598results about How to "Accurate classification" patented technology

The invention provides a method and system for enhancing wafer detection in a semiconductor manufacturing process, and relates to the technical field of wafer detection, and the method comprises the steps: transmitting dual-frequency laser to the surface of a wafer to form a controllable overlapping region, and collecting a beat frequency signal to obtain initial height information; carrying out adaptive filtering processing on the beat frequency signal, reconstructing a three-dimensional contour of the surface of the wafer, and generating an initial defect distribution diagram; and determining a secondary detection area according to the initial defect distribution diagram to perform orthogonal scanning, identifying and rejecting pseudo defect signals, extracting defect features, and determining defect cause types. According to the invention, the accuracy and efficiency of wafer defect detection are improved, and the semiconductor manufacturing quality can be improved.

The invention provides a product surface printing quality detection method based on industrial vision, which comprises the following steps: acquiring paper type and ink type information used by a printed matter, and extracting material spectral characteristic parameters of a paper and ink combination from a pre-established material spectral characteristic database, comprising scattering reflection characteristics of the paper surface and absorption reflection characteristics of ink; for the area with the quality defect, analyzing the spectral data of the area, extracting refined spectral characteristics, accurately classifying defect types through a deep learning model, and analyzing the influence of paper and ink material characteristics on a defect forming mechanism; according to the defect type and the position information, similar cases are retrieved from a pre-established defect knowledge base, a defect cause analysis result and an improvement suggestion are obtained, the material spectral characteristic parameters are matched with defect characteristics, and an evaluation result of the influence degree of the material characteristics on defect formation is obtained.

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

The invention provides a multi-source information fused virtualized network fault rapid positioning method, and relates to the technical field of electric digital data processing, and the method comprises the steps: classifying and sorting historical fault events, constructing a historical dynamic evaluation model, correcting a calibration index, capturing equipment performance changes and abnormities, and enhancing the fault recognition capability. Similar faults are accurately classified and preferentially processed according to severity; in the real-time monitoring stage, real-time multi-source and abnormal data are combined, a real-time dynamic evaluation model and a correction calibration index are calculated, a ratio is applied to calculate a fine adjustment strategy, the real-time performance and accuracy of fault positioning are remarkably improved, and network dynamic changes are quickly responded. And carrying out difference analysis on the adjusted real-time model and the historical model, calibrating a preliminary fault positioning result, and improving the positioning precision and reliability.

The invention discloses a method for identifying impurities and bubbles in a wine bottle based on multi-feature comprehensive judgment, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: employing a high-resolution industrial camera to be combined with an LED light source, and continuously shooting multiple frames of images of the wine bottle under the consistent shooting angle and illumination condition; carrying out the preprocessing of the collected image through employing a self-adaptive histogram equalization and Gaussian blur method; extracting the edges of impurities and bubbles in the wine bottle on the image by adopting a Canny edge detection algorithm to obtain an edge image; segmenting the edge image into a plurality of target areas by using a contour detection technology, and extracting possible bubble and impurity areas from the edge image; extracting target area features including circularity, gray average, gray uniformity, texture features and color space; and according to the extracted features, bubbles and impurities are distinguished by applying a comprehensive judgment rule. According to the method, the bubbles and the impurities are comprehensively judged by adopting multi-feature combination, so that the accuracy and the robustness of detection are greatly improved.

The invention discloses an epilepsy electroencephalogram signal recognition method, system and device and a storage medium, and the method comprises the steps: obtaining an electroencephalogram signal, and calculating phase synchronization information between different channels according to the electroencephalogram signal as an edge feature; filtering the electroencephalogram signals, respectively calculating and extracting time domain features, dynamic features and phase amplitude coupling features corresponding to different wavebands of each channel, and fusing the features into node features; and integrating the obtained edge features and node features into a graph, performing classification by using a graph attention network model, and performing judgment and recognition on the electroencephalogram signals according to a classification result. The invention provides a classification method which is high in performance, has priori interpretability and is used for epilepsy signal identification and prediction, not only considers an interaction relationship among different channels, but also pays attention to and extracts deep features of time domain, dynamics, cross-frequency coupling and the like of nodes, and is more accurate in classification of electroencephalogram signals in different periods.

The invention discloses a road disease detection system and method based on multi-source data fusion. The system comprises a data acquisition module, a data preprocessing module, a disease detection module, a three-dimensional modeling module, a data analysis module and a maintenance module. The data acquisition module is used for acquiring road surface data and sending the acquired data to the data preprocessing module; the road surface data comprises road data, road disease data, road vehicle data, non-motor vehicle data and pedestrian data, compared with the prior art, more comprehensive and more accurate detection of road diseases is realized by fusing multi-source data; by means of multi-dimensional data acquisition of radar data, video data, three-dimensional point cloud data, geographical location information and the like, the limitation of a single data source is overcome; the data preprocessing module can effectively remove noise and abnormal values, accurately classify and mark diseases, and fuse data collected by different sensors, so that the quality and integrity of the data are improved.

The invention discloses a wind power plant equipment fault intelligent diagnosis method and system. The method comprises the following steps: acquiring multi-dimensional sensor data of wind power plant equipment; carrying out preliminary screening on the data by utilizing an edge analysis algorithm, and determining data needing to be further diagnosed; the screened data are input into a pre-constructed fault diagnosis model, the data are fused through a multi-modal deep learning model in the pre-constructed fault diagnosis model, and then a fault occurrence area is determined through transfer learning, domain adaptation and a multi-agent reinforcement learning framework; meanwhile, the causal inference engine and the knowledge graph enhanced neural symbol inference module are responsible for deep processing and fault diagnosis. And finally, inputting the determined fault area and the diagnosis result into a dynamic system health index calculation module to generate a final fault diagnosis result. According to the method, the diagnosis efficiency and accuracy of the equipment fault of the wind power plant are remarkably improved, and a powerful guarantee is provided for stable operation of the wind power plant.

The invention discloses an automatic fine ore sorting method and system based on XRT (X ray tomography) and hyperspectrum, which are used for realizing comprehensive fusion of ore surface and internal information by combining X-ray tomography and hyperspectral imaging technologies so as to improve the recognition precision and the sorting efficiency. XRT is used for extracting the internal structure and density characteristics of the ore, hyperspectral imaging is used for identifying the mineral composition characteristics of the ore surface, and information complementation is achieved. The system adopts a multi-modal convolutional neural network to perform independent feature extraction on XRT and hyperspectral data, and the extracted features are fused through a deep residual network. And the fused features are processed by a cross-modal attention mechanism to ensure that key features of different modals are fully integrated and optimized, and finally high-precision ore classification and sorting are realized. According to the method, the limitation of a single data source on feature extraction is overcome, the ore recognition and sorting precision is greatly improved, and the refined and intelligent development of ore sorting is promoted.

The invention provides a method for creating a structured document based on a deep learning model, and relates to the technical field of data processing, and the method comprises the steps: obtaining basic text information collected by a user, obtaining text data, fragmenting the text data, obtaining text fragmented data, and creating a structured document according to the text fragmented data. Analyzing the structures of the sentences in the paragraphs, determining keywords in the sentences, analyzing the logical relationship between the sentences in the paragraphs, associating the sentence keywords in the paragraphs, analyzing the association degree between the paragraphs in the chapters, identifying core keywords of the chapters, obtaining a chapter keyword data set, and analyzing the field involved in the text. The method comprises the steps of extracting field information of a text to obtain a text keyword data set, constructing a structured document model based on a graph neural network model, and inputting the text keyword data set and text data into the structured document model to obtain a structured document. According to the method, the structured document can be constructed through the deep learning model.

The invention, which relates to the technical field of social emotion analysis, discloses a university social negative emotion characterization analysis system comprising a data acquisition and preprocessing module, a feature extraction and anomaly detection module, an intelligent perception and negative emotion characterization module, and an anomaly risk assessment and response module. Emotional feature information is acquired in real time based on a multi-dimensional data source, and the acquired emotional feature information is cleaned and preprocessed. According to the method, by calculating the data consistency offset coefficient and the strong correlation coefficient, the multi-collinearity problem among multi-dimensional data features is solved, and instability of the model regression coefficient is avoided. And the system identifies abnormal correlation in real time and combines risk threshold classification processing to ensure robust model output. An analysis set is established by continuously collecting data, long-term emotion trend analysis is supported, personalized responses such as reminding, intervention or emergency measures are provided according to risk levels, and accurate management and timely adjustment of student emotional states are achieved.

The invention relates to the technical field of fan blade detection, and provides a wind power plant fan blade detection method and system based on three-dimensional point clouds, and the method comprises the following steps: carrying out the multi-angle scanning of a fan blade through a laser scanner, and obtaining the three-dimensional point cloud data of the fan blade; performing registration processing on the three-dimensional point cloud data, and unifying the three-dimensional point cloud data into the same coordinate system to obtain registered point cloud data; performing block acceleration processing on the registered point cloud data by adopting an octree partitioning algorithm to obtain block acceleration point cloud data; performing feature extraction and feature segmentation on the block acceleration point cloud data to obtain a key feature region of the fan blade; performing defect identification analysis on the key feature region based on a point cloud network enhancement model to obtain a defect detection result, the defect detection result comprising a defect position and a defect type; and generating a detection report containing the defect position and the defect type, and visually displaying the detection report. According to the invention, the integrity of data acquisition and the precision of defect identification are improved, and the efficiency of fan blade detection is improved.

The invention discloses an edge-based open vocabulary segmentation model target identification method. The method comprises the steps of obtaining a target image; initializing Gaussian white noise as a noise contour mask pattern of a target; inputting the target image and the noise contour mask image into an open vocabulary segmentation model to execute the following operations: extracting multi-scale features of the target from the target image and the noise contour mask image; encoding the noise contour mask pattern to obtain encoding features; the multi-scale features are used as condition features to be fused with the coding features, and fusion features are obtained; predicting a de-noised contour mask graph of the target according to the fusion features; and according to the de-noised contour mask graph and the multi-scale features, a single full connection layer is used to predict classification and positioning of the target. According to the method, target identification based on the open vocabulary segmentation model can be effectively and quickly completed.

The invention discloses a Transform remote sensing semantic segmentation method based on an adaptive dynamic attention mechanism, and relates to the technical field of the adaptive dynamic attention mechanism, and the method comprises the following steps: obtaining a remote sensing image data set, and carrying out the data marking and data enhancement; adjusting the remote sensing image into a model input size and a pixel value unified specification, and generating a standardized data set; feature embedding is generated based on a preset embedding module, and position coding is added to enhance position information for decoding; correcting the decoding process by using a self-attention and cross attention module; combining different scale features with continuously iterated updated adaptive weights to obtain a fusion feature value; constructing a multi-task joint loss function based on the to-be-solved problem; refining the fusion feature value through a segmentation module, and generating predicted values of different sub-tasks; according to the method, the problems of information loss and inconsistency possibly occurring during feature fusion in a multi-scale task in a traditional method are solved.

The invention discloses a spatial-spectral combined hyperspectral image classification method based on a multi-scale adaptive attention mechanism, and the method comprises the steps: firstly carrying out the extraction and fusion of features of different scales through a multi-scale feature fusion module, and comprehensively capturing the detailed spectral information of a hyperspectral image; secondly, dynamically adjusting a feature extraction process by using an efficient self-adaptive spectrum-space feature extraction module, and optimizing fusion and representation of spectrum-space features; and finally, enhancing the ability of the model to understand the context relationship in the image by using the context-aware fusion network. The three modules provided by the method are based on a deep learning framework, a convolutional neural network in deep learning can utilize multiband rich spectral information, and the method is suitable for hyperspectral remote sensing image data sets with different spatial resolutions, including a foreign hyperspectral data set and a domestic hyperspectral data set. The method has high adaptability and transportability, and can meet the requirement of image classification more easily.

The invention belongs to the technical field of computer vision and artificial intelligence, and discloses a combined zero sample image classification method based on hierarchical feature fusion. According to the method, a solution based on hierarchical feature fusion is innovatively provided for the technical difficulty of combined zero sample image classification. According to the method, features of different depths in a CLIP model visual encoder are selected and subjected to hierarchical fusion, multi-level and multi-scale visual information is effectively extracted, the fused features are further used for visual and semantic cross-modal interaction, and the understanding ability of the model for complex combinations is remarkably improved. In addition, by introducing a specific loss item, attributes and object features are effectively separated, and the feature aliasing problem is avoided. In a combined zero sample image classification task, the method shows excellent generalization ability and recognition effect, and can significantly improve the classification performance of the model for unknown complex combined images.

The invention discloses a multi-modal learning automatic complaint content analysis and classification method and system, and relates to the technical field of semantic analysis, and the method comprises the steps: collecting multi-modal complaint data, and carrying out the preprocessing of the collected multi-modal complaint data; extracting features of the preprocessed multi-modal complaint data, and fusing the features of different modal data; constructing a complaint content classification model by using the fused features, carrying out model training, and evaluating and optimizing the trained model; and deploying the optimized model for real-time classification. According to the multi-modal learning automatic complaint content analysis and classification method provided by the invention, the complaint content is quickly and accurately classified, and a targeted processing strategy is provided according to the main category, the emotional tendency and the specific theme of the complaint. And an emergency response mechanism is automatically triggered to ensure that problems are processed in real time and effective utilization of resources is ensured. Decision rules are continuously optimized from historical data learning, and the intelligent level of a processing strategy and the customer satisfaction degree are improved.

The invention relates to the technical field of tourist route recommendation, in particular to a tourist route recommendation system and method based on big data. The method comprises the following steps: collecting travel demand data and basic sign information of a user, and performing hierarchical analysis on a demand to obtain master / slave demand data; then, through demand behavior intersection analysis, muscle soreness intensity is simulated in combination with user physical sign data, and the physical degeneration rate is further estimated; based on the physical decline rate, making a rest strategy, and optimizing distribution and adjustment of tourist routes; and finally, transmitting the adjusted tourist route data to a user terminal. According to the invention, the tourist route recommendation technology is improved, so that the tourist route recommendation technology is more perfect.

The invention discloses an electric power fault diagnosis and prediction system based on big data, particularly relates to the field of intelligent diagnosis of an electric power system, and aims to solve the problems of fault response delay and insufficient diagnosis precision. Localized intelligent diagnosis of power faults is realized, and stable operation and rapid recovery of a power system are guaranteed; a priority classification and sorting uploading mechanism is combined to ensure that key data is transmitted preferentially, diagnosis errors caused by delay are reduced, and the analysis stability of a central dispatching center is enhanced; through comprehensive judgment of a global deviation aggregation index and a trust stability harmonic measurement index, accurate classification of local node diagnosis controllability is realized, more accurate key data is guaranteed to be obtained, finally, the fault response capability of a system and the safety of a power system are improved, and powerful technical support is provided for intelligent diagnosis and maintenance.

The invention discloses an image recognition method for electric energy meter recognition. The method comprises the steps that an image with a metering electric energy meter display screen is acquired; preprocessing the image for correcting light reflection distortion of the image; performing text detection, and identifying and positioning a text region of the preprocessed image; character information identification of the concerned text area is carried out; performing layout analysis, and identifying digital information corresponding to different elements in the layout; performing NER detection filtering to obtain entity data in the image; and displaying the entity data. According to the method, the image is preprocessed for image reflection distortion correction, so that the image recognition result is more accurate. According to the method, the Fast R-CNN method is adopted for layout analysis, and different elements such as characters, charts and pictures in the layout can be quickly and accurately positioned and classified.

The invention discloses a DoH encryption malicious traffic detection method based on a deep learning model, and relates to the technical field of network security, and the method comprises the steps: obtaining domain name system DoH traffic based on HTTPS; and inputting the DoH traffic into a pre-constructed traffic detection model to obtain a malicious traffic detection result, the traffic detection model being constructed based on a binary cross entropy and a focus loss function, and the malicious traffic detection method and apparatus can improve the detection precision of the malicious traffic.

The invention relates to the technical field of geological surveying and mapping, in particular to a multi-source data fusion geological surveying and mapping system which comprises a multi-dimensional data collection module, a data calibration and synchronization module, a geological image enhancement module, a data fusion and model generation module and a visualization and interaction module. The data calibration and synchronization module carries out timestamp calibration and geographic position processing on data, the geological image enhancement module enhances geological images, the data fusion and model generation module fuses the processed data and constructs a geological model by using a modeling technology, and the visualization and interaction module provides a multi-dimensional data interaction platform. Through the geological texture recovery sub-module, visual quality of images is improved, reliability and accuracy during geological data and resource evaluation are enhanced, polarized light data are collected through the polarized image processing sub-module, key information such as surface material roughness is revealed, and surface and underground geological processes can be better understood and explained.

The invention relates to the technical field of medical data processing, in particular to a multi-modal medical data classification method, model and equipment and a storage medium. The method comprises the following steps: firstly, carrying out coding alignment processing on original multi-modal medical data to obtain aligned multi-modal features, then converting the aligned multi-modal features into graph data, extracting common features among multiple modals and specific features of each modal, and finally, carrying out multi-modal feature extraction. Finally, the original multi-modal medical data are classified according to the common features and the specific features, the common features reflect the relevance between the multi-modal data, and the specific features can reflect the specificity of modals, so that accurate classification of the multi-modal medical data can be achieved by comprehensively utilizing the common features and the specific features.

The invention discloses a pet peculiar smell detection method and device and a storage medium. The pet peculiar smell detection method comprises the following steps: collecting data in a to-be-detected environment in real time through a sensor array; performing temperature compensation on the sensing signal through a weighted linear temperature compensation algorithm and a weighted adaptive whale optimization algorithm; setting a threshold value, comparing the compensated sensor signal amplitude with the set threshold value, and when any sensor signal amplitude is triggered, starting to collect sensor data with a fixed length; inputting the collected sensor data with the fixed length into a self-adaptive time convolution GSA-TCN network model based on a gating convolution kernel rarefaction strategy for classification and identification; when it is judged that the pet excretes peculiar smell, table look-up, interpolation and concentration calculation are carried out according to the maximum value of the sensor data with the fixed length, and the detection result and the concentration value of the environment to be detected are output. The pet peculiar smell can be effectively detected, a series of problems caused by the pet peculiar smell can be solved, and the application scene is wide.

The invention relates to a visual analysis method and device for multiple internal corrosion failure types of a pipeline. The method comprises the following steps: inputting internal corrosion failure picture data to be recognized into an internal corrosion failure type recognition model to obtain a predicted internal corrosion failure type and a feature map of the last convolutional layer; analyzing the predicted internal corrosion failure type and the feature map of the last convolutional layer by using Grad-CAM to obtain a feature region thermodynamic diagram; based on the predicted internal corrosion failure type and the characteristic region thermodynamic diagram, obtaining the contribution degree of the characteristic of each characteristic region to an identification result; wherein the internal corrosion failure type identification model is obtained by the following steps: obtaining a pipeline internal corrosion failure data set; inputting the internal corrosion failure data set into an initial internal corrosion failure type identification model for training to obtain a trained internal corrosion failure type identification model; wherein the initial internal corrosion failure type identification model is constructed by using a Resnet18 convolutional neural network.

The invention belongs to the technical field of enterprise relation extraction, and particularly provides a transfer learning entity relation extraction method, device and equipment based on field self-adaption and a storage medium. The method comprises the steps that one or more source fields are selected; performing pre-training on the selected source field by adopting a deep learning model, and learning a labeled enterprise relationship data set in the source field; selecting a target domain with unlabeled or partially labeled enterprise relational data, and adjusting pre-trained model parameters by using a domain adaptive algorithm to adapt to data features and distribution of the target domain; after field adaptation of target field data features and distribution is completed, a transfer learning algorithm is deployed to carry out fine adjustment on the adjusted deep learning model; verifying the performance of the fine-tuned deep learning model in the target domain; and identifying and extracting the enterprise relationship and the relationship thereof in the text by applying the fine-tuned deep learning model in the target field. And high quality and consistency of the extracted enterprise relationship and the relationship data thereof are ensured.

The invention discloses a combustion chemical reaction kinetic data processing method and system for an ADN-based liquid propellant, and belongs to the technical field of data processing. According to the method, firstly, key information in the combustion process can be comprehensively captured by obtaining a combustion chemical reaction kinetic vector and an element state linkage vector; structured semantic mapping is carried out on the primitive state linkage vector to obtain a reaction state structured vector and a strategy association demand vector, which is helpful for accurate classification and positioning of combustion reaction related information. And the integration confidence weights of the first data and the second data are determined, so that the association degree of the element reaction data and the visual association labels under different integration strategies can be quantified, and the analysis of the combustion process is more scientific and meticulous. The finally determined visual monitoring result can visually present the characteristics of the element reaction data under different strategies, and clear and accurate data support is provided for deeply understanding the combustion mechanism of the ADN-based liquid propellant, optimizing the performance of the propellant and ensuring safe use.

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 glacier jump prediction and data sample enhancement management method, particularly relates to the field of glacier remote sensing monitoring, is used for solving the problem of accurate identification and processing of surface moraine covering type glacier local albedo abnormal effect, and aims at solving the problem of accurate identification and processing of the glacier local albedo abnormal effect by comprehensively analyzing the coupling relationship between spectrum and temperature and the spatial sensitivity of temperature gradient. And accurate identification and processing of the moraine covering glacier local albedo abnormal effect are realized. According to the method, main causes of albedo abnormity can be effectively distinguished, and an abnormal area is corrected in a targeted manner by scientifically selecting an optical and thermal infrared remote sensing fusion mode or an optical and radar remote sensing fusion mode, so that the glacier identification precision and the jump prediction accuracy are remarkably improved. Through multi-level remote sensing data correction and feature extraction, a high-precision data foundation is laid for subsequent analysis; in the process of generating an enhanced sample and optimizing a prediction model, the reliability and response speed of glacier jump prediction are further improved.

The invention relates to the technical field of animal husbandry, and discloses an intelligent live pig behavior recognition system based on multi-modal data fusion, which comprises a data acquisition module, a data preprocessing module, a feature extraction module, a multi-modal fusion module, a behavior recognition module, a data storage and management module and a user interaction module. According to the intelligent live pig behavior recognition system and method based on multi-modal data fusion, the limitation of a single-modal recognition method and the defect that audio information can supplement visual information are overcome by combining data of two modals of video and audio, the recognition accuracy is improved, and meanwhile, by using an improved AVSlowFast model and a GCT channel attention mechanism, the recognition accuracy is improved. The system can effectively fuse visual and auditory features, and further enhance the recognition capability in a complex environment, so that the system can accurately recognize and classify different behaviors of live pigs under various breeding conditions, and the recognition reliability is greatly improved.