487 results about "Network Convergence" patented technology

The invention discloses a deep learning-based deep fusion network production line fault prediction method, which comprises the following steps of: firstly, acquiring SCADA (Supervisory Control And Data Acquisition) system or sensor data of an automatic production line, and carrying out data preprocessing, feature extraction and fault prediction label construction; then a deep fusion network 1D-CNN-LSTM-Attention-DCE model combining a one-dimensional convolutional network, a long short-term memory neural network, a fusion attention mechanism and a dynamic cross entropy loss function DCE is established, the preprocessed data is input into the constructed model for training, and finally the trained model is used for fault prediction to obtain a fault prediction result. According to the method, a 1D-CNN-LSTM-Attention-DCE fault prediction model is provided, local features are extracted from time sequence data by using the 1D-CNN, then a long-time dependency relationship is captured through LSTM, and finally weight distribution of key features is enhanced through an attention mechanism, so that the processing capability of the fault prediction model on complex time sequence data is comprehensively improved, and the fault prediction efficiency is improved. And the fault of the production line can be accurately predicted within a certain time length range.

The provided are a federated reinforcement learning (FRL) end-to-end autonomous driving control system and method, as well as vehicular equipment, based on complex network cognition. An FRL algorithm framework is provided, designated as FLDPPO, for dense urban traffic. This framework combines rule-based complex network cognition with end-to-end FRL through the design of a loss function. FLDPPO employs a dynamic driving guidance system to assist agents in learning rules, thereby enabling them to navigate complex urban driving environments and dense traffic scenarios. Moreover, the provided framework utilizes a multi-agent FRL architecture, whereby models are trained through parameter aggregation to safeguard vehicle-side privacy, accelerate network convergence, reduce communication consumption, and achieve a balance between sampling efficiency and high robustness of the model.

Disclosed in the present invention are an autonomous driving control system and method based on complex network cognition and end-to-end federated reinforcement learning, and a vehicle device. An autonomous driving algorithm framework (FLDPPO) based on complex network cognition and end-to-end federated reinforcement learning under urban dense traffic is provided, and by designing a loss function, a combination of rule-based complex network cognition and end-to-end federated reinforcement learning is achieved. In the FLDPPO, dynamic driving suggestions are used to guide agents to learn rules, so that the agents can cope with a complex urban driving environment and a dense traffic scenario. Moreover, the provided framework uses a multi-agent federated reinforcement learning architecture, and models are trained by means of parameter aggregation, protecting the privacy of a vehicle end while accelerating network convergence, reducing communication consumption, and achieving the balance between sample efficiency and high robustness of the models.

The invention discloses a network management computing power session method and system based on 6G communication, sensing and computing integration, belongs to the technical field of mobile communication, and aims to solve the technical problem of how to realize flexible scheduling and on-demand distribution of computing power and network convergence resources in a 6G communication, sensing and computing integration network environment under the condition of not changing network equipment. A mobile network environment supporting a computing power-as-a-service mode is constructed for a user, and the adopted technical scheme is as follows: the method comprises the following steps of: deploying a computing network integration sensing network element, a computing network integration control scheduling network element and a computing network integration service arrangement network element on a core network side, so that the improved core network has a communication, sensing and computing power integration function; and through analysis and identification of computing power application request indexes, computing power business arrangement, computing power and network Qos configuration mapping, decision making and scheduling of computing network fusion resources, distributed cooperative computing tasks are issued, so that computing power session creation is completed, and different computing power requirements of the mobile terminal are met.

The invention provides an environment detection method and system based on a sample target detection model. The method comprises the following steps: synchronously acquiring an environment image, a video stream and physical parameters by using a multi-mode sensor; decomposing the data into image features and environmental parameter components through a dual-time sequence control signal, and realizing space-time alignment by adopting a linear phase filter; constructing a foreground region template based on the depth information, and generating target recognition feature representation containing an abnormal blurred target; adversarial training is carried out on the lightweight target detection network in combination with a transfer learning strategy, the network integrates convolutional features and a Transform attention mechanism, and the weight is dynamically adjusted through environmental parameters; fusing a target result and sensor data in real-time detection, and inputting a decision tree model for risk grading; and after the early warning is triggered, reconstructing a false detection sample through an online learning mechanism and iteratively optimizing the model. The system correspondingly comprises a multi-modal data acquisition module, a data enhancement and annotation module, a model training module, a real-time detection and fusion module and an early warning and optimization module. According to the invention, through multi-source data fusion, dynamic data enhancement and an adaptive compensation mechanism, the small target detection precision, the environmental adaptability and the real-time early warning capability are significantly improved.

The invention discloses a hyperspectral image classification method based on an S2CFM-spatial spectrum convolution fusion Mama network model, and the method employs a parallel double-branch structure to extract the spatial context information and spectral sequence features of a hyperspectral image, and finally integrates the features through a dynamic convolution fusion module, thereby achieving the classification of the hyperspectral image. The method solves the problem of unbalanced utilization of space-spectrum information in a traditional method, introduces a space spectrum convolution fusion Mama network, and fuses a multi-scale convolution block (MCB), a dynamic convolution block (DCB) and a space spectrum Mama block (S2MB); the method solves the problems that in the prior art, the capacity of CNN for capturing spectral information is relatively limited, and a complex spectrum-space characteristic relation in hyperspectral data is difficult to fully represent; the problems that in HSI data, due to the fact that the dimensionality is high and the sample size is limited, an over-fitting problem is prone to occurring, and the generalization performance of the HSI data is limited are solved through a Transformers-based architecture.

The invention relates to the technical field of intelligent manufacturing decisions, in particular to a digital twinning-based manufacturing system decision analysis method and system, and the method comprises the steps: deploying a plurality of Internet of Things sensors on a physical manufacturing system, and collecting a physical real-time data stream of equipment in real time; the method comprises the following steps: establishing a virtual data acquisition channel aligned with a physical manufacturing system clock, injecting a physical real-time data stream into a digital twinning creation model, and performing data preprocessing based on distributed edge calculation to delay and compress original data acquisition of the physical real-time data stream to 10ms level, the time sequence database and the NTP / GPS clock are synchronized to ensure the state alignment error lt of the physical-virtual system; compared with the prior art, the deep space-time prediction network is fused with a CNN-LSTM-attention mechanism, the accuracy of multivariable coupled KPI prediction is improved, in addition, model failure is recognized in real time through Page-Hinkley inspection, and a prediction error reaches a relatively stable state through an adaptive retraining mechanism.

The invention discloses a reservoir water regimen analysis method and system based on artificial intelligence, and the method comprises the steps: collecting original signals from multi-source monitoring indexes, such as water level, flow, rainfall and water quality, carrying out the standardized conversion through employing distributed calculation nodes, and forming a unified multi-source data set; based on this, using a feature extraction network to fuse upstream rainfall and reservoir flow, extracting space-time correlation features, and determining a short-term water level change trend; historical water quality abnormal data are integrated through a sequence prediction network, a time sequence is modeled, and potential pollution risks are judged; when the risk exceeds a threshold value, dynamically adjusting the weight of the prediction model, and generating an optimized water regimen simulation scene; finally, resource scheduling logic is fused, multi-scene risks are evaluated, and an optimization management strategy is output. Through deep fusion of spatial-temporal feature extraction and dynamic prediction, accurate water regimen prediction and flood control water supply decision support are realized, and the water resource management efficiency and the pollution prevention and control capability are improved.

The invention discloses a cloud network fusion data processing method and system, and particularly relates to the technical field of data processing. The method comprises the following steps: constructing a link semantic dynamic graph based on space-time correlation analysis by extracting dynamic semantic parameters of transmission links in a heterogeneous network; and meanwhile, performing multi-dimensional semantic analysis on the cloud data stream to generate a data stream semantic fingerprint. The method comprises the following steps: identifying a semantic conflict type through matching degree analysis, reversely analyzing a node switching sequence and bandwidth fluctuation characteristics of a transmission path for a fragmentation strategy mismatch scene, evaluating the matching degree of a link and data processing logic, and generating a semantic compatibility matrix based on a fragment recombination rule and aggregated context characteristics; and the matching degree and the compatibility matrix are input into a dynamic compensation model, a fragment recombination strategy and a priority remapping rule are generated, whether real-time reconstruction of a data processing engine is triggered or not is judged, dynamic adaptation of network transmission semantics and cloud computing logic is achieved, and the real-time performance of data processing and the resource scheduling efficiency in the heterogeneous environment are improved.

The invention provides a service life prediction method for a deep sea watertight connector, and relates to the field of service life prediction, and the method specifically comprises the steps: constructing a tensor data set; inputting the decomposed feature tensor into a multi-scale sparse neural network, and extracting cross-scale degradation features through a cavity convolution module and an attention gating mechanism; the features are fused by using a dual-channel Transform-CBAM (Content Border Administration and Maintenance) network; learning invariant fault representation under deep sea environment disturbance by using a causal graph auto-encoder, and realizing cross-depth working condition distribution alignment through a domain adversarial network driven by a gradient inversion layer; and modeling random fluctuation influence through a nonlinear Wiener process of environmental parameter modulation, performing confidence interval quantization in combination with Monte Carlo path simulation and Bayesian inference, and outputting a dynamic residual life prediction result of the watertight connector. According to the technical scheme, the problem that the service life of the deep sea watertight connector cannot be accurately predicted in the prior art is solved.

The invention provides a computing power resource scheduling method and system based on cloud network integration. Selecting a computing power task to be scheduled as a current scheduling task, and generating a node resource adaptation matrix based on the real-time load data, the cloud network topological relation between the nodes and the dynamic bandwidth data; then calculating the lowest scheduling cost of each node according to the matrix, and determining a dynamic adjustment factor when a resource allocation conflict occurs in the current scheduling task; based on the lowest scheduling cost, the computing power demand scale and the data transmission estimated overhead, calculating the final scheduling overhead for scheduling the current scheduling task to each node; and finally, allocating tasks to a target node according to the final scheduling overhead, updating a running task queue, if a conflict occurs, calling a dynamic adjustment factor to execute resource reallocation, and updating the queue after the reallocation succeeds. And circulating the process until all tasks are scheduled. According to the scheme, optimal scheduling of computing power resources in a cloud network convergence environment can be realized.

The invention relates to a house building construction stage carbon emission dynamic estimation method and system based on full life cycle data, and the method comprises the steps: dividing a construction region based on a BIM model, laying a multi-source sensor network, fusing static BIM data and a dynamic Internet of Things monitoring flow, building a four-dimensional space-time label data set, and carrying out the construction stage carbon emission dynamic estimation based on a double-layer dynamic correction model. Kalman filtering is utilized to eliminate instantaneous interference, LSTM transfer learning is combined to predict mechanical efficiency attenuation, a dynamic correction coefficient matrix of a mechanical aging rate, operator skills and environmental factors is embedded, and a carbon emission value is calibrated in real time; when abnormal emission is detected, a key pollution source is traced and positioned through a graph neural network, a three-dimensional thermodynamic diagram is generated in the digital twinborn model, and component-level carbon flow analysis and early warning are performed, so that the carbon emission estimation precision is remarkably improved, the abnormal traceability time consumption is shortened, and the timeliness is remarkably improved.

The invention provides an RFID label positioning error correction method based on deep learning, and the method comprises the following steps: 1, deploying a multi-mode sensing network in a target region, synchronously collecting radio wave signals and environment auxiliary data of an RFID label, and constructing a space-time multi-dimensional feature data set; step 2, constructing a joint architecture hybrid model composed of a space-time Transform network and a generative adversarial network; according to the method, a space-time multi-dimensional feature data set is constructed by fusing RFID signals and environment auxiliary data through a multi-mode sensing network, adaptive parameters are dynamically generated in combination with a model-independent meta-learning algorithm so as to quickly respond to environment changes, multi-path signal correlation is captured by using a space-time Transform and generative adversarial network combined architecture, feature expression is optimized, and the robustness of the system is improved. The problems that a single signal feature is missing, model parameters cannot dynamically adapt to the environment and the anti-interference robustness of a traditional network is insufficient are effectively solved, and the effectiveness, the real-time performance and the precision of RFID label positioning in the complex environment are remarkably improved.

The invention discloses a multi-mode fusion driven multi-agent Transform collaborative power dispatching method and system, and the method comprises the steps: fusing three types of heterogeneous data, namely power grid topology, time sequence operation and equipment state, through a multi-mode projection network, and forming unified state representation; a Transform encoder is used for modeling a dependency and cooperation relationship between intelligent agents, and a mask decoder is used for generating a cooperation scheduling strategy in an autoregression mode; a strategy is evaluated and optimized by adopting a near-end strategy optimization algorithm and a joint reward function, and finally an instruction is converted into a control signal and a closed-loop learning mechanism is formed. The system comprises a multi-modal state perception and fusion module, a multi-agent collaborative representation module, a collaborative decision generation module, a joint strategy optimization and learning module and a scheduling strategy execution and feedback interface module. According to the method, the multi-source information utilization efficiency and the agent cooperation capability are effectively improved, and safe, stable and economical operation of the power grid under high-proportion new energy access is guaranteed.

The invention discloses a traffic accident detection method based on FFC and GCSA models. The method is innovatively improved based on a YOLOv8 network model. Firstly, a multi-scale feature fusion module FFC is designed in Backbone to replace an original C2f module, and the capability of fusing the multi-scale features of the network can be further improved on the premise of not increasing the network calculation amount, so that the network can fuse the multi-scale features on the level of finer granularity; then, a GCSA attention mechanism is introduced between a C2f module and a Deect module of a Neck layer, and the recognition capability of the model for key features in a complex environment is remarkably enhanced; and finally, establishing a loss function Focal-EIoU Loss for the improved YOLOv8 network structure, so that the network classification detection capability is improved, and the generalization capability of the model is improved. In a specific implementation process, a traffic accident image data set covering multiple scenes is constructed, and specialized data preprocessing is performed; then, end-to-end training and parameter optimization are carried out on the Traffic-YOLO network model obtained after improvement; and finally, integrating the optimized model to a traffic accident detection system for real-time target detection. Compared with the prior art, the method effectively improves the accuracy and robustness of traffic accident detection in a complex scene, and has important practical significance.

The invention discloses an intelligent heterogeneous network fusion optimization method and device based on a large model, and the method comprises the steps: collecting real-time network state data, service demand data and user equipment data of various heterogeneous networks, and carrying out the preprocessing; key features capable of reflecting real-time changes of network states and service requirements are extracted from the preprocessed data; a self-adaptive multi-modal fusion algorithm is adopted, modal characteristics of heterogeneous network data are automatically identified, and weights and parameters in the fusion process are dynamically adjusted, so that the optimal fusion effect is achieved; building a large model driven by deep learning in combination with a cross-network context awareness optimization strategy; and the intelligent fusion module dynamically selects the optimal network path and transmission strategy according to the output result of the large model. According to the method and the device, intelligent fusion of the network is realized by adopting a self-adaptive multi-modal fusion algorithm and a cross-network context sensing optimization strategy based on a large model of deep learning.

The invention discloses a vehicle monitoring method based on frame difference and deep learning fusion, and relates to the technical field of vehicle monitoring, cameras and environment sensors are deployed in a monitoring area, and videos and multi-source data are acquired by means of vehicle-road cooperation; a self-adaptive frame difference method is used, morphology and optical flow estimation are matched, a threshold value is determined according to the environment, and vehicle features are extracted; constructing a deep convolutional neural network with an attention mechanism, and training a model by using various data in combination with migration and reinforcement learning; fusing the two types of features based on a graph attention network to form high-quality fusion features; a space-time diagram convolutional network is combined with an LSTM to track a vehicle and predict a trajectory, a behavior pattern library is constructed to judge abnormity, and classification analysis is performed in combination with an SVM and a knowledge graph. According to the invention, the frame difference and deep learning are fused, the monitoring accuracy is improved, and the vehicle can be accurately identified and detected; the real-time performance is enhanced, the data is quickly processed, and the environmental influence is reduced; traffic management is assisted, and a safe and efficient traffic environment is created.

The invention relates to the technical field of power distribution, in particular to a dynamic power distribution method and system for an automobile charging pile, and the method comprises the steps: extracting the historical load data of the charging pile through a sensor, converting the data into a time series data set in a unified range, and carrying out the window sliding fitting through employing a convolutional neural network based on the time series data set; the future load demand of each charging pile is predicted, meanwhile, a graph structure network of a power transmission relation is constructed, node power distribution information is fused, a charging pile cooperation relation is established, the relation between the power demand of a single charging pile and the power grid bearing capacity is evaluated by adopting a genetic algorithm, power output is adjusted, the output ratio is calculated, and a reasonable power distribution scheme is formed; and finally, monitoring a power grid load and a charging pile operation state in real time, constructing a graph structure of a charging pile cooperation network based on a geographic position, changing independent management of the isolated charging piles into networked cooperation management, and enhancing reasonable resource allocation among the charging piles.

The invention discloses a wind turbine generator state monitoring method driven by network fusion of a knowledge graph and a space-time diagram. The method comprises the following steps: S1, collecting time sequence SCADA data and wind power text data of a wind turbine generator; s2, constructing the wind power text data into a wind power operation and maintenance knowledge graph; s3, generating time sequence diagram data by querying a wind power operation and maintenance knowledge graph and combining the preprocessed SCADA data; s4, carrying out normal behavior modeling on the time sequence diagram data by utilizing the time-space diagram neural network model, predicting each node in the diagram data in the healthy operation time period of the unit in the normal behavior modeling process, and calculating the maximum absolute value of the difference between the predicted value and the actual value of each node as the maximum absolute value of the difference between the predicted value and the actual value; the maximum absolute error is used as a health threshold value of each node to perform state monitoring; in the state monitoring stage, the matching condition of the mapping information of each node in the graph structure in the monitoring result of the real-time data and the fault transmission chain is compared, the health state of the unit is judged, and the fault early warning time is determined. According to the invention, the accuracy and robustness of the monitoring result are enhanced.

The invention discloses a task processing method and device based on a dynamic LoRA network, computer equipment and a storage medium, and the method comprises the steps: receiving a task processing text, recognizing a feature vector of the task processing text, and enabling the feature vector to at least indicate the semantic and context features of the task processing text; calculating correlation with a plurality of to-be-selected LoRA networks according to the feature vector of the task processing text; determining an activation probability of each to-be-selected LoRA network according to the correlation, and determining a to-be-activated target LoRA network according to the activation probability based on a pre-configured gating network; fusing the target LoRA network into a basic model to obtain a fusion model; and performing task processing based on the semantic and context features of the task processing text by using a fusion model so as to load the target LoRA network and then output a processing result of the task processing text. By dynamically accessing the LoRA network, the accuracy and efficiency of task processing are improved.

The invention discloses a human body attribute and identity recognition model training method, a human body attribute and identity recognition method and a related device. The training method comprises the following steps: constructing a human body attribute and identity recognition network comprising a backbone network and a classification layer; performing feature extraction on the pedestrian training image through a backbone network, and performing attribute classification on a first pedestrian feature extracted by the backbone network through a classification layer to obtain a first attribute classification result; calculating an identity loss value based on the identity ID tag of the pedestrian training image and the first pedestrian feature, and calculating an attribute loss value based on the attribute tag of the pedestrian training image and the first attribute classification result; calculating a total loss value through the identity loss value and the attribute loss value; and network parameters of the backbone network and the classification layer are updated through the total loss value until the human body attribute and identity recognition network converges, and a trained human body attribute and identity recognition model is obtained. According to the model training method, the number of model training is reduced, resource consumption is saved, and the requirement for hardware equipment can be lowered.

The invention provides a portable dynamic high-frequency electrocardio monitoring system and method, and provides an efficient solution aiming at the problems that traditional high-frequency electrocardio depends on exercise load, diagnosis is delayed, the detection rate is low and the like in myocardial ischemia diagnosis. Electrocardio acquisition hardware of the system adopts a high signal-to-noise ratio and high-fidelity design so as to enhance the detection capability of high-frequency electrocardiosignals, and data is transmitted to a mobile terminal in real time through a wireless module, so that continuous dynamic monitoring is realized. A software algorithm preprocesses the collected dynamic resting high-frequency electrocardio data, abnormal waveforms are removed, and high-frequency signals are extracted with 3 seconds as a unit. Then, the data are input into a pre-trained electrocardiogram classification network, the network integrates a multi-scale convolution module, a feature splicing module, a long-short term memory network module, a self-adaptive convolution module and other modules, automatic feature extraction and time sequence modeling are achieved, and early myocardial ischemia can be efficiently recognized. The system provides an efficient and real-time solution for early diagnosis and intervention of myocardial ischemia.

The invention discloses a remote sensing target detection method and system based on improved RT-DETR. The method comprises the following steps: step 1, collecting remote sensing image data; step 2, carrying out preprocessing such as denoising, contrast enhancement and definition enhancement on the acquired remote sensing image data; 3, making the preprocessed pictures into a remote sensing data set, and dividing the remote sensing data set into a training set and a verification set in proportion; 4, training the remote sensing data set by adopting an RT-DETR model to obtain a remote sensing target detector; step 5, optimizing various parameters of the target detector on the verification set by adopting a hyper-parameter search verification mode; and step 6, detecting a test image or video by using the remote sensing target detector optimized in the step 5. Compared with an original RT-DETR model, on the premise that original precision is kept, the calculation amount is reduced, and the network convergence speed is increased.

The invention relates to the technical field of Internet content distribution, and discloses a distributed edge cache acceleration method based on PCDN, comprising the following steps: step I: terminal node access and resource initialization, which includes node registration and authentication, resource information reporting and node classification and label management; step II, hierarchical caching strategy and content storage, wherein the hierarchical caching strategy and content storage comprises content popularity grading, cache writing strategy and cache replacement and elimination; and step III, dynamic content scheduling and distribution. According to the distributed edge cache acceleration method and device based on the PCDN, the content popularity and regional distribution are pre-judged in advance through a deep learning model, and bandwidths and resources of different networks are integrated through a network fusion technology, so that the purposes of reducing the number of times of source returning requests, breaking through the transmission limitation of a traditional single network (for example, only depending on a cellular network) and improving the transmission efficiency can be achieved. The effects of node contribution traceability and automatic execution excitation are achieved.

The invention discloses a dual-network fusion driver gesture recognition monitoring method, which comprises the following steps of: improving a YOLOv7 network by introducing a Res-CBAM structure, and enhancing the recognition capability of gesture characteristics in a cabin; the improved network structure is trained on a self-collected cockpit domain gesture data set. According to the method, a BN layer channel pruning method based on L1 regularization sparse training and an unstructured pruning method LAMP based on layer adaptive sparsity are provided, so that a predetermined global sparsity level is achieved; and after pruning, the model recovers the performance through fine tuning training, and performance verification is performed by using a verification set.

The invention relates to the technical field of information recommendation, in particular to a recipe recommendation method based on multi-modal anti-fact learning, which comprises the following steps: constructing a heterogeneous graph; using a graph neural network to obtain network fusion embedding characteristics of each user node as target embedding characteristics of each user node, and network fusion embedding characteristics of each recipe node in each mode; based on network fusion embedding characteristics of each recipe node in each mode, a multi-mode characteristic decoupling module is utilized to obtain mode sharing embedding characteristics, mode specific embedding characteristics and mode fusion embedding characteristics of each recipe node, and then an anti-fact learning network is utilized to obtain final anti-fact embedding characteristics of each recipe node; fusing the modal sharing embedding feature, the modal specific embedding feature and the final anti-fact embedding feature of each recipe node as the target embedding feature of each recipe node; and inputting the target embedded features of each user node and each recipe node into a prediction module, and outputting a prediction score between each user and each recipe. The recipe recommendation precision is improved.

The embodiment of the invention provides an automatic driving method and device based on reinforcement learning, equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a multi-mode state of a vehicle from a simulation environment; based on the multi-modal state, interaction data between an automatic driving decision-making model and a simulation environment is obtained, and the automatic driving decision-making model comprises a feature extraction network, a value network and a strategy network; storing the interaction data into a preset cache region; in response to the training request, obtaining target interaction data from a preset cache region as training data; freezing the feature extraction network; performing PPO reinforcement learning training on the value network and the strategy network according to the training data until the value network and the strategy network converge, and obtaining a trained automatic driving decision model; and performing automatic driving decision through the trained automatic driving decision model. The embodiment of the invention can improve the training effect of the automatic driving decision model so as to improve the accuracy of the automatic driving decision.

The invention discloses a tunnel pavement concrete early-age strength prediction method based on multi-network fusion modeling. The method comprises the following steps: S1, continuously and equally dividing a tunnel center line according to a certain interval; s2, only keeping a left-right adjacent segment relation for the segment, and calculating a direction weighted thermal gradient, a direction weighted humidity gradient and a direction weighted traffic disturbance gradient based on the state vector; s3, writing the state vector of each segment into a sliding window with a set time length at a fixed sampling period; s4, inputting the dynamic graph input tensor into a space-time diagram neural network; s5, comparing the prediction sequence with a preset strength threshold value, identifying potential weak segments, and calculating risk confidence in combination with the gating coefficient; and S6, writing the maintenance instruction packet into a corresponding PLC channel. Potential weak sections can be recognized, spraying, heat preservation curtains and ventilation equipment can be linked, and local precise maintenance and batch open traffic unified management are achieved.

The invention relates to the technical field of course analysis management, in particular to a course analysis management system based on deep learning. The method has the advantages that multi-modal data deep analysis realizes full-dimensional analysis of unstructured data by integrating a 3D-CNN model, a Transform architecture and a BERT model and synchronously extracting an attention hot area, a voice emotional state and a text knowledge point association network of a classroom video; nonlinear behavior modeling adopts an LSTM network and time convolutional network fusion model, a knowledge internalization path and forgetting curve prediction are dynamically generated, parameters are optimized in combination with incremental learning, and a transition rule across knowledge points is captured; a teaching scene-evaluation threshold mapping table is constructed based on a reinforcement learning algorithm through dynamic decision and resource collaboration, collaborative optimization under multi-campus data privacy protection is achieved in combination with a federated learning framework, GPU computing nodes are dynamically allocated through a heterogeneous resource scheduling engine, and the analysis efficiency is improved.

The invention discloses an anomaly detection method and device, equipment and a medium, and the method comprises the steps: obtaining to-be-detected data, and carrying out the multivariate time sequence preprocessing of the to-be-detected data, and obtaining time sequence data; performing time coding on the time sequence data through a time sequence correlation difference sub-model of the pre-training detection model to obtain a time sequence correlation abnormal score; performing spatial coding on the time series data through the spatial correlation difference sub-model, and determining a spatial correlation anomaly score; performing data reconstruction according to the time sequence association exception score and the space association exception score through a full-connection network to obtain an exception score at each time point; and comparing each anomaly score with a preset anomaly threshold to obtain an anomaly detection result. The correlation anomaly score of the time sequence and the correlation anomaly score of the space are extracted through the double-branch pre-training detection model, data reconstruction is completed by fusing information of the time sequence and the space based on the full-connection network, anomaly is found from the perspective of space-time correlation, the better anti-noise capacity is achieved, and the accuracy of the detection result is improved.