121results about How to "Quick classification" patented technology

The invention relates to the technical field of intelligent sorting and stacking, in particular to a rectangular material follow-up sorting, mixing and stacking method and system.The method comprises the steps that information of a plurality of actual rectangular materials is obtained; analyzing and classifying the actual rectangular material information to obtain a classification result; a preset stacking strategy is determined based on the stacking disc information and the sorting result; whether the target rectangular material meets a preset grabbing condition or not is recognized, and grabbing or next-time grabbing is conducted based on the recognition result; calculating a preset stacking position based on the target material information and a three-dimensional boxing algorithm; a target rectangular material model is generated based on the target material information, a preview stacking model is generated based on the target rectangular material model and a preset stacking position, the preview stacking model is analyzed, the dumping risk is judged, and the preset stacking position is adjusted based on the dumping risk; and the actual stacking layout of the stacking disc is analyzed, and whether material sorting, mixing and stacking are completed or not is determined based on the analysis result. The efficiency of the stacking process is improved.

The invention discloses a multi-mode breast ultrasonic diagnosis system based on a dynamic feature fusion network, belongs to the field of medical image processing, and particularly relates to the multi-mode breast ultrasonic diagnosis system based on the dynamic feature fusion network. The invention aims to solve the problem that the existing method is low in breast ultrasonic recognition accuracy. The system comprises a multi-modal data preprocessing main module used for preprocessing a collected multi-modal mammary gland ultrasound image to obtain a preprocessed multi-modal mammary gland ultrasound image; the multi-modal convolutional neural network main module is used for building a dynamic feature fusion network model; the model training main module is used for training an established dynamic feature fusion network model by using the preprocessed multi-modal breast ultrasound image to obtain a trained dynamic feature fusion network model; and the model test main module is used for loading the trained dynamic feature fusion network model, classifying a to-be-diagnosed multi-modal breast ultrasound image, and identifying benign and malignant breast tumors in the multi-modal ultrasound image.

The invention discloses an image segmentation method based on an improved SAM model, and relates to the technical field of image segmentation, and the method comprises the following steps: collecting remote sensing image data sets of various different scenes and categories, and carrying out the data annotation and data enhancement preprocessing operation of remote sensing images; training a preset target detection model by using the labeled remote sensing image data set; using the trained target detection model to predict a remote sensing image, identifying a target area and category in the image, and outputting a prediction result; extracting multi-scale features of each target area detected in the prediction result based on ViT, and performing image segmentation based on SAM to obtain a classification result of each target area; and taking the classification result of each target area as a returned detection result. Through the remote sensing image classification method based on the convolutional neural network, the rapid classification task of the remote sensing images is realized, and powerful technical support and data support are provided for the fields of environment monitoring, urban planning, agricultural management and the like.

The invention discloses a method for generating a three-dimensional building GLTF file based on index compression. The method comprises the following steps: S1, collecting three-dimensional coordinate data of a building; s2, grouping and classifying the data according to floors to form a classification index structure based on a hash table; s3, selecting a reference model and recording Mesh data and vertex coordinates of the reference model; s4, calculating a translation matrix T of the polyhedral structure, and performing coordinate transformation; s5, generating Mesh data of other polyhedrons based on index compression, and reducing redundant surface data by adopting a topology preserving surface optimization algorithm; s6, independently processing the geometric data of each floor, and generating corresponding Mesh data and Node nodes; and S7, combining all floor data to generate a complete GLTF file, and performing compression by using a dynamic Huffman coding algorithm. Through the improved index compression and dynamic Huffman coding technology, the file size is remarkably reduced, the transmission efficiency is improved, and the geometric and topological integrity of the model is ensured.

The invention discloses a circuit breaker contact wear degree intelligent evaluation system, and belongs to the technical field of circuit breaker contact wear evaluation, the circuit breaker contact wear degree intelligent evaluation system comprises a camera, a data collector, a server and a display, the server comprises a circuit breaker type analysis module, a signal processing module, a wear evaluation module, a wear prediction module and a health monitoring module, the circuit breaker type analysis module, the signal processing module, the wear evaluation module, the wear prediction module and the health monitoring module are in communication connection in sequence; the display comprises a data display module; according to the invention, the wear degree of the contact head of the circuit breaker can be intelligently evaluated, and meanwhile, the system also has the functions of wear degree prediction, residual use frequency calculation and wear frequency early warning, so that the maintenance and management efficiency of the circuit breaker can be greatly improved, and the equipment fault risk is reduced.

The invention discloses a benthonic animal community structure recognition method and system based on image recognition, and relates to the technical field of benthonic animal community structure recognition, and the method comprises the steps: carrying out the image collection of a target water area through an underwater camera, and transmitting the collected image to a computer. According to the method, the image recognition technology is adopted, rapid and accurate recognition and classification of the benthonic animals are achieved, the working efficiency is greatly improved, recognition is carried out by utilizing the image recognition technology and combining features such as shapes, textures and colors of the benthonic animals, the confusion rate and the error rate in the classification and counting process are effectively reduced, and the classification accuracy is improved. The accuracy and reliability of the result are improved, the abnormal change of the zoobenthos community structure can be found in time by utilizing a real-time data analysis technology, timely early warning and response are provided for protecting the ecological environment of the water body, targeted suggestions and measures are automatically provided, a user is helped to better improve and protect the ecological environment of the water body, and the user experience is improved. And the scientificity and effectiveness of decision making are improved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an anomaly detection and response system and method for intelligent power heterogeneous data fusion, and the system comprises a historical data and preprocessing module which is used for collecting and preprocessing the historical data of a power grid; the multi-source data feature engineering module is used for carrying out training and anomaly prediction on the data at a certain time interval; the heterogeneous graph network construction module is used for connecting all types of nodes according to the task nodes to construct a heterogeneous graph network; and the heterogeneous graph neural network module is used for performing propagation learning on the heterogeneous graph under the sliding window time by using a heterogeneous graph attention network. According to the method, the abnormal conditions of the power system can be classified quickly and accurately, and corresponding response measures are triggered according to the classification result. The real-time performance and the high accuracy are combined, so that the safety and the stability of the power system can be effectively guaranteed, and the economic loss and the potential safety hazard caused by abnormity are reduced.

The invention relates to the technical field of clustering analysis, and particularly discloses a fruit growth monitoring system, which comprises an acquisition module for acquiring a target value at a time point, acquiring target data based on the target value, and generating a target point; the clustering analysis module is used for setting a clustering radius and clustering the target points according to the density of the target points in the clustering radius; the clustering optimization module is used for adjusting a clustering cluster according to the theoretical gravity center and the maximum distance when the density of the target points in the overlapping region meets the condition; and the result module obtains the standard points and judges the growth state of the fruits based on the standard points. According to the invention, the efficiency of monitoring the growth state of the fruits can be improved.

The invention relates to a target detection method of a tactical AR helmet. Comprising the following steps: a head posture sensing and space positioning module: after a helmet is started, an inertial measurement unit IMU sensor acquires acceleration and angular velocity data of a head through a gyroscope, an accelerometer and a magnetometer; integrating the data of the multiple sensors by using a sensor fusion algorithm including Kalman filtering; creating space mapping between the virtual scene and the real scene; triggering of a target detection module: inputting a real-time video frame captured by a camera into a pre-trained convolutional neural network (CNN) model; the CNN model performs feature extraction according to different detection tasks including target classification and object boundary detection; performing multi-scale detection on a target through multi-layer convolution and pooling operation; generating a plurality of candidate boxes using a regional proposal network (RPN); real-time target tracking and calibration: a detected target position is transmitted to a target tracking algorithm, and tracking is initialized; the size and the position of the tracking frame are adjusted according to the visual angle change of a helmet wearer.

The invention relates to a woolen sweater defect detection method. The method is characterized by comprising the following four main steps: a data preprocessing step, a model construction step, a model training step and a defect detection step. Wherein in the model construction step, strategies such as an attention mechanism and a network structure optimization are introduced, so that the identification capability of the model on woolen sweater defects is improved; in the detection process, automatic positioning and classification of defect areas are realized through a series of key functions. The method is high in detection efficiency, low in comprehensive detection cost and high in detection accuracy.

The invention relates to the technical field of video content processing, in particular to a real-time video sensitive content identification method and system, and the method comprises the following steps: S1, receiving a real-time video stream from a plurality of video sources, and splitting the real-time video stream according to frames; s2, performing language recognition on the audio data split in the S1, and generating corresponding text data; s3, identifying potential sensitive content, and labeling according to the type of the sensitive content; s4, updating the sensitive content definition library in real time according to the latest laws and regulations, social standards and user-defined rules so as to dynamically adjust the judgment standards of the sensitive contents; and S5, classifying the sensitive content preliminarily identified in the S3 according to the sensitive content definition library updated in real time in the S4. According to the method, the deep learning technology and the real-time updating mechanism are adopted, so that sensitive contents in the multi-source video stream can be effectively and quickly identified and processed, the accuracy of content monitoring is ensured, and the latest laws and regulations are met.

The invention discloses an XLPE cable insulation fault diagnosis model based on an adaptive CEEMDAN and a multi-scale convolutional neural network, and the model comprises the steps: decomposing an original fault signal into a plurality of equal sub-signals through a sliding window technology, and enabling each sub-signal to serve as an independent sample; then, a training set and a verification set are selected according to the random principle, it is ensured that the data samples of the fault types account for half of the training set and half of the verification set respectively, and the proportion is balanced; training set fault data and verification set fault data are reconstructed based on the adaptive CEEMDAN; inputting the reconstructed training set fault data into the MSCNN for training, and obtaining a related parameter with an optimal training result; and inputting the reconstructed verification set fault data into the trained multi-scale convolutional neural network MSCNN to obtain a fault identification result. The ACEEMDAN-MSCNN provided by the invention is superior to a basic single-scale CNN (Convolutional Neural Network) model and other multi-scale models.

The invention discloses an on-line defect detection system for float glass production, relates to the technical field of glass defect detection, and solves the technical problem that the quality of a finished product does not reach the standard due to the fact that tiny defects or inclusions in a glass plate are not considered in the prior art. The method comprises the following steps: irradiating a glass plate by laser and collecting to obtain a light propagation image, preprocessing the light propagation image to obtain a gray-scale light image, taking a mode of the light intensity of pixel points in the gray-scale light image as standard light intensity, dividing abnormal pixel points based on the standard light intensity, and obtaining an abnormal feature map in the gray-scale light image based on the abnormal pixel points. Extracting light reaction features in the abnormal feature map; and matching the light reaction characteristics with standard geometric characteristics to obtain a defect shape, obtaining the pixel type and the pixel defect intensity of the defect shape based on the number of abnormal pixel points in the defect shape and the light intensity, and matching the defect shape, the pixel type and the defect pixel intensity with standard defect data to obtain corresponding defect data.

The invention discloses a returned intelligent electric meter sorting assembly line monitoring system. The system comprises a feature fusion sorting module, a digital mapping control module, a chain type tracing management module, a state diagnosis module and an environment management and control module. The feature fusion sorting module collects ammeter data through an industrial camera array, a microphone array, a structured light scanner and an infrared thermal imager, and performs feature fusion classification; the digital mapping control module calculates sorting process control parameters by using a distributed control model and an optimization algorithm; the chain type traceability management module adopts a block chain technology to record data and realize information retrieval; the state diagnosis module performs equipment fault prediction in combination with a data prediction technology; the environment management and control module monitors key parameters of the sorting environment. According to the system, the automation and intelligence level of an electricity meter sorting assembly line is improved, and the problems that an existing system is low in sorting efficiency, lagged in equipment monitoring and the like are solved.

The invention discloses a construction waste classification image recognition system, which comprises an image acquisition module and an image processing module, and is characterized in that the image acquisition module is used for acquiring to-be-recognized construction waste video images; the image processing module is connected with the image acquisition module, and the image processing module is used for extracting multiple groups of key frame images from the construction waste video images, comparing to-be-compared object information on each group of key frame images with recorded information in the construction waste object feature library, and if the to-be-compared object information on each group of key frame images is consistent with the recorded information in the construction waste object feature library, outputting the to-be-compared object information. And determining that the type of the to-be-compared object is the object type corresponding to the recorded information. The construction waste can be quickly identified and classified, and the cost can be saved.

The invention provides a fault diagnosis method for aero-engines with high-dispersity cluster characteristics based on element engines, and solves the problem that same gas path parameter values of engines of the same model are distributed dispersedly in a certain range due to manufacturing process level, assembly tolerance, working conditions, maintenance and the like of the aero-engines in actual engineering. Therefore, the health state of the engine is difficult to judge. Proposing and explaining high-dispersity cluster characteristics of aero-engine gas path parameters; proposing a meta-engine concept aiming at the characteristics, constructing a model of the meta-engine concept, and deriving an engine group with a high-dispersity cluster characteristic by utilizing the model; a wedge-leaf classifier and a novel classifier integration method are provided based on a meta-engine model, and fault diagnosis of an engine with high-dispersity cluster characteristics is achieved. According to the aero-engine fault diagnosis method provided by the invention, the generality and personality of engine gas path parameters are considered, the performance difference between the engine individuals is fully considered, and the aero-engine fault diagnosis method has universality for the cluster.

The invention provides a paper quality detection method and system, and relates to the technical field of defect detection, the paper quality detection method is based on a YOLOV8 model, and the method comprises the steps: carrying out the feature extraction operation of a to-be-detected paper image according to a shallow network feature extraction module, and obtaining an initial feature map; when the deep network feature extraction module performs down-sampling operation on the initial feature map, the initial feature map is divided into a plurality of feature regions, and a weight is divided for each feature region through the adaptive weight down-sampling module, so that a weighted feature map is generated; reversely transmitting the weighted feature map to a shallow network feature extraction module through a reversible feature fusion module to obtain a fused weighted feature map; and determining defect information of the to-be-detected paper image through a deep network feature extraction module according to the fused weighted feature map. According to the invention, the defects on the paper can be identified and classified more accurately, and paper defect detection with higher precision and higher efficiency is realized.

The invention relates to the technical field of medical diagnosis, in particular to an AI-based CBA fluorescence immunoassay judgment method and system and a storage medium, and the AI-based CBA fluorescence immunoassay judgment method comprises the following steps: based on fluorescence immunoassay image data, analyzing and identifying the illumination intensity and vibration error of an image, adjusting exposure parameters and a stabilization algorithm to eliminate errors and noisy points, and obtaining a fluorescence immunoassay result; and generating an image correction processing record. The method has the beneficial effects that the illumination intensity and the vibration error of the fluorescence immune image data are analyzed and adjusted, the noisy points and the error of the image are eliminated, and the definition of a plurality of key biomarkers in the image is optimized by combining image edge information enhancement, contrast adjustment and sharpening processing; the method improves the accuracy and efficiency of visual recognition of the antibody, improves the judgment capability of the type and characteristics of the antibody by calculating the spatial distribution and relative brightness of the antibody in the image, rapidly diagnoses and classifies diseases, and improves the efficiency and speed of processing batch samples.

The invention relates to the technical field of data asset management, in particular to a data asset management system and method. The method comprises the following steps: acquiring a data asset information set from different data sources in real time and performing tag structure sub-column division to obtain data asset information tag description structured sub-columns, and meanwhile, performing time sequence creation synchronization processing and integrating and storing the data asset information tag description structured sub-columns into a data asset management database; performing use frequency and sensitivity evaluation analysis on each piece of data asset sub-information in the data asset management database, and performing data asset access utility evaluation analysis to obtain data access utility of each piece of data asset sub-information; and performing dynamic access right control and full life cycle management design on each piece of data asset sub-information in the data asset management database, and performing automatic management and report feedback recording to generate a data asset information management report. The transparency, safety and efficiency of data asset management can be improved.

The invention relates to the technical field of high-voltage transmission line fault positioning, and discloses a transmission line sound wave positioning method based on wavelet analysis, comprising the following steps: S1, installing acoustic sensors at two ends of a transmission line; s2, decoupling processing is carried out on the collected current signals; s3, performing Mallat algorithm decomposition on the current line mode component to obtain a wavelet coefficient of an approximate part and a wavelet coefficient of a detail part; s4, further de-noising processing is carried out on the current line mode component # imgabs0 #; and S5, obtaining the time when the fault sound wave arrives at the measuring end. According to the method, denoising processing is carried out on the wavelet coefficient # imgabs 1 # of the detail part, misjudgment information introduced by environmental noise in the signal is reduced, the wavelet coefficient is mapped to a unified range [0, 1] through normalization processing, and a variable # imgabs 2 # is introduced to carry out dynamic filtering on the signal, so that residual misjudgment information can be effectively filtered out, and the accuracy of the signal processing is improved. And the beneficial effect of accurately positioning the fault is achieved.

The utility model relates to a simple automatic harvesting intelligent all-in-one machine for root crops, which comprises a machine base structure, a roller component, a root crop harvesting and sorting structure and an electric control structure, and the root crop harvesting and sorting structure comprises a crop harvesting and conveying mechanism and a crop sorting and conveying mechanism. The crop harvesting and conveying mechanism comprises a crop lifting and conveying frame structure, a crop clamping device arranged on the upper portion of the crop lifting and conveying frame structure, a soil loosening mechanism arranged at the side end of the bottom of the machine base structure and a crop mud removing mechanism arranged below the crop lifting and conveying frame structure. The electric control structure comprises a main drive stepping motor arranged on the upper portion of the machine base structure and the idler wheel assembly, an energy converter arranged on the upper portion of the machine base structure, a clamping drive motor arranged on the crop lifting conveying frame structure and a solar conversion plate arranged on the upper portion of the crop lifting conveying frame structure. The agricultural production efficiency is improved, the labor cost is reduced, and agricultural technical innovation is promoted.

The invention provides an information processing method and device, a storage medium and electronic equipment, and relates to the field of intelligent logistics and the field of artificial intelligence. The method comprises the steps that a logistics bill feedback message sent by a client side is analyzed, logistics bill defect information is obtained, and the logistics bill defect information represents the defect of a target logistics bill corresponding to the logistics bill feedback message; determining a target defect type of the target logistics order according to the logistics order defect information; determining a target server corresponding to the target defect type; generating a target logistics bill defect feedback message according to the target defect type and the logistics bill defect information; and sending the target logistics sheet defect feedback message to the target server.

The application provides a kind of underwater structure apparent disease identification method and system based on deep learning, wherein, method includes: according to the combination of fusion model and target recognition model, generate the pre-set underwater structure apparent disease identification model;Underwater apparent disease is identified by the pre-set underwater structure apparent disease identification model;The fusion model is built by improved CycleGAN model and multi-scale Retinex algorithm (MSR) network, for converting underwater image into clear and clear image with obvious features;The target recognition model is obtained by YOLOv5 model, for realizing the positioning and classification of underwater structure apparent disease.The present application solves the problems of inaccurate classification and low recognition accuracy of underwater structure apparent disease by the underwater structure apparent disease identification model, caused by factors such as camera imaging blur, insufficient contrast, dispersion and noise in complex water area.

The application provides a die cutting and hot stamping equipment intelligent state monitoring and fault diagnosis system and method, and relates to the field of intelligent monitoring.The method comprises the following steps: collecting working parameters of multiple key parts of the die cutting and hot stamping equipment, constructing a time sequence collection window, slidingly collecting the working parameters, and obtaining characteristic information reflecting the equipment state; based on the characteristic information, constructing an anomaly detection model, performing anomaly detection on the equipment state, obtaining an anomaly score, and judging whether the equipment state is abnormal according to the anomaly score; for the characteristic information judged as abnormal, constructing a fault diagnosis model based on the fault type to which the characteristic information belongs, performing fault diagnosis on the equipment state, and generating a diagnosis result; and generating a comprehensive diagnosis and operation and maintenance decision report according to the diagnosis result.The application realizes comprehensive perception of the internal state of a closed host through multi-sensor collaborative monitoring and dynamic time sequence collection, breaks through the limitations of traditional monitoring, and provides accurate data basis for early fault warning and predictive maintenance.

The invention discloses an uplink service message identification processing method and device, a terminal and a medium. The method comprises the following steps: acquiring core feature information corresponding to an uplink service message; obtaining a target message core data structural body according to the core feature information; obtaining a PDU session identifier corresponding to an uplink service message based on the target message core data structure body; obtaining a QoS flow identifier based on the PDU session identifier and the target message core data structure body; based on the QoS flow identifier, obtaining an uplink service message after scheduling processing; performing query processing on the QoS flow identifier to obtain a target packet data convergence protocol instance; and completing a QoS identification processing flow of the uplink service message based on the target packet data convergence protocol instance. The invention aims to realize rapid QoS identification, classification and processing of the uplink service message, improve the message processing efficiency and accuracy, and reduce the system resource overhead.

The invention relates to the technical field of virtual games, and discloses a self-learning virtual display method and system based on external cause stimulus input, and the method comprises the steps: monitoring and obtaining a game process state and external cause stimulus input data after normalization quantization processing in real time; generating corresponding original picture data according to the game process state and the exogenous stimulus input data; configuring a choice box to carry out frame selection on the original picture data to obtain sampling picture data; inputting the sampled picture data into the trained mode recommendation model, and obtaining a classification result output by the mode recommendation model; configuring a game virtual mode according to a classification result; a large number of training samples with flexible and variable specifications can be provided for an original mode recommendation model in a training stage, sampling picture data of a large number of players is obtained in combination with a cloud end, classification accuracy is stably improved, individual requirements of the players are considered during classification, game experience of the players is comprehensively improved, and the user experience of the players is improved. And a player can obtain better game experience in the game.

The present invention is applicable to the field of electric power technology, and provides a method, device and electronic device for classifying electric meter faults based on a support vector machine. The method comprises: obtaining the operation information of the target faulty electric meter, inputting the operation information into a pre-trained support vector machine classification model, and obtaining the fault type of the target faulty electric meter; wherein the training process of the support vector machine classification model is: obtaining training data; iteratively optimizing the parameter combination of the support vector machine through a population optimization algorithm, and before reaching a preset number of iterations, using the locust algorithm and the firefly algorithm to jointly update the individual position, and after reaching a preset number of iterations, using the locust algorithm to update the individual position, and obtaining the optimal parameter combination of the support vector machine, thereby constructing a support vector machine classification model. The present invention can reasonably predict the fault type of the electric meter when a fault occurs to the electric meter.

The application discloses a multi-modal radio frequency authentication method based on a multi-scale signal representation, which comprises the following steps: firstly, pre-processing the original IQ signal of a target device received to obtain an instantaneous envelope signal; carrying out multi-scale decomposition and denoising processing on the instantaneous envelope signal to obtain a denoised envelope signal; constructing a multi-modal data set according to the original IQ signal and the denoised envelope signal; carrying out feature extraction and fusion on the multi-modal data set through a pre-trained target feature extraction network to obtain a fused feature representation; and carrying out classification on the fused feature representation through a pre-trained target classification network to output a classification result corresponding to the target device. The amplitude, frequency and time-frequency energy distribution information can be complementarily fused by constructing the multi-modal data set; the multi-modal features are extracted and fused through the target feature extraction network, so that the information loss is effectively avoided; and the target classification network is used for rapid classification, thereby reducing the calculation cost and ensuring the accuracy of identification.

The present invention discloses an early warning method and system for geological disaster monitoring, and relates to the technical field of geological disaster monitoring. The method includes: constructing a disaster monitoring framework; determining the target disaster category and disaster level; importing the target disaster category and the corresponding disaster level into a risk analysis model to generate first disaster risk prediction information; importing the disaster-prone body distribution data in the basic information into a preset vulnerability assessment model to generate disaster-prone body vulnerability assessment information; obtaining and importing the historical disaster monitoring data of areas with the same geographical characteristics into a preset risk analysis model to generate second disaster risk prediction information; optimizing the preset early warning model to obtain a target early warning model; collecting and importing the geological actual data of the target area into the target early warning model to generate monitoring early warning information. The present invention combines data from multiple levels related to geological disasters to conduct accurate and comprehensive analysis, and then conducts efficient geological disaster early warning.

The invention provides an intelligent detection method and system for workpiece surface defects. The method comprises the following steps: carrying out real-time image acquisition on a workpiece conveyed on a production line; performing preprocessing through an end-to-end denoising network model; inputting the denoised and restored new workpiece image into a feature extraction deep learning model, and extracting surface deep features of the workpiece image; inputting the deep features into a surface defect identification network model, carrying out classification processing on the deep features, and identifying various defect types on the surface of the workpiece; and evaluating the overall quality of each workpiece according to the types, the number and the severity of the defects identified on line. According to the invention, the definition and accuracy of the image are improved, the identified defects can be classified, it is ensured that only qualified products are output in the production process, the overall quality and safety of the lithium battery pole piece are effectively improved, and the efficiency of a production line is remarkably improved.