719 results about "Proactive learning" patented technology

The invention relates to the technical field of intelligent operation and maintenance, and discloses an intelligent operation and maintenance method fusing multi-modal data and active learning, and the method comprises the steps: deploying a hierarchical Internet of Things equipment network in a target operation and maintenance region, collecting a heterogeneous operation and maintenance data set, and generating an operation and maintenance feature data set through employing a unified building operation and maintenance service framework cooperating with a plurality of MCPs; inputting the operation and maintenance feature data set and the user feedback information into a deep learning intention recognition model for intention recognition and demand analysis to obtain structured user demand data and an operation and maintenance task priority sequence; according to the operation and maintenance feature data set and the structured user demand data, performing real-time evaluation on the equipment operation state to obtain fault risk early warning data; autonomous decision analysis is carried out through an agent type artificial intelligence engine, an equipment maintenance scheme and a resource scheduling scheme are generated, and then the problems that in traditional operation and maintenance, fault prediction is single, the model adaptability is poor, and prediction results are difficult to convert into effective decisions are solved.

The invention provides a deep learning-based rapid ore sorting method under adaptive illumination intensity, and relates to the technical field of ore sorting, the deep learning-based rapid ore sorting method comprises the following steps: obtaining illumination intensity distribution information and ore three-dimensional point cloud data, and calculating ore space orientation parameters based on quaternion attitude estimation; inputting the obtained data into a layered illumination compensation network, and obtaining an illumination normalized enhanced image through adaptive brightness mapping and local light spot correction in combination with reflectivity recovery and non-local mean filtering; inputting the illumination normalized enhanced image and the ore three-dimensional point cloud data into a multi-branch feature extraction network, constructing feature high-order association, and adopting adaptive feature reconstruction and conditional random field optimization features; and inputting the reconstructed features into a classification model based on active learning, optimizing a feature manifold space by using a self-organizing mapping network, carrying out sample labeling in combination with active sampling of adaptive entropy threshold screening and uncertainty perception, and realizing ore classification and sorting through random forest integration.

The invention discloses an uncertainty and representativeness combined active learning method and system for medical image data annotation, and relates to the technical field of medical image data. The method comprises the following steps of: training a variational auto-encoder infoVAE on an image pool; m samples are randomly extracted from the image pool and labeled, an initial labeled image set is constructed, and a segmentation model is trained on the labeled image set; t rounds of active learning circulation are carried out, and in each round of t active learning circulation, the following steps are specifically executed: screening candidate samples based on a representative method; screening a final sample based on an uncertainty method; updating the labeled data set and the unlabeled data set; retraining the segmentation model on the updated labeled image set, and optimizing model parameters; and obtaining final model parameters. According to the method, by designing a sample selection strategy integrating uncertainty and representativeness, the global performance of the model and the difficult sample segmentation capability are improved.

The invention discloses an image classification and recognition system and method based on an AI training model, relates to the technical field of image classification and recognition, and solves the problem that an existing method lacks dynamic adaptability. Comprising a data monitoring module, a dynamic label correction module, a model distillation module, a model tuning module and a model version control module. The data monitoring module evaluates input data distribution offset in real time by adopting a maximum mean value difference and KL divergence algorithm, and triggers model updating; the dynamic label correction module realizes automatic label correction through clustering active learning and semantic segmentation; the model distillation module uses adaptive incremental learning and a knowledge distillation mechanism to reduce computing resource consumption; the model adjusting and optimizing module adopts an elastic weight integration method to maintain the stability of the model; performance fluctuation is prevented through the model version control module; according to the invention, the flexibility and response speed of electric power facility inspection are greatly improved, and the defect detection precision and the long-term adaptability of the model are remarkably improved.

The invention relates to a multi-modal image threshold segmentation preprocessing method based on a convolutional neural network, and the method comprises the steps: unifying an image into a standard space, carrying out the pixel value mapping, carrying out the resampling, generating high and low frequency sub-bands, carrying out the soft threshold denoising of the high frequency sub-bands, enhancing the contrast of the low frequency sub-bands, and carrying out the fusion; an optimized VGGnet framework is constructed; a noise adversarial network is generated to carry out active learning loop training on a convolutional neural network model; the image is input into the model for prediction; a local entropy and a gradient magnitude are calculated based on a prediction result; optimal segmentation is realized by setting a double-layer matrix of a feature tag-segmentation method; grey matter Dice calculation is carried out on the segmented images, and preprocessing parameters of unqualified images are optimized through a dynamic parameter adjusting module based on a Gaussian process regression model. The segmentation precision and the processing efficiency of the multi-modal image are effectively improved, and the adaptability of the model to a complex image is enhanced.

The present disclosure describes methods, systems, apparatus, and media for object identification and classification, utilizing multi-feature and multi-modal data. This includes shape, material, brand, price, odor, taste, tactility, and sound. The system integrates a server space for data processing, a querying device for iterative searches, and a data interface module for refining results. It features AI-driven image optimization, feature extraction, and pattern recognition, employing novel techniques for fusing multi-feature and multi-modal embeddings utilizing multi-head attention. Additionally, a linker module powered by two active learning with feedback loops AI models consolidates scattered data into a unified object information database. The system also employs novel AI algorithms for isolating the object of interest through a saliency map and semantic analysis, as well as for enhancing raw images with a GAN-autoencoder.

The invention relates to the technical field of semantic label generation management, in particular to an enterprise-level customer data dynamic label management system which comprises an enterprise customer data storage unit, a knowledge fusion unit, a semantic analysis unit and a label generation application unit. The enterprise customer data storage unit obtains enterprise customer data and product related data and broadens data sources, the knowledge fusion unit carries out data standardization processing, entities and relationships are extracted by utilizing an advanced technology and are stored in a knowledge graph, and the semantic analysis unit selects samples by adopting stratified sampling and active learning, so that the data source is expanded. A plurality of technical means are combined to judge and process semantic drift, a deep learning model is optimized, a label generation application unit generates dynamic labels according to an optimization model, the dynamic labels are updated to an enterprise customer relationship management center in real time after clustering, screening and matching operation, real intentions of customers can be accurately obtained, accurate semantic labels can be generated, and the real intentions of the customers can be accurately analyzed. Enterprises are assisted to accurately serve customers, and the market competitiveness is improved.

The invention provides a knowledge base and business system collaboration method under an AI platform, and belongs to the technical field of AI platform digital data processing.The method includes the steps that triple semantic analysis is conducted on query by constructing a multi-level semantic vector representation module, a parallel data retrieval engine is started, vector retrieval, graph reasoning and real-time data pulling are executed at the same time, and the query efficiency is improved; establishing a dynamic confidence evaluation mechanism to evaluate the quality of the data source, executing a weight distribution algorithm based on reinforcement learning, dynamically calculating the weight of the data source according to a query type by adopting a graph convolutional network intelligent routing decision model, and implementing multi-source data fusion and consistency verification to solve data conflicts through a weighted voting mechanism. An intelligent result sorting and filtering system is established, a multi-dimensional evaluation strategy is adopted to output high-quality answers, a continuous learning and feedback optimization loop is constructed, system performance is continuously optimized through active learning and a graph shortest path algorithm, and the technical problem that knowledge base data and a service system cannot effectively and uniformly make decisions is solved.

The invention relates to a security management knowledge graph construction and dynamic updating method based on association modeling, and the method comprises the steps: collecting multi-source heterogeneous data in the field of security management, carrying out the recognition of the data type, carrying out the data conversion, setting an active learning mechanism in a named entity recognition model, carrying out the training, and recognizing an entity from the data. The entity is extracted; constructing an attention-enhanced graph neural network to analyze image data, calculating an attention weight for each node and edge in a message transmission process, and updating node information to realize relation extraction; based on the entity and relational data, constructing a preliminary security management knowledge graph; reasoning and supplementing missing information and relations based on an external standard knowledge base; the data change increment is detected in real time to update the security management knowledge graph, nodes and relationships are newly added or updated in the security management knowledge graph, the security management knowledge graph is efficiently constructed and dynamically updated, and support is provided for cross-modal intelligent question answering and real-time security evaluation.

The invention discloses an industrial surface defect image classification method based on hybrid query strategy active learning, and belongs to the technical field of computer image processing and machine learning. The invention aims to solve the technical problems of high cost, long period and low rare defect recognition rate caused by category imbalance due to dependence on large-scale manual labeling. The core of the method is to execute a hybrid query strategy in an iterative loop: firstly, screening out a candidate sample set of model cognitive ambiguity through uncertainty measurement of prediction entropy; secondly, in the candidate set, a core set and hierarchical thought diversity sampling method is adopted to select a final to-be-labeled sample with both characteristic representativeness and category balance. And the query batch is manually annotated and then is used for carrying out iterative updating and optimization on the model. According to the method, the recognition precision and generalization ability of the classification model on various defects can be remarkably improved with extremely low manual labeling cost, and the model development period is greatly shortened.

A knowledge graph construction method based on active learning and incremental learning comprises the following steps: S1, preprocessing data from a plurality of heterogeneous data sources, and extracting entities, relationships and attributes to form an initial knowledge network; s2, vectorizing elements in the initial knowledge network by using a knowledge graph embedding model, and performing entity alignment based on vector similarity to obtain an initial knowledge graph; s3, screening out candidate knowledge triples with high uncertainty and / or high representativeness from the initial knowledge graph by adopting an active learning strategy, and obtaining user labeling information corresponding to the candidate knowledge triples; s4, performing iterative optimization on a knowledge extraction model and / or a knowledge graph embedding model according to the user labeling information; s5, new data are fused into the optimized knowledge graph in an incremental learning mode, and knowledge conflict detection and resolution are carried out in the fusion process; and S6, circularly executing the steps S3 to S5 until the knowledge graph meets a preset quality condition.

The invention relates to the technical field of design and application of two-dimensional materials, and discloses a design and simulation method of a two-dimensional semiconductor nanometer transistor, which comprises the following steps: collecting multi-source data of design and simulation of the two-dimensional semiconductor nanometer transistor, and screening through a data quality evaluation model to obtain a layered data structure; constructing and training a Bayesian neural network model; key influence parameters are identified through a multi-scale feature extraction algorithm and a parameter correlation analysis algorithm, and an attention algorithm is applied to pay attention to an important parameter combination; meanwhile, the uncertainty is predicted, a sampling point with the most information content is generated, and a prediction confidence interval is provided; through active learning feedback optimization circulation, high-value data points are selected based on prediction uncertainty for verification, and the model is updated until preset precision or resource constraint is achieved; according to the method, through multi-scale feature representation and parameter correlation analysis, invalid parameter exploration is reduced, and meanwhile, the model interpretability is improved through integrated physical constraint and uncertainty quantification.

A seasonal permafrost region roadbed engineering frost heaving damage risk assessment method, device and equipment, and the method comprises the following steps: 1, obtaining different types of environment data, carrying out the preprocessing of the obtained data, and generating a feature set suitable for the input of a deep learning model through the preprocessed data; step 2, converting data from different sources into spatio-temporal features suitable for deep learning model input by using an adaptive data fusion method and a graph neural network; 3, designing and optimizing a deep learning model; 4, introducing an active learning mechanism and updating the model; and step 5, risk assessment and automatic early warning: comparing a prediction result of the deep learning model with a set multi-level safety threshold, generating a multi-level risk early warning report, and providing visual decision support. According to the invention, the technical problems of poor real-time performance, low prediction precision and lack of physical consistency of railway roadbed frost heaving monitoring and early warning in the prior art are solved.

The invention relates to the technical field of deep learning, provides an optimization method of a defect detection model and defect detection equipment, and can be used for industrial quality inspection. According to the method, at least one to-be-detected product data set in production is used for carrying out multi-round iterative optimization on a defect detection model after pre-training, the defect that traditional model training is isolated from a production line environment is overcome, and closed-loop iterative detection and optimization of the model are achieved. In each optimization process, confidence coefficient learning and active learning are combined, the uncertainty of a model is quantified through confidence coefficient learning, a global confidence coefficient threshold value is determined according to the confidence coefficient corresponding to the defect type of each piece of to-be-detected product data, and the threshold value is dynamically adjusted by using the recall rate and the number of optimization times. And during active learning, sample data screening is carried out by using the adjusted global confidence threshold, so that blind labeling or over-fitting labeling is avoided, the quality of the screened samples is ensured, and the accuracy and generalization of a retraining defect detection model are improved.

The invention discloses a multi-dimensional self-adaptive conductive connecting piece welding positioning system, and relates to the technical field of conductive connecting piece intelligent welding positioning, the system comprises a multi-dimensional data acquisition module, and a multi-modal sensor is used for acquiring contour, feature, current and other data; the data processing and analysis module processes data through deep learning and a physical model and predicts deformation; the self-adaptive positioning adjusting module controls the eight-axis linkage mechanical arm to compensate deformation through MPC; the welding process monitoring module fuses multi-source data monitoring and triggers adjustment when abnormity occurs; and the intelligent decision and feedback module realizes closed-loop control and optimization through knowledge graph and active learning decision feedback. Through multi-modal sensing and an intelligent algorithm, accurate positioning and dynamic compensation of welding deformation are achieved, welding parameters are adjusted in a self-adaptive mode, intelligent decision making and remote operation and maintenance are combined, the welding quality and stability are improved, errors and cost are reduced, and powerful support is provided for efficient welding production.

A system and method of real-time optimization of drilling performance metrics during a well drilling operation, for oil and gas as well as geothermal wells, or wells drilled for any other purpose. In a preferred form, the system receives information about allowable drilling metrics and real-time information of performance indicators. The drilling performance metrics and performance indicators are used to build a model to predict drilling parameters likely to optimize one or more drilling performance metrics.

The invention discloses a human-intelligent collaborative domain increment target detection method. According to the invention, an increment strategy and an active learning sampling method are arranged in a flexible increment training loop; reuse and combination of knowledge are realized by using a sparse hybrid expert network, the generalization ability of model increment training is improved, data playback is performed on an old domain sample based on distributed sampling, and knowledge forgetting in the model increment training is relieved; a part of new domain samples with representativeness and diversity are screened through clustering and maximum mean value difference calculation, on one hand, the data size difference of new and old samples is reduced, and on the other hand, the stability and plasticity of the model are balanced by controlling the number proportion of the new and old samples and the round fine granularity of iterative training. According to the method, the adaptability of the team in complex and diversified environments is improved, fine-grained balance of model stability and plasticity is supported, and the method can be applied to a human-intelligent cooperation domain increment target detection scene and has certain practical significance and theoretical value.

The invention discloses an intelligent catalyst design method and system based on multi-objective optimization and deep learning, and aims to solve the problems of limitation of single-objective optimization, high computing resource consumption and the like in traditional catalyst design. According to the method, graph data are constructed by fusing atomic-scale and macroscopic features, multi-target prediction is carried out by utilizing a multi-task graph neural network (GNN), and collaborative optimization of adsorption energy and stability loss is realized by combining an NSGA-II multi-target optimization algorithm and a dynamic weight adjustment strategy of Bayesian optimization. A closed loop is verified through active learning and virtual experiments, candidate materials are dynamically selected, the model is updated, and the efficiency and precision of material design are remarkably improved. The method is suitable for rapid discovery and optimization of the high-performance catalyst, and has a wide application prospect.

The invention discloses an active learning and physical loss-based fatigue crack growth rate prediction method, which comprises the following steps of: splicing and fusing a preprocessed stress intensity factor, a stress ratio, pre-strain and stress amplitude, and taking the fused characteristics as the input of a model; embedding the Jones model into a loss function of the neural network, constructing a physical information time sequence model based on the Jones model, setting a parameter set, selecting a most valuable training sample from a training set by using active learning, retraining the model by using the selected most valuable training sample, selecting an optimal model, and evaluating the optimal model by using a test set; fusing the actually measured stress intensity factor, stress ratio, pre-strain and stress amplitude of the to-be-predicted material, and inputting into the obtained prediction model to obtain a predicted value of the fatigue crack growth rate. By adopting the technical scheme of the invention, the fatigue crack growth rate of the material in the whole life period can be efficiently and accurately predicted at low cost.

The invention discloses a nodular cast iron component and process design method based on an active learning strategy, and belongs to the technical field of material process design. In order to improve the prediction precision and design efficiency of material process design, the method comprises the following steps: collecting experimental data including nodular cast iron components, process, microstructure characteristics and performance in literatures; constructing a nodular cast iron component-process-microstructure characteristic model and a nodular cast iron component-process-microstructure characteristic-performance model, setting different weights for different target performances based on an optimization algorithm, and obtaining optimized nodular cast iron components and process parameters with different performance requirements by adopting a weight-based target function; and through an active learning strategy, data with relatively large uncertainty is preferentially selected for experiment and is supplemented to a data set, then model updating is performed, model prediction precision is optimized, and finally nodular cast iron components and process parameters meeting expected performance requirements are designed. The experiment frequency and cost are reduced.

The invention discloses an Internet of Vehicles CAN bus intrusion detection method based on noise perception active learning, and belongs to the technical field of Internet of Vehicles safety and machine learning. The invention aims to solve the technical problems of false label noise interference, high manual labeling cost, high attack missing report rate caused by class imbalance and the like. The core of the method is to execute a noise sensing mixed query strategy in an iterative loop: firstly, generating a pseudo tag through clustering and correcting by using an integrated noise detector; secondly, calculating uncertainty scores and noise probabilities of the samples, fusing the uncertainty scores and the noise probabilities to obtain a comprehensive score, and preferentially selecting the samples with high uncertainty and low noise probabilities; and then adaptively selecting a sampling strategy according to the model performance and applying category balance constraint. The query batch is used to iteratively update the model while dynamically adjusting the classification threshold to reduce the missing report rate. According to the method, the influence of pseudo label noise can be effectively suppressed, and the attack detection precision and generalization capability are remarkably improved with extremely low labeling cost.

The invention discloses a shield tunneling mud cake blockage prediction method and system, a terminal and a storage medium, and the method comprises the steps: obtaining low-fidelity data of a target tunnel, and training a low-fidelity neural network according to the low-fidelity data to obtain a low-fidelity model; acquiring high-fidelity data, and inputting the high-fidelity data into a low-fidelity model to output a low-fidelity predicted value; fusing the high-fidelity data and the low-fidelity predicted value to obtain extended input data, training a high-fidelity residual network to obtain a high-fidelity residual model, and obtaining a target multi-fidelity model according to the low-fidelity model and the high-fidelity residual model; and obtaining shield tunneling data of the target tunnel, and inputting the shield tunneling data to the target multi-fidelity model to output a mud cake blockage risk prediction result. According to the invention, preliminary modeling is carried out by using low-fidelity data, the dependence on high-fidelity data is reduced, the data processing cost is reduced, and the model prediction precision is improved through the active learning strategy, so that the mud cake blockage risk prediction precision is improved.

The invention provides a collaborative classification method and system fusing advantages of large and small models, and the method comprises the steps: inputting to-be-classified data into a trained zero-sample classification small model, and outputting candidate label domain screening information and an initial classification result; inputting the to-be-classified data, the candidate label domain screening information and the initial classification result into the trained large model, and outputting a final classification result; the training process of the small model comprises the following steps: inputting training data into the zero sample classification small model to obtain a preliminary prediction result; screening and obtaining pseudo label data based on an active learning strategy; checking and re-marking the pseudo-label data by using the large model to obtain a modified pseudo-label data set; and carrying out iterative training on the zero sample classification small model by utilizing the modified pseudo label data set. The method has the advantages that a small model has classification performance close to that of a large model while keeping lightweight calculation characteristics; the calculation burden of a large model is reduced, and the accuracy of classification decision is improved.

The invention relates to the technical field of internet big data and information security, and designs a gearbox fault diagnosis method based on multi-source agent federal field generalization by combining the interaction capability of wide-area data and a local diagnosis agent. According to the method, a dual regularization mechanism is introduced in the training process of each local diagnosis agent, and the problem of negative migration is solved by actively learning domain-invariant fault features, so that the cross-working-condition and cross-equipment generalization diagnosis performance of a final model is remarkably enhanced on the premise of protecting data privacy; meanwhile, a central server is replaced by a decentralized coordination network realized by a block chain technology, and a committee consensus protocol is executed to ensure that the generation process of the global model is open, transparent and non-tampering, so that the single-point fault risk is fundamentally eliminated, the security and robustness guarantee is provided for the whole coordination process, and the method has the advantages of being high in practicability and the like. And the long-term applicability and the fault diagnosis accuracy and reliability of the method in a dynamically changing industrial environment are ensured.

The invention provides a learning progress monitoring method and system for an online education platform, and is applied to the field of online data processing. Through multi-dimensional data acquisition and intelligent analysis, the learning behavior monitoring accuracy is improved, the learning achievement degree of the user is accurately judged, the evaluation objectivity is ensured, the learning behaviors of the user are comprehensively tracked in combination with multiple types of learning data, the limitation of single-dimensional evaluation is avoided, and the user experience is improved. Meanwhile, through monitoring of active learning, passive learning and non-learning behaviors, the learning state of the user is further refined, the authenticity of data is improved, personalized learning habit data of the user is collected, an Ebbinghaus forgetting curve is dynamically constructed, accurate review time recommendation is achieved, the review time period can be adaptively optimized in combination with the change trend of test results, and the review efficiency is improved. The user can review at the best time, and the knowledge retention rate is improved.

The following relates generally to using generative AI to: (i) classify documents; (ii) generate prompts to classify documents; (iii) evaluate the classification performance of prompts; (iv) generate updates to prompts; and / or (v) train classifiers. In some embodiments, one or more processors: generate a prompt for input to the generative AI model; generate classifications for a set of documents from the corpus of documents by inputting the set of documents and the prompt to the generative AI model; based on the classifications, provide the set of documents to a review platform for manual review by a reviewer; obtain review data associated with a subset of documents from the set of documents; and train, by executing a training algorithm, a classifier using the review data as ground truth data, wherein the training algorithm is configured to analyze extracted relevant document portions of the subset of documents to train the classifier.

The invention discloses a main shock and aftershock full-life vulnerability analysis method based on active learning, and belongs to the field of structural anti-seismic safety evaluation. The method solves the problems that an existing full-life analysis method needs high calculation cost and does not consider the influence of environmental factors and main shock and aftershock coupling effects on the initial damage of the structure. The agent model is constructed based on high-precision and low-precision data fusion, and a meta-learning mechanism is introduced to describe internal association among different degradation states, so that the sample utilization efficiency is improved; a generalized learning function is combined with a two-stage active learning strategy to dynamically select a training sample point with the most information amount, efficient refinement of a prediction model in each degradation scene is gradually realized, the calculation cost is further reduced, and the agent model prediction precision is improved. And finally, through a time-varying two-dimensional limit state equation, explicitly considering the correlation between the initial damage evolved along with time and the structure residual capacity, and effectively fusing the coupling effect of environmental degradation and the seismic sequence. The method can be applied to structure vulnerability analysis.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an artificial intelligence data annotation and cue word automatic construction engine system, which comprises a data annotation module for firstly carrying out preliminary annotation on data based on a pre-training model, then automatically annotating a data sample through an active learning algorithm, and meanwhile, monitoring the quality of annotated data in real time; and the cue word automatic construction module generates cue words based on task analysis, optimizes the cue words by using a reinforcement learning technology, and performs classified storage and management on the generated cue words. By adopting the semi-automatic labeling and active learning labeling functions, not only can the workload be greatly reduced, but also the unnecessary labeling work can be reduced, so that the labeling efficiency is remarkably improved, the labeling time is shortened, the large-scale data labeling requirement is met, and the problem of efficiency bottleneck caused by slow manual labeling is solved.

The invention relates to the technical field of new energy power system instability risk assessment, in particular to a new energy power system frequency instability risk assessment method based on a heterogeneous graph attention network. The method comprises the following steps: constructing a wind power-photovoltaic heterogeneous graph model according to a power grid topology; performing combined sampling on different operation modes and anticipated disturbances, and determining corresponding input feature vectors; calculating a frequency stability index value label of the sample set; expanding the training set through an active learning iteration process, and carrying out model training; and inputting the collected operation data into the trained heterogeneous graph attention model, outputting a frequency stability index value, and evaluating the system frequency instability risk in combination with the risk matrix. By adopting the frequency instability risk assessment method for the new energy power system based on the heterogeneous graph attention network, the problem of low efficiency of risk assessment in a high-dimensional uncertain scene is solved, and the heterogeneous graph attention network can reflect the influence of different types of devices at different positions and disturbance types on the dynamic frequency of the system; and the accuracy of frequency instability risk assessment is improved.

The invention belongs to the field of artificial intelligence active learning, and particularly relates to a medical intelligent labeling method based on adaptive density clustering and active learning, which comprises the following steps: acquiring an unlabeled sample set, and converting all unlabeled samples into embedded vectors by adopting a pre-trained medical contrast encoder; randomly selecting part of unlabeled samples from the unlabeled data set for labeling to form a labeled data set training classification model; performing local density calibration according to the embedded vector to obtain a high-density core set and a boundary candidate set; extracting unlabeled samples from the high-density core set and the boundary candidate set according to an adaptive weight evaluation method, labeling the unlabeled samples, and adding the labeled samples into a labeled data set; training a classification model by adopting the annotation data set, if the classification model converges, ending the training, and otherwise, carrying out the next round of iteration; the trained classification model is adopted to realize classification of the medical images; according to the method, the medical active learning performance is remarkably improved through boundary sensitive screening of density clustering and a dynamic balance mechanism of adaptive weight.