921 results about "Feature modeling" patented technology

The invention relates to a cross-modal knowledge reasoning method based on a multi-modal large model. In a cross-modal knowledge reasoning process, an existing model is usually limited by single-modal information extraction and shallow feature fusion, so that deep semantic association among data such as texts, images and videos is difficult to fully capture. In order to solve the problem, the invention provides a model for fusing multi-modal information such as texts, images, videos, documents and the like, and processing of multi-modal data is converted into unified feature extraction, interaction and deep reasoning tasks by fully utilizing a supervision fine tuning strategy, a self-adaptive attention mechanism and a cross-language processing technology. The model adopts a modular design, integrates multi-source data complementary analysis, spatial-temporal feature modeling and emotional semantic analysis, and realizes multi-modal collaborative interaction, dynamic scene understanding, long video key event analysis and man-machine co-emotional response. Through sufficient training, the multi-modal large model shows excellent logical reasoning ability and emotion understanding ability in a complex cognitive task, and a brand new solution is provided for efficient extraction, deep semantic analysis and intelligent response of cross-modal information.

The invention relates to the technical field of red tide anomaly detection, in particular to an ocean red tide anomaly detection method and system fusing multi-source remote sensing and a graph neural network. The method comprises the following steps: acquiring remote sensing image data, unmanned aerial vehicle image data and monitoring data of a monitoring point; performing data preprocessing on the acquired remote sensing image data and unmanned aerial vehicle image data; performing feature extraction and feature fusion on the remote sensing image and the unmanned aerial vehicle image to obtain remote sensing feature data; constructing a space-time diagram structure based on the monitoring data of the monitoring points to obtain diagram structure data; based on a cross-modal comparison self-supervised learning mechanism, carrying out consistency representation learning on a remote sensing feature mode and a graph structure feature mode; by introducing multi-source heterogeneous data and fusing a graph neural network modeling means, the limitation of a single data driving method in the aspects of coarse red tide recognition granularity, low space-time precision and the like is effectively broken through, and the meticulous property and global perception ability of red tide feature modeling are remarkably improved.

The invention relates to the technical field of intelligent agriculture, and discloses a visual intelligent agricultural planting control system. The system comprises an environment data acquisition module used for acquiring multi-source environment sensing data; the growth feature modeling module is used for extracting crop growth state features through a morphological analysis algorithm; the environment regulation and control decision module is used for generating an environment regulation and control instruction set by utilizing a dynamic threshold matching algorithm; the visual interaction module is used for generating a three-dimensional farmland live-action simulated diagram through multi-dimensional data fusion processing; the strategy execution module is used for driving agricultural facilities to execute actions by adopting a self-adaptive control algorithm; an abnormity early warning module is further arranged, and abnormity early warning signals are generated through correlation analysis. The system realizes comprehensive acquisition and analysis of agricultural planting environment data, precise environment regulation and control, visual and visual display and abnormal early warning, effectively improves the intelligent and precise level of agricultural planting, improves the crop yield and quality, and assists the development of intelligent agriculture.

The invention discloses a double-flow remote sensing image change detection method fused with Mama enhancement, which belongs to the field of image processing and comprises the following steps: acquiring images to obtain a remote sensing image data set; preprocessing the obtained dual-time-phase remote sensing image, and dividing the image into a training set and a test set; designing a dual-flow change detection network model integrated with Mama enhancement; training the constructed double-flow change detection network model by adopting training set data until the whole model is converged, and storing an optimal model; and inputting test set data into the trained optimal model, and predicting a change area in the test set. According to the method, MambaBlock and a semantic segmentation aggregation module are introduced, the global feature modeling capability is enhanced under linear complexity, and the detection precision and robustness of a change region are improved by fusing feature information of different levels and multi-scale feature learning.

The invention discloses an electrical fire intelligent identification system based on multi-dimensional sensor fusion. The system comprises the following steps: constructing a reference environment model through multi-sensor scanning, data dimension reduction and intelligent node deployment; multi-sensor time sequence alignment is carried out through edge calculation denoising and dynamic time warping, and high-priority data is processed in real time through a layering mechanism; establishing a fire feature modeling system through LSTM time sequence analysis, mutual information correlation mining and self-supervised learning; through multi-level data fusion, GAN abnormal data generation and fuzzy logic reasoning; through grading alarm, an intelligent fire extinguishing strategy and remote control, full-process coverage from fire detection to emergency response is realized. A fire scene is visualized by means of a three-dimensional thermodynamic diagram, flame dynamic analysis and an augmented reality technology. The system is suitable for fire detection, alarm and response in a complex industrial scene, and can be widely applied to intelligent management of electrical fire.

The invention discloses an industrial odor online monitoring system based on big data. The system comprises a data acquisition module, a preprocessing module, a feature fusion module, a multi-source sensing weight analysis module, a dynamic risk assessment module, a self-adaptive correction module and a real-time feedback module. Data interaction among the modules adopts a block chain encryption transmission protocol, and a feature evaluation mapping chain with a timestamp is established in a distributed database. Through the innovative design of heterogeneous sensor network collaborative perception, cross-modal feature organic fusion, pollution diffusion three-dimensional dynamic deduction and a credible data governance architecture, a new industrial bad smell monitoring normal form with environment intelligent adaptability is constructed. The four technical effects form complementary support from four dimensions of data acquisition credibility, feature modeling scientificity, risk assessment accuracy and system decision robustness.

The invention discloses a data annotation method and system of a collaborative computing architecture based on quantum computing, and belongs to the field of data annotation. The method comprises the steps that S1, multi-modal data are input and preprocessed; s2, extracting features of each mode after preprocessing; s3, coding the features of each mode into a quantum state, and carrying out mode fusion; s4, performing label reasoning on the quantum state after modal fusion, and performing label constraint optimization by using a quantum approximate optimization algorithm; s5, based on a quantum Bayesian network or an approximate causal graph generation method, generating explanation according to a modal contribution causal path, and deducing marginal contribution of each modal to final label prediction by using a joint probability measurement result; and S6, outputting a labeling result. According to the method, a quantum-classical cooperative computing architecture is designed, the efficiency and accuracy of multi-modal data labeling are remarkably improved, the interpretability, the distributed processing capacity and the high-dimensional feature modeling capacity of the system are enhanced, and a brand new solution thought is provided for development of the multi-modal labeling technology.

The invention discloses a multi-modal fusion rumor detection method and system based on a dynamic graph convolutional neural network. According to the method, a dynamic feature graph of a language propagation path is constructed, and potential features in the language propagation process are extracted and analyzed by utilizing time sequence changes and key node relations between nodes in a propagation graph. A neural network is adopted to extract and enhance image data, text semantic features are extracted in combination with a text feature modeling network, text feature vectorization expression is achieved based on a BERT model, and rich semantic information is obtained. And a gating mechanism is introduced to dynamically adjust fusion weights of different modal features, and an information fusion strategy is optimized. A collaborative attention mechanism is further adopted for deep fusion, interactive learning of text, image and propagation path features is enhanced, and the relevance of cross-modal and time series data is improved. And finally, inputting the fused feature vectors into a classifier for accurate classification, thereby realizing accurate detection of the social media rumors. According to the method, the multi-modal features are effectively integrated, and the false information identification efficiency is remarkably improved.

The invention relates to the technical field of computers, and discloses a computing power resource multi-dimensional scheduling method and system based on dynamic weight, and the method comprises a data perception step, a weight generation step, an intelligent decision-making step and a scheduling optimization step. The system corresponds to the method. The method comprises the following steps: a data sensing step: collecting multi-dimensional state parameters of computing power nodes and carrying out feature modeling to construct a global feature space; a weight generation step: dynamically adjusting the weight of each dimension based on a machine learning model and a rule engine; an intelligent decision-making step of screening candidate nodes in the global feature space and evaluating priorities, generating an optimal node cluster and performing resource dynamic slice distribution; and a scheduling optimization step: monitoring an execution effect and performing closed-loop feedback so as to iteratively optimize a weight strategy and decision logic. The problems that in the prior art, the sensing dimension is single, and decision-making weight is rigid are solved, and multi-dimensional accurate sensing, dynamic weight decision making and elastic resource allocation of computing power resources are achieved.

The invention relates to the technical field of video behavior recognition, and discloses a behavior recognition and early warning system for a real-time video stream. The system comprises a spatio-temporal feature modeling module, a behavior fragment extraction module, an anomaly propagation modeling module, a risk area positioning module and an early warning strategy generation module. The spatial-temporal feature modeling module builds a dynamic model based on historical data, captures a skeleton key point three-dimensional coordinate sequence, a motion optical flow vector field and a micro-expression intensity spectrum, and outputs a theoretical behavior mode vector; the behavior fragment extraction module generates a multi-modal difference feature tensor through cross-modal difference analysis; the exception propagation modeling module generates an exception propagation path risk probability distribution cloud picture in combination with spatial constraint and trajectory information; the risk area positioning module identifies a high-risk area and marks a boundary; and the early warning strategy generation module dynamically configures monitoring parameters, starts high-frame-rate micro-expression capture for a high-risk area, and performs a track disturbance test on an adjacent area.

The invention relates to the technical field of airport safety monitoring, and discloses an airport video data real-time analysis system. The system comprises a video stream spatial-temporal feature modeling module, a behavior trajectory map construction module, an abnormal region association analysis module, a risk level semantic judgment module and a situation structure visualization module. According to the method, multi-scale spatial-temporal feature analysis is carried out on an airport monitoring video stream, a multi-dimensional behavior trajectory map is established, abnormal behavior region association is analyzed, risk level semantics are judged, and finally an airport global risk situation thermodynamic distribution map is generated. According to the system, the whole process processing from video data acquisition to risk situation visualization is realized, the abnormal behavior area can be accurately identified, the risk level and category are clear, comprehensive and visual situation information is provided for airport safety management, and the intelligent level of airport safety management is improved.

The invention relates to an underwater image enhancement method based on wavelet Mama, which aims at the problems of color shift, low contrast ratio and fuzzy details of an underwater image, extracts shallow layer features of an underwater low-quality image, inputs the shallow layer features into a multi-scale coding network, and performs joint enhancement on low-frequency color information and high-frequency detail features by using a wavelet Mama unit. Global semantic features are obtained by combining down-sampling layer-by-layer compression, and global modeling of color offset correction and contrast enhancement is completed; the spatial resolution is recovered through up-sampling, and reconstruction and enhancement of texture details and color information are realized in combination with jump connection and a wavelet Mama unit; and finally, the features are mapped to an image domain and fused with input image residual errors, and an enhanced underwater image with natural color, clear texture and balanced contrast is generated. According to the method, frequency domain-space domain joint feature modeling is realized through the wavelet Mama unit, and the color authenticity, the structural definition and the detail perceptibility of the underwater image are remarkably improved.

The invention relates to the technical field of medical information, in particular to an intelligent prediction model and method for postoperative complications of anesthetized patients, and the method comprises the steps: collecting preoperative to postoperative complete-cycle clinical data of a patient through a medical data interface; analyzing operation codes to generate risk features, extracting vital sign dynamic features, and establishing a complication probability mapping relation through a multi-modal fusion network; combining the complication probability and pharmacokinetic parameters to construct an optimization model, and solving an individualized anesthetic dosage interval by using a gradient descent algorithm; vital signs are dynamically monitored in the operation, a dose re-optimization mechanism is triggered, the infusion rate is adjusted, and a closed-loop control link is formed; and generating a visual decision report. According to the method, through deep integration of complete-cycle clinical data and multi-modal feature modeling, preoperative physiological parameters, operation coding semantic information and intraoperative vital sign dynamic modes are subjected to fusion analysis, a nonlinear mapping relation between dosage and complication probability is constructed, and the risk prediction precision and individualized adaptability are remarkably improved.

The invention discloses a feature integration method for interactive convolution and dynamic focusing of infrared images. The feature integration method comprises the steps that infrared image pairs with different resolutions in various real scenes are obtained through an infrared camera; performing degradation preprocessing on a part of original high-resolution images to obtain low-quality high-resolution images to form a mixed low-resolution data set, and dividing the processed data set into a training set and a test set; constructing a double-layer feature extraction module for feature modeling; training a network by using the processed training set, and optimizing a loss function; and inputting a low-resolution infrared image into the trained network, and outputting a high-resolution reconstruction result. According to the method, local and global features are fused, so that the super-resolution reconstruction quality of the infrared image in complex scenes such as low contrast and fuzzy edges is remarkably improved, and meanwhile, relatively high calculation efficiency is kept.

The invention relates to the technical field of earth leakage protection monitoring, and discloses an earth leakage circuit breaker remote monitoring system integrated with the Internet of Things. An electric leakage characteristic modeling module of the system obtains real-time monitoring data, extracts current waveform characteristic parameters, identifies an abnormal waveform mode and a first occurrence time sequence, and generates an original electric leakage characteristic template; the network path generation module performs topological sorting on the monitoring nodes based on the template, establishes an equipment connection path and constructs an Internet of Things topological path; a path anomaly analysis module extracts a node sequence and screens abnormal transmission paths to obtain an abnormal path set; the risk level judgment module collects terminal node risk tags and obtains a risk level tag group through matching; and the topological structure output module counts associated nodes, divides abnormal paths, establishes a mapping relation and generates a remote monitoring topological table. The system improves the accuracy and efficiency of electric leakage monitoring, and is suitable for a complex power network environment.

The invention relates to the technical field of robots, and discloses a robot nondestructive testing method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-modal sensing data and motion state parameters; constructing a three-dimensional material feature model and analyzing to generate an initial defect feature evaluation model; loading material attributes and detection precision constraints to generate a comprehensive model, and combining motion parameter simulation to obtain path regulation and control data; training the dynamic defect prediction model to obtain a detection path correction model and generating initial detection parameters; obtaining dynamic correction simulation information based on the initial parameters and the like; constructing a multi-objective optimization model, and optimizing to obtain an optimal detection path parameter; and generating a safety detection probability by combining real-time model reasoning, and adjusting a detection strategy to realize dynamic path matching. The system comprises a data acquisition module, a feature modeling and analysis module, a comprehensive evaluation and simulation module and the like. The method improves the detection precision, efficiency and adaptability, and is suitable for nondestructive detection of complex targets.

The invention discloses a pipe network operation and maintenance management system based on data analysis, which relates to the technical field of municipal infrastructure operation and maintenance management and comprises an equipment feature modeling module, a group anomaly identification module, a common-mode risk tracing module, a dynamic risk modeling module, a regulation and control strategy optimization module and a closed-loop self-adaptive updating module. Based on historical operation data and real-time acquisition parameters, feature coding is performed on the model, batch, position and time sequence of the sensor, and an equipment attribute mapping matrix is constructed. According to the method, the equipment attribute mapping matrix and the group anomaly identification mechanism are constructed, and external induction factor positioning and the dynamic risk weight map are combined, so that intelligent adjustment of regulation and control parameters and anomaly interference avoidance are realized, a closed-loop optimization process is constructed, and the identification accuracy, the control safety and the operation toughness of a pipe network system in a multi-disturbance scene are improved.

The invention discloses a traffic flow prediction method based on multi-view fusion and diffusion diagram convolution. The traffic flow prediction method is suitable for dynamic modeling and space-time dependence extraction in a complex traffic scene. The method comprises the following steps: firstly, extracting short-term fluctuation and long-term periodic characteristics through double-path time slice convolution, and modeling multi-scale time dependence; in the aspect of spatial modeling, three types of graph structures including a static physical graph, a historical semantic graph and a current feature graph are fused, a sparse dynamic graph is generated through a Top-K mechanism, multi-order diffusion graph convolution is executed in combination with a static graph, and local and global spatial features are extracted. Furthermore, a space-time fusion strategy of bidirectional cross gating is provided, the information circulation direction between short-term and long-term features is dynamically adjusted, and coordinated fusion of multi-scale features is realized. And finally, the traffic state of multiple time steps in the future is output through a gating structure and a non-regression prediction module. According to the method, the modeling capability of the model for the complex traffic dependency relationship is effectively enhanced, and the prediction precision and robustness are remarkably improved.

The invention relates to the technical field of agricultural environment intelligent regulation and control, in particular to an agricultural environment intelligent regulation and control method and system based on a cloud platform, and the method comprises the steps: collecting farmland environment parameters and crop image data through a multi-source sensor, filtering the farmland environment parameters and crop image data through an edge computing node, and transmitting the filtered farmland environment parameters and crop image data to the cloud platform; preprocessing the farmland environment parameters and the crop image data, and extracting time domain and space domain features; an agricultural environment state index prediction model is constructed based on a multi-head self-attention encoder, training of the agricultural environment state index prediction model is completed through historical data, the agricultural environment state index prediction model is deployed as a cloud service API, farmland environment parameters and crop image data input in real time are processed online, a control instruction is generated according to a prediction result, and the control instruction is sent to the cloud service API. Accurate and intelligent regulation and control of the agricultural environment are completed through Internet of Things protocol issuing equipment. Through dynamic feature modeling and multi-index collaborative optimization, the precision of agricultural environment regulation and control and the resource utilization efficiency are remarkably improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an image detection method, device, equipment and medium based on adversarial generation. Performing global feature modeling by adopting an image feature extraction module of a self-attention mechanism, generating a forgery probability graph in combination with a forgery region recognition module, constructing a joint loss function based on a detection loss value and an adversarial loss value, and optimizing model parameters of a generator, the feature extraction module and the recognition module through the joint loss function to obtain a forgery probability graph; and finally, a counterfeit detection model for identifying counterfeit information in the image is formed. According to the method, the diversity of training data is improved through adversarial sample generation, the image feature modeling capability is enhanced through a self-attention mechanism, multi-dimensional loss optimization is realized through fusion of counterfeit region difference information, and the detection precision and robustness of the model to a counterfeit image are improved.

The invention relates to the field of government affair work order intelligent processing, in particular to a government affair work order intelligent processing method and system based on space-time semantic clustering and a large language model. According to the scheme, unified data feature modeling is conducted on a work order to be processed, an improved DBSCAN clustering algorithm is executed on the work order through a weighted space-time semantic three-dimensional distance measurement formula, and combined clustering of space, time and semantic features is achieved; calculating priority scores of the work orders, and dynamically allocating scheduling resources according to the clustering scale and the priority of the work orders; based on a retrieval enhancement generation technology of an RAG framework and an FAISS vector retrieval library, historical similar work orders are matched, a few-sample learning case is generated, and two sets of differential treatment schemes are generated by controlling temperature parameters of a large language model; visual display and interactive analysis of work order clustering are realized through an interactive GIS platform; and establishing a quality feedback closed loop of work order reconstruction. The method is suitable for intelligent government affair work order processing.

The invention relates to the technical field of architectural design drawing recognition, in particular to an architectural drawing multi-dimensional defect feature extraction and automatic prompting method and system. The method comprises the following steps: preprocessing collected architectural design drawing data; carrying out primitive recognition and semantic tag extraction on the preprocessed drawing based on deep learning; carrying out multi-dimensional defect feature modeling based on the semantic tags identified and extracted by the primitives; defect identification and intelligent prompting are carried out based on the modeled defect features; and generating a defect report. According to the method, full-dimensional automatic identification and accurate prompt of building design drawing defects are realized, the limitation of traditional manual examination on efficiency and coverage range is broken through, dominant problems such as geometry, layers and annotation can be quickly positioned, hidden defects such as standard conflicts and semantic contradictions can be deeply mined, and the comprehensiveness of drawing quality control is improved.

The invention relates to an industrial Internet of Things anomaly detection method based on time sequence and text joint modeling, and belongs to the technical field of industrial Internet of Things anomaly detection. The method comprises the following steps: constructing text prompt information based on collected industrial Internet of Things time sequence data, and respectively taking the text prompt information as inputs of a time sequence channel and a text prompt channel; a sensor association graph is constructed by using a multi-hop GCN, and on the basis of the association graph, time feature modeling from local to global is completed by using multi-scale expansion convolution and combining a differential attention mechanism; performing word segmentation processing on the text prompt information through a word segmentation device, and encoding the text prompt information into vector representation; and calculating attention weight between time sequence embedding and text prompt embedding, fusing to obtain joint embedding representation, enhancing the joint embedding representation, inputting the enhanced joint embedding representation into MLP for reconstruction, calculating an abnormal score through a reconstruction error, and carrying out industrial Internet of Things anomaly detection according to the abnormal score. The method is high in anomaly detection accuracy, and can improve the equipment anomaly perception and risk early warning capability.

The invention relates to the technical field of fault diagnosis, in particular to a complex equipment fault diagnosis method and system based on dynamic feature modeling. The method comprises the following steps: acquiring multi-channel sensor data; performing data preprocessing on the acquired multi-channel sensor data; extracting initial channel features from the preprocessed data; on the basis of a direction perception mechanism, performing convolution enhancement after splicing the initial channel features, and generating global context features of structure perception; performing multi-time-sequence scale feature fusion on the global context features based on a multi-scale modulation mechanism; performing health trend guidance on the fused features based on a trend guidance supervision mechanism; the diagnosis precision, the trend perception capability and the practical response efficiency of the system are remarkably improved, the system is effectively adapted to core application scenes of multi-industry equipment in predictive maintenance, online fault perception, remote diagnosis analysis and the like, and the system has good popularization prospects and practical values.

The invention relates to the technical field of retrieval enhancement generation, in particular to a method for automatically adjusting retrieval enhancement generation parameters based on content feature modeling. The method comprises the following steps: receiving an original query text of a user, performing component analysis, identifying terminologies, general vocabularies and question entities, and quantifying to form query fingerprints; acquiring a historical behavior sequence of the user, and constructing a score reflecting the level of the user by combining the query fingerprints and adopting a time decay weighting algorithm; the user level score is converted into specific retrieval parameter configuration, and a retrieval strategy blueprint is formed; guiding document library retrieval according to the retrieval strategy blueprint, and screening out a candidate knowledge set which is most matched with the professional level of the user; and according to the user level score, a preset instruction template is intelligently filled, and a situational generation instruction is constructed. According to the method, the problem of non-uniform cognitive load caused by a traditional system is solved through a retrieval enhancement generation technology, and the technical knowledge transmission efficiency and the user satisfaction are remarkably improved.

The invention relates to the technical field of big data service, in particular to a chemical fiber raw material impurity spectrum intelligent analysis system which comprises a spectrum feature deconstruction module, an impurity feature modeling module, a periodic drift analysis module and a component quantification output module. According to the method, noise is suppressed through moving window scanning in combination with Savitzky-Golay filtering, peak shape features are reserved, the signal-to-noise ratio is increased, feature distortion caused by mean filtering is avoided, segments are divided through extreme value density, weak impurity recognition is enhanced in combination with a dynamic threshold value, and a multi-dimensional fusion model is established through peak width change rate and baseline offset convolution. Linear dimension reduction limitation is broken through to improve discrimination precision, dynamic time warping is used for aligning peak height difference and symmetry degree time sequence, drift and interference influences are eliminated, periodic error accumulation is solved, Kalman filtering is used for carrying out recursive optimization on compensated concentration, model lag is reduced, and a closed-loop optimization system is constructed through multi-stage feature decoupling and dynamic compensation. The sensitivity is improved; and the misjudgment rate is reduced.

The invention provides a remote intelligent operation monitoring method and system for an intelligent substation, relates to the technical field of intelligent operation and maintenance of substations, and relates to multi-source heterogeneous sensing, depth feature modeling, fault prediction evaluation and model self-optimization. According to the method, electrical, environmental and meteorological data are collected through heterogeneous sensors, a structured original data set is constructed, time sequence prediction is carried out in combination with a convolution-LSTM model, a Transform fusion network is utilized to output a fault probability and a confidence interval, online early warning and response control are realized, and the method has a federated learning driven adaptive updating capability.

The invention relates to the technical field of intermediate frequency furnace sintering temperature control, and discloses a sintering temperature control system of an intermediate frequency furnace. The system comprises a multi-source data acquisition module which is used for acquiring multi-dimensional thermodynamic data, covering temperature distribution, sintering power and heat flow track data in a sintering process in real time; and the temperature field analysis module is used for carrying out dynamic compensation correction processing on the multi-dimensional thermodynamic data, inputting the multi-dimensional thermodynamic data into a sintering analysis processing layer for characteristic modeling, and generating a sintering temperature regulation and control instruction. The sintering analysis processing layer comprises a data preprocessing module and a thermodynamic modeling module, the data preprocessing module performs operation such as temperature interval division and abnormal value elimination on original data, and the thermodynamic modeling module is obtained based on historical data cooperative training. According to the system, through multi-dimensional data acquisition and analysis processing, the sintering temperature can be accurately regulated and controlled, the quality of sintered products and the production efficiency are effectively improved, and the system has good universality and adaptability.

The invention discloses a long-time pedestrian re-identification method based on dual-path cooperation and key frame guided reconstruction. The method comprises the steps of firstly collecting a pedestrian video to be recognized, and extracting a video feature sequence; space and time position coding is introduced into the video feature sequence; capturing local fine-grained dynamic features through a local dynamic feature capturing path, and modeling long-range time sequence association through a cross-frame global feature modeling path; then, dual-path feature complementation is realized through bidirectional gating interaction; further screening out key frames, and realizing feature reconstruction through a full-frame attention propagation mechanism; and finally fusing the dual-path fusion features, the key frame guide reconstruction features and the refined features to generate pedestrian identity features. And processing pedestrian identity features to obtain standardized feature vectors, performing similarity comparison on the standardized feature vectors and pedestrian features in an image library, and returning a matching list. According to the method, video time sequence information is fully utilized, and the problem of insufficient robustness caused by appearance change in long-time pedestrian re-identification is effectively solved.

The invention belongs to the technical field of new-generation information, and particularly relates to a power plant metal supervision entity relationship extraction method based on dual coding, which comprises the following steps: multi-modal data preprocessing: collecting and cleaning data, and carrying out data labeling; constructing a dual coding joint learning model: designing a network layer architecture, and training the dual coding joint learning model; constructing and querying a dynamic knowledge graph: extracting a model to generate a triple, and performing time sequence evolution analysis, causal reasoning interface and dynamic updating; and incremental knowledge updating and dynamic model optimization: an incremental learning and feedback module forms a bidirectional closed loop between the knowledge graph and the relationship extraction model, and continuous evolution of the system is ensured through dynamic knowledge updating and adaptive model optimization. According to the method, through bidirectional feature modeling of dual paths, collaborative representation optimization between entities and relationships is realized while context information is captured, so that the requirements of complicated data types and diversified semantic associations in an engineering scene are met.