909 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 a low-cost cell segmentation method, system and device based on active learning. The method comprises the following steps: selecting an initial cell image for preprocessing and bounding box labeling; forming a training set and constructing a target detection model for training so as to predict a bounding box of pictures of the verification set; taking the bounding box as a prompt for segmenting a cut model (SAM), and outputting a corresponding cell mask; adopting a Monte Carlo discarding method to predict the uncertainty of the unlabeled pictures, and selecting the pictures with higher uncertainty to be labeled by experts; adding the marked image data into the training set of the last round for updating, and repeating the training and sample selection of the model; and outputting a model weight and an index record after the required performance is achieved. According to the method, the data annotation cost of a cell segmentation algorithm is greatly reduced on the premise of ensuring the model performance.

The invention discloses a new equipment rapid fault diagnosis method based on transfer learning. The method comprises the following steps: firstly, carrying out self-supervised feature representation learning on normal operation data of new and old equipment by using a variational auto-encoder, and aligning features to the same space; then pre-training a multi-source migration model based on meta-learning on an existing equipment fault data set to quickly obtain an initial diagnosis model of new equipment; fine tuning is carried out in combination with a small amount of annotated data, and the model is continuously optimized by adopting an interactive active learning strategy. And meanwhile, a centralized fault knowledge base is constructed through the cloud, end-cloud collaborative distributed online learning is realized, and the model can continuously adapt to a new environment. According to the method, the research and development efficiency of a new equipment fault diagnosis model is greatly improved, the problem of data shortage is effectively solved, fault knowledge sharing between equipment is realized, and the method has remarkable application value.

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 discloses a multi-modal federation active learning-based network anomaly detection method, which comprises the following steps of: fusing data of a plurality of modals through multi-modal feature aggregation to generate uniform feature representation; an active learning mechanism is introduced into the federated learning framework, and distributed nodes are allowed to autonomously select learning strategies according to characteristics and distribution conditions of own data; the node isomerism in the distributed environment is dealt with through an adaptive learning optimization strategy; the communication efficiency is optimized and the global synchronization frequency is reduced through a progressive federated synchronization mechanism; according to the method, multi-modal data fusion and federated active learning are combined, so that the precision and efficiency of network anomaly detection are improved on the premise of protecting data privacy.

The invention discloses a fault root cause analysis method based on multi-source equipment data fusion. According to the method, multi-source heterogeneous data such as equipment operation data, maintenance records and environment data are collected and efficiently fused, a fault mode is automatically recognized from fused data, and time sequence evolution characteristics related to faults are mined. And based on the established knowledge base of the fault modes and reasons, and in combination with interactive Bayesian network reasoning and manual feedback, the root cause of the fault is deduced. According to the method, innovative technologies such as active learning and transfer learning are introduced, and the intelligent level, accuracy and efficiency of fault diagnosis are improved. And a visual interface visually presents an analysis process, supports man-machine interaction correction, and enhances interpretability. The method is suitable for the fields of industrial equipment, transportation tools, medical equipment and the like, and the system stability and usability are 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 invention discloses an equipment state prediction method based on weak supervised learning. According to the method, through innovative means such as a hierarchical labeling strategy, an active learning module and an anomaly detection and automatic labeling module, the requirement for manual data labeling is greatly reduced. Meanwhile, various semi-supervised learning models are fused, data distribution is comprehensively learned, a multi-modal fusion attention mechanism is innovatively introduced, heterogeneous data are comprehensively utilized, and the prediction precision is improved. According to the method, a data enhancement and expansion technology is further designed, the generalization ability of the model is enhanced, online incremental learning is supported, and continuous optimization of the model is achieved. According to the method, the future state of the equipment can be efficiently and accurately predicted under the condition that the annotation data is poor, the prediction cost is reduced, and the method has important theoretical value and wide application prospects.

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 provides an annotation data quality evaluation method based on active learning, and relates to the technical field of data collection, and the method comprises the steps: obtaining historical annotation data and historical use scores, screening the historical annotation data according to the historical use scores, obtaining high-quality annotation data, and constructing an annotation quality evaluation model, analyzing the annotation data type that the annotation person is good at, distributing the unannotated task data to the annotation person to obtain a real-time annotation data set, inputting the real-time annotation data set into an annotation quality evaluation model to obtain a first quality score, performing interactive verification on the real-time annotation data set to obtain a second quality score, and obtaining a deviation value through comparison. When the deviation value is smaller than a preset threshold value, the annotation quality evaluation model is preliminarily adjusted, and after the use score of the real-time annotation data set is received, the annotation quality evaluation model is secondarily adjusted; the quality evaluation method can be improved.

The invention discloses an active learning-based electric power knowledge graph construction method and system, and relates to the technical field of electric power market transaction data analysis, and the method comprises the steps: collecting data, cleaning the collected data, generating word prediction task data of an electric power transaction scene, and training an electric power field word embedding model; generating an entity relationship training sample, inputting a word embedding model, performing entity relationship label prediction through an entity relationship joint extraction model, extracting a high-quality sample based on active learning to perform part-of-speech tagging, and training the model based on a tagged sample; and applying the trained entity relationship joint extraction model to power transaction data to construct a knowledge graph, performing manual correction and entity unification, and storing the knowledge graph into a Neo4j database. According to the method, active learning and deep learning are combined, so that the sample labeling cost is effectively reduced, and meanwhile, the model performance is ensured.

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.

The invention provides an equipment operation manual vector knowledge base construction method. According to the method, heterogeneous multi-modal data such as texts, images, videos and three-dimensional models related to equipment are collected, semantic vector coding is conducted on the multi-modal data through a large pre-training model, the multi-modal data are fused into a unified vector space, and vector representation of equipment knowledge is constructed. An efficient index is established based on vector representation, and intelligent retrieval and association services of a semantic level are supported. And an interpretable vector coding technology is also introduced, so that the semantic interpretability of the vector is endowed, and a visual interface is provided for analyzing a vector distribution mode. And continuous expansion and optimization of the knowledge base are realized through active learning and online learning strategies. According to the method, heterogeneous data integration, intelligent semantic service, interpretability enhancement and knowledge automatic updating are realized, intelligent knowledge service support is provided for the fields of equipment operation and maintenance and the like, and the method has important application value.

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 intelligent position information recommendation, in particular to an intelligent position recommendation method based on artificial intelligence, which comprises the following steps: collecting basic information and behavior data of a user, and constructing a user portrait; acquiring position information, extracting key information to establish a position information base, and introducing an expert system to supplement the position information; understanding implicit significance of position description through a natural language processing method and a semantic analysis method; performing feature extraction on the user portrait and the position information, and constructing a feature data set; training a recommendation model; user feedback is actively inquired through an active learning algorithm; and generating a position recommendation list for the user through the trained recommendation model. The method optimizes description of position information, is more convenient for users to understand, and solves the problem that accurate user portraits cannot be constructed due to lack of data for users and new positions in specific fields through an active learning algorithm and introduction of an expert system.

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 relates to an insect pest semi-supervised target detection method combining active learning and multi-scale view learning. The method comprises the following steps: constructing a semi-supervised target detection data set; performing data enhancement on the semi-supervised target detection data set; constructing a semi-supervised model and generating a pseudo label; performing multi-scale view learning through the student model to obtain a multi-scale view prediction result; performing semi-supervised training; performing active learning, and updating the semi-supervised target detection data set; and inputting a to-be-detected field corn image into the finally trained teacher model to obtain a final pest detection result. According to the method, active learning is combined to select some data which is beneficial to the model and can effectively improve the performance for labeling, and the labeling cost is utilized to the maximum extent; adding a multi-scale view learning structure, and capturing effective information; and finally, under the condition of limited 20% annotation data, the detection precision of more than 80% annotation data can be realized, and the annotation cost is greatly saved.

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.

The invention discloses a multi-scene visual algorithm evaluation method based on an electric power artificial intelligence platform, and the method comprises the following steps: S1, integrating data in an electric power scene, and generating a multi-modal data set; s2, storing and preprocessing the data set, and extracting key features; s3, based on a multi-stage active learning mechanism, selectively sampling data and optimizing a visual algorithm; s4, the optimized algorithm is migrated to different environments, parameters are adjusted through a self-adaptive strategy, and models adapting to different conditions are generated; s5, in combination with deep learning and expert knowledge, optimizing an evaluation process; s6, performing real-time fault injection and elasticity evaluation by using a fault mode library and a simulation technology; s7, constructing a double-layer digital twinning virtual evaluation environment, and verifying the validity of the algorithm under different conditions; and S8, recording and tracking the evaluation data and generating an evaluation report by using a distributed data management system. According to the invention, through an intelligent tuning and evaluation mechanism, the efficiency and reliability of power equipment monitoring and fault prediction are improved.

The invention provides a nervous tissue identification method based on artificial intelligence, and relates to the technical field of medical intelligent detection. According to the nervous tissue identification method, nervous tissue region annotation is carried out on 452 HE-dyed section images of bladder cancer, pancreatic cancer and porta-bile duct cancer by using QuPath software. 70% is used as a training set, 10% is used as a verification set of a training process, and 20% is used as an independent test set to train the nnUnet model. The whole training process is combined with an active learning strategy to enhance the specificity of the model. By using the algorithm and the deep learning technology, the nerve peripheral infiltration in the pathology is accurately and quickly evaluated, the workload of manual identification is greatly reduced, and the diagnosis accuracy is improved. The machine identification of tumor peripheral nerve invasion has obvious practicability, importance, clinical diversity and actual clinical value, and shows that the deep learning technology improves the potential of tumor detection and diagnosis.

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 a mechanical structure reliability analysis method and system based on an active learning agent model, and belongs to the technical field of mechanical structure reliability analysis, and the method comprises the steps: analyzing the working condition and load condition of a mechanical structure to be subjected to reliability analysis, and determining a performance function of the mechanical structure in combination with the safety working requirements of the structure; based on the principle of equal probability conversion, the input variables are converted into a standard normal space, and Monte Carlo reliability analysis samples are generated; in a standard normal space, using a center cross method to generate a 4n initial fitting sample, calculating a function value of the sample, obtaining an initial response matrix, and fitting an initial proxy model; and establishing a distance constraint learning function based on the existing agent model and the fitting sample, and iteratively updating the agent model, the fitting sample, the response value matrix and the failure probability in combination with a prior reliable circular ring sample reduction method until a reliability analysis result with enough precision is obtained, and ending the reliability analysis system.