1063 results about "Screening method" patented technology

The invention provides an HVAC system temperature control and energy consumption optimization method based on deep reinforcement learning. Through an entropy-based data screening method, a strategy evaluation module and a design reward function, HVAC system temperature control and energy consumption optimization are realized under external condition interference. According to the entropy-based data screening method, the value of data for agent training is calculated through an error formula, high-value data is repeatedly used for agent training, and the training effect is enhanced; the strategy evaluation module is used for further solving the problem of overestimation of a Q value on a double-Q structure, correcting the output of the Q value, reducing the influence of a random Q value, and adding regularization of a strategy and an actual action into a loss function updating process, so that the influence of random noise on the Q value is eliminated, and the accuracy of strategy output is ensured; a reward function for controlling the temperature and optimizing the energy consumption is designed, so that the intelligent agent can balance the contradiction among multiple tasks, and the optimal solution of multi-target task intersection is searched, so that the HVAC system can control the temperature to be always kept in the temperature range, and meanwhile, unnecessary energy consumption is reduced.

The invention discloses an intelligent information screening method and system for a human resource system, and relates to the technical field of human resource systems. The problem that a traditional matching method is difficult to deeply mine semantic association and cannot accurately measure the matching degree of candidates and posts is solved. According to the method, through multi-step intelligent data processing and optimization, the candidate screening efficiency and accuracy are remarkably improved, a semantic analysis technology is adopted to construct a multi-layer topic tree and an emotion analysis model, and deep semantic matching of candidate resumes and position requirements is achieved; meanwhile, candidates are intelligently screened by using a bidirectional semantic matching network, the screening effect is continuously optimized by mining potential high-matching candidates and historical data feedback, bidirectional recommendation is realized through a block chain communication link, the security and efficiency of data transmission are guaranteed, complex enterprise recruitment requirements can be effectively adapted, the recruitment period is shortened, and the recruitment efficiency is improved. The man-post matching accuracy is improved, and the human resource management cost is greatly reduced.

The invention discloses a BERT model-based resume screening method and system, and belongs to the technical field of deep learning and text classification. The method comprises the following steps of: obtaining post demand text data and job seeker resume text data, and preprocessing the post demand text data and the job seeker resume text data; based on a TFIDF-LDA model, subject term extraction and category feature expansion are carried out on the preprocessed text vector; performing word extraction vocabulary filtering on the subject word vector after category feature expansion based on N-gram of information entropy; a deep learning matching degree calculation module is combined to calculate the comprehensive matching degree of the posts and the job seekers, and the resumes of the job seekers are preliminarily screened in combination with a set threshold value; and carrying out resume text classification based on the FE-BERT model to obtain a resume screening result. According to the method, the problems that the ability of candidates is difficult to accurately evaluate and different post requirements cannot be adapted or the talent screening accuracy is low due to the reasons of inaccurate keyword matching, incapability of understanding contexts and the like in the existing resume screening method can be solved.

The invention discloses a quantitative scientific research project screening method based on patent situation analysis, and the method comprises the steps: obtaining patent data, and carrying out the vectorization of a patent text through a pre-trained Chine-BERT model; the method comprises the following steps: performing dimension reduction processing on patent text feature vectors by using a UMAP algorithm, performing clustering analysis on the feature vectors after dimension reduction by using a K-Means + + algorithm, identifying professional technical themes and technical effect themes, merging documents of the same clustering category into a text unit, calculating the importance of each word by using a TF-IDF algorithm, and extracting the feature vectors of the patent text by using the TF-IDF algorithm. Extracting a theme keyword of each cluster; and a technology-effect matrix is constructed based on a clustering result, and a quantitative screening result of the scientific research project is obtained through calculation of a technology life cycle, technology innovation evaluation and market competitiveness evaluation. The objective of the invention is to provide a comprehensive and efficient scientific research project screening method through an advanced semantic understanding patent clustering method, and help to rapidly screen scientific research projects.

The invention relates to the technical field of plant growth-promoting bacterium screening, in particular to a thunberg fritillary bulb growth-promoting bacterium colony screening method and system based on image recognition. The screening method comprises the following steps: establishing a three-dimensional gradient dilution system of a thunberg fritillary bulb rhizosphere soil sample, and collecting a bacterial colony original image under a specific wavelength combination by adopting a multispectral imaging device. According to the method, by establishing a multispectral collaborative imaging mechanism and a dynamic growth modeling system, the technical problems of feature dimension deficiency and space-time correlation fracture in a traditional method are effectively solved. An improved wavelet transform algorithm is adopted to break through the optical interference limitation of an agar matrix, and high-fidelity extraction of bacterial colony intrinsic textures is realized; according to the constructed three-dimensional feature space fusion model, morphological topological parameters, texture entropy distribution and growth differential features are deeply coupled through nonlinear mapping, and the biological correlation of feature representation is remarkably improved.

The invention discloses a multi-mode teenager idiopathic scoliosis screening method based on a back RGB-D image, and belongs to the technical field of image processing and scoliosis screening, and the method specifically comprises the steps: collecting an RGB-D image pair of a subject in an Adams anteflexion posture, carrying out the manual marking of an RGB color image, constructing and training a back key point detection model, and carrying out the detection of the back key point. And establishing a calculation rule of a maximum trunk rotation angle, a minimum trunk rotation angle and a back contour asymmetry index, and establishing an AIS classification rule based on the RGB-D data set, thereby completing AIS classification of the to-be-detected subject. According to the non-contact radiation-free AIS screening method, comprehensive utilization of back two-dimensional and three-dimensional information is achieved by means of data complementation of the RGB mode and the D mode, the problem of feature deficiency in a single mode is solved, and the method has the advantages of being fast, efficient, robust and objective.

The invention provides a method for predicting the quality of a sparse small sample industrial process based on a stacked network model. The method comprises the following steps: collecting end point quality report data of an industrial production process; performing hierarchical processing on the acquired data according to the missing rate, and removing abnormal data in combination with a quartile method and production experience; generating a synthetic data expansion small sample data set by adopting a conditional generative adversarial network; obtaining a first-layer basic model based on an accumulated contribution rate screening method of an SHAP value; constructing a first layer of a stacked integrated learning model and adjusting hyper-parameters by using Bayesian optimization; constructing a Ridge meta learning device to integrate the output of the basic model and constructing a second-layer network; a six-fold cross validation training model is adopted; predicting performance through a multi-index quantitative model based on the test set; and verifying the prediction precision of the end-point phosphorus content and the temperature by using real converter production data. The method can realize high-precision prediction of the end point quality index of the complex industrial generation process, and is beneficial to ensuring the product quality and improving the production efficiency.

The invention discloses an Alzheimer's disease early screening method based on magnetic resonance imaging, and relates to the technical field of magnetic resonance imaging, and the method comprises the steps: obtaining information identity data and magnetic resonance scanning image data of a to-be-detected person; preprocessing the magnetic resonance scanning image data, and calculating a brain area volume and a DTI-ALPS index according to the preprocessed magnetic resonance scanning image data; constructing a brain network and calculating global network attributes and regional node attributes according to the brain network; substituting the information identity data, the brain area volume, the DTI-ALPS index, the global network attribute and the area node attribute of the to-be-tested person into an Alzheimer's disease screening model to calculate diagnosis parameters; and comparing the diagnosis parameter with the optimal diagnosis threshold value to obtain a screening result. According to the method, the brain colloidal lymphatic network function is evaluated by means of multiple high-sensitivity nerve image indexes, and the early screening capability of the Alzheimer's disease is improved.

The invention discloses an Alzheimer's disease auxiliary screening system based on intelligent interaction, particularly relates to the field of computer-aided diagnosis, and is used for solving the problem that in an existing screening method, it is difficult to quantify cognitive performance differences of life knowledge and professional knowledge at the same time. The method comprises the following steps: constructing a task interaction group covering life knowledge and professional knowledge, collecting and coding multi-dimensional interaction operation of a testee in a task process, and generating an interaction vector matrix; further performing jump point identification, vector residual calculation and invalid operation density statistics on the interaction behavior through a preset task logic chain, and quantifying the operation deviation condition of the interaction behavior; respectively generating life and professional cognitive performance indexes based on the analysis result, and constructing a cognitive deviation evolution curve of a difference value of the life and professional cognitive performance indexes along with time change in a set period; and finally, through identifying a continuous rising trend in a cognitive deviation evolution process, auxiliary screening and early warning of asymmetric degradation of cognitive competence are realized.

The invention relates to the technical field of engineering intelligent algorithms, in particular to a jet grouting pile forming quality and construction optimal parameter prediction method and system, and the method comprises the following steps: building a data sample set based on similar historical engineering cases; the construction stratum soil bodies of the jet grouting piles are classified to obtain different stratum soil body categories, and construction process sensitive parameters are obtained; performing an orthogonal test to obtain an orthogonal test result so as to establish a jet grouting pile construction numerical simulation model to obtain a simulation data sample set; a jet grouting pile strength prediction model is constructed, and a jet grouting pile forming quality prediction result is obtained; establishing constraint conditions, and optimizing the pile-forming quality prediction result of the jet grouting pile according to an optimization algorithm to obtain an optimal solution set; and in combination with actual jet grouting pile construction conditions, optimal construction parameters are obtained according to an optimal solution screening method. According to the method, the optimal construction parameters of the jet grouting pile project can be rapidly and efficiently obtained, so that the construction scheme is optimized, and the pile forming quality of the jet grouting pile is guaranteed.

The invention discloses an AI auxiliary screening method based on a mammary gland molybdenum target image, and relates to the technical field of image data identification processing, and the method comprises the following steps: S1, image collection: collecting mammary gland molybdenum target image data of a patient, carrying out the standardization processing, removing the noise in the image, standardizing the gray value, and enhancing the local contrast, and obtaining a structured image data set. According to the AI auxiliary screening method based on the mammary gland molybdenum target image, multiple machine learning algorithms are fused for focus classification, so that the classification accuracy is improved; multiple classification models are constructed in an integrated learning mode, prediction results are fused through a weighted average mechanism and a voting mechanism, model prediction confidence is calculated for weighted fusion, the advantages of all the models are brought into full play, and the limitation of a single model is reduced; the screening accuracy and efficiency of the mammary gland molybdenum target image are improved, the focus detection and classification difficulty is reduced, and the condition that the model has more false negative or false positive results is improved.

The invention discloses a coronary heart disease preliminary screening method and device based on facial feature analysis and a medium, and relates to the technical field of image understanding, and the method comprises the steps: extracting each part sub-region of a human face, and obtaining a tensor image of each sample data through the stacking of the sub-regions; obtaining the flattened feature maps of the tensor images, and integrating the feature maps to obtain a feature matrix of the corresponding sample data; calculating a feature mean value in the image dimension direction according to the feature matrix, and taking the feature mean value as a global feature tensor of a corresponding sample; carrying out dimension reduction processing and nonlinear transformation on the global feature tensor, and carrying out binary classification probability distribution output of relevance between the subregions and the coronary heart disease; performing updating iteration of the classification weight of the sub-region through cross entropy loss function constraint and a stochastic gradient descent optimizer; and performing primary screening of the coronary heart disease through the iterated primary screening model of the coronary heart disease. According to the method, the key feature capturing capability of the model is improved, and then the judgment capability on the coronary heart disease risk is enhanced.

The invention provides a multi-modal large model incremental training data screening method, and relates to the technical field of data processing, and the method comprises the steps: executing modal structure analysis on newly added multi-modal data, extracting each modal vector, calculating a semantic matching degree, and removing samples lower than a preset first threshold value; calculating a multi-level semantic distance between a sample embedding vector and a historical clustering center in a unified semantic space, and dividing a core semantic region sample, a boundary semantic region sample and a discrete semantic region sample according to the change rate of the multi-level semantic distance; performing semantic fine-grained alignment on the boundary semantic region samples, when multimodal unstable distribution is detected, executing local context reconstruction to repair semantic deviation, and if the multimodal unstable distribution is still unstable, removing the semantic deviation; performing multiple rounds of small-batch reasoning, calculating a semantic stability coefficient based on a semantic prediction result, and when the semantic stability coefficient is lower than a preset second threshold value, determining that the sample is a potential drift sample and removing the potential drift sample; constructing an incremental training data set; according to the method, the autonomy and accuracy of incremental training data screening are improved.

The invention provides a siRNA gene inhibition efficiency screening model construction and training method, a siRNA gene inhibition efficiency screening device and a siRNA gene inhibition efficiency screening method. The construction and training method comprises the following steps: acquiring first sequence information of target mRNA and second sequence information of siRNA; obtaining first space image information of the target mRNA and second space image information of the siRNA; constructing a siRNA gene inhibition efficiency screening model, and training a first neural network model by using the first sequence information and the second sequence information to extract sequence features; training a second neural network model by using the first spatial image information and the second spatial image information to extract spatial structure features; and fusing the sequence features and the spatial structure features, and training a third neural network model by using the fused features. Therefore, the accuracy of screening the siRNA with the inhibition efficiency on the target gene can be improved.

The invention provides a detection and identification method and device for a mixed text image, and the method comprises the steps: collecting an original image set, constructing a data set, and carrying out the preprocessing of the data set; based on a convolutional network classifier, a CRAFT detection model and a TROCR recognition model, performing model training by using the data set to generate an optical character recognition model; acquiring a test set in the data set, and performing text detection and type recognition on the test set by using the optical character recognition model; performing picture lifting processing on the test set; based on the type recognition result, performing text recognition on the processed test set by using an optical character recognition model to generate a recognition result; fusing the identification results to generate a fused identification result; using a multiple screening method to optimize the fused recognition result, and generating a unique text recognition result; and comparing the unique text recognition result with the corresponding text picture content, and calculating and counting the recognition accuracy of the optical character recognition model.

The invention discloses an intelligent literature screening method and system based on zero sample voters. The method comprises the following steps: expanding a literature set based on seed literatures, constructing a classification system comprising a plurality of zero sample voters, screening literatures related to a target topic through a majority voting mechanism, and iteratively expanding the literatures to obtain more literatures related to the target topic. The zero sample voting device integrates subject term matching, language model pre-training, multi-large language model voting and a semantic embedding vector technology, adaptively determines a threshold value in combination with an improved binary search algorithm, and realizes high-precision classification without training data. The system supports parallel processing and intelligent API management, and the processing efficiency of a large-scale literature set is remarkably improved. The method is suitable for the fields of academic research, literature retrieval and the like, can quickly construct a large-scale high-correlation literature information base, and particularly meets the retrieval requirements of emerging technologies or interdisciplinary themes.

The invention discloses microminiature needle body high-speed visual screening equipment and a screening method thereof, and belongs to the technical field of industrial automatic detection and sorting. The equipment comprises an equipment frame, a feeding module, a visual identification module, a grabbing module, a control module and a material receiving module. The feeding module is used for conveying to-be-screened needle bodies. The visual identification module performs image acquisition and model identification on the needle body; the grabbing module is provided with a plurality of grabbing clamping jaws, can move in the horizontal direction and the vertical direction under the driving of the control module, and grabs a plurality of needle bodies of the same model at the same time at a time. The material receiving module comprises a plurality of material receiving boxes and a transposition driving mechanism for driving the material receiving boxes to move so as to align the target material receiving box to the grabbing module. The equipment disclosed by the invention can be widely applied to high-efficiency sorting of micro-miniature needle bodies with the diameters ranging from 0.3 mm to 3mm and the lengths ranging from 3mm to 77mm, has high precision, high speed and high reliability, and is suitable for large-scale production and multi-variety and small-batch production requirements.

The invention belongs to the technical field of molecular biomedicine, and provides a colorectal cancer early screening method based on multi-omics sequencing, which comprises the following steps: collecting a plasma sample to be detected, collecting sequencing data to be detected, and classifying a colorectal tumor early screening model. The training process of the colorectal tumor early screening model comprises the steps of original sequencing data acquisition, quality control and human reference genome comparison, reference methylation data acquisition, tumor specific region screening, plasma cfDNA sequencing data acquisition, coordinate determination sequencing data acquisition, methylation feature set screening and terminal motif feature screening. And carrying out breakpoint motif feature screening, feature merging and model training. By constructing the colorectal tumor early screening model, the non-invasive colorectal cancer detection method with high cost effectiveness is realized, the economic cost of sequencing is reduced, and the accuracy and sensitivity of detection are remarkably improved.

The invention discloses an early lung cancer screening method based on transfer learning. The method comprises the following steps: S1, obtaining preprocessed three-dimensional volume data; s2, generating a multi-scale enhanced feature map; s3, obtaining a preliminary micro-nodule detection result; s4, obtaining a first-stage optimization model; s5, performing second-stage training on the first-stage optimization model by adopting a double-normal-form transfer learning strategy to obtain a transfer optimization model; s6, embedding an adversarial domain adaptive module in the migration optimization model to obtain a cross-domain robust model; and S7, in a clinical reasoning stage, outputting a micro-nodule detection result for the new chest low-dose spiral CT original image data by using the cross-domain robust model. According to the invention, the model can adaptively emphasize the local gradient difference between the lung micronodule and the background texture, thereby improving the discrimination capability of the weak boundary region.

The invention provides a literature screening method and device, electronic equipment and a storage medium, and the method comprises the steps: extracting all literature data related to a screening topic from a literature library, and downloading a full text of the literature data and a corresponding abstract part; generating a cue word according to the screening theme, inputting an abstract part corresponding to the literature data and the cue word into an intelligent screening model, judging whether the literature data meets a PICO requirement or not through the intelligent screening model, and outputting a first screening result; the cue words and the literature data are input into an intelligent screening model in a full text mode, whether the literature data meet the PICO requirement or not is judged through the intelligent screening model, a second screening result is output, and the intelligent screening model is one or more large language models with the natural language understanding ability; and performing cross validation according to the first screening result and the second screening result, and screening literatures meeting PICO requirements or related to the current theme by using a large language model, thereby improving the accuracy and efficiency of literature screening.

The invention provides a cancer patient gene methylation feature screening method based on DQN reinforcement learning, which converts a gene methylation feature screening problem into a reinforcement learning problem by constructing a deep Q network model, and dynamically selects the most representative methylation feature by taking maximization of prediction accuracy as a target. The method comprises the following steps: firstly, preprocessing gene methylation data of a cancer patient, then continuously optimizing a feature selection strategy in a multi-round training process through a DQN model, and finally screening out key methylation features closely related to cancer diagnosis and prognosis. The method can effectively reduce the feature dimension, improves the generalization ability of the model, and has wide application prospects in early diagnosis, personalized treatment and prognosis evaluation of cancers.

The invention discloses a grain defective product detection method combining fingerprint spectrum and finite element analysis, and particularly relates to the technical field of grain quality detection.The grain defective product detection method comprises the following steps that grain chemical and physical characteristics are extracted through a fingerprint spectrum and a finite element model, and key characteristic vectors are obtained through dimension reduction screening; on the basis of defective grain grade labels, mutual information is calculated, cross-modal analysis is carried out, and a strong dependency feature group is identified; feature sparsity and stability evaluation are combined, features are optimized by adopting a self-adaptive screening method, a food quality knowledge graph is finally constructed, and intelligent detection and quality evaluation of defective food are realized; according to the method, the accuracy of a detection model, namely a grain quality knowledge graph, is improved through feature sparsity and feature stability evaluation, an automatic grain defective product detection and recognition mechanism is constructed by utilizing a multi-modal information fusion method of fingerprint spectrum and finite element analysis and combining a mutual information analysis and dynamic feature screening algorithm, and the detection accuracy is improved. And the dependence on manual intervention and experience judgment is reduced.

An interactive depression preliminary screening method based on a large language model comprises the steps that data collection and preprocessing are conducted, a divided data set is used for conducting model fine adjustment on an open-source pre-trained Chinese large model, and the large language model is obtained; performing topic control in a dialogue process by using a finite-state machine, and performing topic classification and severity judgment on user answers by calling a large language model; dialogue content of a user is received and converted into a text to be transmitted back to a server side, a finite-state machine judges and gives a score according to topic classification and severity of a large language model, the next action is judged based on the score, a next question returned to the client side is obtained, and meanwhile, the large language model is called to perform psychological comfort for answer content of the user; after all the topics are inquired, the score of the user in each type of topics is calculated, and a test result is output. According to the application, the screening efficiency of the depression patients is improved.

The invention relates to a clinical test item subject intelligent screening method and device, a medium and equipment, and relates to the technical field of clinical trials, and the method comprises the following steps: inputting each processed data into a preset subject screening model to obtain a target subject; screening out evaluation indexes easy to be abnormal from the curative effect evaluation indexes corresponding to the target clinical test item, and determining corresponding easy-to-occur dimension data when each evaluation index easy to be abnormal is abnormal; when easy-to-occur dimension data exist in the patient data of each target subject, determining the corresponding easy-to-occur dimension data as key dimension data, and verifying the corresponding target subject according to the key dimension data and the easy-to-anomaly evaluation index of the key dimension data existing in the corresponding easy-to-occur dimension data; and if the verification is passed, determining the corresponding target subject as a final subject of the target clinical test item. The method has the effect of improving the accuracy of the screening result.

The invention relates to the technical field of biological information, in particular to a translation efficiency prediction method, a screening method, a model training method and electronic equipment. The translation efficiency prediction method is realized based on a translation efficiency prediction model, and the translation efficiency prediction model comprises an embedding module, a coding module and a prediction module. The method comprises the following steps: acquiring sequence data of messenger ribonucleic acid; extracting features of the sequence data through the embedding module to obtain feature representation of messenger ribonucleic acid; the feature representation is input into the coding module, the input feature representation is subjected to convolution processing through the coding module, a convolution result is coded based on an attention mechanism, and the updated feature representation is output according to a coding result; and performing translation efficiency prediction on the updated feature representation through the prediction module to obtain a translation efficiency prediction result. According to the embodiment of the invention, the translation efficiency of the messenger ribonucleic acid can be accurately predicted with high throughput, the screening efficiency is improved, and the screening cost is reduced.

The invention relates to the technical field of artificial intelligence and thermal power production fault detection, in particular to a thermal power production fault detection data measuring point screening method and system based on a clustering algorithm, and the method comprises the steps: obtaining historical fault data of thermal power plant production equipment, and selecting related measuring points to form a multi-dimensional time series data set; and performing embedding processing on the time sequence data by using the time sequence large model to generate a feature vector with a set dimension. And then, carrying out clustering analysis on the feature vectors by adopting a clustering model to obtain a clustering result. And finally, screening out the measuring points related to the fault points of the production equipment of the thermal power plant according to a clustering result, obtaining a corresponding screening result, and providing support for equipment fault prediction and diagnosis.

The invention relates to a large law model fine tuning data screening method and device and a medium, and belongs to the technical field of artificial intelligence. Generating and forming a preference data set, training a legal quality scoring model by using the preference data set, and dynamically adjusting weights of a simple compliance sample and a complex dispute sample by using a balance focus loss function; performing quality scoring on the candidate law fine tuning data set, calculating a complexity score of the candidate law fine tuning data set, and generating a quality-complexity scoring data set of the candidate law fine tuning data set; and constructing a dependency tree of a grammar dependency relationship, performing clustering analysis on vectorized dependency tree features, and performing cluster division and sorting on candidate law fine adjustment data sets so as to merge the candidate law fine adjustment data sets into final fine adjustment sub-data sets and complete screening. The problems of semantic distortion and training deviation caused by a traditional screening method are effectively solved, and a systematic solution is provided for efficient training of a large model in the legal vertical field.

The invention provides a data set keyword generation and screening method based on a large language model, and belongs to the field of natural language processing and artificial intelligence. The method comprises the following steps: collecting comment text data and known keywords thereof; dividing the text data into blocks; generating preliminary keywords by the large language model; performing preliminary screening on the preliminary keywords in the preliminary keyword list in combination with a TF-IDF algorithm and a TextRank algorithm; and performing semantic and emotion correlation screening on the preliminarily screened keywords through a large language model to obtain final keywords. According to the method, the keyword generation and screening technology is remarkably improved, and the method is particularly suitable for large-scale text analysis tasks needing high precision and high efficiency.

The invention provides an abnormal value screening method based on particulate matter component reconstruction, and relates to the technical field of environment monitoring. The method comprises the following steps: obtaining standard ion component data, standard carbon component data and standard inorganic element component data; obtaining a plurality of reconstruction component data; target PM2.5 data are determined; determining a doubt reconstruction component data judgment result of the plurality of reconstruction component data at each moment; determining a univariate time sequence abnormal point judgment result of each kind of reconstruction component data at each moment; determining a multivariable time sequence abnormal point judgment result of the multiple reconstruction component data at each moment; and determining whether the reconstruction component data at each moment is abnormal data. According to the method, the component reconstruction characteristics under different pollution levels can be evaluated, and the understanding of the model on the relationship among the particulate matter components is enhanced, so that the stability and accuracy of identifying whether the reconstructed component data is abnormal data are improved, the calculation efficiency is optimized, and environment monitoring auditing personnel are assisted to make decisions.

The invention provides a stone curtain wall millimeter wave image rapid defect marking, training and image screening method and system, and the system comprises an image display module which is used for displaying a collected stone curtain wall millimeter wave image; the automatic labeling module is used for carrying out preliminary defect labeling on the input millimeter wave image; the man-machine interaction module provides a user interface to allow a user to check, audit and correct the labeling result; the database result output module is used for outputting the final labeling result in a standard format and supporting multi-dimensional screening and exporting functions; the defect identification model is used for training and identifying defects in the stone curtain wall millimeter wave image based on a deep learning model; and the image screening module is used for evaluating the quality of the image and screening out a high-quality image according to a set threshold value based on a screening algorithm of image quality. Through automatic and intelligent technical means, the stone curtain wall detection efficiency and accuracy are improved, and the safety and durability of the building curtain wall are ensured.