupled with the multimodal sensor module and configured to normalize, temporally align, and transform the modality-specific data streams into high-dimensional feature embeddings using a variety of encoders, wherein the visual encoder uses convolutional or vision transformer architectures, the audio encoder uses a spectral-temporal feature extractor, and the sensor encoder transforms raw analog data into context vectors suitable for multimodal alignment; a multimodal processing unit consisting of a transformer-based large language model (LLM) trained on paired multimodal datasets and configured to perform semantic fusion, context abstraction, and inference across the aforementioned aligned multimodal feature embeddings to generate a contextual understanding of environmental and behavioral states; an adaptive agent controller coupled to the multimodal inference processing unit and configured to instantiate, manage, and terminate a variety of task-specific intelligent agents, each agent being a software unit configured to perform a specialized function selected from meeting summarization, behavioral analysis, misplaced object detection, or environmental anomaly identification, with the agents dynamically interacting with the inference engine to retrieve contextually relevant multimodal embeddings for task execution; a personalization and adaptive learning subsystem consisting of a user preference database and a neural memory structure configured to update and refine model parameters based on user-specific interaction history, thereby enabling personalized output generation, prioritization of recommendations, and long-term behavioral adaptation; and An output generation interface is operationally connected to the adaptive agent controller and configured to produce multimodal output in textual, visual, and auditory form. The interface is capable of displaying human-readable summaries, notifications, and visual reconstructions of identified entities or environmental states.

The invention provides a dynamic graph neural network modeling method for space-time big data, and relates to the technical field of data processing, and the method comprises the steps: mapping a network function entity into a topology vertex and mapping a topology correlation characteristic into a weighted transmission link, and triggering a sequence through a signaling event to drive topology reconstruction, and generating a communication network topology model; inputting the communication network topology model into a dynamic graph neural network, executing state feature space aggregation of a topological vertex neighborhood through a spatial-temporal feature extraction layer, and fusing time evolution dependency of a historical topological sequence to generate a network node spatial-temporal state tensor; and based on the network node space-time state tensor, a particle swarm optimization algorithm is adopted to calculate a whole network risk level quantitative topology feature, and network resource strategy optimization is dynamically executed to suppress end-to-end risk conduction. The adaptive capacity of the network to the dynamic scene is improved.

The invention discloses an enterprise data asset intelligent analysis method and system based on AI recognition, and the method comprises the steps: receiving an enterprise multi-source heterogeneous data stream, carrying out the joint feature extraction and semantic alignment through a pre-trained multi-modal fusion recognition model, and generating a structured data asset recognition result; constructing a dynamic enterprise data asset atlas according to the structured data asset identification result in combination with the data access trajectory and authority metadata collected in real time; performing spatio-temporal evolution analysis on the dynamic enterprise data asset map, and extracting potential data value density features and risk exposure features; inputting the data value density features and the risk exposure features into a self-organizing mapping network to generate a data asset grading topological graph; and based on the data asset grading topological graph, through strategy constraint reinforcement learning, generating an executable data governance action sequence. According to the embodiment of the invention, the identification precision and real-time analysis capability of special assets of enterprises can be improved.

The invention relates to the technical field of reservoir earth and rockfill dam leakage abnormity safety monitoring and early warning, in particular to an earth and rockfill dam leakage abnormity real-time monitoring and early warning system based on deep learning and a medium. The system comprises a data sensing transmission module, a data fusion processing and analysis module, an early warning evaluation module, a system management and maintenance module, a database management module and an emergency response command module. Through a well-ground collaborative full-dimensional electrical method and shallow earth surface and full-section distributed optical fiber sensing, the system collects and transmits multi-source data. And multi-mode fusion and a deep learning algorithm are adopted to realize multi-physical field feature extraction and three-dimensional modeling. The system generates graded early warning information based on dynamic threshold and multi-factor coupling, and realizes automatic real-time monitoring, intelligent early warning and efficient management of leakage abnormity of the earth and rockfill dam in combination with a database, management maintenance and emergency response functions. According to the invention, the accuracy of earth and rockfill dam leakage abnormity identification and the intelligent level of early warning are improved.

The invention relates to the technical field of elevator equipment state monitoring and fault diagnosis, and discloses an elevator traction machine running state real-time diagnosis method and system based on high-frequency sampling. According to the method, vibration (larger than or equal to 20 kHz), current (larger than or equal to 10 kHz), sound / sound emission, temperature and rotating speed signals of a traction machine are synchronously collected through a high-frequency multi-mode sensor array; capturing early weak fault transient characteristics; the edge computing unit completes data preprocessing, time synchronization, feature extraction and anomaly detection, and uploads key data to a cloud end through cloud-edge collaboration; the cloud end adopts a working condition self-adaptive strategy and a multi-modal fusion model to carry out deep diagnosis, and outputs fault types, positions and grades; and combining incremental learning and a degradation model to realize health quantification and residual life prediction. Through fusion of high-frequency data capture and an intelligent algorithm, the early fault detection capability, variable working condition adaptability and diagnosis real-time performance of the traction machine are improved, and a solution is provided for predictive maintenance of an elevator.

The invention discloses a GIS partial discharge intelligent diagnosis system and method based on one-dimensional ultrahigh frequency signal analysis, and relates to the technical field of power electrical equipment intelligent monitoring, and the system comprises a signal collection and preprocessing module which is used for collecting ultrahigh frequency signals of GIS equipment and obtaining preprocessed signal data through a dynamic threshold algorithm; the discharge initial judgment module is used for performing multi-dimensional sequential judgment to eliminate interference discharge data so as to obtain effective discharge signal data; the feature extraction module is used for performing time domain kurtosis and pulse width analysis, frequency domain energy distribution analysis and time-frequency domain wavelet entropy calculation based on the multi-dimensional features of GIS partial discharge, and generating an optimized feature subset; and the type identification module is used for identifying the partial discharge type by using the integrated learning model to obtain a diagnosis result. According to the invention, the problem of unstable recognition accuracy caused by insufficient signal preprocessing, single feature representation and single classification algorithm in the prior art is solved.

The invention discloses a metal cutting process parameter optimization analysis method based on machine learning, and particularly relates to the field of machine learning. Comprising multi-dimensional process parameter feature extraction and preprocessing, cutting state intelligent identification based on integrated learning, dynamic process parameter sensitivity analysis and weight calculation, process parameter intelligent optimization under a multi-target constraint condition, and adaptive parameter adjustment and real-time control strategy. According to the method, the interaction relationship between complex nonlinear features and process parameters in the cutting process is comprehensively captured, and accurate and intelligent recognition of different cutting states such as normal cutting, tool abrasion and abnormal flutter is achieved through a three-layer integrated learning architecture; the technical bottlenecks that an existing system lacks real-time self-adaptive adjustment capacity and is low in process optimization efficiency are overcome, pertinence and effectiveness of parameter adjustment are ensured, and the technical current situation that machining quality fluctuates and repeatability is poor due to traditional fixed parameters is changed.

The invention provides a fatigue life prediction and residual life evaluation method for a high-power heavy-duty gearbox, and belongs to the technical field of intelligent operation and maintenance based on computer data processing. Comprising the following steps: acquiring dynamic data in an operation process, and performing multi-scale decomposition to form multi-source multi-scale data; inputting the multi-source multi-scale data into a designed multi-scale fatigue feature extraction module and a health state prediction module to obtain a multi-scale health index sequence and a health state label; establishing a fatigue damage evolution model, introducing the generated health index sequence for self-adaptive updating, outputting a comprehensive damage value, performing staged evaluation of fatigue degradation to obtain a damage label set, and performing multi-scale health index sequence and health state labels as well as the comprehensive damage value and the damage label set to obtain a multi-scale health index sequence and health state labels; inputting into a designed double-source fusion fatigue life prediction model, and outputting residual life prediction quantity; according to the invention, high-precision prediction and residual life evaluation of the fatigue life of the high-power heavy-duty gearbox are realized.

The invention provides an intelligent scheduling and control method and device for an integrated energy system. According to the method, power, gas and heat resource operation data are acquired, multi-scale layered modeling is performed according to a time scale and a space scale, and a power resource state space model, a gas resource flow continuity model, a heat resource heat balance model and a multi-energy coupling characteristic constraint model are established; carrying out feature extraction and dimension reduction representation by adopting a deep auto-encoder network; cooperative training of multiple groups of cognitive models is carried out through a split hierarchical federal learning framework, and a global intelligent model is obtained; constructing a neural architecture search network with a hybrid bionic learning rule, setting a hierarchical scheduling target, and generating a hierarchical intelligent scheduling strategy; and a fault-tolerant control mechanism is constructed, and error detection and correction of operation deviation are realized. According to the invention, multi-time scale collaboration, collaborative learning under multi-device group privacy protection and high-reliability fault-tolerant control are realized, and the operation efficiency and reliability of the integrated energy system are remarkably improved.

The invention discloses a fault diagnosis and detection system for production automation equipment. The fault diagnosis and detection system comprises a data sensing layer which is used for carrying out multi-mode signal acquisition and real-time preprocessing; the feature extraction layer is used for constructing a recursive block convolution module, capturing transient impact features in four time steps by using an L1-layer gating convolution unit, associating a 16-time-step cross-block periodic degradation mode with an L2-layer sparse attention mechanism, aggregating multi-sensor spatial-temporal features by using an L3-layer global context node, and performing multi-scale feature extraction; the causal reasoning layer is used for establishing a physical constraint driven causal graph engine and outputting a fault propagation path with probability weight; the state modeling layer is used for constructing a continuous health evolution model by adopting a Shenchang differential equation, embedding a physical constraint loss function, and performing equipment full life cycle health state prediction and residual service life estimation in combination with a three-stage memory fusion mechanism of LSTM short-term memory, differentiable neural dictionary medium-term memory and knowledge graph long-term memory; and the decision support layer is used for generating a personalized maintenance work order.

The invention relates to the technical field of drainage basin water scheduling, and discloses a drainage basin water regulation and control optimization method based on ecological element changes. The method comprises the following steps: deploying a drainage basin monitoring system, and collecting ecological element real-time data such as a hydrological parameter sequence and a remote sensing image; after the data is cleaned and converted, hydrological trend features and spatial distribution features are extracted by adopting a feature learning model, and the hydrological trend features and the spatial distribution features are fused into unified ecological representation through a cross-modal alignment mechanism; inputting the unified ecological representation into a physically constrained neural network prediction model, and outputting a water regimen dynamic prediction value; and finally, based on the predicted value, a water resource regulation and control instruction is generated and executed by using a multi-objective decision algorithm so as to optimize the watershed water circulation process. According to the method, feature extraction comprehensiveness is improved through multi-source data fusion and cross-modal analysis, prediction reliability is enhanced in combination with physical constraints, reasonable allocation of water resources is achieved by means of multi-target decision, the ecological condition of a drainage basin can be improved, and the water utilization efficiency is improved.

The invention belongs to the technical field of emergency management, and discloses a natural disaster emergency rescue system based on multi-source sensing information fusion. The system is composed of a multi-source sensing data acquisition module, a data preprocessing and space-time registration module, a cross-modal feature extraction module, a multi-modal information fusion and conflict resolution module, a disaster type identification and grade discrimination module, a disaster influence range prediction and diffusion modeling module, and a dynamic emergency path planning and response plan generation module. A rescue scheduling and command control module; and an emergency feedback and closed loop dynamic correction module. Through multi-source sensing data fusion, cross-modal feature extraction and deep information fusion technologies, a full-space-time and full-process natural disaster emergency rescue system is constructed, comprehensive sensing, accurate recognition and dynamic plan generation of a disaster site are realized, the rescue response speed and decision scientificity are remarkably improved, and the intelligent level of emergency rescue is comprehensively improved.

The invention relates to the technical field of machine vision, and discloses a machine vision-oriented cross-modal image-text analysis method, which comprises the following steps of: partitioning an input image to generate an image block sequence; inputting the image block sequence into a visual converter for multi-scale feature extraction, and generating target visual features; encoding the input text to generate a target text feature; inputting the target visual features and the target text features into a deep reconstruction bottleneck network for compression alignment, and generating a cross-modal compression vector; and inputting the cross-modal compression vector into a large language model to generate cross-modal decoding information, so that cross-modal redundant information can be effectively filtered, compact shared semantic representation can be learned, the information integrity of the compression process is ensured through bidirectional reconstruction verification, cross-modal semantic alignment is realized, and the method has the advantages of high efficiency and high reliability. Omnibearing cross-modal content generation from the whole to details is achieved, and the requirements of different application scenes are met.

The invention discloses a multi-modal large model interpretable diagnosis method and system for a wind turbine generator, and relates to the technical field of wind turbine generator fault diagnosis, comprising the step of combining multi-modal data (vibration, time sequence, image and text) and topological information to realize fault diagnosis through cross-modal contrast learning and topological modeling. The method comprises the steps of multi-modal feature extraction, standardization and alignment, and feature fusion through topology embedding optimization and a cross-modal attention mechanism. In the fault diagnosis process, dynamic correction and path reliability evaluation are introduced by using a regular Agent and a topology consistent Agent, weighted fusion is performed on each modal feature and a topology structure, and finally an accurate fault type and a component positioning result are output. Through combination of knowledge retrieval and a multi-Agent decision model, the adaptability and precision of fault diagnosis are improved, especially in a complex environment, the fault mode of the wind turbine generator can be effectively identified, and the system reliability is improved.

The invention discloses a digital intelligent switch cabinet state comprehensive sensing system based on AI, and the system comprises a multi-source data collection module, a data preprocessing and synchronization module, an edge calculation feature extraction module, an AI intelligent fusion recognition module, an expert rule diagnosis module, and a cloud comprehensive evaluation and decision module. Various types of sensors are deployed to respectively acquire environmental parameters, electrical parameters and partial discharge signals generated in the operation process of the switch cabinet to form an original multi-modal data stream. The method has the advantages that the recognition precision and response speed of the complex operation state of the switch cabinet are improved, hidden faults under multi-modal data mismatch can be effectively found, and the misjudgment and missed judgment risks are reduced. Meanwhile, a closed-loop diagnosis system is constructed, intelligent evaluation and interpretable feedback of fault types, positions and trends are achieved, scientificity and reliability of operation and maintenance decisions are enhanced, and the method is suitable for intelligent upgrading of an electric power system.

The invention discloses a closed-loop fault diagnosis method based on the combination of an AI intelligent agent and power equipment simulation, which is applied to the field of power system fault diagnosis, and comprises the following steps: on the basis of a preset knowledge graph basic data set and power system multi-source data, performing data cleaning, feature extraction and knowledge integration; constructing a unified power equipment fault diagnosis knowledge graph, and performing reasoning on the knowledge graph and time sequence characteristics in combination with large model fine tuning or a mixed reasoning engine of a graph neural network to generate M candidate fault hypotheses; calculating the similarity between simulation and actual measurement waveforms through a DTW algorithm and a frequency spectrum comparison method, and screening high-consistency hypotheses; based on the logic verification rule base, performing causal graph reasoning, constraint checking and anti-factual thinking on the high-consistency hypotheses, and eliminating non-logic hypotheses; feeding back the abnormality found in the verification link to the AI agent, dynamically adjusting the reasoning strategy through reinforcement learning, and generating a convergent diagnosis result; and outputting a target diagnosis conclusion based on the converged diagnosis result.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a power equipment fault intelligent diagnosis method and system based on deep learning. The method comprises the following steps: automatically learning high-dimensional space-time correlation features in original time series data through a deep feature extraction network, and generating feature vectors representing potential abnormal modes of equipment; performing adaptive weight distribution on the high-dimensional space-time correlation features by using an attention enhancement mechanism, and marking a fault sensitive area to form enhanced fault features; inputting the enhanced fault features into a multi-level classifier for joint fault mode recognition and severity evaluation, and outputting a diagnosis result tensor containing a fault type and confidence; and an equipment maintenance decision signal is triggered based on the diagnosis result tensor, and the feature extraction network and classifier parameters are iteratively optimized according to feedback data, so that the intelligent level of operation and maintenance of the power equipment can be comprehensively improved.

The invention relates to the technical field of body-equipped intelligent robots, in particular to a multi-mode body-equipped intelligent robot control method and device, and the method comprises the steps: synchronously collecting visual, auditory, tactile, force sense and body perception information, and unifying the information to the same time-space reference through a cross-mode time-space stamp alignment mechanism; hierarchical feature extraction and fusion are carried out on the multi-modal information, and unified multi-modal scene state representation is generated; reasoning a decision based on the representation by using a body agent framework, and outputting a control instruction; motion planning and control, visual servo tracking in a non-contact stage and dynamic parameter correction in a contact stage are executed according to instructions; optimizing the multi-modal strategy network through an incremental strategy distillation mechanism based on the interactive data flow; the problem of space-time asynchronization of multi-modal sensing information is solved through a cross-modal space-time stamp alignment mechanism.

The invention relates to the technical field of power equipment state monitoring, and discloses a power equipment state evaluation and early warning method and system. The method comprises the following steps: collecting multi-source monitoring data of power equipment, and obtaining an equipment state data set by adopting a collaborative preprocessing method; a multi-dimensional feature extraction method is adopted to extract feature parameters reflecting the operation state and the degradation degree of the equipment; constructing an equipment health degree evaluation model, and obtaining the equipment health degree through a multi-time scale evaluation method; predicting a future deterioration trend and state transition time; establishing a grading early warning decision-making mechanism to realize early warning of the state of the power equipment; and identifying factors of equipment state degradation by adopting a root cause analysis method, and generating operation and maintenance decision suggestions according to historical cases. According to the invention, the health state of the power equipment can be accurately evaluated, and degradation trend prediction and fault early warning are realized.

The invention discloses a building engineering quality monitoring system, and relates to the technical field of building engineering monitoring, the building engineering quality monitoring system comprises a collection module, an analysis module, a monitoring module and an early warning module, the collection module collects first quality monitoring data of building engineering and obtains historical monitoring data, and transmits the data to the analysis module; performing feature extraction and data analysis on the first quality monitoring data to obtain second quality monitoring data, storing historical monitoring data and presetting quality standard data, transmitting the second quality monitoring data and the quality standard data to a monitoring module, performing dynamic comparison on the real-time second quality monitoring data and the preset quality standard data, and outputting the result. The method comprises the steps of generating quality anomaly feature parameters, transmitting the quality anomaly feature parameters to an early warning module, matching a preset early warning strategy according to the quality anomaly feature parameters, sending out graded early warning signals, and carrying out multi-dimensional early warning by integrating multi-dimensional data acquisition and analysis, dynamic feature index extraction and dynamic standard construction, so that the engineering quality monitoring accuracy and the management and control timeliness are improved.

The invention discloses a remote sensing image semantic segmentation method based on CNN-Transform-SAM dynamic collaboration and scene adaptation, and a constructed remote sensing image segmentation network comprises a scene attribute analysis module, a dynamic backbone decision module, a CNN-Transform expert sub-network, a cross-modal feature calibration module, a multi-modal prompt generator and an SAM adaptive general sub-network. And all the modules realize dynamic collaboration through data interaction. Wherein the scene attribute analysis module analyzes image resolution, spectrum and target scale attributes, the dynamic backbone decision-making module matches the optimal feature extractor according to the image resolution, spectrum and target scale attributes, the CNN-Transform expert sub-network generates small target enhanced adaptive masks through multi-scale interaction and up-sampling refinement, the cross-modal feature calibration module optimizes the masks and semantic distribution to generate alignment masks, and the cross-modal feature calibration module outputs the alignment masks. And the multi-modal prompt generator generates a multi-modal optimization prompt set based on the alignment mask, and guides the SAM adaptive universal sub-network to complete segmentation. The method effectively solves the problems of poor small target segmentation, fuzzy boundary and lack of remote sensing exclusive semantic priori in the prior art.

The invention relates to the field of bridge structure dynamic response analysis, and discloses a windmill bridge coupling response analysis method. According to the method, wind speed, wind direction and vehicle speed data are collected, and a data set is constructed by combining finite element and CFD coupling numerical simulation; a parallel encoder is adopted to fuse Transform feature extraction and LSTM time sequence processing to generate a hybrid prediction response; constructing a physical constraint and composite loss function based on a train-bridge motion equation, and optimizing neural network parameters through a subtraction average strategy; and finally, predicting dynamic response through forward propagation and verifying physical consistency to form a model optimization closed loop. According to the method, a deep learning method and physical equation constraints are fused, the analysis precision and calculation efficiency of windmill bridge coupling response are remarkably improved, and a more reliable dynamic evaluation means is provided for bridge wind resistance design.

The invention relates to the technical field of information retrieval and generation, in particular to a retrieval enhancement method based on multi-modal data fusion and modal perception. According to the method, firstly, a dual-channel architecture is adopted to perform feature extraction and coding on a text and an image respectively, and mutually independent embedded representation spaces are constructed, so that high-quality collaboration and matching of cross-modal representation are realized; and a pseudo-pairing generation mechanism is introduced to effectively mine and reconstruct the existing non-paired data in the knowledge base. And designing a query modal perception and dynamic weighting mechanism for accurately controlling the fusion proportion of the image-text bimodal information in the retrieval stage so as to match the modal demand difference of different query contents. And further executing aggregation retrieval and reordering of the cross-modal information by using dynamic weighted fusion retrieval to generate a candidate set of multi-modal responses. According to the method, accurate matching and dynamic weight adjustment of the image-text content are realized, and the accuracy and expression integrity of the generated content are improved.