1114 results about "Sample Label" patented technology

Disclosed are a rapid inversion method and apparatus for icing thickness of a power transmission line, and a related device. The method comprises: acquiring meteorological data of the place where the power transmission line is located, wherein target meteorological factors in the meteorological data are determined in advance by means of association analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data; and inputting the meteorological data into a trained rapid inversion model to obtain an icing thickness inversion value, wherein the model is obtained by training by using the meteorological monitoring data as a training sample and icing thickness data as a sample label, and the icing thickness data comprises icing thickness monitoring data and icing thickness simulation data obtained by means of numerical simulation calculation. Abundant icing thickness simulation data is obtained by means of numerical simulation calculation, solving the problem of insufficient icing thickness data, meeting the high-precision training requirements of deep learning, and improving the generalization ability of the model; and using the trained rapid inversion model to implement rapid inversion of the icing thickness of the power transmission line achieves relatively high accuracy.

The invention discloses an automatic optimization method for cue words of a large language model, and relates to the technical field of cue word optimization. Comprises: setting an initial cue word; constructing training data, gradient generation cue word templates, cue word editing templates, optimizers and task models; randomly sampling a small batch of data from the training data as a training set, and predicting a sample of the training set by the task model according to the initial cue word to obtain an answer; comparing the answer with a sample label of a training set to obtain an error example set; inputting the error example set and the initial cue word into a gradient generation cue word template, and generating a gradient analysis request; the optimizer model receives and analyzes the gradient analysis request to generate a second natural language gradient; and inputting the second natural language gradient and the initial cue word into a cue word editing template, and modifying the initial cue word by the optimizer model according to the cue word editing template to generate a second candidate cue word. The technical problem that the efficiency of manually writing prompt words is low is solved.

The invention relates to the technical field of battery health management, in particular to a battery fault unsupervised detection method based on diffusion Transform and confidence coefficient calibration, which comprises the following steps: acquiring multi-modal time sequence data in a battery operation process, and performing preprocessing, including data cleaning, normalization processing, alignment and sampling; a diffusion Transform self-supervised learning framework is constructed, and the framework comprises a diffusion process based on a cosine scheduling strategy, multi-scale Transform architecture coding and a cross-modal self-adaptive fusion mechanism. Through the framework, potential space representation is optimized, and the battery state confidence coefficient is calculated; the optimal detection threshold value is dynamically determined by adopting a Bayesian optimization framework, whether the battery state is normal or faulty is judged according to the comparison result of the battery state confidence coefficient and the optimal detection threshold value, dependence on a fault sample label is completely eliminated, and a high-performance fault detection model can be trained only by utilizing normal sample data.

Provided is a defect detection method and device, computer equipment and a storage medium. The method includes: acquiring an RGB image, a depth image and a sample label of a detection object sample; performing feature map extraction and feature map fusion on the RGB image and the depth image by a feature extraction network of the defect detection model, to obtain a fused feature map; performing defect detection based on the fused feature map by a feature reconstruction network of the defect detection model, to obtain a defect score map, wherein the defect score map being obtained by fusing a global defect score map which is generated based on a global defect detection network with a local defect score map which is generated by a local defect detection network; and updating parameters of the defect detection model based on the defect score map and the sample label.

The invention discloses an image reconstruction method based on a multi-window cross feature fusion attention mechanism. According to the method, the resolution of an original image is reduced through bicubic interpolation to obtain model training data, and the original image is used as a sample label. For training data, shallow layer features are extracted through blueprint separable convolution; and improving an efficient separable distillation module to obtain a plurality of attention fusion distillation modules, and extracting deep features. A feature fusion module based on multi-window cross attention is used to carry out operations such as multiple times of segmentation, attention calculation, multi-window cross attention calculation, recombination and the like on deep features, and feature enhancement is realized. And fusing the features with shallow layer features, and outputting a reconstructed high-resolution image. Models with different reconstruction multiplying powers can be obtained according to different sampling multiplying powers under training data.

The invention provides a training method of a document image tampering detection model and a tampering detection method and device.The training method of the document image tampering detection model comprises the steps that multi-scale visual domain features are extracted from a sample document image, and multi-scale frequency domain compressed sensing features are extracted from frequency domain information; acquiring tampered area edge mask data from the document image; fusing the multi-scale visual domain features and the multi-scale frequency domain compressed sensing features to obtain multi-modal fusion features; performing semi-supervised training on the multi-scale sensing network by taking the multi-scale visual domain feature as a sample feature of a first prediction head, taking the multi-modal fusion feature as a sample feature of a second prediction head, taking a real label or a pseudo label as a sample label and taking joint loss as a loss function to obtain a document image tampering detection model; according to the method provided by the invention, document image tampering pixel-level detection under low labeling cost is realized, and the detection precision of a document image tampering detection model is improved.

The present application provides a training method for a text processing model, a training apparatus for a text processing model, an electronic device, a program product, and a storage medium. The method comprises: acquiring a sample text set; splicing at least two independent sample texts among a plurality of independent samples texts to obtain a plurality of spliced sample texts; on the basis of the plurality of spliced sample texts, calling an initialized text processing model to perform feature extraction processing to obtain a plurality of spliced sample features; on the basis of each spliced sample feature, calling a masked attention mechanism to perform prediction processing to obtain a predicted text, wherein the masked attention mechanism comprises: masking each independent sample in the spliced sample features; on the basis of the difference between the predicted text and a sample label, determining a loss function; and on the basis of the loss function, performing parameter update processing on the text processing model to obtain a trained text processing model.

The invention discloses an intelligent manufacturing defect automatic detection and classification method based on machine vision, and particularly relates to the technical field of defect automatic detection and classification, by constructing a high-resolution multi-source sample data set and introducing image preprocessing operation, defect expressions under different manufacturing batches, surface states and illumination conditions are covered, and the defect detection and classification accuracy is improved. Generating a defect probability heat map through an image segmentation network, extracting a primary defect candidate region, calculating a pseudo defect high-frequency interference coefficient by combining a high-frequency pseudo defect feature tensor, and calculating a multi-class defect overlapping coupling coefficient based on multi-classification confidence distribution and semantic adjacency; pseudo defect interference intensity and multi-class defect boundary fuzzy degree in the defect candidate area are accurately described, a sample label pollution risk assessment model is constructed to realize automatic identification and screening of high pollution risk samples in training data, and interference of mistakenly labeled samples on deep model training is significantly reduced; and erosion of error feature-label mapping on the generalization ability of the model is effectively prevented.

The invention belongs to the technical field of aero-engine state monitoring and intelligent fault diagnosis, and discloses a multi-modal information fusion bearing fault diagnosis method based on self-supervised learning. The method comprises the following steps: firstly, through mask reconstruction self-supervision pre-training, extracting stable feature representation insensitive to mask disturbance from an unlabeled multi-modal signal, and dynamically updating each modal feature reference point by using an index moving average algorithm; in a downstream fault diagnosis task, a multi-modal joint decision model comprising a pre-training encoder, a single-modal classifier and a fusion classifier is constructed, and adaptive weighted fusion of multi-modal decision is realized through contribution degree calculation based on a cooperative game Shapley value in combination with a deviation degree of modal features and a reference point. According to the method, the dependence of the deep neural network on fault labeling data is effectively reduced, the accuracy and robustness of the diagnosis system in a multi-modal signal diagnosis scene are improved through a dynamic fusion mechanism, and the method is suitable for industrial scenes with limited sample label resources.

The invention provides an arc discharge detection method and device for a photovoltaic inverter and electronic equipment, and the method comprises the steps: collecting sample current data corresponding to the photovoltaic inverter, and classifying and marking the sample current data as arc data and arc-free data; taking the sample current data as a data sample, taking the arc data and the arc-free data as sample labels corresponding to the data sample, and training a preset neural network model; converting the trained neural network model into an algorithm program, deploying the algorithm program to a preset micro-control unit, inputting real-time current data collected by the micro-control unit into the neural network model, and determining a data type to which the real-time current data belongs; and when the data type is the electric arc data, determining that the photovoltaic inverter has a direct current arc discharge phenomenon. And low-cost and high-precision intelligent arc discharge detection can be realized.

The embodiment of the invention relates to the technical field of video detection, in particular to a video behavior recognition method, device and equipment based on multi-mode large model fine tuning. A specific embodiment of the method comprises the steps of obtaining a video behavior recognition data set and an initial video behavior recognition model; for each piece of video behavior identification data, executing the following steps: determining a key frame image corresponding to a video frame sequence included in the video behavior identification data; storing the key frame image to a preset image storage position; based on the label text template, the key frame image, the image storage path and a behavior label included in the video behavior identification data, a training sample is generated, and the training sample comprises a sample image and sample label data; training the initial video behavior recognition model, and determining the initial video behavior recognition model as a video behavior recognition model; and inputting the target video data into the video behavior recognition model to obtain video behavior text information. According to the embodiment, the training duration of the video behavior recognition model can be prolonged.

The invention discloses a medical image recognition system based on label noise robust learning, and provides a hard sample label refinement strategy based on a confidence perception weighted prototype and an effective noise sample joint correction method to process divided subsets in correction before training so as to obtain training data with higher quality; in progressive hard sample reinforcement learning, data are input according to the learning difficulty of samples for training, the ability of model learning discrimination feature representation is improved by integrating cross entropy loss, consistency loss and credible contrast loss, and the influence of medical tag noise is reduced. According to the method, by integrating label refinement and a progressive hard sample reinforcement learning technology, the accuracy and robustness of medical image recognition under the condition of noise label data are effectively improved, overfitting of the model to noise samples is relieved, and the method can be used for correctly building a disease auxiliary diagnosis model under the condition that the noise label samples exist in training data.

The invention discloses a cold fresh mutton freshness nondestructive testing method based on a double-branch hierarchical spectral feature sensing network, and relates to the field of mutton freshness detection.The cold fresh mutton freshness nondestructive testing method comprises the steps that mutton samples with different freshness are obtained, and freshness index determination and hyperspectral image acquisition are conducted; determining a sample label according to the freshness index; the method comprises the following steps: processing a hyperspectral image by using different preprocessing and feature selection combination methods as sample features, and constructing a plurality of training data sets; constructing a double-branch hierarchical spectral feature sensing network as a detection model, and performing training by using different training data sets; and calculating evaluation indexes of the trained detection models, and carrying out nondestructive detection on the freshness of the chilled fresh mutton by taking the detection model corresponding to the optimal pretreatment and feature selection combination method as a final freshness detection model. According to the spectrum feature sensing network based on the double-branch hierarchy, spectrum features are fully sensed by applying a multi-module joint mechanism, and high-precision detection of the freshness of the chilled fresh mutton is achieved.

The invention discloses a cultivated land interplanting forest identification method combining mixed pixel decomposition and deep learning. The method comprises the following steps: generating basic classification data by processing remote sensing image data; on the basis of historical monitoring data and classification standards, cultivated land interplanting forest sample labels are established, and a standardized sample set is constructed; calculating end member abundance and a cross end member contribution ratio by using a mixed pixel decomposition technology, and completing preliminary classification in combination with a region area; designing a deep learning network architecture, and performing model training and optimization by using a multi-scale and direction feature extraction technology; automatically extracting spectrum, texture and spatial features through the model, and fusing to generate a classification result; and performing performance evaluation on the model by adopting a verification set and a test set, and optimizing classification parameters. According to the invention, accurate classification and identification of cultivated land interplanting forest ground feature targets are realized.

The invention provides a text processing model training method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a sample text set; splicing at least two independent sample texts in the plurality of independent sample texts to obtain a plurality of spliced sample texts; calling an initialized text processing model to perform feature extraction processing based on the plurality of spliced sample texts to obtain a plurality of spliced sample features; based on each spliced sample feature, calling a mask attention mechanism to carry out prediction processing to obtain a predicted text, the mask attention mechanism comprising: respectively masking each independent sample in the spliced sample features; determining a loss function based on the difference between the predicted text and the sample tag; and performing parameter updating processing on the text processing model based on the loss function to obtain a trained text processing model. According to the method and the device, the text prediction accuracy of the text processing model obtained by training can be improved.

The invention discloses a data processing method, device and equipment and a readable storage medium, and the method comprises the steps: inputting business sample data into an initial large language model, predicting the business sample data through the initial large language model, and obtaining M lexical element prediction vectors; based on the M lexical element prediction vectors, generating a sample text result and a sample confidence coefficient corresponding to the sample text result; generating a correctness reward value based on a sample label corresponding to the business sample data and the sample text result, and generating a confidence coefficient calibration reward value based on the sample confidence coefficient, the sample label and the sample text result; and based on the confidence calibration reward value and the correctness reward value, performing reinforcement learning training on the initial large language model to obtain a target large language model. By adopting the method, the confidence of model output and the accuracy of a prediction result can be improved.

The invention discloses an online incremental learning method and system based on a self-adaptive B + tree index, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing an extended self-adaptive B + tree index structure, inserting a new sample, and calculating a trajectory disturbance value; generating a disturbance score by combining the disturbance value and a node state, and adding a new sample and an associated node sample into an incremental learning scheduling queue when a condition is met; when a node splitting, merging or reconstructing event occurs, acquiring an affected node and updating a structural code of the affected node; monitoring sample label track change, adjusting a label confidence mark when a threshold value is exceeded, and limiting participation frequency according to a screening mechanism; and performing forgetting compression operation on the leaf nodes with low access frequency and small label fluctuation degree. By constructing an adaptive B + tree index and combining disturbance-driven scheduling, structure change response and forgetting compression strategies, sample management refinement, learning update high efficiency and structure maintenance controllability are realized, and the stability and resource utilization efficiency of online incremental learning are improved.

The invention discloses a malicious encrypted traffic detection method and system based on incremental learning, and belongs to the technical field of network security. The method comprises the following steps: processing original traffic into a standardized feature sequence by adopting a double-layer nested data organization structure, and constructing a sample set; pre-training a malicious traffic detection model by using the sample set; model parameters of the pre-trained malicious traffic detection model are optimized in an incremental learning mode, an experience buffer area used for storing historical training samples, model output results of the historical training samples and sample labels is arranged in the incremental learning process, and the model parameters are continuously updated in the model parameter optimization process; the problem of disastrous forgetting of the model in the continuous learning process is solved by combining dynamic experience playback, stability constraint and a double-layer element updating mechanism; and finally, detecting data to be detected by using the trained model. According to the method, the detection accuracy of the malicious encrypted traffic can be effectively improved, the continuous adaptive capacity of the model is kept through incremental learning, and the method has good practical value.

A gait recognition method based on surface electromyographic signals and transfer learning comprises the steps that a surface electromyographic signal collecting system is designed and manufactured, and electromyographic signals of eight muscles of the legs of a subject are collected through an electromyographic sensor and data collecting equipment; the method comprises the following steps: recording gaits of a subject through motion capture equipment, carrying out timestamp alignment on electromyographic signals and gait information, carrying out label signal labeling on the electromyographic signals, and carrying out filtering and feature processing to obtain a training data set; an LDA-LSTM gait phase recognition algorithm is constructed; constructing an improved MCD transfer learning framework; and carrying out training optimization on the constructed transfer learning framework parameters to enable the recognition and classification effect of the transfer learning framework parameters in the target domain to be optimal, and storing the trained model as a whole model containing the training weight of the target domain again for recognizing the gait phase of the target domain. According to the method, the cross-individual identification accuracy of the model is improved, and the problems of difficulty in sample label labeling, high cost and the like when different individuals are trained are solved.

The present disclosure provides a fault prediction method, a fault prediction model training method, a computing device, a storage medium, and a computer program product. The fault prediction method comprises: obtaining abnormal log data and unit attribute information of a service processing unit; determining an abnormal event sequence on the basis of the abnormal log data; and inputting the unit attribute information and the abnormal event sequence into a fault prediction model to obtain a fault prediction result of the service processing unit, wherein the fault prediction model is obtained by performing training on the basis of a positive sample, a first sample label corresponding to the positive sample, a negative sample, and a second sample label corresponding to the negative sample, the positive sample comprises a positive sample abnormal event sequence and sample unit attribute information, and the negative sample comprises a negative sample abnormal event sequence and sample unit attribute information. The training data of the fault prediction model is richer, so that the accuracy of prediction results of the fault prediction model during applications is improved.

The invention relates to the technical field of applied geophysics, in particular to a logging-while-drilling shear wave velocity processing method, device and equipment and a storage medium. The method comprises the following steps: dividing a parameter range and a step length, determining a stratum parameter combination, and taking the stratum parameter combination as a data set sample feature; constructing a frequency dispersion data set according to the obtained data set sample labels; performing data cleaning on the frequency dispersion data set, and correcting error samples in the data set; establishing a neural network, training a frequency dispersion data set, and verifying the feasibility of the model; an inversion objective function is established through a joint inversion method, the shear wave velocity is inversed by adopting a low frequency band, and the mud velocity is inversed by adopting a high frequency band; an optimization method is added, so that the number of forward calculation times in inversion is reduced, and the inversion efficiency is improved; and replacing the current depth point with the next depth point, and returning to execute the optimization method until the transverse wave velocity processing of the full depth section is completed. According to the method, the rapid frequency dispersion correction under the well logging while drilling is realized, the calculation efficiency is improved, and the calculation cost is saved.

The invention relates to a tool wear compensation control method, device and equipment and a medium, and relates to the field of machining control, the method comprises the following steps: adopting a wear state label with a label to carry out supervised constraint, adopting a Baum-Welch algorithm with label correction to carry out iterative optimization, and adopting a Baum-Welch algorithm with label correction to carry out iterative optimization; enabling the wear detection model to output an optimized state transition probability matrix and an optimized observation probability matrix; the wear feature vectors of different time steps, the optimized state transition probability matrix and the optimized observation probability matrix serve as training samples, the tool compensation amount corresponding to the wear feature vectors serves as a sample label, and a wear compensation prediction model is trained to be in a convergence state; and inputting the wear feature vector of the current time step into a wear compensation prediction model to predict the tool compensation amount of the operation tool in the future time step, and inputting the tool compensation amount into the numerical control machine tool to carry out tool wear compensation. The wear compensation amount of the tool can be predicted in real time and compensated, so that the service life of the tool is prolonged.

The invention relates to the technical field of artificial intelligence and deep learning, in particular to a road ice coagulation phase change latent heat intelligent prediction method and system based on an LSTM neural network, and the method comprises the steps: building a three-dimensional monitoring network: taking the side surface of a road as an X axis, the length direction as a Z axis, and the height direction as a Y axis, building a three-dimensional rectangular coordinate system, constructing a fiber grating sensor distributed topology network and a temperature monitoring network; a data acquisition and processing step: acquiring multi-dimensional state information; establishing a phase change physical model, taking phase change layer melting depth information as a sample label, and extracting a training data set and a test data set from the space-time simulation data; inputting the training data set into an LSTM network for training, and establishing a phase change state prediction model by taking the melting depth of the phase change layer as an output target; verifying the prediction precision of the LSTM network by using the test data set; and high-precision prediction of the road icing state is realized.

The invention relates to a non-cooperative communication signal modulation identification method based on multi-scale feature fusion extraction, which belongs to the technical field of cognitive radio communication, and comprises the following steps: generating time domain signals of communication signals in different modulation patterns, and preprocessing to obtain a plurality of baseband IQ signals as sample data; forming a communication signal data set with the corresponding modulation pattern as a sample label; initializing a multi-scale feature fusion extraction network model, and training the multi-scale feature fusion extraction network model by using the modulation signal data set to obtain a trained multi-scale feature fusion extraction network model; and obtaining a time domain signal of a non-cooperative communication signal in real time, performing preprocessing, inputting the trained multi-scale feature fusion extraction network model, and obtaining a recognition result of a corresponding time domain signal modulation pattern. Accurate and efficient identification of the non-cooperative communication signal modulation pattern is realized.

The embodiment of the invention provides a model training method, a facial expression recognition method and device and electronic equipment, and relates to the technical field of video processing. The model training method comprises the following steps: acquiring a sample video and a first sample label; extracting a time feature and a space feature of the sample video by using a time-space feature extraction network in the facial expression recognition model of the initial structure; calculating an attention weight representing the correlation between the spatial feature and the time feature by using a mapping network; performing weighted aggregation on the time features by using the attention weight to obtain fused spatio-temporal features; inputting the fused spatial-temporal features into a classification network to obtain a first recognition result; and performing model training based on the difference between the first recognition result and the first sample label to obtain a trained facial expression recognition model with higher accuracy.

The invention discloses a multi-target information recommendation method, system and device based on position depolarization, and the method comprises the steps: obtaining log data of information browsed by a user, and carrying out the preprocessing and analysis, and obtaining a user related data set, a position related data set and an information data set; performing feature extraction on the user related data set to obtain a user feature set, and performing feature extraction on the information data set to obtain an information feature set; constructing an information recommendation pre-training model; training an information recommendation pre-training model based on the sample label data, the position related data and the sample feature data to obtain an information recommendation model; reasoning the to-be-recommended data based on the information recommendation model to obtain a click preference score and a browsing preference score so as to obtain an information recommendation result. According to the information recommendation method, the limitation of an existing information recommendation method on the information arrangement sequence and effective browsing is solved, the accuracy of an information recommendation system and the user experience are improved, and the requirements of a user for personalized and efficient information acquisition are met.

The invention discloses a hydraulic engineering full-link core drilling quality detection intelligent management method and system, and the method comprises the steps: S1, selecting a drilling position for drilling and coring, and obtaining a sample; s2, sample label information is read and synchronized to an LIMS system, electronic tracking codes are generated, and classified storage is carried out according to preset positions; s3, scanning the code to obtain sample information, verifying the identity of the sample, and testing the sample after the sample is correct; s4, after sample detection is finished, encrypting sample data, transmitting the encrypted sample data to an LIMS system, and generating a sample report through a Web application program in combination with an NLG; and S5, pushing the detection report to the representative unit through a notification mechanism, and synchronously sending the report to the representative designated mailbox to complete transmission of report information. According to the method, a whole-process intelligent ecological system from a drilling site to laboratory detection to report delivery is formed, the space-time limitation and technical barriers of information acquisition are broken, and the timeliness and transparency of project quality information transmission are improved.

The invention relates to the technical field of data processing, in particular to the technical field of artificial intelligence, and provides a mining model training method and device, electronic equipment and a storage medium which are used for improving venation mining efficiency and quality. The method comprises the following steps: training an initial mining model based on a first sample set to obtain an intermediate mining model; the model corresponds to a plurality of tasks, and each task represents a sub-process of the event venation mining process; the first sample set comprises a first sample and a sample label associated with each task; inputting at least one second sample associated with the task into the intermediate mining model to obtain a candidate result set output for each second sample; screening each candidate result contained in each obtained candidate result set according to a preset evaluation standard to construct a second sample set; the second sample set comprises each second sample and the corresponding positive candidate result and negative candidate result; and training the intermediate mining model based on the second sample set to obtain a target mining model.

The invention relates to the technical field of GNSS deception jamming detection, in particular to a GNSS deception jamming detection method and system based on a random forest, a GNSS software receiver is adopted to process deception data sets of different scenes, parameters of different processing stages are extracted to serve as sample features, sample tags are added according to the deception occurrence moments of the scenes, and the deception jamming detection method and system based on the random forest are obtained. The parameter characteristics of different processing stages comprise signal processing stage characteristics, original observed quantity characteristics and PVT calculation result characteristics; gNSS deception jamming detection is used as a dichotomy problem of signals not subjected to deception jamming and signals mixed with deception jamming, a random forest classifier is constructed by utilizing extracted sample training, and whether the deception jamming signals exist in GNSS signals to be detected or not is judged by utilizing the classifier. According to the method, the GNSS deception jamming is detected by selecting the parameters of different processing stages as the features and constructing the random forest classifier, the importance of each feature in deception detection is deeply analyzed, and a reference is provided for deeply understanding deception behaviors and reasonably formulating an anti-deception strategy.

The invention provides a model distillation method and device, a session method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to a knowledge distillation technology and a large model technology. The method comprises the following steps: acquiring a pre-trained teacher model and a newly constructed student model; inputting the training sample into a teacher model and a student model, and adjusting parameters of the student model according to loss between output of a middle feature layer of the teacher model and output of a middle feature layer of the student model to obtain a first middle model; and inputting the training sample into the teacher model and the first intermediate model, and adjusting parameters of the first intermediate model according to the loss between the output of the teacher model prediction layer and the output of the first intermediate model prediction layer and the loss between the output of the first intermediate model prediction layer and the sample label to obtain a student model for executing the target task. The model distillation process is performed in multiple stages, so that the condition that the student model cannot converge due to few parameters is avoided, and the model distillation efficiency is improved.