430 results about "Interaction network" patented technology

The invention provides a hydrogen energy storage equipment leakage fault early warning method and system based on deep learning, and the method comprises the steps: collecting the multi-source sensing data of hydrogen energy storage equipment in real time, constructing a multi-dimensional feature matrix, building the nonlinear mapping of pressure fluctuation and gas concentration through a bidirectional interaction network, and carrying out the early warning of the leakage fault of the hydrogen energy storage equipment. And performing spatial modeling on the temperature gradient and the vibration spectrum to generate a fusion feature tensor. And then, inputting the fused feature tensor into a spatio-temporal reasoning model, predicting equipment leakage and energy loss, and outputting a leakage probability cloud picture and an energy loss vector. And an entropy sudden change area is identified based on an energy loss vector, when the high-density leakage area and the entropy sudden change area are overlapped in a continuous detection period, a multi-stage early warning signal is triggered, a leakage source thermodynamic diagram and a pressure balance parameter set are generated, a self-adjusting system is activated to dynamically correct the valve opening degree, network weight is updated, and a closed-loop control link is formed. The early warning accuracy and the response speed of the leakage fault of the hydrogen energy storage equipment are improved.

The invention provides a face target detection method based on improved YOLOv8, and the method comprises the steps: carrying out the preprocessing of a face data set, constructing and training an improved YOLOv8 network model, inputting a to-be-detected image into the model, and obtaining a prediction result; the improved YOLOv8 network model comprises a backbone network, a neck network and a head network; the backbone network comprises a convolution module CBS and a feature fusion module C2f of an original model, a deformable attention mechanism DAttention is introduced to improve the feature fusion module C2f in the backbone network, the C2f of the last layer is replaced, an attention-based intra-scale feature interaction network is used to replace a spatial pyramid pooling module, and the feature fusion module C2f of the original model is obtained. And optimizing the bounding box loss function through the angle constraint loss function. According to the invention, the precision of a face target detection task is effectively improved, and especially for dense small face image detection, the problems of missing detection and wrong detection of targets are reduced.

The invention provides a pedestrian trajectory prediction method based on window attention and a space diagram interaction network, and belongs to the technical field of computer vision. The technical problems of difficult long-time dependence modeling and complex space interaction are solved. According to the technical scheme, the method comprises the following steps: S1, acquiring data of a data set; s2, in the time dimension, designing a window mask mechanism, and adjusting the attention receptive field at each moment; s3, constructing a hierarchical heterogeneous graph convolutional network according to a spatial dimension, and combining a pedestrian dynamic interaction graph with a scene static semantic graph; and S4, inputting the time dimension features and the space dimension features into a multi-scale expansion convolutional network to generate a multi-modal trajectory. The method has the beneficial effects that the model is subjected to experimental verification on a public data set ETH / UCY, the experimental result proves the effectiveness of the model, the superior performance of the model is shown on key indexes, and the generalization ability in processing different scenes is also excellent.

The invention belongs to the field of combat management, and particularly relates to an air real-time combat management system based on hybrid intelligence, which is characterized in that a cross-domain thermodynamic perception situation map and a cross-domain fusion situation map are generated through sensing module multi-modal target data through situation fusion, threat analysis and target sorting; the hierarchical autonomous decision-making module analyzes combat requirements by using an enhanced hierarchical and hierarchical subsystem, constructs and generates a sub-target sequence and an interactive network through target decomposition and a constraint node network, and generates an optimal tactical control instruction set in combination with resource prediction allocation and tactical evaluation; the cross-layer intervention module dynamically adjusts an autonomous decision permission weight and an instruction according to a task risk, a communication state and a decision score, and realizes the control right of a person in a decision ring by using the instruction of a commander as the highest intervention decision instruction of each layer; the analogue simulation module integrates the subsystems and the man-machine constraint boundary, and performs collaborative decision simulation until the standard is reached; and integrated management of real-time sensing of the air combat situation, intelligent hierarchical decision under dynamic constraint, man-machine permission flexible adjustment and collaborative simulation verification is realized.

The invention discloses a multi-modal sentiment analysis method and system based on multi-dimensional perception, and relates to the technical field of sentiment analysis, and the method comprises the steps: inputting to-be-recognized multi-modal sentiment data into a trained multi-modal sentiment analysis model, the multi-modal sentiment analysis model comprises a feature extraction network, a transmembrane interaction network, a multi-dimensional sensing network and a sentiment prediction network; performing feature extraction on the to-be-recognized multi-modal emotion data through the feature extraction network, and constructing aligned text features, aligned audio features and aligned video features; inputting the aligned text features, the aligned audio features and the aligned video features into a cross-membrane interactive network for feature interaction, and determining interactive fusion features; carrying out feature extraction on the interactive fusion feature along a plurality of feature dimensions in sequence based on a multi-dimensional sensing network to generate a mixed multi-modal feature; and performing emotion scoring on the mixed multi-modal features by using an emotion prediction network, and outputting a target emotion score. Based on the above scheme, improvement of sentiment analysis precision is facilitated.

The invention provides an unstructured data processing method and system, and relates to the technical field of natural language, and the method comprises the steps: carrying out the tensor decomposition of unstructured data, obtaining a standardized feature vector, constructing a self-organizing critical state feature learning network in an isolation calculation space, constructing a feature interaction network based on quantum entanglement perception, and carrying out the recognition of the feature interaction network. And establishing a hierarchical causal graph for feature screening, realizing semantic feature vector generation by adopting multi-scale feature fusion, and establishing an intelligent protection mechanism. The feature extraction accuracy can be effectively improved, the data processing reliability is enhanced, and the system operation efficiency is improved.

The invention discloses a teaching management method and system based on electronic technology courses, and relates to the technical field of teaching management, and the method comprises the steps: collecting and preprocessing multi-source data, constructing an interactive network diagram of students in courses, and carrying out the classification of student groups; constructing a knowledge graph in combination with the course data and the learning behavior data, and initializing a personalized learning path based on the knowledge graph and student group features; and learning resources of different paths are recommended through a multi-view attention mechanism. The multi-level learning path constructed through the knowledge graph ensures that the students grasp knowledge step by step, can adapt to individual differences of the students, performs resource recommendation by using a multi-view attention mechanism, and can realize high-matching-degree resource pushing on the basis of capturing individual features of the students, thereby effectively improving learning efficiency and resource utilization rate, and improving learning efficiency. The dynamic optimization of the learning path is realized, and the adaptability and pertinence of teaching management are remarkably improved.

The invention relates to the technical field of medical monitoring and early warning, and discloses a postoperative care risk early warning system for neurosurgical patients. According to the system, real-time monitoring flows of electroencephalogram, intracranial pressure and body surface myoelectricity of a patient are continuously received, and a dynamic interaction network of neuroelectrophysiology and intracranial mechanical states is constructed so as to represent the coupling relation among electroencephalogram rhythm, pressure conduction and postoperative skull windowing area tissue compliance. The system analyzes three types of core parameters of cerebral cortex excitability, cerebrospinal fluid circulation load and cranial cavity compensation space from the network, further calculates a brain tissue perfusion risk and a neural structure compression risk, and generates a corresponding nursing early warning signal and a physiological regulation path. According to the scheme, deep coupling and mechanism risk early warning of multiple physiological signals are achieved, and the postoperative complication risk can be recognized earlier and more accurately.

The invention provides a cognitive unmanned aerial vehicle network spectrum sharing method based on multi-agent reinforcement learning. The method comprises the implementation steps that a cognitive unmanned aerial vehicle network model and a cognitive unmanned aerial vehicle network and multi-agent reinforcement learning interaction network model are constructed; obtaining a training data set and defining a reward function; and carrying out iterative training on the interactive network model. In the process of training the interactive network model, the multiple agents interact with the cognitive unmanned aerial vehicle network in real time through reinforcement learning, spectrum resource allocation can be adaptively adjusted according to the communication requirement of each cognitive unmanned aerial vehicle and the dynamic change of the environment, and the spectrum resource allocation efficiency is improved. And the loss of the local Q network in each time step is calculated according to the target Q value corresponding to each experience calculated by calculating the reward of interaction between each Q agent and each environment state through the throughput of each cluster member on each channel, so that the resource waste is reduced, the spectrum conflict is avoided, and the maximization of the network throughput is realized. Therefore, the spectrum utilization rate is effectively improved.

The invention belongs to the technical field of environment regulation and control, and discloses a livestock breeding environment dynamic prediction and regulation and control method based on machine learning. Comprising the following six key steps: firstly, preprocessing multi-source data, and constructing a standardized feature data set; secondly, performing time sequence feature extraction and environment-biological response correlation analysis to obtain a multi-factor interaction network; then, constructing a dynamic coupling model of the environmental parameters and the production efficiency; a multi-target reinforcement learning regulation and control model is constructed based on the animal husbandry production efficiency prediction space; predictive environmental parameter regulation and risk assessment are carried out in combination with real-time monitoring data; and finally, intelligent environment intervention is executed, and a regulation and control strategy is iteratively optimized through production index feedback. According to the method, the breeding environment is converted from passive response to active prediction, complex correlation understanding between environmental factors and biological indexes is established, and multi-target balance optimization of production efficiency, energy consumption and animal welfare is achieved.

The invention discloses a multi-source monitoring data fusion method based on deep learning, and the method comprises the steps: carrying out the standardization and space-time dimension alignment processing of multi-source monitoring data, constructing a multi-scale data sub-sequence, inputting a multi-scale space-time feature interaction network based on a Mamba structure, extracting and interacting multi-scale space-time features, constructing a cross-modal data topological graph structure, and carrying out the fusion of the multi-source monitoring data. And dynamically calculating and adjusting attention weights of nodes and edges of the topological graph by using an adaptive cross-modal graph attention mechanism, generating dynamically optimized cross-modal fusion features, performing collaborative feature decoding, and outputting a fusion result. According to the method, the multi-source data fusion precision and generalization ability in a complex monitoring scene are improved, and the fusion feature expression ability and decision reliability are improved.

The invention discloses an embroidery stitching method backstepping and dynamic reproduction method based on deep learning, and belongs to the technical field of embroidery stitching method identification, and the method comprises the steps: collecting stitch data; fusing the three-dimensional point cloud data acquired from multiple view angles by using a point cloud registration algorithm, and constructing a multi-modal data set; constructing a dynamic graph space-time interaction network, and extracting feature vectors in the multi-modal data based on the dynamic graph space-time interaction network; constructing a stitch inverse model to obtain a stitch space layout instruction, dynamic process parameters and an optimized array sequence; and constructing a dynamic reproduction model to obtain an actual embroidering action sequence. According to the invention, the deep features of the embroidery method in the embroidery image can be automatically learned, and the accuracy of the embroidery method backstepping and the authenticity of the dynamic reproduction are obviously improved; the method can achieve the precise reverse deduction of a plurality of embroidery methods under the conditions of complex textures, different light conditions and various embroidery angles.

The invention provides an IBS micro-ecological transplantation intelligent prediction method and system based on multi-omics driving, and relates to the technical field of biomedicine. The method comprises the following steps: establishing a multi-omics data fusion subsystem to collect metagenome, metabolome, host genome and clinical phenotype group data of a target patient; inputting the data into a flora-metabolite combined network analysis model to construct an interaction network and extracting features; generating an incidence matrix based on the features and the host genome data and calculating indexes; generating indexes through a dynamic response algorithm in combination with the clinical phenotypic data and the indexes; and outputting a curative effect prediction result by using a transfer learning framework combined with modeling. The system comprises a data acquisition module, a network analysis module, a correlation calculation module, a dynamic response module and a joint modeling module. According to the method, multiple omics data are integrated, the flora and host relation is accurately mined, intelligent prediction of the micro-ecological transplantation curative effect is achieved, powerful support is provided for IBS personalized treatment, and meanwhile data processing and safety guarantee measures are taken.

The invention discloses a deep forgery detection method based on a multi-granularity collaborative attention mechanism, and the method comprises the following steps: extracting multi-level features through a backbone network, achieving the self-adaptive region division and weight fusion through a dynamic space grouping attention mechanism, and solving the problem that a conventional method is insufficient in attention to a distributed forgery region; a double-path channel decoupling module is designed to separate high-frequency artifacts and low-frequency semantic features, and feature coupling interference is eliminated; a cross-granularity feature interaction network is constructed, local details and global semantic features are collaboratively optimized, and the fusion efficiency of multi-scale forged clues is improved; and finally, a detection result is output through the classifier. According to the method, the defects of weak cross-domain generalization ability, low multi-granularity information utilization efficiency and the like caused by incomplete space attention coverage and channel feature interference in the prior art are overcome, the detection precision and robustness are remarkably improved, the stable performance is kept in a complex degradation scene, and the method can be widely applied to scenes such as digital content security auditing and identity authentication.

The invention discloses a group behavior recognition method based on dynamic and static characteristics and multiple interactive networks, and relates to the technical field of computer vision, comprising the following steps: preprocessing original video data and skeleton node data to obtain dynamic and static characteristics of participants; multi-level character features are obtained by extracting coarse-grained key character information and restoring fine-grained character information; the method comprises the following steps of: obtaining a complex space-time interaction feature by applying a Space-Transform and a Temporal-Transform, and obtaining the complex space-time interaction feature by applying the Space-Transform and the Temporal-Transform; predicting an identification result through data fusion; dynamic features are utilized to supplement static features, and group behaviors of participants are comprehensively and meticulously analyzed; in order to emphasize the key figure information, the key figure information is used as a consistency constraint to guide the focus of the space-time interaction network, and the recognition capability of the model on the space-time dynamic state of the key figure is enhanced.

The invention relates to the technical field of American ginseng quality detection, in particular to an American ginseng quality detection method and system based on S-transformation and multi-task deep learning. Near infrared spectrum data of American ginseng to be detected are extracted, and time-frequency conversion is performed on the near infrared spectrum data through S-transformation; obtaining a time-frequency characteristic pattern used for representing time-frequency domain information of the near infrared spectrum; and inputting the to-be-detected American ginseng time-frequency feature map into a pre-trained multi-task deep learning model, and identifying the producing area of the to-be-detected American ginseng and predicting the quality index of the to-be-detected American ginseng by using the multi-task deep learning model. The multi-task deep learning model comprises a feature extraction network used for extracting time-frequency features of each detection task of the feature map, a feature interaction network used for enhancing feature complementation between the tasks and performing feature fusion, and a multi-task head network used for executing a production place identification task and a quality index prediction task according to the time-frequency features and outputting the tasks. The method can be suitable for quality analysis and origin classification of small American ginseng samples.

The invention discloses a video crowd counting method based on a cascaded cross-domain feature interaction network. The method comprises the following steps: carrying out data enhancement processing of random cutting and horizontal flipping on a current frame and front and back frames of the current frame; and constructing a cross-domain feature interaction network composed of a spatial domain branch and a frequency domain branch. The frequency domain branch extracts frequency domain feature output of different stages through a high and low frequency signal aggregation module and a feature encoder based on adjacent frames; the spatial domain branch is based on a single-frame image, and static spatial semantic features are extracted through a feature encoder. Cascade fusion is carried out on the double-branch features on multiple scales, two-way channel cross attention is utilized to reconstruct time sequence correlation frequency domain features of a current frame, and fusion and reconstruction of the two domain features are achieved through a cross-domain feature mutual modulation module. And after the reconstructed double-branch features are processed by the fusion network, outputting a crowd density map of the current frame by a density regression head. And after training is completed, storing the optimal model for video crowd counting. According to the invention, through cross-domain feature cascade and bidirectional time sequence modeling, the accuracy and robustness of crowd counting in a video scene are effectively improved.

The invention relates to the technical field of power transmission line monitoring, and discloses a power transmission line real-time monitoring method and platform. The method comprises the following steps: establishing a multi-omics data fusion subsystem to collect metagenome, metabolome, host genome and clinical phenotype group data of a target patient; inputting the data into a flora-metabolite combined network analysis model to construct an interaction network and extracting features; generating an incidence matrix based on the features and the host genome data and calculating indexes; generating indexes through a dynamic response algorithm in combination with the clinical phenotypic data and the indexes; and outputting a curative effect prediction result by using a transfer learning framework combined with modeling. The system comprises a data acquisition module, a network analysis module, a correlation calculation module, a dynamic response module and a joint modeling module. According to the method, multiple omics data are integrated, the flora and host relation is accurately mined, intelligent prediction of the micro-ecological transplantation curative effect is achieved, powerful support is provided for IBS personalized treatment, and meanwhile data processing and safety guarantee measures are taken.

The invention relates to the technical field of medical image processing, in particular to a nuclear magnetic image brain tumor detection method and system, and the method comprises the steps: obtaining an initial nuclear magnetic brain tumor image, taking a dual-convolution cross-stage division network as a backbone network, taking a partial visual state space network as a feature enhancement network, lightening a YOLOv8 model, and improving the performance at the same time; in the YOLOv8 model with improved performance, the constructed re-parameterized dynamic selectable large-kernel convolutional network is used as a multi-scale feature interaction network in the neck structure, and the performance of the YOLOv8 model is further improved by using re-parameterization, so that the improved YOLOv8 model is obtained; performing iterative optimization training on the improved YOLOv8 model by using the initial image data set to obtain a nuclear magnetic image brain tumor detection model; and inputting the initial image data set into a nuclear magnetic image brain tumor detection model for detection, and outputting a nuclear magnetic brain tumor detection result. According to the invention, the accuracy and efficiency of brain tumor detection can be improved.

The invention discloses a fleet formation flight implementation method and device, equipment, a medium and a product, and belongs to the technical field of aeronautical communication. The method comprises the following steps: establishing an air-ground interconnection communication link to realize real-time data interaction between a ground control unit and a plurality of flying civil aircrafts and between the plurality of civil aircrafts; based on an air-ground interconnection communication link, an airborne ad hoc network with a leading aircraft as a core is constructed, and an information interaction network in the formation is formed. Acquiring formation flight environment data; determining a safe area of formation flight based on the formation flight environment data, and calculating the maximum number of aircrafts in the formation and the relative positions of the aircrafts in the formation; and issuing the maximum number, the relative position and the flight decision information to each airplane in the formation through the airborne ad hoc network so as to execute formation flight. According to the embodiment of the invention, the real-time performance and accuracy of communication between the fleet can be effectively improved, and the airspace operation efficiency and flight safety are improved through the formation flight of the fleet.

The invention relates to the related technical field of rehabilitation information communication interaction, in particular to a real-time interaction method and system suitable for multi-modal rehabilitation medical information, and the method comprises the steps: determining a multi-modal data flow, generating an initial interaction network architecture, using a heterogeneous data feature encoder, adding an upper sampling feature pointer and a lower sampling feature pointer, and carrying out the real-time interaction of the multi-modal rehabilitation medical information. According to the method, dynamic allocation optimization is carried out by using dynamic adaptive elements, short-time communication adjustment is carried out by using different interactive requests according to the dynamic adaptive elements, configuration optimization is carried out according to real-time scheduling of multi-modal data streams, and a self-adaptive interactive network architecture is set, so that the problem that under different interactive requests and data streams, the real-time scheduling of the multi-modal data streams is not influenced is solved. According to the technical scheme, the technical problems that the multi-modal data feature extraction and fusion capability is insufficient, and interaction requirements cannot be met are solved, path selection optimization in a multi-path transmission topological structure is achieved, short-time communication adjustment is carried out according to different interaction requests and data flow conditions, and it is ensured that the interaction requests can be quickly responded and processed.

The invention relates to the technical field of elevator component performance analysis, in particular to a construction method and system for an elevator component performance model and a storage medium. The method comprises the following steps that elevator use records are collected, flow frequency spectrum modeling is carried out to generate start-stop frequency spectrum features and elevator use mode features, then part response analysis is carried out on the use mode features to obtain dynamic characteristic indexes, the independent performance of parts is calculated, and the independent performance of the parts is calculated. And an elevator interaction network is reconstructed according to the independence performance and the use mode characteristics, energy consumption distribution of the elevator is calculated, overall parameters of the elevator are obtained, framework simulation is conducted, framework movement performance loss is calculated, part position projection is conducted on a simulation framework based on part independence performance, interaction performance is evaluated, and therefore an elevator part performance model is constructed. According to the elevator part performance model construction method, elevator start-stop frequency spectrum characteristics and energy consumption distribution can be accurately described, and the response characteristics and interaction performance of the parts can be dynamically evaluated.

The invention provides a super-lens reverse design method based on a selective dual-channel perception fusion network, and the method comprises the steps: obtaining a picture-phase spectrum data set through obtaining K pairs of original images and corresponding original phase spectrums; inputting the data to an adaptive difference frequency feature extraction network ADFFNet; inputting a selective non-common feature interaction network SFIFNet to respectively obtain image frequency features and spectral frequency features; the fusion reconstruction features of the image and the fusion reconstruction features of the spectrum are obtained; obtaining a picture generation result and a spectrum generation result; according to the method, the non-common frequency characteristics between the image and the corresponding spectrum can be deeply mined and deeply fused, the mapping accuracy between the image and the corresponding spectrum response can be improved, and the generation accuracy and efficiency of the image and the spectrum can be improved.

The invention discloses a multi-modal data joint embedding method based on a hierarchical progressive arithmetic interaction network, and the method comprises the following steps: obtaining text data and image data from the same semantic entity, and extracting a text local feature, a text global feature, an image local feature and an image global feature; inputting the text local feature and the image local feature into an atomic layer, and processing based on a Cartesian product to generate a first-order interaction feature; inputting the first-order interaction features into a combination layer, and carrying out nonlinear transformation processing to generate enhanced nonlinear interaction features; and inputting the nonlinear interaction features into the aggregation layer, and generating a multi-modal joint embedding vector in combination with the text global features and the image global features. The method effectively solves the problems of modal isomerism, single interaction level, lack of dynamic adaptability and the like in the prior art.

The invention discloses a method for depicting and analyzing a heavy non-aqueous phase pollution site based on microbial structure information, which comprises the following steps of: based on a historical geological survey report and a historical leakage event, defining a pollution analysis area, and constructing a site pollution conceptual model by combining high-density resistivity with a stable isotope tracer method; performing sample collection and detection on the target area to obtain area sample detection information; performing microflora analysis according to the regional sample detection information, and judging a potential pollution retention region of the target region to obtain pollution region analysis information; carrying out multi-source data coupling by combining pollution area analysis information and area sample detection information, and carrying out pollution field three-dimensional description on a target area to obtain an area DNAPLs pollution condition diagram; a degradation function gene interaction network is constructed, restoration potential grading is performed on a target area, and area restoration suggestion is performed, so that the limitation of a traditional investigation method is broken through, and accurate analysis and restoration assistance of pollution distribution are realized.

The invention discloses a large model system based on a calculation acceleration chip, and relates to the field of large models. Comprising a plurality of calculation acceleration units and a management server, and an inter-chip and off-chip data interaction network is formed and realized; a mixed video memory of the calculation acceleration unit is matched with an SSD to form a multi-source storage mode; a normalized network-on-chip, an interconnection transmission system, a storage control system and a plurality of calculation acceleration cores are arranged in the calculation chip; the normalized network-on-chip can read model parameters of a target position based on the storage control system and send the model parameters to the calculation acceleration core for calculation and recovery; and interacting with the management server and other computing acceleration units based on the interconnection transmission system, and reading and storing external model parameters and inter-chip model parameters. The technical problems of insufficient video memory capacity, too high hardware cost and limited transmission bandwidth in a traditional scheme are effectively solved through collaborative design of a mixed video memory architecture and a normalized network-on-chip in combination with a multi-stage routing control and dynamic configuration mechanism.

Disclosed is a wake-interaction network analysis model for wind farm optimization and method to manage and mitigate complex wake interactions in wind farms. Operationally, our method creates a dynamic network model where each wind turbine is treated as a node within a comprehensive network. The interactions between these nodes, representing the wake effects of one turbine on another, are mapped as weighted edges in the network. These weights are quantified based on sophisticated wake models, incorporating factors like wind speed, direction, and atmospheric conditions. Furthermore, our inventive method and model exhibits a dynamic adaptability to changing wind conditions. Unlike traditional static models, it recalculates the network's edges in real-time, reflecting the varying impact of wake interactions as wind direction and speed fluctuate. This dynamic adaption advantageously ensures that the model remains accurate and relevant under different environmental scenarios.

The invention relates to the technical field of classroom interaction, and discloses a classroom interaction evaluation method and system based on voice data, and the method comprises the steps: collecting classroom voice data, and converting an audio signal in the voice data into a digital signal; the collected audio signals are preprocessed, the audio is converted into characters, and voice data of different speakers are separated; analyzing the voice data of different speakers to obtain a speaker interaction sequence; carrying out statistics on the speaker interaction sequence to obtain interaction frequency characteristics among different speakers; constructing a classroom interaction network based on the speakers based on the obtained interaction durations and interaction frequencies among the different speakers; a social network analysis technology is utilized to perform deep analysis on a classroom interaction network, and classroom interaction behaviors are evaluated through quantitative evaluation parameters. According to the invention, the accuracy and efficiency of classroom interaction analysis are improved, and targeted classroom interaction organization and improvement suggestions are provided for teachers through deep analysis of interaction behaviors.

The invention provides a federal cross-modal retrieval method and system based on interactive prompts, and relates to the field of cross-modal information retrieve.The federal cross-modal retrieval method and system based on interactive prompts retrieve similar second modal data from a second modal data set by using first modal data based on the feature similarity of two modal data comprises the steps that initial features of the two modal data are extracted respectively; performing multi-layer bidirectional interaction between the initial features of the two modals by using a cross-modal interaction network obtained by federal learning and taking a prompt vector as an intermediary to obtain final features of the two modals after cross-modal interaction; calculating feature similarity based on the final features of the two modalities, and screening similar second modal data; according to the method, federal learning and prompt learning are combined, so that the effectiveness and universality of a cross-modal retrieval technology are improved, and the problems of privacy protection and performance optimization in cross-modal retrieval are solved.

The invention discloses a bidirectional GCN-BERT scientific data classification method based on rotary coding and dynamic gating, which comprises the following steps of: firstly, preprocessing original text data, acquiring a classification mark containing global information by utilizing a pre-training model, and adding the classification mark to the beginning of an input text; secondly, feature optimization is carried out on the classification marks through a CorNet neural network, and then position enhancement and global interaction are carried out through a rotation position enhancement multi-layer feature interaction network RP-MLFIN; and then the image is transmitted to a bidirectional image convolution neural network for feature interaction and image convolution processing, and image level representation is generated. Finally, the classification marks after feature optimization and the representation of the graph level are transmitted to a classifier, BERT prediction and GCN prediction are generated, prediction results are fused through an attention mechanism, and a final classification decision is generated. According to the method, the processing capability of text data with strong context dependence and the stability and robustness of a classification result are improved.