221results about How to "Increase training speed" patented technology

The invention discloses a quantitative training method and system for a deep neural network, and the method comprises the steps: obtaining an original neural network model and a verification data set, and generating a quantitative priority through hierarchical sensitivity evaluation and topology analysis; on the basis of the layer sensitivity matrix, differentiated quantization parameters are configured for each layer, and quantization constraints are established; constructing an error compensation mechanism, and generating an error compensation strategy; executing dual-scale adaptive quantization training, and respectively adopting an independently optimized quantization strategy for forward propagation and back propagation; dynamically adjusting quantization parameters according to the training state and the resource constraint; and evaluating model performance and resource efficiency. According to the method, through multi-dimensional sensitivity evaluation, a dynamic quantification strategy and system error compensation, the precision and efficiency of quantification training are improved, and meanwhile it is guaranteed that deployment resource constraints are met.

The invention discloses an efficient auditing method and system based on an edge computing technology, and relates to the technical field of auditing methods and systems.The efficient auditing method comprises the following steps that S1, data collection and preprocessing are conducted, specifically, business data are collected in real time through various sensors and interfaces at edge nodes, and preprocessing is conducted; s2, edge side data analysis: performing real-time analysis on the preprocessed data by utilizing edge computing resources; s3, feature extraction and model training; s4, constructing a risk assessment and early warning model based on edge analysis and a model training result; s5, edge and cloud collaborative auditing; the edge node compresses and encrypts the processing result and the key feature data and then uploads the data to the cloud; and S6, visualizing an audit result and generating a report. According to the method, data acquisition and preprocessing, analysis and model training are realized through edge calculation, the auditing efficiency and accuracy are improved, a risk assessment and early warning model is constructed, the edge and the cloud are coordinated, and comprehensive, timely and reliable auditing support is provided for enterprises.

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.

The invention discloses a large language model training method and system based on elastic federal low-rank adaptive fine tuning, which adopts federal aggregation based on singular value decomposition (SVD) to reconstruct a local LoRA module of a client into a local increment matrix, then aggregates the local increment matrix into a global increment matrix, and generates a LoRA module of the next round through SVD, thereby effectively eliminating aggregation errors of traditional FedLoRA. According to the method, the LoRA rank is dynamically distributed for each weight matrix, and the balance between statistics and hardware efficiency is realized. In order to further reduce communication overhead and maintain model precision, a self-adaptive matrix freezing mechanism is introduced, and whether freezing is carried out or not is judged according to training stability of a weight matrix. According to the method, challenges of traditional FedLoRA in the aspects of training efficiency, communication overhead, model precision and the like are solved.

The invention discloses a lifelong target re-identification method based on descriptive text prompt prototype compensation, relates to the field of computer vision, and aims to display and solve the problem of feature drift caused by model increment update by introducing a prompt prototype compensation module. The module generates a multi-modal vision and text prototype for each target category through a vision language pre-training model, and maps old task features to a new task feature space through a cross attention mechanism so as to realize fine-grained semantic drift compensation. In addition, a boundary perception prototype correction module is designed to solve the problem of boundary confusion caused by updating of old prototypes. The module dynamically samples false features in compensation distribution to correct old prototypes with fuzzy boundaries, focuses on categories easy to confuse to maintain clear decision boundaries, optimizes cross-task and intra-task correction loss to reduce category confusion, effectively alleviates the problem of disastrous forgetting, and improves the adaptability and generalization ability of the model.

The invention discloses a human face sensitive data protection method based on an elastic anti-interference privacy protection mechanism, belongs to the field of information processing, and provides a dynamic self-adaptive sampling strategy based on information entropy in a data preprocessing stage, and the sampling rate is adjusted according to the distribution characteristics of a human face data set and the weight of sensitive information. And the model performance is maximized on the premise of ensuring user privacy. In order to obtain a better privacy protection effect, an entropy adjustment differential privacy mechanism is designed, and Gaussian noise of different degrees is adaptively added according to an information entropy value of face data after a face data set is dynamically and adaptively sampled, so that refined privacy protection of face sensitive data under differential privacy constraint is realized. In a model training stage, an elastic anti-interference training method is provided, diversified adversarial samples are dynamically generated in different stages of model training, and the over-fitting risk of the model is reduced while the robustness of the model to various types of adversarial attacks is enhanced.

The invention relates to the technical field of farmland identification, and discloses a remote sensing image classification and farmland identification method based on deep learning, comprising the following steps: S1, data collection: acquiring remote sensing image data covering a target farmland area; s2, data preprocessing and labeling: preprocessing the remote sensing image data, and labeling the preprocessed data; s3, model construction: constructing a convolutional neural network model, and training the model by using the preprocessed remote sensing image data and annotation data; and S4, remote sensing image classification and farmland identification: inputting a to-be-identified remote sensing image into the trained convolutional neural network model, and outputting a classification result by the convolutional neural network model. According to the invention, transfer learning and fine tuning technologies are utilized, and a pre-trained deep learning model is applied to a remote sensing image farmland identification task, so that the remote sensing image farmland identification task can adapt to farmland identification tasks of different regions, different seasons and different crop types.

The invention discloses an in-structure sound field bounded uncertainty analysis method based on a physical information neural network. The method comprises the following steps: establishing a physical information loss function and establishing a physical information driven neural network; obtaining an input uncertain parameter value range of the internal sound field, obtaining a plurality of parameter levels, and training a sound pressure prediction model under the parameter levels; acquiring sound pressure of a sample point and establishing a data set; establishing a data driving residual error based on the data set, establishing an overall loss function by using the data driving residual error and a physical information loss function, and training a parameter-containing physical information driving neural network to obtain a parameter-containing internal sound field sound pressure prediction model; and establishing an interval model, and obtaining an internal sound field sound pressure uncertainty distribution range by using a global search algorithm and the parameter-containing internal sound field sound pressure prediction model. The method can solve the problem of prediction of the sound field in the structure containing uncertain parameters, and can effectively improve the calculation efficiency on the premise of ensuring that the calculation precision meets the engineering requirements.

The invention discloses a TEC space-time prediction method based on fusion of feature analysis and a self-attention mechanism, and the method comprises the steps: screening strong effective features through analyzing the correlation between TEC historical data and each feature parameter, calculating the attention weight between data points on each time sequence through employing a self-attention coding mechanism, and carrying out the weighted summation to obtain the attention output. In an ionosphere total electron content prediction task, firstly, for sun and geomagnetic activity characteristic parameters, the correlation between each parameter and a TEC sequence in the same time period and a TEC sequence after a day interval is evaluated, strong correlation characteristics are screened, TEC sequences of adjacent grid points are used as characteristic quantities, multiple spatio-temporal characteristic matrixes of different time scales in a global range are established, and the total electron content of the ionosphere is predicted. And encoding the input feature information according to a self-attention encoding mechanism to obtain an attention output result, and decoding in a decoding layer through a linear model to obtain a TEC predicted value at a future moment. According to the method, efficient extraction of spatio-temporal information can be completed, and higher-precision prediction of the TEC is realized through a self-attention mechanism.

The invention relates to the technical field of artificial intelligence, and discloses a multi-modal model training fine-tuning optimization method based on artificial intelligence, which comprises the following specific steps: preparing and preprocessing data, collecting a large-scale multi-modal data set, constructing an image text data set containing one million high-quality images and text description accurately corresponding to the images, and performing fine-tuning optimization on the image text data set. According to the method, data are subjected to comprehensive and meticulous cleaning operation, noise data and mistakenly labeled data in the data are strictly removed, so that the accuracy and reliability of the data are ensured, and the effective utilization rate of the data can be increased by at least 20% through data cleaning; wherein the image data is screened, blurred, low-resolution and unclear-content images are removed, it is ensured that each image can clearly convey specific visual information, and text description, grammar error checking, spelling error and semantic ambiguity parts are corrected or deleted.

The invention discloses a regional school site selection optimization method and system based on an improved black plinuan search algorithm, and the method comprises the steps: building a regional school site selection optimization model through an XGBoost algorithm, and enabling the regional school site selection optimization model to achieve the optimization of a multi-target optimization function composed of school bearing pressure, student school accessibility and school service coverage rate as a target; according to the method, a regional school site selection optimization model is solved through an improved Black-South optimization algorithm, and the improved Black-South optimization algorithm is obtained through a Sine chaotic mapping initialization population, a golden sine search strategy and the search performance of a Gaussian disturbance improvement algorithm, so that the diversity of the population is increased, and the global search and local optimization capability of the algorithm is improved. According to the method, the regional school site selection optimization model can be established through the XGBoost algorithm, the optimization speed can be effectively improved, and the global search and local optimization capability of the algorithm can be effectively improved by improving the Black-Youlinuan optimization algorithm and increasing the diversity of populations.

The invention relates to a remote sensing target detection method and device based on multiple scales and an efficient attention mechanism, and the method comprises the steps: obtaining a target remote sensing image, inputting the target remote sensing image into a target detection model, and obtaining a target detection result; wherein the target detection model comprises the following steps: replacing a 3 * 3 common convolution in the sixth network layer ELANBlock of the YOLOv7 by using a 3 * 3 depth separable convolution; replacing a 3 * 3 common convolution in the ELANBlock of the eighth network layer of the YOLOv7 by using a 5 * 5 depth separable convolution; using a 7 * 7 depth separable convolution to replace a 3 * 3 common convolution in the ELANBlock of the tenth network layer of the YOLOv7; an MIA-M module based on multi-scale efficient attention is used for replacing the 17th network layer ELANBlock and the 23rd network layer ELANBlock of the YOLOv7; an MIA-S module based on multi-scale efficient attention is used for replacing the ELANBlock of the 21st network layer of the YOLOv7; and replacing the ELANBlock of the 25th network layer of the YOLOv7 with a multi-scale efficient attention MIA-L module to obtain a target detection model.

The invention relates to a tropical cyclone strength intelligent forecasting method and device based on feature adaptive optimization. The method comprises the following steps: constructing an initial data set; the initial data set is divided into a model training sample and an independent test sample; selecting a pre-training model; inputting the model training sample into a pre-training model for feature adaptive optimization, and obtaining a high impact factor set influencing tropical cyclone strength prediction accuracy; performing model optimization training; and carrying out model robustness test and tropical cyclone strength intelligent forecasting. According to the method, the high impact factor set which is most critical to tropical cyclone strength forecasting can be rapidly extracted, and the tropical cyclone strength forecasting accuracy is remarkably improved.

The invention discloses a hierarchical object modeling and rapid reconstruction method based on NeRF, and the method comprises the following steps: image preprocessing: initially obtaining an image video frame through a camera, carrying out the related processing of an input image, including semantic segmentation, depth estimation, normal estimation and internal and external parameter calibration, and generating a corresponding semantic graph, a depth graph, a normal graph and camera parameters; space partitioning: partitioning the scene according to the semantic graph information and defining a bounding box; adaptive sampling: performing adaptive sampling by combining the depth map, the normal map and the camera parameters, and determining a sampling point set; and performing hierarchical vectorization SDF reconstruction, performing hierarchical vectorization SDF reconstruction by using the sampling points to obtain hierarchical SDF representation describing the shape of the object, converting the hierarchical SDF into a triangular mesh model, and completing three-dimensional object modeling and rapid reconstruction. The invention provides a hierarchical object modeling and rapid reconstruction method based on NeRF, objects in a scene are rapidly reconstructed, and downstream editing tasks, interaction and other applications are supported.

The invention provides a bar code detection method and system based on improved YOLOv8, and relates to the technical field of target detection.The method comprises the steps that a sample set with a plurality of bar code pictures is established, and each bar code picture is provided with a bar code position label and a bar code category label; a bar code detection model is constructed, and the bar code detection model comprises a backbone network module, a neck network module and a detection head module which are connected in sequence; establishing a joint loss function comprising a DFL loss function and a CIoU loss function; inputting the extended data set into a bar code detection model to train the bar code detection model until the joint loss function value is smaller than a preset joint loss function value; obtaining a to-be-detected bar code picture; and inputting a to-be-detected bar code picture into the trained bar code detection model, and outputting a predicted bar code position and a predicted bar code category. Detection resource consumption is reduced, and detection accuracy and detection speed are improved.

The invention relates to a transformer substation flood prevention case text classification method and device, equipment and a medium, belongs to the field of natural language processing text classification, and is used for carrying out multi-label classification on transformer substation flood prevention case texts to be predicted based on a completely trained improved BERT model to obtain disaster cause labels of the flood prevention case texts. The improved BERT model comprises an embedded layer, an encoder layer, a TextCNN (Convolutional Neural Network) layer and a Seq2Seq layer; the transformer substation flood prevention case text classification method comprises the steps of extracting a text vector of a to-be-predicted transformer substation flood prevention case text based on an embedded layer, and compressing the text vector by adopting a lightweight strategy; extracting global semantic features of the compressed text vector based on an encoder layer; performing feature extraction on the global semantic features based on a TextCNN layer to obtain feature vectors; the feature vector is coded and decoded based on the Seq2Seq layer, the disaster-causing cause label of the flood prevention case text is obtained, the overall classification performance is enhanced, and the accuracy of the single cause label is improved.

The invention provides a multi-modal data integration, matching and interpolation method based on optimal transmission driving. According to the method, a Wasserstein auto-encoder model driven by an optimal transmission theory is constructed. The model can capture complex distribution of different modal data, and effectively deals with a feature sparsity problem through regularization of a potential space. And meanwhile, the similarity between the same kind of modals is enhanced by the model through comparative learning based on sample categories, so that an encoder with strong feature extraction and matching capabilities is trained, the data integration and matching process is optimized, and the accuracy of data interpolation is also remarkably improved. The innovative method successfully deals with the core challenge of multi-modal data integration and analysis in the field of data science, and shows wide application prospects and remarkable actual values especially in the fields of medical images, automatic driving, sentiment analysis and the like.

The invention discloses a trapezoidal sail multi-target size optimization method based on an NSGA-II algorithm, and relates to the technical field of unmanned sailboats. According to the method, the aspect ratio, the taper ratio and the camber ratio are selected as design parameters of the trapezoidal sail, after multiple sets of design parameters are sampled and obtained within the value range of the design parameters based on a Latin hypercube sampling method, a trapezoidal sail model is constructed by utilizing fluid simulation analysis software for each set of design parameters, and the trapezoidal sail model is obtained. Performance evaluation parameters corresponding to each group of design parameters are obtained through simulation, a database is constructed, the database is utilized to train a Kriging agent model for replacement, multiple groups of trapezoidal sail design parameters to be preferentially selected are selected, and multi-target size optimization is performed on the trapezoidal sail design parameters based on an NSGA-II algorithm and the trained Kriging agent model. And determining optimal trapezoidal sail design parameters and verifying the accuracy of the optimal trapezoidal sail design parameters. According to the method, trapezoidal sail design parameters and performance evaluation parameters are combined, and a basis is provided for optimization of a sail design scheme by using an NSGA-II method and a Kriging agent model.

The invention relates to a pet health discrimination method and device based on a gradient lifting xgboost model. The method comprises the following steps: S1, acquiring a historical detection data record of an intelligent pet cat litter basin; s2, performing data set division and xgboost model verification and training on the historical detection data by adopting a data set division method of ten-fold cross validation, and optimizing the xgboost model in each cross validation; s3, performing identification model training based on an xgboost algorithm according to the historical detection data to obtain a cat health condition discrimination model corresponding to the intelligent pet cat litter basin and health index importance corresponding to the pet cat litter basin; s4, monitoring the performance of the xgboost model, and performing incremental updating of the pet health discrimination model and continuous optimization of feature selection according to historical detection data and new detection data; and S5, smoothing the pet health index to obtain a warning threshold value of the intelligent pet cat litter box, and when the real-time detection data of the intelligent pet cat litter box exceeds the warning threshold value, performing pet health abnormity warning on a pet owner.

The invention provides a power battery high-precision temperature field modeling method based on an embedded optical fiber sensor, and the method comprises the steps: building a distributed optical fiber temperature sensing system in a lossless manner, obtaining the internal and external temperature data of a battery, and only employing a small number of parameters, such as the voltage, current, temperature, etc. Establishing a battery internal temperature field prediction model based on the GRU neural network; the Bayesian optimization algorithm is introduced in the model training to perform hyper-parameter search, the training speed can be effectively improved, and the temperature field modeling precision is also ensured by taking the EKF-based battery SOC and SOH joint estimation result as the model input. The method provided by the invention can be widely applied to commercial batteries of various models, and is beneficial to early identification of various faults which may cause abnormal internal high temperature, such as negative electrode lithium precipitation, internal short circuit, overcharge and the like, so that the use safety of the battery can be improved, and the intelligent management level of the power battery is improved from the overall level.

The invention discloses a low signal-to-noise ratio DOA estimation method based on an auto-encoder and a deep neural network, comprising a low signal-to-noise ratio DOA estimation method and a DOA estimation method combining DAE and CNN, the low signal-to-noise ratio DOA estimation method comprises the following steps: giving parameters such as array radar receiving antenna array element number M, array element position dm, signal-to-noise ratio SNR, input signal sin and the like; obtaining an array receiving data covariance matrix R; taking a real part and an imaginary part of a received signal covariance matrix R in an incidence angle [-60 degrees, 60 degrees] range as input Y1 of the neural network, constructing a data set, and distinguishing a training set and a test set according to a proportion of 8: 2; dAE network parameters are initialized, data in the training set are imported, forward propagation is completed, meanwhile, back propagation is conducted on errors, and network weights are synchronously updated; a DAE network structure is further introduced to optimize signal processing, the DOA estimation accuracy is improved, and the requirement for complex computing resources is lowered.

The invention provides a wind turbine generator fault diagnosis system and method, and the system comprises a data generation module which is used for calculating corresponding simulation data according to the fault mechanism of equipment through employing an aerodynamic system model, a transmission system model and a variable pitch system model, learning a distribution mode reflecting fault categories through a data training generation model together with historical faults, and generating virtual fault data; and the fault diagnosis module is used for performing fault diagnosis on the input operation data of the wind turbine generator by using the trained probabilistic neural network. The method has the advantages that enough training data can be generated according to training requirements, meanwhile, the distribution range of the training data is wider than that of mechanism simulation data, the training data is closer to real operation data, and the precision of a fault diagnosis model is greatly improved; compared with a single probabilistic neural network algorithm, the fault diagnosis module has the advantages that the training process of the probabilistic neural network is optimized by utilizing the genetic algorithm, and the training speed is increased.

The invention provides a GPU cluster NLP task parallelization system and method based on a particle swarm optimization, and the method comprises the steps: carrying out the analysis of an input NLP model based on a task decomposition module, dividing the NLP model into a plurality of subtasks, and collecting and recording the GPU cluster resource state based on a GPU resource management module, a plurality of sub-tasks are mapped on a GPU cluster based on a task allocation module, a plurality of independent particle swarms are constructed, task allocation is optimized by using a particle swarm algorithm based on a particle swarm optimization module, task execution is scheduled according to an optimized task allocation scheme based on a task scheduling module, and task execution is completed. And based on a result processing module, collecting and integrating sub-task calculation results on each GPU, and outputting the sub-task calculation results. According to the method, the NLP training speed is remarkably increased, the resource utilization efficiency is effectively improved, and the method is suitable for being used in a compute-intensive NLP task and particularly has a remarkable effect in a scene where GPU resources are rich and highly parallel computing is needed.

The invention relates to the technical field of business process automation, in particular to an employee automatic business process processing method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining a general teacher model and a target student model used for an automatic business process, and a feedback confirmation result of the operation of the target student model; and performing primary knowledge distillation optimization on the target student model according to the general teacher model. Wherein the feedback confirmation result is used for controlling the learning strength of the target learning model to the general teacher model during the optimization. Compared with the prior art, the target student model is dynamically adjusted by using the feedback confirmation result, so that the target student model is more and more accordant with the personalized operation habit of the user along with the increase of the operation frequency, and the feedback confirmation result is combined with the knowledge distillation technology to accelerate the training speed of the target student model; the application flexibility of the automatic business process technology is improved, and the problem that the business process automation technology in the prior art is lack of individuation is solved.

The invention discloses a product intelligent detection model minimization learning method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring product image training sets of different projects in different fields; respectively extracting guidance feature maps of at least two scales of each product sample image in the product image training set through a pre-trained original deep learning model; according to the guidance feature map of each scale, determining a feature information fusion matrix and a guidance signal fusion matrix of a network layer corresponding to each scale in a preset fine and small neural network model; and according to the feature information fusion matrix and the guidance signal fusion matrix, learning network parameters in a corresponding network layer in a preset fine and small neural network model, and generating a target product detection model. According to the scheme, the network structure size of the target product detection model is remarkably reduced, the training speed of the target product detection model is improved, and the target product detection model can be effectively ensured to learn the globally optimal solution.

The invention provides a wind power prediction method and device based on a meteorological large model, a server and a medium. The method comprises the following steps: constructing a multi-scale prediction model; acquiring historical actual power of the wind power station, and acquiring multi-scale historical meteorological elements through the large meteorological model; training the multi-scale prediction model, and performing hyper-parameter optimization on the multi-scale prediction model through an improved arithmetic optimization algorithm; and obtaining multi-scale instant meteorological elements through the meteorological large model, inputting the multi-scale instant meteorological elements into the multi-scale prediction model after hyper-parameter optimization, and generating a wind power prediction result based on the meteorological large model. According to the wind power prediction method and device based on the meteorological large model, the server and the medium, the limitation of a traditional wind power prediction method can be overcome, and the accuracy and the stability of a wind power prediction result are improved.

The invention relates to the technical field of radio frequency quadrupole accelerators, in particular to a method for predicting electromagnetic field distribution of a radio frequency quadrupole accelerator by adopting a support vector machine, which comprises the following steps of: acquiring an electric field signal, a magnetic field signal and electromagnetic field distribution in the radio frequency quadrupole accelerator by presetting an electric field probe and a Hall sensor; denoising, de-trending, normalizing and smoothing the collected electric field signal and magnetic field signal to improve the signal quality and the accuracy of subsequent analysis; performing wavelet transform analysis on the collected electric field signals, extracting electric field characteristic parameters, performing wavelet transform analysis on the collected magnetic field signals, and extracting magnetic field characteristic parameters. According to the method, the wavelet transform and the support vector machine are combined, the advantages of the wavelet transform in the aspects of multi-scale signal analysis and noise suppression can be fully played, and meanwhile, the precision, efficiency, robustness and adaptability of radio frequency quadrupole accelerator electromagnetic field distribution prediction are remarkably improved by utilizing the strong classification and regression capability of the SVM.

The invention relates to the technical field of artificial intelligence, and discloses a time series prediction method based on long and short term features, which comprises the following steps: inputting multi-dimensional time series data with the length of T; the method comprises the following steps: processing input time sequence data through a long and short feature layer in an encoder to generate long-term features and short-term features, and performing feature fusion on the extracted long-term features and short-term features; the long and short feature layer comprises a convolutional neural network and a long and short-term memory neural network, the convolutional neural network is used for extracting multi-dimensional data features of the input data, and the long and short-term memory neural network is used for extracting long-term and short-term features of the input data. By combining the long and short feature layers of the convolutional neural network and the long and short-term memory neural network, the short-term fluctuation and the long-term trend in the time sequence data can be effectively extracted, and the multi-scale feature extraction technology enables the model to better capture the complex time sequence dependency relationship in the data, so that the accuracy of time sequence prediction is remarkably improved.

The invention discloses a deep learning-based multi-scale feature fusion marine target identification method, which comprises the following steps of: acquiring picture and video data of various marine targets of a marine ship, and acquiring and generating a marine target detection data set, ocean targets are divided into 10 types of yachts, warships, passenger ships, cargo ships, sailboats, tugboats, kayaks, navigation marks, lighthouses, fishing boats and the like, a multi-scale feature fusion module is added in a deep learning network for the problem that the detection precision of a self-built ocean target data set is insufficient, and the detection precision is improved by fusing multi-layer features and injecting global information into a higher layer. An improved deep learning network model used for sea target identification is constructed, the method has the characteristic of having a good detection effect on small sea targets, multiple targets and overlapped targets, the model can be deployed in navigation cameras of ships after iteration training is finished, a monitoring system is established in a matched mode, and the detection accuracy is improved. And various targets on the sea can be monitored in real time.

The invention discloses a long text analysis method, device and equipment based on a hybrid expert model. The method comprises the following steps: acquiring a long text to be analyzed; inputting the long text into a target analysis model to obtain a target attention result; the target analysis model comprises a gated attention unit improved based on a hybrid expert model; and on the basis of the target attention result, generating an analysis result corresponding to the long text, so that the model analysis accuracy can be effectively improved on the basis of improving the calculation efficiency.