1945 results about "Domain adaptation" patented technology

The invention provides an improved YOLOv11s safety helmet wearing detection model and an optimization method thereof, and relates to the technical field of computer vision target detection. According to the improved YOLOv11s safety helmet wearing detection model and the optimization method thereof, the improved YOLOv11s safety helmet wearing detection model comprises the following modules: a multi-modal fusion module, a space-time analysis module, a domain adaptation module, a topological optimization module and a dynamic architecture module; and the multi-modal fusion module is used for realizing feature decoupling by adopting channel separation convolution based on input RGB and near-infrared images, fusing visible light and thermal radiation features through a dynamic weight distribution algorithm, implementing affine transformation alignment on multi-scale features by utilizing a spatial transformation network, and generating a multi-modal feature graph. Through fusion of visible light and near infrared spectrum features and implementation of dynamic weight distribution, complementarity of target texture and thermal radiation features under a complex illumination condition is enhanced, and the problem of feature distortion of single-mode data in a strong backlight or low-illumination scene is solved.

The invention discloses a data anomaly diagnosis method and system based on a knowledge graph and a large model. According to the method, multi-source data including structured database records, semi-structured technical documents and unstructured expert experience descriptions are obtained and preprocessed, a knowledge graph containing entity, relation and attribute levels is established, domain adaptation training is conducted on a large language model through the knowledge graph, and the large language model is obtained. And constructing a hierarchical reasoning framework to realize data exception identification, diagnosis and solution generation. The method solves the technical problems of non-uniform knowledge representation, limited diagnosis capability, single reasoning logic and the like of a traditional data anomaly diagnosis method, and has the following advantages: uniform representation and storage of multi-source heterogeneous data are realized; the domain understanding ability of the large language model is improved through knowledge injection; the accuracy and efficiency of abnormality diagnosis are improved by adopting a hierarchical reasoning framework; and experience accumulation and continuous optimization are supported, and high practicability and expansibility are achieved.

An intelligent analysis method based on medical document structure perception and multi-modal fusion comprises the following steps: carrying out structure topology modeling on a medical document, extracting visual layout, text meta-information, space coordinates and semantic keyword features, constructing a semantic topological graph and dynamically shielding irrelevant contents; selecting an extraction path according to a document type, performing deep semantic analysis and entity recognition on a text-type document, and performing visual enhancement OCR recognition on a scanning-type document; the features are injected into a medical knowledge graph, and feature fusion, semantic verification, relation reasoning and information completion are achieved through a graph neural network; a three-stage strategy optimization model of basic pre-training, domain adaptation and online reinforcement learning is adopted; and large-scale processing is realized through a dynamically aggregated distributed architecture. The method is used for intelligent analysis and structured conversion of documents of hospitals, medical insurance and medical scientific research. The problems that heterogeneous medical document analysis adaptability is poor, multi-modal fusion is difficult, medical knowledge utilization is insufficient, and large-scale processing efficiency is low are solved.

The invention belongs to the technical field of remote sensing image imaging, and provides a remote sensing image unsupervised domain adaptation method based on comparative learning and multi-prototype alignment, and the method specifically comprises the steps: constructing a teacher-student network, and setting a cross-domain multi-prototype alignment module and a pixel-level cross-domain comparative learning module which are needed in training in the teacher-student network; during teacher-student network training, a cross-domain multi-prototype alignment module is used for extracting prototypes of all categories in a source domain and a target domain and minimizing the feature distance of the prototypes, and a pixel-level cross-domain contrast learning module is used for explicitly modeling the global semantic relationship of cross-domain pixel samples; and an embedding space with high intra-class compactness and high inter-class separability is established.

The invention provides an underwater target detection method based on multi-modal features and domain adaptation. The method comprises the following steps: S11, acquiring a sonar image, an optical image and environmental data; s12, extracting a sonar feature and an optical feature, encoding the environment data into an environment channel weight, and dynamically adjusting a fusion proportion of the sonar feature and the optical feature through the environment channel weight to obtain a fusion feature; s13, performing spatial attention calculation on the sonar features to obtain a spatial weight map, enhancing the optical features by using the spatial weight map, and performing forced alignment with the sonar features at the target edge; and S14, decoupling the fusion feature into a synthetic domain feature, decoupling the fusion feature and the environment data into a real domain feature, and gradually aligning the synthetic domain feature and the real domain feature through asymptotic domain alignment to complete construction of a target detection model. According to the invention, multi-modal data acquisition, dynamic feature fusion and decoupling and embedded real-time detection are combined, so that the precision of underwater target monitoring is remarkably improved.

The invention discloses a multi-modal medical image fusion diagnosis system based on artificial intelligence, and the system comprises the following steps: extracting shared features of CT and MRI images through a convolutional neural network, and mapping the shared features to the same feature space; a two-way step-by-step alignment strategy is adopted, a three-dimensional deformation field matrix is generated, and cross-modal image anatomical structure alignment is achieved; calculating modal feature weights and eliminating distribution differences through an attention mechanism and an adversarial domain adaptation layer; constructing a CT-MRI image block contrast learning task, and optimizing a shared feature encoder; a conditional generative adversarial network is used for generating a false image of a missing mode according to the semantic segmentation map, and data distribution is constrained through a Wasserstein distance; uniform feature extraction of multi-modal medical images is realized through a shared feature encoder, the cross-modal image alignment accuracy is improved in combination with a bidirectional deformation field prediction module, and the comprehensiveness and accuracy of fusion features are enhanced by using a multi-modal feature fusion module.

The invention discloses a wind power plant equipment fault intelligent diagnosis method and system. The method comprises the following steps: acquiring multi-dimensional sensor data of wind power plant equipment; carrying out preliminary screening on the data by utilizing an edge analysis algorithm, and determining data needing to be further diagnosed; the screened data are input into a pre-constructed fault diagnosis model, the data are fused through a multi-modal deep learning model in the pre-constructed fault diagnosis model, and then a fault occurrence area is determined through transfer learning, domain adaptation and a multi-agent reinforcement learning framework; meanwhile, the causal inference engine and the knowledge graph enhanced neural symbol inference module are responsible for deep processing and fault diagnosis. And finally, inputting the determined fault area and the diagnosis result into a dynamic system health index calculation module to generate a final fault diagnosis result. According to the method, the diagnosis efficiency and accuracy of the equipment fault of the wind power plant are remarkably improved, and a powerful guarantee is provided for stable operation of the wind power plant.

The invention belongs to the technical field of steel production equipment fault diagnosis, and particularly relates to a steel production equipment fault diagnosis system based on a large language model. The system comprises a data processing module, a large language model training module and a retrieval enhancement generation module. Through domain data processing and model training, an intelligent diagnosis platform specially used for steel production equipment is constructed. The data processing module is responsible for performing feature extraction on the sampled data and constructing a vector database to ensure that the model can perform efficient semantic matching; the training module performs field adaptive adjustment on the large language model to improve the reasoning ability of the large language model in a specific field; the retrieval enhancement generation module realizes fault analysis and technical guidance with strong pertinence and high accuracy by integrating a vector database and a generative answer mode; the system runs locally or on a privatized server, all data processing, model calculation and generation processes are ensured to be completed in a controlled environment, and the privacy of user data is fully protected.

The invention discloses a passive unsupervised domain adaptive medical image segmentation method and device based on pseudo labels, and relates to the technical field of computers, and the method comprises a supervised source domain model training stage, an unsupervised adaptive target domain model training stage and a segmentation stage. The method specifically comprises the following steps of: performing pixel-level self-marking on a source domain medical image by applying pseudo-tag pixel-level uncertainty estimation to generate a reliable pseudo-tag; and on this basis, a strong and weak enhanced teacher-student target domain model is used, and a high-quality pseudo tag is fully utilized to train a target domain medical image, so that the network adapts to representation specific to the target domain medical image. According to the method, unsupervised segmentation is carried out on the target domain data graph on the premise that the source domain model and the target domain unmarked data are known, source domain data do not need to be accessed, the features of the source domain model can be reasonably utilized, and the problem existing in SFUDA can be well relieved; and the accurate segmentation capability on the target domain is still maintained under the condition that less data is available compared with the UDA method.

The invention discloses a field specialized large model fine tuning and deployment method and system based on adaptive optimization, belongs to the technical field of artificial intelligence and machine learning, and aims to solve the technical problem of how to improve the rapid adaptation capability of a large model on small-scale field data. In order to meet the requirements of special fields of law, medical treatment, finance and the like on professional terms and complex contexts, the technical scheme adopted by the invention comprises the following steps of: data processing and sample generation: performing cleaning, feature extraction and small sample expansion on field data, and generating a high-quality training sample through a field feature guide mechanism; small-sample fine tuning and migration: realizing rapid field adaptation of a large model through a small-sample learning technology and dynamic Prompt optimization, and reducing dependence on large-scale annotation data in combination with cross-field migration learning; compressing and optimizing the model; performing automatic deployment and collaborative reasoning; and monitoring and adaptive optimization are carried out.

The invention relates to the technical field of welding material performance testing, and discloses an acoustic-optical-electric synergistic welding material fatigue performance testing method and system, and the method comprises the steps: synchronously collecting a first multi-mode signal data set of a welding material in a fatigue testing process; carrying out fusion processing to obtain a fusion feature vector; performing time sequence feature extraction to obtain time sequence comprehensive representation; constructing and training an initial fatigue performance multi-task learning model comprising a shared feature extractor and a task-specific sub-network based on time sequence comprehensive representation; implementing domain adaptation and transfer learning on the fatigue performance multi-task learning model to obtain a target fatigue performance multi-task learning model; acquiring a second multi-mode signal data set in real time and inputting the second multi-mode signal data set into the target fatigue performance multi-task learning model to obtain a welding material fatigue performance test result, so that acoustic, optical and electric multi-mode signals can be effectively integrated, and high-precision, multi-task and migratable welding material performance test is realized.

The present invention discloses a method and system for smart grid fault self-healing based on generative artificial intelligence, which relates to the field of smart grid fault self-healing. The method includes: obtaining and preprocessing multi-source heterogeneous data; generating a pre-trained language model and performing domain adaptability fine-tuning, adding a task-specific output layer; performing feature fusion using a multimodal data fusion method, and using annotated historical fault data sets for supervised training to obtain fault diagnosis results. Fault self-healing is modeled as a Markov decision process, and a deep reinforcement learning algorithm is used to interactively learn the optimal decision-making strategy with a power grid simulation environment, and an optimal fault self-healing plan is generated and converted into specific operation instructions. The present invention integrates multi-source heterogeneous data, performs accurate positioning and description generation, improves the reliability and self-healing ability of the smart grid, and ensures rapid recovery of normal operation when a power grid fails.

The invention relates to a talent matching and intelligent recruitment method and system based on an AI large model. The method comprises the steps of obtaining multi-modal data of candidates and post demand data of recruiters; performing semantic extraction and feature fusion on the multi-modal data through a multi-modal fusion encoder to generate a comprehensive feature vector containing semantic association features and behavior features; performing field adaptation processing on the comprehensive feature vector based on a dynamically updated industry knowledge graph to generate a skill label set of candidates; performing dynamic matching degree calculation on the skill label set and post demand data according to historical recruitment feedback data by adopting a reinforcement learning model to generate a recommendation list; and outputting the recommendation list to a recruiter terminal, and performing online optimization on the reinforcement learning model based on operation behavior data of a recruiter. According to the invention, intelligent matching of the job seeker and the recruitment demand is realized, and the recruitment efficiency and accuracy are improved.

The invention provides a transfer learning-based power transmission line fault positioning method and system. Real-time monitoring data of a target power transmission line are collected, meteorological information and satellite remote sensing images are combined, ambient environment changes are analyzed, anomaly detection is performed, an abnormal data set is obtained, and a comprehensive fault feature space is constructed; an adversarial domain adaptation algorithm is adopted to optimize a comprehensive fault feature space, and a long-short-term memory network, an attention mechanism and a graph convolutional network are used for data processing to generate an enhanced fault feature representation; constructing an integrated learning framework based on Bayesian optimization, predicting the target power transmission line by using the plurality of preliminary basic models, integrating all prediction results through an adaptive weighting strategy, and generating initial fault probability distribution; determining fault positioning information by using a geographic information system technology and a topological sorting algorithm; the invention provides an efficient and accurate power transmission line fault positioning method, and provides powerful support for safe operation of a power system.

The invention discloses a network security situation analysis method and device based on multi-agent collaboration, and the method comprises the steps: firstly constructing an agent architecture and a route for network security situation assessment analysis based on an open source large language model, carrying out the role definition of each agent in the agent architecture through combining with a Prompt prompt word, and stipulating the communication format of the agent; based on domain knowledge, a dynamic rank learning LoRA algorithm is adopted to carry out fine adjustment on each agent in the agent architecture, based on a natural language rule base, a commander agent is utilized to coordinate a collusion agent and a simulated blue army agent, multi-dimensional analysis is carried out through reflection, inquiry and debate mechanisms, and a network security situation assessment result and trend prediction are generated. Through combination of dynamic LoRA fine tuning and a multi-agent debate mechanism, the problems that universality and field adaptability are difficult to balance and complex attack intention analysis is insufficient in a traditional method are solved, and the accuracy and prediction reliability of network security situation assessment are remarkably improved.

Embodiments provide a generative AI creation framework to a customized generative AI stack using a foundational model (such as GPT) based on user-defined prompts, a natural language description of the task to be accomplished, and domain adaptation. In one embodiment, organization-specific knowledge may be injected into either the prompt and / or the foundational model. In this way, the customized generative AI stack thus supports a full spectrum of domain-adaptive prompts to enable a full spectrum of personalized and adaptive AI chat applications.

The invention provides a small sample plankton image enhancement recognition method and a small sample plankton image model building method, and belongs to the technical field of underwater image enhancement. The method comprises the following steps: firstly, acquiring and sorting plankton microscopic image data, and constructing a normalized data set; secondly, designing a small sample plankton image enhancement recognition model based on a feature map reconstruction technology, performing feature extraction on the image by adopting a deep convolutional neural network, generating an intermediate layer feature map, and realizing category discrimination in combination with a feature map reconstruction mechanism; the model fuses multiple key designs oriented to cross-domain adaptation and structure perception, the distribution difference between different data domains is relieved, and the characterization capability of the model on the complex morphological structure of plankton is also remarkably improved; and finally, performing end-to-end training and optimization on the model under a meta-learning framework to obtain an optimal model. Experimental results show that the method shows excellent classification performance on a plurality of plankton data sets, and high-precision recognition can be achieved under the condition that the number of samples is limited.

The invention relates to a micro-expression recognition method based on a cross-source double-branch dynamic space-time diagram convolutional network model, and belongs to the technical field of deep learning and pattern recognition. According to the method, a cross-source double-branch twin space-time diagram structure network is provided to mine subtle motion features of a facial structure when expressions change, and domain invariant features are learned through a twin structure. According to the design, facial global information is modeled through a global information and dynamic spatio-temporal feature extraction network, fine motion information of a facial key structure is extracted through an attention enhancement twin spatio-temporal diagram fusion network, facial structure association when expressions occur is fully modeled, and domain adaptation is performed by constructing cross-domain joint loss.

The invention provides a multi-mode-based unsupervised domain adaptive hyperspectral image classification method and system. The method comprises the following steps: extracting global features through an image encoder, classifying image samples by using a double classifier, aligning the same-kind distribution of a source domain and a target domain, and generating a pseudo label for the target domain; text features are extracted through a text encoder, the text features and image features are subjected to comparative learning, the distance between the text features and the image features of the same category is shortened, and the separability of data is improved. The system comprises a domain adaptation module and a vision-language alignment module, the domain adaptation module obtains image features through an image encoder, obtains prediction results through a double classifier, and selects one of the prediction results as a target domain pseudo tag; and the vision-language alignment module obtains corresponding text description by using the source domain label and the target domain pseudo label, and after a text encoder obtains text features, the text features are aligned with the image features obtained by the domain adaptation part.

The invention provides an intelligent path planning method and system based on a large language model, and relates to the field of path planning. According to the invention, an LLM-based multi-level collaborative optimization framework optimizes an original mathematical model and an algorithm strategy for a new demand described by a natural language by integrating the semantic understanding ability of the LLM, so that the algorithm strategy is optimized on the basis of a constructed first mathematical model and a constructed first genetic algorithm. The optimized second mathematical model and the optimized second genetic algorithm are generated in combination with changing new requirements, so that the problems of expressive limitation of engineering modeling by directly using LLM cue words and insufficient field adaptability of generating a meta-heuristic algorithm can be solved, and the scene adaptability of a traditional framework can be improved. Besides, the code proxy based on the MCP is constructed, and a hierarchical progressive self-correction mechanism of the code proxy is combined with standardized scheduling of the MCP, so that omnibearing automatic processing from a surface code error to a deep mathematical model problem is realized.

The invention discloses a machine tool thermal error prediction method based on multi-modal deep learning and domain adaptation, and the method comprises the steps: constructing an infrared image feature extraction module, and extracting the low-dimensional thermal features of infrared image data; constructing a spatio-temporal feature extraction module, and extracting spatio-temporal features in the current and power data; constructing a multi-modal feature fusion module, and fusing the low-dimensional thermal features and the spatial-temporal features to obtain fused features; a thermal error predictor is constructed, thermal error prediction is carried out according to the fusion features, and prediction loss is calculated; machine tool operation data under different working conditions are collected as a source domain and a target domain; through processing of the steps, fusion features of the source domain and the target domain and prediction loss of the source domain are obtained. Inputting the fusion features of the source domain and the target domain into a deep transfer learning module, calculating domain alignment loss, constructing a total loss function in combination with the prediction loss of the source domain, and performing joint optimization on the model; and predicting the thermal error of the target domain after optimization is completed. According to the invention, the prediction accuracy can be improved.

The invention discloses a data processing flow optimization method and system based on a large language model, and relates to the field of data processing, and the method comprises the steps: obtaining multi-source data of different data sources; the multi-source data is input into a field adaptation module, an initial multi-source data set is obtained, and the field adaptation module is used for recognizing the field type of the multi-source data and correcting and expanding the multi-source data according to the field type; inputting the initial multi-source data set into a large language model to obtain a data processing rule; performing data processing on the initial multi-source data set by adopting a data processing rule to obtain a processed multi-source data set; the processed multi-source data set is input into a field adaptation module, a final multi-source data set is obtained, and the field adaptation module is used for adjusting the processed multi-source data set according to the field type. The data processing efficiency and quality can be effectively improved.

The invention discloses an unsupervised domain adaptive medical image segmentation method and device based on multi-scale features, and relates to the technical field of computers, and the method comprises the steps: constructing a multi-scale feature fusion segmentation network based on double attention; taking the multi-scale feature fusion segmentation network as a generator, and constructing a first discriminator and a second discriminator; training based on the generator, the first discriminator and the second discriminator to obtain a trained multi-scale feature fusion segmentation network; and segmenting a medical image to be processed by using the trained multi-scale feature fusion segmentation network. According to the method, multi-scale features are introduced, feature representation of different levels is considered, and alignment of source domain and target domain features is realized through an adversarial feature alignment method and adversarial learning, so that the performance and generalization ability of a segmentation model on a target domain are improved; moreover, the method does not need to use a target domain label, and can well solve a problem of unsupervised domain adaptation of a medical image segmentation task.

The invention relates to the technical field of power transmission and distribution production, and discloses a data integration and multi-modal diagnosis method based on a power transmission and distribution scene, and the method comprises the following steps: S1, enhanced integration of multi-source heterogeneous data: collecting time sequence monitoring data, text procedures and image data of power transmission and distribution equipment, constructing an equipment topological correlation graph through a graph attention neural network, and carrying out the enhanced integration of the multi-source heterogeneous data; node feature embedding is optimized through self-supervised comparative learning, an adversarial variational auto-encoder is designed for edge data, and an enhanced sample is generated in combination with physical constraints of equipment. According to the data integration and multi-modal diagnosis method based on the power transmission and distribution scene, the field adaptability and reliability of a diagnosis result are improved while the model fine tuning cost is reduced, and the knowledge migration problem of a general model in the power transmission and distribution scene is solved; the introduction of a dynamic knowledge graph and a multi-dimensional evaluation system realizes the real-time integration of new regulation knowledge and the comprehensive evaluation of model performance, and ensures the sustainable evolution ability and decision transparency of the diagnosis model.

The problem of domain shift error in computer vision models and other perception components is addressed. In a label approximation phase, an approximate label distribution is computed for each input of a target batch using a trained machine learning (ML) perception component. In an online label optimization phase, a modified label distribution is assigned to each input of the target batch, via optimization of an unsupervised loss function that (i) penalizes divergence between the approximate label distribution and the modified label distribution for each input of the target batch (ii) penalizes deviation between the modified label distributions assigned to input pairs of the target batch having similar features.

The invention belongs to the technical field of large model thinking maps, and discloses a large model thinking map prompt learning system for common sense questions and answers. The big model thinking map prompt learning system for common sense questions and answers provided by the invention comprises a knowledge map generation module, a thinking map reasoning module, a prompt learning module, a domain adaptation module and a reasoning interpretability module. The invention provides a large model thinking map prompt learning system for common knowledge questions and answers, and the system improves the answering ability of a common knowledge question and answer model through multi-level knowledge structure reasoning in a mode of combining the thinking map and prompt learning. The system not only enhances the inference ability for complex common sense questions, but also improves the accuracy of domain common sense questions and answers by constructing a domain-specific thinking map, and provides the interpretability of the inference process.

The invention provides a passive field adaptive target detection model generation method based on class prototype alignment and a target detection method, and the method comprises the steps: carrying out the further extraction of target features from the features extracted from a student model and a teacher model through a target detection frame in a training process employing the teacher model and the student model; iteratively updating a first type prototype and a second type prototype which belong to the same target type on the basis of the extracted features of the target detection frame and target type prediction results output by the student model and the teacher model on the basis of the features of the target detection frame, and constructing the alignment loss of the prototypes by using the type prototypes; according to the method, feature extraction results and prediction results of the student model and the teacher model are aligned according to the feature extraction results and prediction results of the student model and the teacher model, so that historical knowledge is brought into the training process through iterative updating of the class prototype, the problem of model training collapse caused by incorrect supervision signals brought by false labels is avoided, the performance of the target detection model obtained through training is improved, and the training efficiency is improved. Therefore, the accuracy of the target detection result output by the target detection model is improved.

The invention provides a domain adaptation cross-modal medical image segmentation method and device based on boundary comparison, equipment and a medium, and relates to the technical field of medical image segmentation. The method comprises the following steps: respectively acquiring a source sample and a target domain image from a source domain data set and a target domain data set; the first image segmentation model is used as a teacher model, and weights are distributed for the pseudo labels of the target domain images; a training sample is obtained through bidirectional cross-domain cutmix; performing supervision and self-training by taking a weight learnable first model as a student model; combining supervision loss and comparison loss during training to pull a query sample to a prototype positive sample and push a boundary negative sample as a target optimization parameter, and obtaining a second image segmentation model; and finally, segmenting a second modal medical image by using the model. The method has significant advantages in cross-modal medical image segmentation, and the segmentation performance can be effectively improved.

The invention relates to the technical field of image processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a data processing method, device and equipment based on cross-domain feature alignment and a medium. The method comprises the following steps: generating potential space representation based on linear projection and position coding, inputting a pre-trained time sequence processing unit to extract and decompose target domain features, realizing alignment of different scale feature distributions by using domain adaptation parameters, fusing the scale features through a hierarchical attention weight mechanism, and generating target image data. According to the method, potential spatial features are extracted by performing blocking and coding on the image data, feature extraction and multi-scale decomposition are realized in combination with a time sequence processing unit, alignment processing of different scale features is completed by using domain adaptation parameters, and the accuracy of local detail recovery and global structure maintenance in a decryption process is effectively improved.

Techniques for zero-shot and few-shot transfer of domain-adapted base networks are described. Multiple machine learning task layers are trained using a shared base feature extractor network. At least one task layer is trained with samples and corresponding labels from a first domain as well as a second domain. At least one other task layer is trained with samples and corresponding labels from only the first domain. Ultimately, the other task layer(s) are adapted to generate labels for the first domain via the base network being weighted based on all trainings.