278939results about "Biological models" patented technology

An emergency response and crisis management system comprises a computing system which performs steps comprising: aggregating real-time and historical data from multiple data sources; processing the data using artificial intelligence techniques; analyzing the processed data to detect and classify active crises to predict the likely development and trajectory of the ongoing crises, and assess potential short-term and long-term impacts across one or more sectors comprising one or more of public health, economy, infrastructure, environment, and social stability; generating multi-dimensional, interactive visualizations of the analysis results comprising one or more of geospatial maps, time series charts, and network diagrams; providing recommendations for crisis management and response tailored to different stakeholder roles; facilitating integration with external systems and applications through a comprehensive application programming interface (API) layer; and continuously adapting the system's models and algorithms based on one or more of real-world outcomes, expert input, and user feedback.

A system and method are disclosed for generating hyperspectral images from multi-modal sensor data including RGB, LiDAR, thermal, and near-infrared inputs. Training data includes hyperspectral images and corresponding multi-modal measurements. Spectral band grouping is performed based on correlation coefficients. A multi-modal decomposition network with cross-modal attention mechanisms generate reconstructed hyperspectral images by fusing complementary sensor information. A fine-tuning network creates reconstructed RGB images. A comprehensive quality assurance system analyzes spectral consistency, cross-modal coherence, and fusion artifacts to generate quality metrics. Missing data compensation strategies handle corrupted sensor inputs using information from other modalities. The system includes temporal integration for video sequences and multi-resolution processing for different sensor resolutions. Quality metrics guide network weight adjustments to improve reconstruction accuracy while maintaining robustness to sensor failures and environmental variations.

The invention provides a medical decision-oriented multi-modal data dynamic fusion and labeling method and system, and relates to the technical field of medical decision-making, and the method comprises the steps: collecting medical images, electronic medical records and physiological monitoring data of a patient, extracting multi-modal features such as a focus form, a disease type, a symptom, a treatment record and a physiological index, and carrying out the fusion and labeling of the multi-modal features; and constructing a dynamic fusion labeling model. According to the model, multi-modal features are coded, similarity is calculated, a feature association graph is constructed, feature aggregation is carried out, labeling is carried out in combination with a medical knowledge base, and a dynamic labeling vector is generated. And inputting the dynamic labeling vector into a medical decision support model, and based on similar case analysis and deep reinforcement learning, generating a diagnosis and treatment suggestion containing a treatment scheme and early warning information. By dynamically fusing multi-modal data and an online updating mechanism, the accuracy and efficiency of medical decision making can be improved, and personalized diagnosis and treatment are realized.

The invention provides a method and system for analyzing defects in wafer manufacturing based on big data, and relates to the technical field of big data, and the method comprises the steps: collecting technological parameter information, defect scanning images and manufacturing process data information, and carrying out multi-scale feature pyramid network processing and fusion to obtain fusion features; the fusion features are analyzed through a deep learning network, the deep learning network adopts a multi-task learning framework to complete a defect classification task, a defect segmentation task and a defect evolution prediction task at the same time, consistency loss based on graph matching is introduced, and a defect type recognition result and a feature map of defect space distribution are obtained; based on the characteristic spectrum, when it is detected that the process parameters are abnormal, analyzing historical defect data by using a graph neural network containing a time sequence attention mechanism; technological parameter constraint conditions are set in combination with an expert knowledge base, and technological parameters are adaptively adjusted through a reinforcement learning method. According to the invention, the accuracy of defect detection and classification is improved.

The invention provides a news scene three-dimensional reconstruction and visualization method based on multi-source remote sensing data, and relates to the technical field of three-dimensional reconstruction, and the method comprises the steps: extracting multi-modal data feature points through employing a spatial position weighted iterative nearest point algorithm and a tensor projection algorithm; after bidirectional attention deep neural network processing and local geometric consistency constraint screening, registration multi-source remote sensing data is generated, data enhancement is carried out through a variational auto-encoder network and a generative adversarial network, the enhanced data is used for depth information generation and texture feature migration, an initial three-dimensional grid model is generated based on a Poisson reconstruction algorithm, and the initial three-dimensional grid model is constructed; and carrying out topological optimization by combining multi-view projection consistency constraint and a grid optimization algorithm to obtain an optimized three-dimensional scene model, setting a space division function, carrying out space division, constructing a grade model and a depth region, generating a scene semantic segmentation map, and updating a visual scene.

A method for detecting an infrared ship target based on an improved YOLOv7 is provided, including the following steps: obtaining an infrared maritime ship data set; reforming a YOLOv7 network structure based on an MobileNetv3 network and a bidirectional weighted feature pyramid network, and obtaining an infrared ship target detection model by introducing an attention mechanism and an optimized loss function; training and verifying the infrared ship target detection model based on the infrared maritime ship data set to obtain the infrared ship target detection model trained; and detecting a maritime ship based on the infrared ship target detection model trained.

The application provides a fault prediction method and apparatus, an electronic device and a storage medium. The method comprises: obtaining a vibration signal collected by a sensor installed on a target component of a target device, and cleaning and segmenting the vibration signal to obtain a target vibration signal; inputting the target vibration signal into a target anomaly judgment model to obtain an output result, and according to the output result, determining whether the target vibration signal is abnormal to obtain an anomaly judgment result; when the abnormal judgment result shows that the target vibration signal is abnormal, inputting the target vibration signal into a target fault prediction model to obtain a fault prediction result, wherein the target fault prediction model is obtained by combining an encoder of the target anomaly judgment model and a newly added full connection layer. The application solves the problem in the prior art that a faulty device cannot be timely maintained because the fault can only be monitored when the device fault is quite obvious.

The invention relates to the technical field of power equipment early warning, in particular to a power equipment anomaly detection early warning system and method. The method specifically comprises the following steps: acquiring multi-source sensing data of target power equipment; performing cross-modal collaborative denoising based on semantic graph modeling and multi-scale residual feedback; fusing the space-time similarity and abnormal diffusion characteristics of the equipment, constructing a weighted relation graph, carrying out abnormal sensitive clustering by using a graph neural network, and identifying a potential abnormal group; abstracting historical anomalies into fault gene vectors, matching an evolution path, and predicting a new anomaly propagation trend; an expert knowledge graph and a graph neural network are introduced, double-domain decisions are dynamically fused through an objection-driven game, and the early warning credibility is improved; grading early warning is triggered according to propagation influence evaluation, abnormal features and evolution paths are written back to a knowledge base in a structured mode, collaborative optimization of the model and a rule base is driven, and a detection-early warning-optimization self-closed-loop system is formed. According to the method, the problems of dynamic relevance modeling, new anomaly prediction and decision credibility are solved.

The invention relates to the technical field of privacy data protection, and discloses a privacy data protection method and system based on homomorphic encryption and federated learning, and the method comprises the steps: processing original health data collected by Internet of Things equipment of a plurality of pension institutions, and obtaining a preprocessing data set and a privacy risk assessment result; encrypting to obtain a double encrypted data set; constructing a decentralized federated learning framework, and calculating global training parameters; performing noise injection processing and model iteration training to obtain a privacy protection model; performing trusted execution environment deployment on the privacy protection model, and performing identity verification through role-based multi-level access control and zero-knowledge proof to obtain a security access strategy; edge node distributed deployment is conducted on the privacy protection model, cross-mechanism health data analysis is conducted through a secure multi-party computing protocol, a collaborative analysis result is obtained, various privacy protection technologies are adopted, and efficient utilization of data is achieved while data privacy is protected.

The invention relates to a dynamic data pipeline construction method based on artificial intelligence and multi-modal data processing, and belongs to the technical field of data fusion treatment and artificial intelligence. According to the method, a multi-modal deep learning model is adopted, semantic analysis is performed on business documents, user requirements and function specification instructions, and key indexes, data requirements and logic constraints are extracted; constructing a multi-modal knowledge graph, performing unified representation and feature extraction on structured and unstructured data resources, and performing embedded learning by using a graph neural network; based on a deep semantic matching model and a hybrid recommendation system, realizing accurate matching of business requirements and data resources; modeling generation of a data processing flow into a Markov decision process by adopting a reinforcement learning strategy, and automatically generating an optimized data processing workflow; the adaptability of the model to new business requirements is improved by utilizing a meta-learning algorithm; and dynamic scheduling and execution of tasks are realized through a workflow engine. According to the invention, the data processing efficiency can be improved.

The invention provides a dynamic health adaptive monitoring method and system using artificial intelligence, and relates to the technical field of health monitoring, and the method comprises the steps: carrying out the noise reduction through a hierarchical diffusion probability model through multi-source heterogeneous health data, extracting preliminary features through combining with an improved attention auto-encoder, learning discriminative features through a contrast learning network, and carrying out the recognition of the discriminative features; inputting the discriminative features into an adaptive wavelet neural network for multi-scale feature decomposition, inputting the discriminative features into a dynamic graph neural network to obtain a health feature tensor, obtaining time sequence features by using a hierarchical memory enhancement network, and generating a health knowledge graph in combination with a dynamic routing capsule network and a causal reasoning network; and inputting the time sequence characteristics and the health knowledge graph into a deep Bayesian network for health risk assessment, and obtaining an adaptive monitoring scheme through a model prediction control network by using a hierarchical reinforcement learning network and combining a multi-agent collaborative optimization system and a deep deterministic strategy gradient network.

The present application relates to the technical field of load prediction, and provides an electrical load prediction method and device based on spatial-temporal correlation. The method comprises: performing spatial-temporal modeling on the basis of historical electrical load data and historical environment data to obtain a multi-layer spatial-temporal model, wherein each layer model is a directed graph and represents spatial causality in the fixed time, and a directed edge between the layer models represents temporal causality; on the basis of an interpretable spatial-temporal attention transformer, performing feature extraction and priori knowledge fusion on the multi-layer spatial-temporal model to obtain spatial-temporal characteristics of an electrical load, wherein the interpretable spatial-temporal attention transformer comprises a spatial causal attention network, a temporal attention network, and a spatial dependence comparison module; and on the basis of the spatial-temporal characteristics of the electrical load, and the real-time electrical load data and the real-time environment data of a target electrical node, predicting by using a trained STEF-DHNet model to obtain the predicted electrical load data of the target electrical node. The present application can improve the prediction accuracy and the model applicability.

The invention discloses an auditing decision support system and method based on a dynamic knowledge graph, relates to the technical field of computers, and aims to solve the problems that auditing data are heterogeneous and complex, risk identification is not timely and causal interpretation is lacked. According to the system, multi-modal audit data is collected in real time through a streaming event processing framework, and a dynamic audit knowledge graph with timeliness weight is constructed. Based on a graph calculation engine and cross-domain rule mining, identifying a high-frequency risk mode, and generating a risk conduction path graph; further fusing a multi-modal graph attention network, identifying and positioning abnormal entities, and outputting abnormal nodes and risk links thereof; and finally, the abnormal node embedding representation is dynamically updated through the time sequence diagram attention network, an interpretable audit causal map is generated in combination with a structural causal model, and closed-loop support from data acquisition and risk identification to interpretive audit decision is realized. The intellectualization and transparency of audit decision making are improved, and an efficient and traceable decision making basis is provided for a complex audit scene.

The invention provides an AI-based big data distributed computing task automatic optimization method and system, and relates to the technical field of AI. The method comprises the following steps: constructing a multi-modal spatial-temporal feature sensing network to extract spatial-temporal features of tasks and resources, and training a hierarchical hybrid decision network to perform global task scheduling and local resource allocation. The global strategy network adopts a layered deep reinforcement learning architecture, and generates a decision by combining Monte Carlo tree search and priority experience playback; and the local execution network optimizes local deployment based on the graph neural network and multi-agent collaborative learning. In addition, a distributed anomaly detection network is deployed to monitor the performance in real time, self-adaptive adjustment and optimization are achieved through enhanced transfer learning, and finally the perception network is updated through knowledge distillation to achieve model evolution. According to the method, the execution efficiency and the resource utilization rate of the big data distributed computing task can be effectively improved, and the system operation cost is reduced.

A system and method for extending AI-enhanced decision platforms with deontic and normative reasoning capabilities that enhance adjustably autonomous decision-making through a novel integration of symbolic and neural approaches. The invention uses hierarchical and fuzzy deontic logic implementations alongside connectionist AI / ML to manage obligations, permissions, and prohibitions while maintaining observer awareness to achieve goals while incorporating knowledge across multiple expert domains. The system employs dynamic event and spatio-temporal knowledge graphs along with debate mechanisms, enabling high-assurance automated reasoning while preserving explainability through neuro-symbolic integration. In at least one embodiment, the invention operates through a federated distributed computational graph architecture that allows for arbitrary scaling while maintaining coherence, consistency and supporting compound workflows. The invention provides a framework for AI systems to make logically consistent, ethically-aware decisions by combining deontic reasoning with multi-agent coordination, token space communications and knowledge, including on intermediate results, enabling automated decision-making for a variety of applications.

The invention provides an intelligent subway equipment fault diagnosis method and system assisted by a large language model, and relates to the technical field of data processing, and the method comprises the steps: extracting key information through a large language model, constructing a multi-dimensional equipment fault knowledge graph, obtaining a historical fault data set, and extracting key fault monitoring parameters related to the fault, obtaining a sensing state data set, and judging whether the sensor state data is abnormal or not; and calling a pre-constructed sensing distortion correction algorithm, generating a fault monitoring correction parameter and executing parameter correction, inputting multi-dimensional monitoring data into a diagnosis engine driven by a large language model, and outputting a most possible fault type, cause analysis and recommendation processing strategy and a fault identification report. The technical problems that in the prior art, due to the lack of fusion modeling capacity for the unstructured fault text and the structured monitoring data, the intelligent degree of fault diagnosis is low, and accurate recognition and causal analysis are difficult to achieve are solved, and the fault recognition response speed and accuracy are improved.

A scalable platform for orchestrating networks of specialized AI multi-agent networks that enables secure collaboration through token-based protocols and real-time result streaming with advanced dynamic chain-of-thought pruning. The central orchestration engine manages domain-specific agents, implementing sophisticated multi-branch reasoning with contribution-estimation layers that evaluate each agent's utility using Shapley value-inspired metrics. The system employs information-theoretic and gradient-based surprise metric to guide memory updates and dynamic reasoning expansion, preventing local minima stagnation while preserving valuable insights through adaptive forgetting mechanisms. The platform unifies Monte Carlo tree search with contribution-aware estimation to detect high-synergy expert combinations while maintaining privacy through partial data approaches. It scales across distributed computing environments, enabling complex collaborative tasks like materials discovery, product engineering and manufacturing process design, biomedical research, and drug development. The system supports multi-party economic rewards through systematic contribution effort, cost and importance tracking, while standardized interfaces manage security, privacy, and policy constraints across heterogeneous agents.

The invention provides a big data platform scheduling task and data collaborative smooth migration method and system, and relates to the technical field of big data, and the method comprises the steps: constructing a digital twin environment of a target system, collecting task operation state data of a source system, extracting task features through a deep neural network, and carrying out the clustering and grouping. And deploying the task group to a digital twin environment, analyzing a task association relationship and a resource competition relationship based on a graph neural network, and generating a task stability score in combination with a task operation index. And constructing a migration risk prediction model to perform quantitative evaluation on the migration risk, and determining a migration priority and an execution sequence according to the quantitative evaluation. And making corresponding resource configuration, data synchronization and fault recovery plans for each task group, carrying out migration drilling in a digital twinning environment, and optimizing a migration scheme by utilizing a reinforcement learning algorithm. The migration risk can be effectively reduced, the smoothness and stability of the migration process are guaranteed, and the migration efficiency is improved.

The invention relates to the technical field of industrial automation control, and discloses a multi-machine collaborative industrial robot intelligent scheduling system and an application method.The system comprises a data acquisition module for acquiring real-time motion data through a multi-modal sensor; the feature fusion module is used for generating environment dynamic feature data based on graph neural network fusion data; the strategy generation module is used for generating collaborative strategy parameters by utilizing a collaborative reinforcement learning model; the trajectory optimization module is used for constructing a multi-target trajectory optimization model to plan an optimal synchronous trajectory; the motion control module is used for establishing a layered motion control model to realize cooperative motion control; a dynamic resource allocation module can also be included to optimize resource allocation. The application method sequentially executes corresponding steps according to the modules of the system. According to the method, the environment can be accurately sensed, the cooperation strategy can be optimized, the efficient track can be planned, accurate motion control and reasonable resource allocation can be realized, and the cooperative motion control capability and the production efficiency of the industrial robot in the complex environment can be effectively improved.

The invention provides a digital power grid power cloud resource real-time hierarchical distribution method, which comprises the steps of dividing power cloud resources into a plurality of sub-resource pools according to a physical architecture and a topological structure of a digital power grid, setting a special resource pool for key equipment and sensitive loads of the power grid, and dynamically adjusting network topology and a routing strategy. A low-delay and high-reliability network transmission channel is provided through a priority queue and a bandwidth guarantee mechanism; for each sub-resource pool, extracting periodicity, tendency and randomness characteristics of a load by analyzing historical load data and a current system state of power grid equipment, and updating a load prediction result in real time; after incremental resources are migrated, a power grid control request is routed to a corresponding computing node by adopting a consistent Hash algorithm in a sub-resource pool, load balancing is realized by dynamically adjusting the number and distribution of virtual nodes of a Hash ring, and weights of the virtual nodes are dynamically adjusted according to load optimization indexes of the nodes so as to adapt to power grid load changes.

A 3D target detection method based on multimodal fusion and a depth attention mechanism includes the following steps: obtaining and preprocessing original point cloud data and original image data; inputting the preprocessed point cloud data and image data into a 3D target detection network based on multimodal fusion and the depth attention mechanism, where the 3D target detection network based on multimodal fusion and the depth attention mechanism includes a generation phase for 3D bounding box proposals and a refinement phase for 3D bounding boxes, and the network outputs parameters and classification confidence of a target bounding box; training the 3D target detection network based on multimodal fusion and the depth attention mechanism; and processing the collected lidar point cloud data and image data by using the trained detection network, and outputting 3D target information, to realize 3D target detection.

The invention discloses an ancient building risk prediction management and control method and system based on a large model, and relates to the technical field of ancient building protection. An ancient building risk prediction management and control system based on a large model comprises a multi-source data acquisition module, a multi-modal data fusion module, a large model risk prediction module, a risk assessment and early warning module, a digital twinborn dynamic management and control module and a repair decision module. According to the method, the structure state data, the visual image data and the environment data are fused, so that the state of the historic building is comprehensively perceived; the self-supervised learning pre-trained ViT-GPT model is combined with the LSTM time sequence model, so that the time sequence analysis capability and the multi-modal data processing capability of risk prediction are remarkably improved, the future damage probability and the risk trend of the historic building can be accurately predicted, and the defects of the prior art in long-time span risk prediction are overcome.

The invention discloses a decision-making method and model for off-line reinforcement learning and continuous on-line fine tuning, and the method comprises the steps: obtaining original text-image pair data and historical track data, and obtaining an enhanced state sequence through feature matching verification and standardization processing; performing sequence prediction by using a multi-level attention mechanism, and obtaining pre-training model parameters through knowledge distillation and task adaptability enhancement; on the basis of stability evaluation and plasticity control, online knowledge migration is carried out on the model, and optimized model parameters are obtained by combining experience playback optimization; and finally, performing multi-dimensional performance evaluation and resource optimization. According to the method, through multi-modal feature fusion, dynamic knowledge migration and an adaptive optimization mechanism, the problems of insufficient feature representation, disastrous forgetting, low optimization efficiency and the like are effectively solved, and the learning efficiency and generalization ability of the model are improved.

The invention discloses a transformer area intelligent fusion terminal data processing system based on edge calculation, relates to the field of edge intelligence, and solves the problems of poor real-time performance and poor data exception processing accuracy of an existing intelligent fusion terminal data processing system. According to the method, communication between micro-services is efficiently managed through the container arrangement engine and the service grid, the message transmission delay is reduced, and resource allocation is further optimized through a resource scheduling algorithm based on reinforcement learning, so that system resources are used most reasonably; according to the method, anomaly detection is rapidly and accurately carried out through a space-time heterogeneous fusion network model, hierarchical processing of data and on-cloud training of the model are realized through a cloud-edge collaborative architecture, edge nodes participate in model training through a federated learning mechanism, the model performance is optimized, the transmission time of the data in the network is shortened, and the problem positioning speed is increased; the real-time performance and the reliability of an existing system are greatly improved.

The invention provides a home abnormal state signal detection method and system based on multi-modal sensing, and relates to the technical field of detection, and the method comprises the steps: collecting human body motion, acoustics and environment parameters through a millimeter wave radar, an acoustic sensor and an environment sensor, inputting the parameters into a deep fusion network, a spatio-temporal attention mechanism and a multi-scale convolutional neural network are used to extract a spatio-temporal feature sequence, and joint probability features are formed in combination with an acoustic feature spectrum analysis result. And inputting the joint probability features into a time sequence knowledge graph, and obtaining scene adaptive features after processing by a graph attention network and a double-flow auto-encoder network. And finally, the multi-task learning network is combined with the risk propagation neural network and the recursive neural network to carry out anomaly prediction and risk level evaluation, and is combined with historical early warning information to output an early warning strategy. According to the invention, multi-modal data can be effectively fused, the accuracy and reliability of home abnormal state detection are improved, and a more accurate risk assessment and early warning strategy is provided.

An advanced model management platform for optimizing and securing generative artificial intelligence systems such as large language models (LLMs) and diffusion models. The platform incorporates various techniques to address the limitations of current generative AI systems, such as hallucination, lack of validation, security vulnerabilities, and inadequate model management. The system employs reinforcement learning algorithms for model optimization, retrieval augmented generation (RAG) for hallucination mitigation, domain-specific validation against expert knowledge, model distillation and similarity scoring for security, adversarial training for robustness, and attention mechanism search and model blending for advanced management and neuro symbolic AI routine combinations. By integrating these techniques, the platform significantly improves the performance, reliability, and security of generative AI across a wide range of tasks and domains leveraging the best elements of symbolic and connectionist techniques alongside automated planning and modeling simulation.

The invention provides a notarization intelligent question and answer customer service method and system based on a knowledge graph, and relates to the technical field of information, and the method comprises the steps: collecting multi-source heterogeneous data in the notarization field, forming an entity set and a relationship set, combining to form an initial knowledge graph, carrying out a dynamic update mechanism based on time decay, and supplementing to form a dynamic knowledge graph. Carrying out vectorization expression to obtain an atlas vector; receiving a multi-modal problem, determining fusion features, performing deep semantic understanding, obtaining semantic features, determining a user intention, and forming a structured query expression; based on the user intention and the structured query expression, carrying out multi-hop reasoning in the dynamic knowledge graph, carrying out similarity calculation by utilizing graph vectors, determining a reasoning path in combination with the user intention, carrying out knowledge association reasoning along the reasoning path, obtaining a preliminary reasoning result, carrying out interpretability analysis on the preliminary reasoning result, and obtaining a final reasoning result; and generating a reasoning chain and a confidence score, forming a detailed reasoning result, and finally generating a personalized answer.

Provided is a rolling bearing fault diagnosis method based on FFT coding and L-CNN, including: obtaining original bearing fault vibration data, extracting intrinsic mode components of different frequency bands in the original bearing fault vibration data, calculating a permutation entropy value corresponding to each of the intrinsic mode components, and performing wavelet threshold denoising according to the permutation entropy value to obtain a denoised reconstructed time domain signal; performing fast Fourier transform to the denoised reconstructed time domain signal to obtain a frequency domain signal and a phase angle corresponding to the time domain signal, reconstructing the frequency domain signal according to a preset rule, retaining frequency domain data of features of the phase angle, and drawing FFT-x heat maps of different fault type data according to an amplitude range; and constructing an model L-CNN, and inputting coded data into the L-CNN model, and obtaining fault diagnosis results.

Disclosed in the present invention are a health monitoring system and monitoring method for wind turbine blades. In the present invention, fault signals are extracted and collected on the basis of multi-sensor monitoring, and the collected signals are amplified and denoised. Preprocessed signal data is then further fused with spectral features of an acoustic emission signal and a vibration signal, self-supervised health representation learning is performed to generate severely scarce negative samples, and classification of measured data collected from healthy and unhealthy blades is performed by means of auxiliary tasks, thereby implementing pseudo-label-based supervised learning. In the present invention, data fusion, EMD denoising, self-supervised learning and LSTM model training technology are used, such that blades of a wind turbine generator can be monitored in real time online, high-precision diagnosis can be performed on faults that have occurred, and inspection and fault type determination for evaluating the state of health of the current blade are performed, thereby meeting the requirements of a wind power market for online monitoring of wind turbine blades.

A small sample steel defect detection method based on an attention feature pyramid mechanism, comprising: first acquiring initial multi-scale feature maps by means of a convolutional neural network, then by means of a top-down and transverse connection mode, using an improved multi-scale attention network to process the initial multi-scale feature maps one by one to obtain intermediate multi-scale feature maps, then by means of a bottom-up and transverse connection mode, using the improved multi-scale attention network to process the intermediate multi-scale feature maps one by one to obtain final multi-scale feature maps, and finally outputting a final classification result; using a pseudo-label semi-supervised learning algorithm to train a detection network model, using a locally linear embedding algorithm to perform dimension reduction and visualization processing on high-level features of training output results, screening for mistakenly labeled and incorrectly labeled images and removing labels, then putting the images into unlabeled image data, and performing re-training to generate pseudo labels so as to expand a training set until the training requirement is met; and inputting an image to be detected into a trained detection network model for identification.