14094 results about "Training data sets" patented technology

In embodiments, systems and methods for improving machine-learning systems are disclosed. In embodiments, a system includes a data pool system that is configured to receive data from a plurality of different data sources and maintain a training data set that is used to train a specific machine-learning model based on the data from the plurality of different data sources. In embodiments, the system further includes a data scoring system that determines a data reliability score corresponding to the new data based on a set of intrinsic features of the new data and a data scoring model, wherein the data pool system selectively adds the new data to the training data set based on the reliability score of the new data. The system also includes a machine learning system that trains the specific machine-learning model based on the training data set.

Systems and methods for computing time series predictions are provided, including a two-stage classifier-and-regressor processor. The classifier is trained on the complete data set while the regressor is trained on a pruned dataset. The classifier includes an Extreme Gradient Boosting classifier. The regressor includes an attention mechanism and a Long Short-Term Memory (LSTM) neural network. For a series of successive time period computations, a current output of the LSTM neural network is recursively fed back as an input to the attention mechanism for a subsequent time period computation. The output of the regressor is scaled by the output of the classifier to adjust for overfitting caused by the pruned training dataset.

An example method can include providing a natural language instruction and user interface image data to a machine-learned sequence processing model that is configured to process image data and generate commands for controlling the target computing device, wherein the machine-learned sequence processing model has parameters learned using an interface recognition objective based on an evaluation of an interface recognition output generated based on processing a rendered training interface from a pre-training dataset and an interface navigation objective based on an evaluation of a user interface command generated based on processing a rendered training interface from a fine-tuning dataset; receiving, from the machine-learned sequence processing model, a command indicating an interaction with the user interface to implement the natural language instruction; and generating, based on the command, a control signal configured to initiate the interaction.

The invention relates to a model training method and device, equipment, a storage medium and a product. The method comprises the following steps: constructing a training data set according to a target text reasoning chain obtained by converting multi-modal data; according to the training data set, performing supervision fine tuning on the pre-trained multi-modal large language model to obtain a basic reasoning model; performing optimization processing on the basic reasoning model according to reinforcement learning training of long thinking to obtain a target reasoning model; the target reasoning model is used for outputting a target answer containing a reasoning process according to the input multi-modal data. Therefore, the long text constraint can be directly used for reinforcement learning, and the training efficiency is greatly improved; and by adopting long-thinking reinforcement learning training, the model can easily learn a correct thinking process in training, so that the reasoning ability of the multi-modal large language model for processing a complex visual reasoning task is improved, and the correct thinking process is displayed in the reasoning process.

Device, system, and method for automatically detecting and classifying personally identifiable information (PII) in documents and files. A method includes performing a deterministic rule-based search, in a plurality of stored documents, for PII data-items. If the deterministic rule-based search indicates that a particular document is more likely than not to contain a PII data-items then the method includes: extracting a textual snippet from the particular document, wherein the textual snippets surrounds the PII data-item; adding the textual snippet and the particular document to one or more training datasets utilized for training a Large Language Model (LLM) configured to find PII data-items in documents for Named Entity Recognition (NER) in those documents.

The invention relates to the technical field of structural health monitoring and intelligent diagnosis, in particular to a structural fatigue damage identification method based on acoustic emission and deep learning, and the method comprises the steps: collecting a structural response signal under a fatigue load through an acoustic emission sensor array, inputting the structural response signal to a CNN-BiLSTM-Attention mixed deep learning model, and carrying out the recognition of the structural fatigue damage through the CNN-BiLSTM-Attention mixed deep learning model; the model extracts local time domain features through a dynamic adaptive convolution kernel, captures long time sequence dependence by using a bidirectional long-short-term memory network, focuses key damage features through a bimodal space-time attention mechanism, divides damage stages based on a nonlinear dynamic threshold algorithm of fracture opening amount, constructs a training data set of physical-data fusion, and performs dynamic time domain feature extraction. The learning rate is optimized by adopting a gradient sensitive cosine annealing algorithm, and the robustness of the model is improved in combination with an anti-noise and anti-loss function. The method integrates physical characteristics and an intelligent algorithm, and has the advantages of adaptive noise suppression, strong cross-domain generalization ability, high real-time performance and the like.

The invention relates to the technical field of skin disease diagnosis, and discloses an AI auxiliary decision support system for skin disease diagnosis, which integrates an image acquisition module, an image analysis module and a comprehensive analysis and diagnosis decision module. A high-definition image of the skin of a patient is obtained through high-precision skin photographing equipment, and a training data set is formed by combining basic information of the patient. A deep learning algorithm is utilized to train a skin disease recognition model and an illness state evaluation model, and accurate recognition of skin disease types and objective evaluation of severity are realized. And the comprehensive analysis module fuses output of the two models, constructs a fusion decision model and provides comprehensive diagnosis suggestions. And the diagnosis decision module is used for generating a disease type judgment and illness state evaluation report based on the trained model in combination with real-time image data so as to effectively assist doctors in making decisions. The accuracy, the efficiency and the popularization degree of skin disease diagnosis are improved, and complex and changeable diagnosis requirements in clinical practice are met.

The invention relates to the technical field of natural language processing, and discloses a question and answer task processing model training method, device and equipment and a storage medium, and the method comprises the steps: adjusting a question and answer task processing model according to an initial training data set and a first model training algorithm, and obtaining a first intermediate question and answer task processing model; according to the initial training data set and the first intermediate question and answer task processing model, obtaining a first reasoning step and first annotation information for processing the question and answer task, and generating a first target training data set; according to the initial training data set and a second model training algorithm, adjusting a question and answer task processing model to obtain a second intermediate question and answer task processing model; and adjusting the second intermediate question and answer task processing model according to the first target training data set to obtain a target model. The problems that when the model for processing the question and answer task is trained, the accuracy of the model is affected by the quality of the manually-labeled data due to the dependence on the manually-labeled data, and the training process is high in cost and low in efficiency are solved.

The invention relates to a method for predicting the load and validating material parameters of a mechanical object (10), such as in particular a rim (20) of a vehicle, in a load situation, such as a pressure test, comprising: - Creating a training dataset (220) wherein the training dataset (220) includes 3D models, CAD models, images, drawings, sensor signals from sensors (280) and other data such as material parameters, parameter values ​​and / or properties of different designs and geometries of the object (10); - Training (S20) a simulation model (350) with the training data set (220); - Generating (S30) input data (250) with user-defined requirements for a load prediction and / or validation of material parameters of the mechanical object (10) and passing the input data (250) to the trained simulation model (350), wherein the input data (250) contains material parameters, parameter values ​​and / or properties of the object (10); - Performing (S40) a simulation and generating simulation results (370) from the simulation model (350), wherein the simulation results (370) comprise a force-displacement curve (375); - Generating (S50) output values ​​(550) by analyzing the simulation results (370), wherein the output values ​​(550) include a load prediction and / or material parameters.

The invention discloses a data set construction method and system for training a professional field large model, and the method comprises the steps: collecting multi-source heterogeneous data, carrying out the fusion and preprocessing of the data through a dynamic time sequence tensor decomposition method, and generating a standardized three-dimensional data tensor; recombining and optimizing the data by adopting a hierarchical graph structure processing method, and generating an optimized feature matrix, a feature importance vector and a data reliability matrix; performing enhancement and knowledge fusion on the data by adopting a probability matrix decomposition method to generate an enhanced data set; and verifying and dynamically optimizing the data by adopting a polyhedral projection method to generate a final training data set. According to the method, the quality of data in the professional field is improved, and the technical problems of insufficient data time sequence correlation analysis, inaccurate quality evaluation, fixed enhancement strategy, insufficient verification constraint and the like are solved.

The invention provides a road bridge crack detection method and system, and the method comprises the steps: collecting a bridge surface multi-view image, and constructing a training data set containing crack feature labeling through quality screening and standardized labeling; preprocessing the image by using a multi-scale feature fused deep convolutional neural network and carrying out semantic segmentation, initially identifying a suspected crack region and generating a segmentation mask; and constructing a BeNNS proxy model based on the mask, and establishing a mapping relationship between the detection result and the bridge structure topology, the stress flow field and the service function chain so as to evaluate the result reliability. And inputting an evaluation result into a hybrid evaluation mechanism, performing online real-time detection and offline batch verification to optimize precision, and outputting a verified crack region. Finally, morphological analysis is conducted on the area, geometric parameters and danger levels of cracks are extracted and integrated to a bridge health monitoring system, a crack evolution tracking algorithm and an early warning mechanism are established, and dynamic tracking early warning is achieved. The problem of low detection precision in a complex environment can be solved.

The invention provides a storage battery pack performance evaluation method and system based on big data, and relates to the technical field of storage battery performance evaluation, and the method comprises the steps: obtaining the charging and discharging data of a to-be-evaluated storage battery under different working conditions, carrying out the denoising processing of the charging and discharging data, carrying out the adaptive normalization processing, and obtaining the standard charging and discharging data, equalization processing is carried out, time domain features and frequency domain features are extracted respectively, and high-dimensional feature vectors are obtained through combination; performing dimension reduction operation on the high-dimensional feature vector to obtain low-dimensional embedded representation, generating an initial data set, dividing the initial data set into a training data set and a test data set, constructing an initial prediction model and performing hyper-parameter optimization to obtain a first prediction model; and acquiring real-time charging and discharging data, constructing a real-time feature vector, adding the real-time feature vector into the first prediction model to generate a real-time performance parameter, filtering the real-time performance parameter, constructing a health state prediction model for prediction, and obtaining a comprehensive performance evaluation result.

The invention relates to an automatic optimization method for a model cue word, which comprises the following steps of: acquiring an initial cue word and a corresponding training data set which comprises input data and a corresponding real label; and then, inputting the initial cue word and the input data into a target model together to generate a corresponding prediction label. And on the basis, guiding a target model by using a feedback prompt word, and generating language prompt feedback by comparing the predicted tag with the real tag. The feedback is used for identifying potential defects in the initial cue word, optimizing the initial cue word based on the feedback, and finally generating a target cue word. The cumbersome process of manually adjusting the cue words is reduced, gradual improvement of the cue words is achieved through a feedback mechanism, and high accuracy and consistency of model output are ensured.

The invention discloses a super-resolution image reconstruction method, system and device based on dynamic frequency domain adaptive coding and contrast constraint optimization, and a medium. The method comprises the following steps: creating an original training data set; image data features and application scenes are considered, and feature extraction is performed on image data by adopting a modular design method; in combination with discrete cosine transform and inverse transform thereof, adaptive transform coding is carried out on different frequency components in the image features through a dynamic weight adjustment mechanism; the U-Net and Transform architectures are combined, isotropic design is optimized, a diffusion model and a feature fusion and reconstruction technology are applied, and diffusion process reconstruction is achieved; by introducing a contrast loss function, contrast learning is carried out between images with different resolutions, and the feature learning ability is enhanced. The image reconstruction method is more intelligent and efficient, and can effectively deal with frequency feature recovery and detail reconstruction problems in a complex image scene.

The invention discloses a knowledge graph analysis and question answering method and device based on a large language model. The method comprises the steps of obtaining original data, performing data processing based on a large language model to obtain target data, constructing a knowledge graph according to the target data, and storing the knowledge graph into a graph database; acquiring an open source data set, and processing the open source data set by using the large language model to obtain a training data set; according to the graph database, constructing a dictionary which is used for reflecting a graph structure of the graph database; utilizing the training data set, the dictionary and a preset prompt instruction to finely adjust the large language model to obtain an optimized large model; generating a query statement by utilizing the graph database and the optimization large model according to a query problem of a user, and determining a query result in the graph database according to the query statement; and based on the optimization large model, carrying out integration processing on the query question and the query result to obtain a final answer. According to the method, the construction process of the knowledge graph is simplified, and the accuracy of analysis and question answering is improved.

The invention relates to a metro field large language model evaluation method and system. The method comprises the following steps: step 1, constructing a data set; the step 1 comprises the following steps of: 1.1, collecting public professional data; step 1.2, collecting internal professional data; 1.3, collecting a general data set; 2, data processing; in the step 2, the following steps are executed: step 2.1, data formatting; step 2.2, data cleaning is carried out; step 2.3, performing data enhancement; 3, fine adjustment of the model; in the step 3, the following steps are executed: step 3.1: constructing a training data set; step 3.2, fine adjustment of the model; step 3.3, carrying out model evaluation; 4, constructing an evaluation system; in the step 4, the following steps are executed: step 4.1, determining evaluation indexes; step 4.2, constructing an evaluation system; step 4.3, constructing an intelligent agent; step 4.4, multi-agent cooperation is carried out; and 5, performing model evaluation.

The present application discloses a cloud resource prediction method and system based on a GC-LSTM neural network model, an electronic device, and a readable storage medium. The method comprises two stages: a training stage and a prediction stage. In the training stage, historical data of cloud resources is collected and normalized to obtain a training data set, input data and labels used for training a neural network are organized and made, and an established GC-LSTM neural network model is trained. In the prediction stage, by means of acquired real-time sampling data, the trained model is loaded to perform result prediction, and, on the basis of a prediction result, resources may be scheduled and distributed to respond in advance. The present application aims to predict customers' demands for resources in advance and optimize customers' cloud experience. The model provided by the present application is simple and has few parameters, can guarantee the real-time performance of the prediction result, is practical and feasible, is suitable for the prediction of cloud resource utilization, and provides a guarantee for instant scheduling of resources.

The invention relates to the technical field of image processing, and discloses a lightweight image super-resolution reconstruction method based on frequency domain-spatial domain assisted Mama, which comprises the following steps: acquiring an original image data set and carrying out data preprocessing on the original image data set to acquire a training data set and a test data set; introducing a frequency domain-spatial domain Mama layer and an interaction layer based on transpose and self-attention features, and constructing a lightweight image super-resolution reconstruction model based on frequency domain-spatial domain assisted Mama; inputting the training data set into a lightweight image super-resolution reconstruction model based on frequency domain-spatial domain assisted Mama for training to obtain a trained lightweight image super-resolution reconstruction model with weight based on frequency domain-spatial domain assisted Mama for reconstructing a low-resolution image into a high-resolution image; inputting the test data set into a trained lightweight image super-resolution reconstruction model with weight and based on frequency domain-space domain assisted Mama to obtain a reconstructed high-resolution visual image; according to the method, lightweight image super-resolution is realized.

The invention discloses a long-tail image recognition method based on multi-modal semantic generation and image-text fusion. The method comprises the following steps: extracting structured semantic description from a tail image; carrying out semantic rewriting and enhancement based on a multi-modal visual language model, and generating an image semantic extension description; the image semantic extension description is optimized based on semantic duplicate judgment and a style alignment mechanism, and an optimized text description set is obtained; inputting the optimized text description set into a text graph model, generating a tail class image sample, performing semantic and visual quality screening, and constructing to obtain an enhanced image set for training; constructing a training data set based on the original long-tail data set and the enhanced image set, and training an image-text fusion classification model; and inputting a to-be-identified image into the trained image-text fusion classification model, and outputting classification results of all categories. According to the method, the discrimination capability in a long-tail distribution scene is enhanced, and the method has a stronger generalization characteristic.

The invention discloses an image semi-supervised semantic segmentation method and system based on pixel-level correction, and relates to the technical field of computer vision and semantic segmentation, and the method comprises the steps: constructing a training data set which comprises a labeled image and an unlabeled image, and the labeled image is an image labeled with a pixel-level label; carrying out random diversity image enhancement to obtain a weakly-enhanced labeled image, a weakly-enhanced unlabeled image and a strongly-enhanced unlabeled image; constructing a teacher-student model; training a teacher-student model by using the training data set, constructing a total loss function based on a supervised loss function, a cross-image unsupervised loss function and an agent-related loss function, and optimizing and updating network parameters of the teacher-student model through the total loss function until the total loss function is minimized, so as to obtain the teacher-student model. Obtaining a trained teacher-student model; and inputting a to-be-segmented scene image into the trained student model, and obtaining and outputting a more accurate image semantic segmentation result.

The invention provides a service prediction method and device based on a time sequence model, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of historical time sequence data, and obtaining a training data set; performing fast Fourier transform on the training data set to obtain frequency domain data and frequency component intensity; extracting a plurality of main frequency components and corresponding period values from the frequency domain data, and determining a plurality of two-dimensional feature tensors according to the period values and the training data set; constructing L layers of time blocks including feature mapping, an attention mechanism and a feedforward network according to the two-dimensional feature tensor, and establishing residual connection between adjacent time blocks to obtain a time sequence model to be trained; performing feature extraction on each two-dimensional feature tensor by applying a multi-branch convolutional network to obtain a one-dimensional representation vector, and performing weighted fusion on the one-dimensional representation vector according to the frequency component intensity to obtain a fusion feature; and training the to-be-trained time sequence model through the fusion features, and outputting an analysis report of historical time sequence data.

The invention discloses an improved YOLOv11-based high-reflection and high-transmittance material surface defect detection method, which comprises the following steps: S1, acquiring a mobile phone screen surface defect image, preprocessing and labeling, and generating a training data set containing three defects of scratches, edge breakage and cracks; s2, constructing a defect detection model; s3, averagely dividing an input image into four independent detection regions, adopting a bounding box overlapping area weight distribution strategy for cross-region defects, and performing partition counting on the image by using a defect detection model; s4, constructing a surface defect detection network meeting the real-time requirement of the industrial production line, and outputting a detection result and a processing frame rate; s5, pixel-level mask segmentation is carried out on the scratch defect, and contour coordinates and geometric features are extracted; and S6, fitting the actual damage size of the scratch defect on the surface of the high-reflection and high-transmittance material according to the segmentation result. According to the method, the detection speed is high under the condition that the accuracy is ensured, and a reliable solution is provided for surface flaw detection of the high-reflection and high-transmittance material.

The invention discloses a power equipment fault prediction method based on support vector regression, and aims to improve the prediction accuracy. The method comprises the following steps: firstly, collecting multi-dimensional operation parameter data of power equipment, and constructing an original monitoring data set; a data set is segmented through a sliding time window, wavelet transform is used for noise reduction, and then a normalization method is applied to generate a standardized data set. Time domain and frequency domain features are further extracted, a feature vector space is constructed, an optimal feature subset is screened through a mutual information method, and a training data set is generated; performing preliminary training on a support vector regression model by using the training data set to generate candidate support vectors, and screening a support vector set with the maximum contribution through an optimization algorithm; a grid search method is adopted to adjust kernel function parameters and penalty factors, and a support vector set is further optimized. And evaluating the performance of the model through cross validation, applying the optimized support vector regression model to power equipment fault prediction, and generating a fault occurrence probability prediction value.

The invention discloses an image label noise learning method based on granular ball calculation and contrast learning, and the method comprises the steps: obtaining image data, carrying out the preprocessing of the image data, inputting the preprocessed image data into a trained image label noise learning model, and obtaining an image classification result. The training process of the image label noise learning network comprises the following steps: acquiring an image training data set, and performing preprocessing and data enhancement on the image training data set; respectively extracting feature representations of the strong data enhancement sample and the weak data enhancement sample by adopting a contrast learning framework SimSiam, inputting the feature representation of the weak data enhancement sample into a granular ball calculation layer, inputting a feature matrix of the granular ball sample and a label thereof into a classifier after clustering to obtain an image classification result p, and calculating classification loss; predicting the feature representation of the strong data enhancement sample through a prediction layer, and calculating comparison loss by taking an image classification result p as an indicator function; and the network is optimized through back propagation of the comparison loss and the classification loss. According to the invention, the network performance can be obviously improved.

The invention provides an infectious disease early warning and monitoring method and system based on big data and deep learning, and relates to the technical field of infectious disease early warning, and the method comprises the steps: obtaining infectious disease historical data, crowd movement track data, medical treatment data and environment monitoring data as a training data set; establishing a space-time propagation link diagram and carrying out dynamic segmentation coding to generate a propagation characteristic sequence; training a deep learning model based on the propagation feature sequence to predict an infectious disease propagation inflection point and a high-risk area propagation probability; and when the propagation probability exceeds a preset threshold value, generating early warning information and pushing the early warning information to a monitoring terminal. According to the invention, accurate prediction and timely early warning of the transmission trend of infectious diseases can be realized, and the epidemic prevention and control efficiency is improved.

The invention provides a self-adaptive polarization modulation-based inter-satellite laser communication and signal scheduling method, which relates to the field of laser communication, and comprises the following steps of: acquiring polarization state information of emitted and received light beams, calculating a mismatch degree, generating a compensation parameter, constructing a polarization state prediction model by using a deep learning neural network for pre-correction, and calculating the mismatch degree; a polarization modulator is adopted to perform real-time modulation and establish a link quality evaluation model, carrier synchronization and channel compensation are realized based on an adaptive optical carrier recovery technology of coherent detection, a link state is monitored in real time, and a training data set is updated.

The invention discloses an electrical equipment life prediction system and method based on deep learning, and belongs to the field of electrical equipment life prediction, and the method comprises the steps: constructing a data set, and carrying out the preprocessing; performing convolution operation on the time sequence data in the data set, extracting local features to obtain a convolutional neural network, capturing a long and short term dependency relationship of the time sequence data in the data set by using LSTM to obtain a recurrent neural network, and fusing output features of the convolutional neural network and the recurrent neural network to obtain comprehensive feature representation; constructing a deep learning model based on the fusion of a convolutional neural network and a recurrent neural network, adding an attention mechanism, adopting a mean square error as a loss function, optimizing model parameters, carrying out model training by utilizing a training data set, evaluating model performance by adopting a verification set, and adjusting hyper-parameters; and inputting real-time data into the trained model, predicting the residual life of the electrical equipment, and designing an online learning mechanism. According to the invention, the accuracy and real-time performance of prediction are improved.

The invention discloses a power transformer fault auxiliary decision-making method and system based on a knowledge graph and a large language model, and the method comprises the steps: obtaining power transformer fault text data, carrying out the preprocessing, obtaining fault-related text and table data, preliminarily defining an ontology, selecting a part of text data for marking, and carrying out the recognition of the ontology; a plurality of named entity recognition and relation extraction models are trained, an optimal model is determined, then triple extraction is carried out on unlabeled text data, and a knowledge graph is constructed; predicting a potential entity relationship in the knowledge graph based on a link prediction model, and complementing the knowledge graph under the large language model and human assistance; constructing a semantic search model training data set based on the large language model and training a semantic search model; based on the complemented knowledge graph, the trained semantic search model is utilized to retrieve knowledge graph sub-graphs according to the problem, and auxiliary decision making is completed. According to the method, the problem of low potential knowledge utilization level in the existing power transformer fault auxiliary decision-making based on the knowledge graph is solved.

The invention provides a medical image segmentation method, which comprises the following steps: acquiring PET indirect development original image data, and preprocessing the image, including denoising, contrast enhancement and gray level normalization, to obtain a preprocessed PET image data set; designing segmentation middleware, integrating a plurality of segmentation algorithms including threshold segmentation, region growth and level set methods, and selecting proper segmentation algorithms for different types of lesion regions according to feature vector analysis results; pET image data with labels are generated through the simulation technology, a training data set is constructed in combination with real case data, the sample size is expanded through the data enhancement technology, and a large-scale data set used for algorithm training is generated; and the segmentation result of the U-Net is refined by using the segmentation middleware, the lesion area edge is focused on, and the lesion boundary is accurately positioned through an edge detection algorithm to obtain a fine segmentation result.

The invention relates to the technical field of image processing, and provides a training data set labeling method and device for AI visual identification, and the method comprises the steps: obtaining and processing original image data, extracting feature mapping, inputting a target detection model to obtain a preliminary labeling result, carrying out the analysis, and determining a clustering center and a candidate target set; the candidate target set is classified based on the clustering center, the confidence degree of the classification labeling result is calculated, labeling data with the confidence degree higher than a threshold value serve as high-confidence-degree labeling data, rechecking and consistency checking are conducted on data with the confidence degree lower than the threshold value, and consistency labeling data are generated; and the target detection model is optimized in combination with the high-confidence data, the low-confidence data is re-labeled by using the optimization model, and the high-confidence data and the re-labeled data are combined to generate a complete labeled training set to train the recognition model. Through the above scheme, the consistency and confidence of the data are ensured, and the problems of inconsistent labeling and missed labeling and false labeling in complex scenes and multi-target recognition are effectively improved.