74 results about "Label quality" patented technology

The invention discloses a flood storage and detention area change pattern spot identification label generation technology based on style decoupling. The technology comprises the following steps: S1, constructing and preprocessing a change detection data set; s2, constructing a conditional diffusion generation network based on a decoupling encoder; s3, decoupling extraction and orthogonalization representation of content-style features are carried out; s4, constructing a multi-target training strategy and two-stage model training; s5, injecting and fusing style features based on cross attention; s6, cross-domain style migration and diversified label generation; and S7, based on label quality screening of physical and semantic double constraints, outputting a high-quality change detection expansion data set. Compared with the prior art, the method has the advantages that by introducing a content-style decoupling mechanism, the style and the content of the generated sample are independently and accurately controlled, and the change detection label which is consistent in ground feature layout, diversified in imaging style and accurately labeled at a pixel level is generated.

The invention discloses a mass data automatic label generation method based on a large model and a rule engine, which comprises the following steps: S1, multi-source data acquisition and preprocessing: acquiring data through a unified data interface, and then performing data cleaning, data standardization processing and data format conversion to obtain standard input data; s2, constructing a label system framework; s3, generating a large model label; s4, performing intelligent clustering and label refining; s5, rule engine constraint and optimization; s6, evaluating and optimizing label quality; and S7, automatically expanding and updating the tag system. According to the method, automatic label generation of mass multi-source heterogeneous data is realized through a large model and rule engine technology under the condition of no personnel intervention, a large-scale label system containing thousands of labels is constructed, meanwhile, the label system can be rapidly updated along with product iteration and keep timeliness, and the generated labels are accurate and extensible.

In various examples, data collection vehicles or machines may be equipped with one or more LiDAR sensors (and / or other sensors), and the LiDAR sensor(s) may be used to collect frames of LiDAR data representing various real-world conditions. The LiDAR data may be processed using one or more deep neural networks (DNNs) such as a transformer neural network to generate auto-labels representing detected dynamic obstacles of any designated class. Tracking may be applied to generate object tracks (tracklines), estimate velocity, and / or handle occlusions. In some embodiments, the object tracks may be refined based on geometry and / or confidence to improve their accuracy. In some embodiments, the auto-labels are classified to generate an estimated representation of quality, and auto-labels with at least a threshold quality score may be skipped during human labeling. As such, auto-label quality scores may be used to accelerate human validation of auto-labeled scenes by skipping high quality auto-labels.

The invention provides a self-adaptive target detection method, system and device in online testing, and relates to the technical field of computer vision and machine learning, and the method comprises the steps: obtaining an input image, and respectively inputting the input image to a fixed teacher model and a to-be-optimized student model to obtain a prediction result; calculating consistency distillation loss based on prediction results of the two parties to maintain the stability of the model, generating high-quality pseudo labels through a dynamic pseudo label generation process based on a teacher prediction result, and calculating supervision loss to drive the model to adapt to a target domain; and finally, combining the two losses to optimize the student model and outputting a detection result. According to the method, the technical problems of unstable pseudo tag quality and high model updating overhead in self-adaption during testing are effectively solved, and the precision, robustness and deployment efficiency of the target detection model in an unknown domain environment are remarkably improved.

The invention discloses a full-automatic label printed matter inspection machine, and belongs to the technical field of label quality inspection, the full-automatic label printed matter inspection machine comprises a rack, a workbench and an unwinding roller are respectively mounted below the front surface of the rack, a winding roller and a display screen are respectively arranged above the front surface of the rack, and guide rollers are rotatably connected to the left and right sides of the front surface of the rack at equal intervals; an industrial camera is installed on the front face of the rack and located below the display screen. The device further comprises a supporting plate, the supporting plate is installed on the front face of the workbench through bolts, a vertical lead screw is connected to the interior of the supporting plate through a bearing, and a first motor is installed at the bottom of the supporting plate. According to the full-automatic label presswork inspection machine, through cooperative driving of multiple motors and air cylinders and combination of an innovative structure of clamping inclined stripping, circulating stripping and magnetic force accurate pressing, full-process automation, zero-damage and high-thoroughness stripping of unqualified labels is achieved, the problems of residues and displacement are thoroughly solved, and the production efficiency and the stripping effect are greatly improved.

The invention discloses an unsupervised video clip retrieval method based on time sequence anchor point mining and semantic alignment, which comprises a video retrieval training system based on time sequence anchor point mining and point supervised learning, and the system comprises a key anchor point extraction module, a semantic alignment description generation module and a point supervised learning enhancement module. Key time anchor points are extracted from an original unlabeled video sequence through a key anchor point extraction module, then a pseudo-label triple is constructed through a semantic alignment description generation module, a weak supervision video clip retrieval model is trained accordingly, and in the training process, the pseudo-label triple is extracted from the original unlabeled video sequence. Constructing a point supervised contrast learning target through a point supervised learning enhancement module to further optimize the model, so that the finally trained weak supervised video clip retrieval model outputs a clip starting and ending time boundary related to query statement semantics; the problems of low pseudo tag quality, fuzzy positioning boundary and inconsistent semantic space in an unsupervised scene are effectively solved, and the positioning precision and generalization ability of video clip retrieval are remarkably improved.

The label quality inspection machine capable of automatically correcting and supplementing the materials comprises a first base and a second base, a screening device is fixedly installed in the middle of the right end of the first base, a first servo motor is fixedly installed on the front portion of the right end of the first base, and a controller is fixedly installed on the rear portion of the right end of the first base. A detection device is fixedly installed in the middle of the upper end of the second base, a conveying belt is installed between the first base and the second base, a feeding table is fixedly installed at the front end of the first base and the front end of the second base jointly, a second servo motor is fixedly installed on the left portion of the upper end of the feeding table, and a feeding roller is fixedly installed at the output end of the second servo motor. A first material receiving box is installed at the rear end of the first base and the rear end of the second base jointly. According to the label quality inspection machine capable of automatically correcting the errors and supplementing the materials, scanning detection is carried out through the visual inspection camera, and when the visual inspection camera detects that information of hang tags is fuzzy and is not correct, the unqualified hang tags are sucked up through the negative pressure suction cup.

The invention relates to a bridge-crossing type label-domain-free adaptive damage identification method, which belongs to the technical field of bridge structure health monitoring and comprises the following steps of: 1, constructing a three-tower type feature extractor comprising a time domain tower, a frequency domain tower and a modal tower to obtain a cross-modal combined feature; 2, aligning with a modal map through modal consistency constraint; 3, utilizing a multi-scale and dynamic frequency band attention mechanism to adaptively highlight a damage sensitive frequency band; 4, confrontation and cooperation mixed alignment is adopted, feature distribution differences are reduced, and modal physical consistency is kept; 5, a self-training and multi-teacher distillation mechanism guided by modal confidence is designed under the non-labeling condition, and the pseudo label quality and the training stability are improved; and 6, introducing physical constraint regularization to ensure that a result accords with a structural dynamics rule. According to the method, the damage probability distribution, the modal similarity heat map and the reliability index are finally output, target domain labeling is not needed, and the accuracy, the robustness and the engineering applicability of cross-bridge damage identification can be improved.

The application discloses a semi-supervised sea surface target detection method, system, device and storage medium, and relates to the field of target detection. A confidence threshold adjustment model of sea surface target categories is established, and a classification loss function of unlabeled data is determined according to the confidence threshold adjustment model; a regression loss function of the unlabeled data is adjusted through boundary box consistency regularization; and the confidence threshold is used to improve the pseudo-label quality in the model training process. The confidence threshold of each sea surface target category is dynamically adjusted, the pseudo-label quality is improved, the strong dependence on the intersection over union in the traditional positive and negative sample matching mechanism is relieved through boundary box consistency regularization, the quality of the boundary box is improved, and then the sea surface target detection performance is improved.

The application provides a low-bubble adhesive label quality monitoring method and system based on image analysis, and belongs to the technical field of adhesive labels. The low-bubble adhesive label quality monitoring method based on image analysis comprises the following steps: acquiring image acquisition data of a low-bubble adhesive label, wherein the image acquisition data is digital image data obtained by imaging the low-bubble adhesive label containing a pattern area under preset imaging conditions; performing image processing on the image acquisition data to generate processed image data for representing label region brightness distribution, gray scale distribution and texture distribution; analyzing image abnormalities formed by bubble points in an adhesive layer at corresponding apparent positions of a face material layer according to the processed image data to generate bubble point candidate region data; and performing quality determination on the low-bubble adhesive label according to the bubble point candidate region data to obtain a quality monitoring result.

The invention relates to a semi-supervised semantic segmentation method based on adaptive pseudo label generation, which realizes adaptive control of pseudo label quality by constructing category prototype representation containing a feature mean value and a standard deviation and introducing standard deviation information into a pseudo label screening and prototype consistency learning process. The method comprises a class prototype generation module, an adaptive pseudo-label generation module and a prototype consistency learning module, dynamically adjusts a pseudo-label screening threshold by combining prediction probability distribution and class prototype similarity, and introduces a prototype-based feature consistency constraint in a training process. Therefore, the segmentation precision and the training stability of the semantic segmentation model are remarkably improved under the condition of a small amount of annotated data.

The present application relates to a kind of heart ultrasound video semantic segmentation pseudo-label generation method based on optical flow guide, belong to computer vision and medical image processing field.The method includes: selecting two key frames in heart ultrasound video frame sequence, and obtaining the segmentation mask of two key frames by artificial labeling;Optical flow model is fine-tuned using two key frames, the frame between two key frames, the frame of first key frame left side preset quantity and the frame of second key frame right side preset quantity;Based on the fine-tuned optical flow model, the forward optical flow sequence from first key frame to second key frame and the reverse optical flow sequence from second key frame to first key frame are predicted;Based on forward optical flow sequence and reverse optical flow sequence, generate forward propagation mask sequence and reverse propagation mask sequence, and carry out position weighted fusion, obtain the pseudo-label of unlabelled frame.The technical problem that the present application aims to solve is that the label of heart ultrasound video semantic segmentation is difficult to obtain and the quality of pseudo-label obtained is poor.

The present disclosure relates to a solution on label quality indicator for model positioning based on PRU is proposed. In particular, a target UE receives a signal from LMF to consider the assessment of the label quality using the PRU information based on the target UE capability. Furthermore, the target UE reports the quality indicator of the label. In this way, the accuracy assessment of the label used for data collection for AIML positioning can be improved.

The application provides a labeled sample data generation method and an electronic device, and the method comprises the following steps: acquiring multiple frames of images for a target scene; determining the marking position information of each marking object in each frame of image, and determining the initial spatial pose of each marking object in each frame of image; determining the target coordinate system corresponding to the multiple frames of images; determining the global spatial structure information corresponding to the multiple frames of images according to the multiple frames of images, the target coordinate system corresponding to the multiple frames of images, the marking position information of each marking object in each frame of image and the initial spatial pose of each marking object in each frame of image; and generating labeled sample data based on the global spatial structure information corresponding to the multiple frames of images and the labeling information of the target object in the multiple frames of images. The application can realize the collaborative improvement of multi-view key point labeling in efficiency, multi-view consistency and controllability of labeling quality without relying on complex external three-dimensional reconstruction process or special calibration software.

The invention discloses a multi-modal noise label correction method, equipment, a device and a medium, and relates to the technical field of data noise processing, the method is characterized in that a noise label is filtered by constructing semantic invariant prototype representation of a multi-modal sample, and the noise label is corrected by using association between the multi-modal sample and a prototype, so that the label quality is improved, and the data processing efficiency is improved. And the condition that the downstream multi-modal learning model is misled by the wrong label data is avoided, so that the reliability and generalization in the multi-modal data training process are ensured.

The invention belongs to the technical field of AI training data annotation, and particularly relates to an AI active learning-based annotation quality dynamic verification and authority management and control method, which comprises the following steps of: initializing a core module, a rule base and an authority matrix; the AI active learning model samples and distributes samples based on data uncertainty and annotator ability matching; the dynamic verification module executes multi-dimensional verification and feeds back abnormal features; the authority management and control module dynamically adjusts the authority according to the verification result; and iteratively optimizing the model and the rule base based on feedback, and circulating until the annotated data meets a quality threshold value. According to the method, autonomous optimization of labeling quality, resource dynamic configuration and advanced avoidance of abnormal labeling are realized, the abnormal labeling recognition accuracy and the resource configuration efficiency are remarkably improved, the model iteration speed is increased, and excessive dependence on manual intervention is not needed.

The application discloses a mass data automatic label generation method based on a large model and a rule engine, and comprises the following steps: S1, multi-source data acquisition and preprocessing: data is collected through a unified data interface, and then standard input data is obtained through data cleaning, data standardization processing and data format conversion; S2, label system framework construction; S3, large model label generation; S4, intelligent clustering and label refining; S5, rule engine constraint and optimization; S6, label quality evaluation and optimization; S7, label system automatic expansion and update.The application realizes automatic label generation of mass multi-source heterogeneous data through the large model and the rule engine technology without personnel intervention, constructs a large-scale label system containing thousands of labels, ensures that the label system can be quickly updated with product iteration, maintains timeliness, and the generated label is accurate and expandable.

The application relates to a cross-architecture industrial control system binary code unified representation and efficient labeling method. The method comprises the following steps: firstly, acquiring binary codes of a cross-architecture industrial control system, and converting the binary codes into a unified intermediate representation containing industrial control specific semantic labels; then, constructing a semantic graph containing industrial control semantic features based on the unified intermediate representation; then, performing representation learning on the semantic graph through a graph Transformer to obtain a unified vector representation of the cross-architecture industrial control binary code; then, pre-labeling an unlabeled industrial control binary code segment based on the unified vector representation; finally, selecting samples from the pre-labeling result according to a preset strategy to perform artificial fine labeling, combining the artificial fine labeling result to construct a quality evaluation system, and forming a closed-loop improvement of labeling quality and model performance. The method solves the problems of inconsistent representation of multi-architecture industrial control binary codes, low efficiency and poor quality of large-scale labeling, realizes cross-architecture semantic unification and efficient and accurate labeling, can provide high-quality data set support for industrial control system vulnerability detection and malicious code tracing, and is suitable for key industry industrial control equipment scenes.

The present application relates to the technical field of data processing, more particularly, to a kind of dynamic graph disambiguation-based partial multi-label data classification method and system, three reliable label sets are constructed according to output, confidence, consistency, weighted similarity between instances is constructed based on the occurrence frequency of candidate partial multi-label in three reliable label sets, the discriminative score of candidate partial multi-label, the dependency between instances, structured noise is suppressed using weighted similarity, multi-scale similarity graph is constructed and adaptively fused, a graph propagation mechanism is introduced by introducing label confidence dynamic adjustment, and the collaborative evolution of classifier and label quality is realized by progressive multi-stage training. The method effectively solves the problems of feature-semantic ambiguity, structured noise interference, label contribution imbalance, single-scale graph limitation and the like.

This invention belongs to the field of wind power equipment diagnosis, specifically relating to a semi-supervised acoustic signature diagnosis method for wind turbine blades based on meta-optimization. The method includes the following steps: acquisition and preprocessing of wind turbine blade acoustic signature signals; construction of labeled and unlabeled datasets; initialization and baseline training of the semi-supervised diagnostic model; pseudo-label correction and construction of a quality scoring network; virtual model update based on corrected pseudo-labels; meta-loss calculation based on labeled data; determination of the training value of sample-level pseudo-labels; training of the pseudo-label quality scoring network and sample selection; iterative training of the semi-supervised model and diagnostic output. This invention achieves dynamic evaluation and adaptive correction of pseudo-label quality by explicitly modeling the impact of unlabeled sample pseudo-labels on the model optimization objective. This improves the accuracy and robustness of wind turbine blade fault diagnosis under limited labeled data conditions, enhances stability during training convergence, and improves the accuracy of the final model.

Example embodiments of the present disclosure provide a solution for determining a position label quality indicator In an example method, a first device receives, from a second device, a positioning configuration and assistance data for determining a label quality indicator. The assistance data is determined based on the following: at least one ground truth position of at least one third device reported by the at least one third device to the second device, and at least one position of the at least one third device, the at least one position is estimated by the second device based on the positioning configuration and measurements reported by the at least one third device. The first device determines the label quality indicator based on the positioning configuration and the assistance data. The first device transmits, to the second device, the determined label quality indicator.

This invention discloses an infrared small target detection method based on multi-source knowledge-driven dynamic pseudo-label generation, belonging to the field of infrared target detection technology. Addressing the problems of limited point-level annotation supervision information, low initial pseudo-label quality, and easy pseudo-label drift during training, this method first generates static pseudo-labels using multi-source prior knowledge such as the energy distribution, local contrast, spatial compactness, background smoothness, and target area consistency of infrared small targets. Then, a dual-model framework consisting of a teacher model and a student model is constructed. A dynamic scoring map is built using teacher model prediction, energy prior, and spatial distance penalty terms. Dynamic pseudo-labels are generated by combining dynamic weight adjustment strategies and threshold shrinkage strategies. Finally, the student model training is jointly supervised by the dynamic pseudo-labels and prior consistency regularization terms. This method can gradually improve the quality of pseudo-labels under weak point-level supervision, enhance model training stability and target region representation ability, and can be used for infrared small target detection tasks.

The application provides a labeled sample data generation method and an electronic device, and the method comprises the following steps: acquiring multiple frames of images for a target scene; determining the marking position information of each marking object in each frame of image, and determining the initial spatial pose of each marking object in each frame of image; determining the target coordinate system corresponding to the multiple frames of images; determining the global spatial structure information corresponding to the multiple frames of images according to the multiple frames of images, the target coordinate system corresponding to the multiple frames of images, the marking position information of each marking object in each frame of image and the initial spatial pose of each marking object in each frame of image; and generating labeled sample data based on the global spatial structure information corresponding to the multiple frames of images and the labeling information of the target object in the multiple frames of images. The application can realize the collaborative improvement of multi-view key point labeling in efficiency, multi-view consistency and controllability of labeling quality without relying on complex external three-dimensional reconstruction process or special calibration software.

The present application relates to the technical field of computer vision and remote sensing image processing, in particular to a remote sensing image labeling method and system based on transfer learning, comprising the following steps: obtaining a basic model and constructing a differentiated sub-model to form an integrated system, using multi-model prediction and weighted fusion according to reliability and confidence, dividing pseudo label grades based on batch distribution self-adaptation, performing multi-dimensional re-evaluation on uncertain samples and generating soft labels, and finally combining different weights for iterative training. Through the adaptive grading threshold based on batch confidence distribution, the present application replaces the fixed threshold, realizes the dynamic adjustment of pseudo label quality division, avoids the problems of insufficient samples in the early stage of training and noise accumulation in the later stage, and improves the screening robustness. At the same time, the spatial consistency analysis and multi-dimensional re-evaluation mechanism are introduced to repair uncertain samples and generate soft labels, which significantly improves the utilization efficiency of unlabeled remote sensing data under the premise of suppressing noise.

1. The name of the design product: digital electronic label product inspection machine. 2. The use of the design product: the device for detecting the quality of the label. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective drawing.

The utility model discloses a washable composite label, and relates to the field of labels, the washable composite label comprises a label base material A, the bottom surface of the label base material A is fixedly provided with a label base material B, the periphery of the joint of the label base material A and the label base material B is fixedly provided with a tensile component, the top surface of the label base material A is coated with polyurethane modified glue, and the top surface of the label base material B is coated with polyurethane modified glue. A waterproof film group is adhered to the top surface of the polyurethane modified adhesive, a groove is formed in the periphery of the top surface of the A label base material, and a fluorescent layer is fixedly arranged on the surface of the groove. According to the water-proof label, waterproof glue and the burr-proof assembly are arranged, the waterproof film set and the PET bottom film are used for preventing water on the surface of the label, the waterproof glue is matched with the silicon rubber sleeve so that the periphery of the label can be sealed and wrapped, external water cannot enter the label easily during water washing, and the label is affected with damp, and the polyester wrapping edge is glued to the surface of the silicon rubber sleeve through the water-proof adhesive; friction force generated during washing does not cause burrs around the label easily, the attractiveness is higher, and the label quality is also improved.

A terminal according to one embodiment of the present disclosure includes: a reception unit that receives a setting related to at least one report pertaining to a label, a quality indicator of the label, and a time stamp of the label, such setting used for collecting data for artificial intelligence (AI)-based positioning; and a control unit that, on the basis of the setting, controls at least one report pertaining to the label, the quality indicator, and the time stamp. According to one embodiment of the present disclosure, highly accurate positioning can be achieved.

The invention relates to a software aging prediction method and device based on feature reconstruction and tag guidance. The method comprises the following steps: acquiring a source code of target software and an aging tag sample corresponding to the source code; extracting a metric feature and a graph structure feature from the source code, and reconstructing the metric feature and the graph structure feature into a feature image; based on the feature image, obtaining aging feature representation of the source code through self-training of contrast learning optimization; generating a pseudo tag for an unlabeled code unit in the source code by using tag propagation assisted by a buffer area and the aged tag sample; constructing a data set based on the source code, the aged tag sample and the pseudo tag; and based on the aging feature representation and the data set, training a prediction model and performing aging prediction on the target software. Through feature reconstruction and buffer area assisted label propagation, the stability and reliability of the pseudo label are improved, and the problem that the quality of the pseudo label is poor in the initial training stage of a traditional self-training method is solved.

The invention relates to the technical field of surrounding rock label automatic optimization, and discloses a surrounding rock label automatic optimization method based on pseudo label weighting and belief propagation. The objective of the invention is to solve the problem that spatial correlation and feature coupling among data are not fully utilized in the prior art; a differential processing mechanism for samples with different confidence degrees is lacked; an iterative optimization closed-loop system is not formed; and fuzziness between adjacent levels cannot be effectively processed. The method comprises the following steps: S1, data preparation and preprocessing; s2, initial model training; s3, confidence evaluation and sample classification; s4, adjusting labels and weights; s5, iterative optimization is carried out; and S6, outputting a final model. Through multi-round iterative optimization, the label quality is gradually improved, and finally the accuracy and reliability of the surrounding rock stability identification model are improved.

The invention relates to a three-stage label re-labeling method and device based on a universal audio language multi-mode large model. The method comprises the following steps: firstly, extracting a model through audio features, and generating three-section structured description containing overall description, voice and music features from processed audio; embedding the audio content into a semantic enhanced prompt template, inputting a tag prediction language model, and generating a prediction tag matched with the audio content by combining a tag quantity control mechanism of corpus statistical characteristics; then, a multi-modal label alignment model is used, the prediction label is mapped to an original label category of the data set through three-layer matching, and candidate labels are obtained; and finally, the similarity between the candidate tags and the audio is calculated through cosine similarity, and the tags of which the scores are not lower than a threshold value are reserved as results. The method does not depend on the correctness of the original label, even if the original label is poor in quality and incomplete, a high-quality re-labeling result can still be output, and the inherent defects of an existing method are overcome.