1515 results about "Model learning" patented technology

The invention provides a multi-modal sentiment analysis method based on knowledge distillation and a dynamic fusion mechanism. The multi-modal sentiment analysis method comprises the following steps: pre-training a single-modal teacher model; a single-mode teacher model is used for guiding the learning of a multi-mode student model, and through an interactive knowledge distillation mechanism, the middle layer probability distribution of the teacher model is used as a target to learn the correlation between modes and the cross-mode characteristics; interactive knowledge distillation comprises three loss functions: firstly, calculating the difference of output distribution of output layers of a teacher model and a student model, and defining the difference as cross-modal knowledge distillation loss; secondly, adding alignment loss based on a real label, and constraining a prediction result of the student model to be close to a real emotion label in a cross entropy form; and finally, introducing label smoothing loss to soften the real label. According to the method, the pre-trained single-mode teacher model with relatively good performance is stored and is used for guiding the learning of the multi-mode student model, meanwhile, the loss function is introduced to optimize the multi-mode student model, so that the multi-mode student model is gradually aligned with the output distribution of the teacher model, and meanwhile, the adaptive capacity of the multi-mode student model to the modal heterogeneity is enhanced. The single-mode teacher model greatly reduces the complexity of the model, reduces the calculation amount, and has better performance in the field of multi-mode sentiment analysis.

Disclosed is an industrial question answering model training method based on reinforcement learning and knowledge base matching, comprising the following steps: S1, collecting professional knowledge questions and answers in an industrial field to construct an industrial knowledge base, training a reward model, carrying out, for industrial knowledge questions and answers, matching comparison on outputs of an industrial question answering model and content of the industrial knowledge base, and obtaining reward values on the basis of similarities; S2, sorting the reward values, and using a sorting loss function to train and update parameters of a reward model network; and S3, carrying out industrial question answering model training, incorporating a penalty term for the reward values, and using a reinforcement learning algorithm to train the industrial question answering model multiple times to obtain an optimal strategy. According to the industrial question answering model training method based on reinforcement learning and knowledge base matching of the present invention, the reinforcement learning algorithm is used, and iterative training is carried out multiple times, thereby helping the industrial question answering model to learn and understand industrial professional knowledge and improving the question answering accuracy of the industrial question answering model.

The invention discloses a capacitor appearance intelligent defect detection method based on YOLO-NAS and Transform fusion, and belongs to the field of artificial intelligence and industrial automation, a lightweight backbone network is combined with MobileViT, a feature extraction architecture is optimized through NAS, and the global feature expression ability is improved; a Transform-FPN (Fabry-Perot Networking) is introduced to realize multi-scale feature fusion; instructing student model learning by utilizing high-order features of the teacher model through feature distillation; optimizing small target and irregular defect detection precision by adopting an improved positioning loss function; and the Soft-NMS and the DIOU-NMS are combined, and the calculation complexity is reduced through model pruning and hybrid quantization, so that the real-time detection deployment of the embedded equipment is realized. According to the capacitor appearance intelligent defect detection method based on YOLO-NAS and Transform fusion, the problems of missing detection of small targets, difficulty in distinguishing multiple defects and high model calculation complexity are solved by combining a lightweight backbone network, a Transform module, multi-scale feature fusion and an improved loss function.

The invention provides a cross-domain target detection method and system based on semi-supervised learning in extreme weather, and the method comprises the steps: enabling a student model to learn bounding box regression knowledge of a trained teacher model through distillation, so as to achieve the regression capability in extreme weather; performing instance-level feature adversarial training on a pre-training detection model which is obtained in a distillation stage and has a regression capability in extreme weather by using an intermediate-state image which is generated by a diffusion model and is closer to a target domain and has smaller noise, and determining a new teacher model and a new student model based on the detection model after the adversarial training; in the fine tuning stage, a dynamic category pseudo label screening strategy is utilized to screen pseudo labels generated by a new teacher model, and a screened target domain pseudo label is utilized to train a new student model to obtain a target detection model used for detecting a to-be-detected image in extreme weather. The phenomena of leak detection and error detection in extreme weather scenes in the prior art can be reduced, and the original reasoning speed is kept.

The invention relates to the technical field of motor control, and discloses a brushless motor adaptive control method and system based on artificial intelligence, and the method comprises the steps: collecting the multi-point temperature data of a motor, building a thermal dynamic model, and reconstructing the complete temperature field distribution; identifying a relation function between motor parameters and temperature, and establishing a temperature sensitive parameter model; in combination with temperature field distribution and a temperature sensitive parameter model, learning long-term influence of control actions on temperature distribution, and predicting temperature evolution trends under different control strategies; constructing a multi-objective optimization control strategy, and generating a motor control instruction and a heat dissipation control instruction; dynamically selecting an optimal heat dissipation strategy combination according to the generated control instruction, the current working condition and the predicted heat influence; according to the invention, high-precision control and thermal management optimization of the brushless motor in a temperature change environment are realized.

The invention discloses a resource allocation method and device for a large model cluster, equipment, a storage medium and a program product. Comprises: determining configuration parameters based on a configuration task selected by a user; determining at least one of a computing power demand, a bandwidth demand and a video memory demand based on the configuration task and the configuration parameters; constructing a constraint condition and a target function according to at least one of the computing power demand, the bandwidth demand and the video memory demand; and carrying out iterative optimization on the target function by utilizing a preset planning algorithm based on the constraint condition so as to solve the unknown configuration parameter and obtain a target configuration parameter. According to the resource allocation method for the large model cluster, provided by the embodiment of the invention, the optimal large model learning parameter or hardware resource allocation can be determined, and the efficiency and reliability of resource allocation of the large model cluster are improved.

The invention discloses a real-time prediction method for muck improvement parameters of a shield under-crossing existing tunnel, and the method comprises the steps: carrying out the refined preprocessing of non-under-crossing section shield tunneling data, enabling an obtained data set to be used for the training of a machine learning integrated prediction model, and obtaining a muck improver dosage integrated prediction model; meanwhile, slump experiments are carried out for different types of stratums, the optimal water content and foam injection ratio parameter range is determined, and a reliable decision basis is provided for a shield driver. The quality of a data set and the prediction precision of a machine learning model are remarkably improved through a finer data preprocessing means; the machine learning integrated prediction model fuses learning capabilities of different machine learning models, so that the prediction precision of the model is further improved; and machine learning and experimental means are combined to realize accurate and rapid prediction of the use amount of the modifier, so that safe and smooth tunneling of the shield under the existing tunnel is ensured, and the method has certain timeliness and economical efficiency.

The invention discloses a multi-modal ship target individual identification method and system, and relates to the technical field of ship target identification, and the method comprises the steps: obtaining multi-modal data of a target region, and constructing a training set and a test set; each training sample in the training set is input into a target individual prediction model, a multi-granularity adaptive loss function is adopted as a loss function to carry out model training, and the target individual prediction model adopts an image feature extraction method based on cross-modal guide enhancement to carry out feature extraction and splicing fusion on each training sample; and a target individual identification result of each training sample is obtained by adopting a visual angle self-adaptive fusion method of embedded type label information. And after training is completed, a trained target individual prediction model is obtained, each test sample in the test set is input into the trained target individual prediction model, and a final target individual identification result is obtained. According to the invention, the generalization ability of model learning individual features can be improved, and the accuracy of ship target individual identification is improved.

The invention discloses a text retrieval enhancement generation method and device, a medium and equipment, and relates to the technical field of retrieval enhancement generation. Comprising the following steps: establishing a database through vectorized corpora, and screening and labeling key information to generate a golden section vector library; extracting an adversarial sample from an external database by using a training problem, and fusing the adversarial sample with related corpora in a golden section vector library to obtain a training set; and adding a noise classification layer to improve the language large model, and training the improved language large model by using the fusion training set. When a user question is processed, relevant corpora are recalled, noise is recognized through the classification layer, context representation is generated through the attention fusion layer, and the output layer dynamically adjusts a decoding strategy and generates an answer. According to the method, a large language model added with a noise classification task is trained through the fusion training set, so that the model can identify and distinguish different types of noise, the adaptability of the model to different types of noise is enhanced, the model is helped to learn how to distinguish related and unrelated information, and thus the method is more robust when an actual problem is processed.

The invention relates to the technical field of intelligent lock recognition, in particular to an intelligent lock image feature recognition method and system based on deep learning. The recognition method comprises the following steps: constructing a multi-branch deep neural network model, wherein the multi-branch deep neural network model comprises a backbone network, a feature extraction branch and a feature fusion branch; a framework training model is used to learn identity recognition, attitude estimation and environment perception tasks; and identifying the comprehensive feature representation by using a trained framework training model, and generating a control instruction of the intelligent lock according to an identification result. According to the intelligent lock image feature recognition method based on deep learning provided by the invention, comprehensive analysis of multi-dimensional information such as identity, posture and environment is realized by constructing the multi-branch deep neural network model.

The invention discloses a log abnormal behavior detection method and system based on periodic pattern mining and incremental learning, and relates to the technical field of system abnormality monitoring. The method comprises the steps of obtaining original log data and executing preprocessing operation; main periodic frequency components are extracted through time frequency analysis to form a periodic set, a periodic stable part sequence and a transient change part sequence are divided, and a periodic modeling mechanism and a transient modeling mechanism are used for modeling; a joint prediction model is constructed, Monte Carlo Dropout is introduced to estimate uncertainty, and Bayesian weighting is adopted to generate a prediction value; abnormity is judged through a periodic residual error, a transient residual error and an overall residual error, and an abnormal causal path is analyzed and identified in combination with transfer entropy; a memory sample driven playback and distillation mechanism is adopted to execute incremental training, and modeling structure parameters are dynamically adjusted. The method has the capabilities of periodic rule modeling, unsteady behavior expression, prediction fusion, abnormal causal identification and continuous model learning.

The invention discloses a wire drawing machine operation state evaluation method and system based on deep learning, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: deploying a multi-source sensor at a preset part of a wire drawing machine, and forming a multi-dimensional operation data flow; the deep learning evaluation model is trained based on the standardized time series data set, model parameters are optimized through a cross entropy loss function, the model learns the characteristic difference between a normal working condition and an abnormal working condition, and the deep learning evaluation model is trained based on the standardized time series data set. And inputting a multi-dimensional operation data flow collected in real time into the trained deep learning evaluation model to generate a dynamic evaluation report. According to the wire drawing machine operation state evaluation method and system based on deep learning provided by the invention, a visual operation state score can be output, detailed fault type probability distribution is given, and intelligent support is provided for equipment maintenance decision.

The invention provides a content recommendation method and system based on multi-modal data fusion, and relates to the technical field of content recommendation, and the method comprises the steps: obtaining multi-modal data of a user, and integrating the multi-modal data through a deep learning model to obtain a multi-dimensional user portrait; a comparative learning module is adopted to extract potential interests from historical data of the user; the preference of the user in the aspect of recessive behaviors is learned through a contrast learning model, a recessive interest model is established to obtain comprehensive interest representation, feedback and behavior data of the user are obtained in real time, and a reinforcement learning algorithm is used for adjusting a recommendation strategy in real time to obtain an optimized recommendation strategy; and according to the optimized recommendation strategy, using a user feedback mechanism to collect feedback data after the user participates in real time to train and optimize a recommendation system so as to obtain a final content recommendation system. The invention provides a multi-modal data fusion content recommendation method and system, and solves the technical problem of data singleness.

The invention discloses a complex exponential signal joint spectrum reconstruction and parameter estimation method and device, and relates to the field of signal processing, and the method comprises the steps: S1, constructing noise-containing complex exponential signal training data and label data; s2, constructing a dual-module neural network model comprising a super-resolution denoising reconstruction module and a parameter prediction module; s3, training the dual-module neural network model by using the training data and the annotation data to obtain a trained dual-module neural network model; and S4, performing frequency spectrum reconstruction and parameter prediction by using the trained dual-module neural network model, and performing signal post-processing on the output to obtain estimation parameters of the angular frequency, the attenuation factor, the real part amplitude and the imaginary part amplitude. According to the invention, a cascade neural network architecture of a super-resolution denoising reconstruction module and a parameter prediction module is designed, and angular frequency detection is converted into a Gaussian distribution heat map regression task; meanwhile, a sparse activation labeling mechanism is adopted, the parameter truth value is only reserved at the spectrum peak position, and the model learning complexity is remarkably reduced.

The invention relates to the technical field of rehabilitation training detection, in particular to a rehabilitation training detection method and system based on artificial intelligence, a standard action library is constructed through standard action videos shot at multiple angles, and track and angle features of key joints are extracted for user training comparison; the skeleton key points of the user are extracted in real time through a MoveNet network, and efficient posture recognition in a home scene is achieved; analyzing position difference, angle change and acceleration characteristics by combining a space-time sequence matching algorithm, generating a dynamic matching degree index, and positioning a deviation joint to generate a correction prompt; introducing an attention mechanism model, learning the contribution degree of each joint to cycle recognition, dynamically selecting a dominant joint for action counting, recognizing starting and ending points of an action cycle through an acceleration curve, and finishing effective action statistics in combination with a dynamic threshold value, so that the counting accuracy and the self-adaptive capability are improved; therefore, the training cost is reduced, the evaluation credibility is enhanced, and accurate statistics and analysis of rehabilitation training data are realized.

The invention relates to the technical field of industrial Internet of Things detection, in particular to an industrial Internet of Things equipment detection method and system based on a federal map neural network. The method comprises the steps of obtaining real-time operation state data of each device and a measurement value of a sensor, constructing a topological graph by using input data as device node features, introducing a knowledge graph based on the topological graph, fusing a client device state and knowledge graph information, and obtaining a client device state information fusion result. Introducing an attention mechanism to adaptively adjust the weight of the local model of the client; the method comprises the following steps: fusing node features, performing feature enhancement based on the fused node features, establishing a federated graph neural network client dynamic scheduling strategy based on reinforcement learning, and performing a node classification task of graph structure data by using a global model. The method improves the performance of the model in the absence of annotation data, enables the model to learn more robust features, and improves the judgment accuracy of equipment faults.

The embodiments of the present application relate to the technical field of artificial intelligence, and provide an information recommendation method and apparatus, a device, and a storage medium. The method comprises: performing training on the basis of historical user material interaction information to obtain a deep semantic recall model and a deep semantic sorting model; and by means of the deep semantic recall model, recalling a plurality of candidate materials corresponding to a user identifier, and by means of the deep semantic sorting model, determining and sorting preference scores of the plurality of candidate materials and recalled materials of other paths, so as to recommend materials, thereby eliminating dependence on operation experience, and improving the recommendation effect. The training enables the deep semantic recall model to learn the text semantic representation of the user material interaction information, so that when materials are recalled, the literal semantics of the materials is more concerned, thereby improving the accuracy of the recalled materials. The deep semantic sorting model is enabled to learn the behavior semantic representation of the user material interaction information, so that when the recalled materials are subjected to preference scoring and sorting, the user behavior information of the material feedback level is more concerned, thereby improving the user click rate.

The invention relates to the technical field of electric bicycles, and discloses a data-driven electric bicycle battery fire hazard detection and protection method, which comprises the following steps: S1, multi-modal data acquisition and fusion, S2, data preprocessing and feature extraction, S3, data-driven intelligent detection: classifying normal and abnormal states through a supervised learning model, S4, hierarchical protection strategy, and S5, data-driven intelligent detection. S5, cloud data optimization and model continuous learning; S6, model data updating; S7, intelligent linkage and long-term optimization; S8, cloud risk data acquisition; and low, middle and high three-level protection mechanisms are adopted. Through dynamic risk assessment, charging and discharging power is limited in a medium risk, a charger is automatically disconnected, a user is prompted to stop operation, active protection is triggered in a high risk, and sound-light alarm and remote notification are triggered at the same time, so that accidents are prevented from further spreading.

The invention relates to an intelligent control method for a high-speed aircraft, and the method comprises the steps: building an aircraft control architecture, carrying out the decision-making of a neural network model, training a decision-making neural network, and carrying out the real-time compensation of a control instruction according to the flight state of the aircraft, so as to achieve the control of a variable-configuration high-speed aircraft. An aircraft controller adopts a model + learning double-layer architecture, a decision neural network is designed to be of a Double Network structure, overload errors of pitching, yawing and rolling channels are considered in a reward function design, training of a decision neural network model is based on a double-delay deterministic strategy gradient algorithm, a training process is optimized by adopting a prior experience playback technology and a target strategy smoothing mechanism, and a decision neural network model is obtained. The control system can achieve real-time intelligent adjustment of control instructions, overload quantities and attitude angles of three channels of the aircraft and corresponding rudder deflection instructions output by the controller at the last moment are obtained from the environment, the intelligent body outputs control instructions of pitching, yawing and rolling channels, and therefore intelligent control over the variable-configuration high-speed aircraft is achieved.

The invention provides a network intrusion detection method based on pre-training language model federal segmentation learning, aiming at dual requirements of privacy protection and attack recognition in a network intrusion detection system. For the challenges of difficult traffic feature extraction, limited edge device computing power, data privacy barriers among distributed nodes and the like in attack detection, the method fuses the privacy protection mechanism of federated learning and the computing unloading advantages of segmentation learning, and constructs a pre-training language model learning architecture oriented to traffic feature analysis. According to the method, a pre-training language model is decoupled into an edge side lightweight module and a cloud deep reasoning module through a hierarchical segmentation strategy, and balance optimization of global model stability and local personalization is realized through federal aggregation based on a multi-head attention mechanism. An adversarial enhancement mechanism is introduced to the edge side, the feature extraction ability of a pre-training language model is combined with the dynamic game of a generative adversarial network, and the generalization ability of the model to complex network attacks is improved through adversarial sample reconstruction.

The invention provides a lease risk dynamic assessment method and system based on index data, and relates to the technical field of risk assessment, and the method comprises the steps: obtaining historical lease data and lease index data of a lease transaction, extracting lease features, and combining the lease index data to construct and form a feature set for training a lease risk assessment model; the method comprises the steps of constructing a target variable for model learning, constructing a lease risk assessment model to be integrated in a risk assessment engine, performing preliminary risk assessment by using a loan interest rate and a repayment amount of lease index data, and calling the lease risk assessment model to recalculate a risk score by using a tenant credit score and a historical transaction mode. Adjusting the final risk level of the lease transaction; and calculating a weighted comprehensive risk score according to the lease index data, and grading the lease transaction risk according to a comprehensive risk score interval. According to the invention, risk factors in the leasing process can be rapidly identified and responded, and the leasing risk can be analyzed and predicted in real time.

A federated object detection learning method based on representation enhancement and weighted aggregation under cloud-edge-terminal environment comprises the steps of: 1) building a centralized federated learning framework under cloud-edge-terminal environment; 2) locally conducting representation enhancement training to strengthen model learning for few-shot category after receiving a model from the server at the client; 3) carrying out the weighted aggregation for client models in accordance with sample distribution to obtain the global model after receiving models from all clients at the server. With regard to the problem of existing federated object detection learning on low global model accuracy and weak generalization ability, the present invention can improve the accuracy and generalization ability of global object detection model.

The invention discloses a model optimization method and system based on knowledge distillation and model pruning, and belongs to the technical field of electric power operation and maintenance. The model optimization method comprises the following steps: segmenting and predicting a large amount of unlabeled power operation and maintenance data by using a pre-trained teacher model, generating a preliminary segmentation mask, and generating a domain-specific pseudo tag for the segmentation mask; training a lightweight student model based on a knowledge distillation method by taking the pseudo tag as a supervision signal, and enabling the lightweight student model to learn soft distribution of the teacher model; and adopting a modularized pruning strategy based on sparse training to prune the lightweight student model, and adjusting model parameters based on an annotation data set in the power field to obtain an optimized lightweight student model. The method is used for operation maintenance of power grid equipment, and can reduce the defect omission ratio and reduce the inspection frequency.

The invention relates to the technical field of artificial intelligence, in particular to a large model training system and method based on multi-modal medical data fusion, and the method comprises the steps: collecting multi-modal medical data, and carrying out the feature extraction and pre-calculation of the multi-modal medical data; performing fusion analysis on the information distinguishing value evaluation of the sample features and the label association strength to obtain a context adaptability regulation factor of the sample data; performing modal consistency analysis and modal significance analysis on the multi-modal medical data sample to obtain an information value deepening regulatory factor of the sample data; performing optimization adjustment on the original attention score through a context adaptability adjustment factor and an information value deepening adjustment factor to obtain a final attention score; and multi-modal data feature fusion and model training are performed through the final attention score, so that the accuracy of learning medical knowledge by the model is improved, and the final performance of the model trained by the training system on a target task is improved.

The invention discloses a time sequence knowledge graph retrieval enhancement generation method and device and a medium. The method comprises a preparation stage and an answering stage. In the preparation stage, firstly, a large language model is finely adjusted, so that the large language model can recognize different types of time-related problems; through the design of prompts and task decomposition examples, the model can learn how to decompose a complex time sequence problem into a plurality of subtasks; meanwhile, a query statement template is designed for each subtask, so that the large model learns how to generate a specific query statement according to each subtask; in the answering stage, the model receives the user question and identifies the question type; corresponding prompts are matched and decomposed into a plurality of sub-tasks; the model generates a query statement for each operation and executes query to extract data from the knowledge graph; and integrating the recalled knowledge with the original question to generate a final answer. According to the method, the accuracy and efficiency of time sequence reasoning are improved, the generation capability is enhanced, and the interpretability of the large language model is improved.

The invention discloses a medical image recognition system based on label noise robust learning, and provides a hard sample label refinement strategy based on a confidence perception weighted prototype and an effective noise sample joint correction method to process divided subsets in correction before training so as to obtain training data with higher quality; in progressive hard sample reinforcement learning, data are input according to the learning difficulty of samples for training, the ability of model learning discrimination feature representation is improved by integrating cross entropy loss, consistency loss and credible contrast loss, and the influence of medical tag noise is reduced. According to the method, by integrating label refinement and a progressive hard sample reinforcement learning technology, the accuracy and robustness of medical image recognition under the condition of noise label data are effectively improved, overfitting of the model to noise samples is relieved, and the method can be used for correctly building a disease auxiliary diagnosis model under the condition that the noise label samples exist in training data.

The invention belongs to the technical field of pathological diagnosis, and discloses an artificial intelligence-based lung cancer pathological section analysis and system, which introduces identification basis visual information generated by an artificial intelligence model, and combines the correction operation of a plurality of pathologists on a model identification result and the acquisition of correction reasons, so that the pathological section analysis of the lung cancer is realized. Further performing consistency analysis on the correction results to generate uniform data, and finally performing incremental training on an artificial intelligence model by using the data, thereby constructing a closed-loop feedback optimization mechanism combining artificial intelligence and expert knowledge. The model performance problem caused by insufficient training data coverage, expert labeling efficiency and result inconsistency of an artificial intelligence model in pathological diagnosis is solved, and model learning and performance improvement are achieved.

The invention relates to the technical field of artificial intelligence and the like, and provides an intelligent replenishment management method and system based on artificial intelligence, and the method comprises the steps: calculating the historical order data of a target product on an e-commerce platform, and calculating the historical inventory data of the target product in each regional warehouse; and analyzing the historical order data and the historical inventory data through a machine learning model to obtain the correlation characteristics of the orders and the inventory of the target product in different time periods and different areas, training an intelligent inventory allocation model through the correlation characteristics of the orders and the inventory, so that the intelligent inventory allocation model learns to automatically adjust the inventory allocation, and the intelligent inventory allocation efficiency is improved. And according to the regional replenishment demand of the target product, the trained intelligent inventory allocation model is utilized to analyze the current order of the target product and the current inventory state of the target product in each regional warehouse to generate an inventory allocation plan of the target product in each regional warehouse, so that replenishment management adapts to the demand change, and the replenishment efficiency is improved. And regional requirements are quickly responded.

The invention discloses a detection laboratory total factor digital twinning model construction method and an intelligent operation and maintenance system, and relates to the field of digital twinning, and a total factor digital twinning model comprises a detection laboratory physical object model, a detection laboratory virtual model, a total factor data model, a data interaction model, a learning decision model and an operation and maintenance management model. Real-time mapping is kept between the physical object model and the virtual model of the detection laboratory; the total element data model is used for collecting, inputting, processing and updating multi-source heterogeneous data in the digital twinborn model of the detection laboratory; the data interaction model carries out fusion transmission on real-time data among the models; and meanwhile, the learning decision-making model performs autonomous decision making and diagnosis, and functions are integrated and displayed through the operation and maintenance management model, so that the intelligent operation and maintenance level of the detection laboratory is further improved. The whole detection process of the detection laboratory is digitalized, the communication cost of the detection test process is saved, the manpower and time cost is saved, and the detection efficiency is improved.

The invention discloses an AI algorithm optimization method and system based on a deep learning technology, and relates to the technical field of deep learning model optimization, and the method comprises the steps: carrying out the preprocessing of a data set, carrying out the normalization and standardization processing, and dividing the data set into a training set, a verification set and a test set; a self-attention mechanism is introduced into a convolutional layer of the ResNet-18 deep learning model, and the weight of each channel is dynamically adjusted by calculating a self-similarity matrix of a feature map; training the model by using the training set data, and dynamically adjusting the model learning rate in the training process; an optimal hyper-parameter combination is automatically searched through a hyper-parameter tuning method; the number of model parameters and the calculation amount are reduced through a static quantification method; exporting and deploying the model, importing the test set, and testing the performance of the model; according to the method, a self-attention mechanism is introduced into the convolutional layer of the ResNet-18 model, the weight of each channel is dynamically adjusted, the attention of the model to important features is enhanced, and the feature extraction precision is improved.