914results about How to "Prevent overfitting" patented technology

The invention provides a multi-modal large model construction and operation method and system for reservoir dam safety. The method comprises the following steps: constructing a training set, wherein the training set comprises a single sample; multi-modal data as model input: sensor data arranged on the dam, historical hidden danger records, engineering technology documents formed in various stages of planning, design, construction and operation of the dam, information resources related to dam safety, geometric and material information of the BIM model, timestamps and spatial position information; the probability value of occurrence of the hidden danger event serving as the training label is obtained; the training set is adopted to train a multi-mode pre-training model based on a Transform framework; performing real-time prediction and early warning on potential safety hazards of the dam; and calculating the actual influence degree, the comprehensive risk score, the dynamically set early warning threshold and the emergency measure suggestion of the hidden danger event according to the probability value of whether the hidden danger event occurs or not output by the model. The scientificity and effectiveness of dam safety monitoring are comprehensively improved.

The invention relates to the technical field of model construction, and discloses a neural network-based frozen soil unfrozen water content detection model construction method and system. The method comprises the following steps: carrying out segmented sampling test on a clay sample in a temperature interval of 0 DEG C to-20 DEG C to obtain a multi-dimensional original data set, and carrying out standardization and principal component analysis on the data set to obtain a standardized feature vector; and performing three-stage classification marking on the feature vectors to obtain a training data matrix. A deep neural network is adopted to carry out five-fold cross validation training, and a prediction model of three hidden layers is constructed. And performing correction calculation on model output according to soil mineral composition and porosity parameters, and finally identifying an abnormal value through root-mean-square error analysis and a three-time standard deviation principle to obtain a standardized prediction result. According to the method, the mapping relation between the thermal parameters and the unfrozen water content is established, correction is carried out in combination with the soil body characteristic parameters, and the technical problem that the prediction precision of the unfrozen water content is not high in the prior art can be solved.

The invention discloses an energy storage lithium battery life degradation prediction method and system, and the method comprises the steps: obtaining and preprocessing lithium battery operation data, constructing a time sequence, carrying out the normalization processing, and dividing a training set and a test set; based on the normalized data, constructing a multi-head self-attention mechanism MSA module with masks, capturing multiple features in the input data through different time windows, and extracting an important feature set through a feature fusion method after screening; based on the important feature set, key hyper-parameters are preliminarily set, and an MSA-LSTM comprehensive prediction model is constructed and used for processing time sequence data and predicting the service life of the battery; an artificial bee colony algorithm is adopted to optimize hyper-parameters of the MSA-LSTM comprehensive prediction model; and training the optimized MSA-LSTM comprehensive prediction model by using the training set, verifying and evaluating the prediction performance by using the test set, predicting unknown data by using the MSA-LSTM comprehensive prediction model, and calculating the remaining service life RUL of the energy storage lithium battery. And safety accidents caused by battery faults are prevented.

The invention discloses a large language model parameter fine tuning method, system and device, a storage medium and a product, and relates to the field of natural language processing. The fine tuning method comprises the steps that a pre-training model and a parameter matrix of the pre-training model are acquired, a parameter fine tuning module is arranged on a self-attention layer of the pre-training model, the parameter fine tuning module comprises LoRA modules of different task types and a router, each LoRA module comprises a general feature matrix and a specific feature matrix, and the general feature matrixes of the multiple LoRA modules are shared; obtaining a fine tuning data set; loading and freezing a parameter matrix of the pre-training model, and initializing parameters of a parameter fine tuning module; and performing fine tuning on the parameters of the parameter fine tuning module based on the fine tuning data set to obtain a fine-tuned large language model. Parameters of the MoE architecture are remarkably reduced, it is ensured that the model captures differences of various tasks to the maximum extent, and the cross-task generalization of the model is ensured.

The invention discloses a highway pavement temperature forecasting method based on physical constraints, which comprises the following steps of: collecting and preprocessing meteorological data of all stations in a region, historical observation data of pavement temperature and geographic data, and adding time information to construct time features; building a U-net neural network model, carrying out space field data correction on the multi-station multi-meteorological element forecast data, and outputting corrected meteorological data of each station; constructing a bidirectional LSTM network on the basis of the U-net model, processing time sequence data, and evaluating and optimizing model performance by using a loss function; physical constraints including the time relation of temperature change, seasonal and day and night change characteristics, material thermal characteristics, a thermal balance equation and the like are added into the model, and a model result is optimized; and evaluating the generalization ability and forecasting precision of the model by using a test set, and finely adjusting model parameters. According to the method, the precision and reliability of road surface temperature prediction are remarkably improved, and a reliable basis is provided for traffic management and safety early warning.

The invention relates to the technical field of geological disaster evaluation, in particular to a mine geological disaster risk comprehensive evaluation method considering spatial distribution characteristics. The method comprises the following steps: acquiring mine multi-source spatial data; performing mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological risk distribution map; performing spatial region potential disaster probability analysis on the mine geological risk distribution map to generate mine geological distribution disaster probability data; and performing high-complexity spatial region screening on the mine geological risk distribution map through the mine geological distribution disaster probability data to obtain high-complexity spatial region data. According to the method, multi-source data are integrated, spatial distribution characteristics are emphasized, active and inactive areas are distinguished, ecological and water body changes are analyzed, and the accuracy and comprehensiveness of mine geological disaster risk comprehensive evaluation are improved.

The invention provides a zero-sample dynamic MRI reconstruction method based on global and local diffusion models, and the method comprises the following steps: generating an image data set based on original two-dimensional dynamic full-sampling heart magnetic resonance multi-coil data; designing a global and local time interlaced sampling strategy to construct two types of training data sets for generating a network model by adopting global and local cascade learning networks of a two-stage learning mechanism; performing prediction, correction, low-rank constraint and data consistency on data alternation by using an iterative solution algorithm for rapidly extracting prior information of a network model; and applying an iterative solution algorithm to the trained network model, testing, outputting a dynamic magnetic resonance reconstruction image, and evaluating the image quality. According to the method, the complete coding data is constructed through different time interlaced sampling strategies, the image is quickly and accurately reconstructed under the under-sampling condition in combination with the image prior information of the network model, and the quality and efficiency of the reconstructed image are remarkably improved.

The invention provides a gearbox fault diagnosis method and device based on a digital twinborn and composite adversarial domain discrimination network, and the method comprises the steps: inputting a target actual measurement operation parameter of a target gearbox into a feature extraction module of a fault diagnosis model, and obtaining a target feature vector of the target actual measurement operation parameter; inputting the target feature vector into a classification module of a fault diagnosis model to obtain fault diagnosis prediction information of the target gearbox; wherein the fault diagnosis model is obtained by performing iterative training on a composite adversarial domain discrimination network based on sample actual measurement operation parameters and sample simulation operation parameters of the sample gearbox and fault labels corresponding to the sample simulation operation parameters; the sample simulation operation parameters are obtained by simulating a dynamic model of the digital twinning dynamic simulation model of the sample gearbox. According to the invention, effective and accurate fault detection can be carried out on the gearbox under the condition that the effectively marked fault sample data is limited.

The invention discloses a large language model training method and system based on elastic federal low-rank adaptive fine tuning, which adopts federal aggregation based on singular value decomposition (SVD) to reconstruct a local LoRA module of a client into a local increment matrix, then aggregates the local increment matrix into a global increment matrix, and generates a LoRA module of the next round through SVD, thereby effectively eliminating aggregation errors of traditional FedLoRA. According to the method, the LoRA rank is dynamically distributed for each weight matrix, and the balance between statistics and hardware efficiency is realized. In order to further reduce communication overhead and maintain model precision, a self-adaptive matrix freezing mechanism is introduced, and whether freezing is carried out or not is judged according to training stability of a weight matrix. According to the method, challenges of traditional FedLoRA in the aspects of training efficiency, communication overhead, model precision and the like are solved.

The invention relates to the technical field of medical image processing, and particularly discloses a pathological tissue image-based tumor analysis method, which comprises the steps of data acquisition and preprocessing, network construction, image enhancement, adjacent layer feature fusion, image classification and knowledge distillation. According to the scheme, features are extracted from different levels by adopting an image enhancement and comparative learning method, the capability of extracting global features and capturing local details of the model is improved, and by calculating strong and weak enhancement difference loss, it is ensured that enhancement operation does not excessively change feature representation of the image, and overfitting of the model is prevented; features are extracted and fused from each layer of feature map of the teacher network through an attention mechanism, and the detail capturing ability of the model to a pathological image is enhanced; a knowledge distillation method is used, knowledge of a teacher network is introduced, and a student network not only pays attention to classification of hard tags, but also can capture a relative relationship between classes, so that the classification accuracy is improved, and the calculation resource demand of a model is reduced.

The invention discloses a twin network performance prediction method and device based on a graph neural network and a storage medium, and belongs to the technical field of communication networks, and the method comprises the steps: carrying out the preprocessing of the obtained historical information of a physical communication network, and obtaining a dependency graph data set; initializing the state of each node in the dependency graph data set to obtain the initial hidden state of each node; the initial hidden state is used to train a pre-constructed network performance prediction model to obtain a trained network performance prediction model, and the network performance prediction model obtains iteratively updated hidden state information and adjusts model parameters through cooperative work of an attention mechanism, a message passing neural network and a gating circulation unit; and inputting the obtained real-time information of the physical communication network into the trained network performance prediction model to obtain a performance prediction result, thereby improving the stability, accuracy and efficiency of performance prediction of the digital twin communication network.

The invention discloses a multi-task blood vessel segmentation model construction method based on a hybrid encoder. The encoder is a Swin Transform path multi-layer encoder based on a Mamform module, and the Mamform multi-layer encoder carries out data processing in combination with a W-MSA and an improved Mamba module; the decoder is a multi-task decoder and consists of three independent decoding paths which are respectively used for blood vessel segmentation, contour edge segmentation and blood vessel connectivity segmentation, and each decoding path adopts Swin Transformblock as a construction block and is used for generating feature mapping with the same size as an input image; an attention mechanism is shared, learned features are shared among decoders, the number of model parameters can be reduced, and overfitting is prevented; in the training process, a total loss function is formed through a loss function of a vascular connectivity decoding path, a self-distillation loss function and the like, the total loss function is calculated, model parameters are updated by using a back propagation algorithm, the segmentation performance of the model is gradually optimized, and after training is completed, the model can carry out precision on a vascular image.

The invention provides an environmental pollution risk assessment method and system based on deep learning, a computing device and a storage medium, and relates to the technical field of environmental pollution risk assessment, and the method comprises the steps: determining a preliminary environmental pollution condition of a target region through employing a multi-scale multi-factor coupling analysis method based on the parameter values of physicochemical property parameters and background information; verifying and correcting the initial environmental pollution condition to obtain a target environmental pollution condition; according to the target environmental pollution condition, the historical environmental pollution risk assessment result, the public health data and the parameter values of the organism response parameters, the target environmental pollution risk assessment result is obtained; and an environmental pollution risk assessment model including a deep learning-based multilayer perceptron, an attention mechanism and a generative adversarial network is adopted to assess the overall influence degree of the environmental pollution condition of the target area on public health and an ecological system, so that a target environmental pollution risk assessment result can be obtained. According to the technical scheme provided by the invention, the accuracy of the target environmental pollution risk assessment result is improved.

The invention discloses an AI model service platform data set labeling method and system, and relates to the technical field of data set labeling, a to-be-labeled data set is split according to a data type, and whether an existing labeling model capable of respectively processing the currently split to-be-labeled data set exists in an AI model service platform is identified; evaluating the annotation performance of the annotation model based on the evaluation index of the annotation model, and then updating the annotation model based on data enhancement; labeling the split to-be-labeled data set by using the updated labeling model to generate a first labeling result; performing secondary annotation on the first annotation result based on multi-model joint annotation to generate a second annotation result; and screening and identifying an unqualified annotation data set in the second annotation result through the confidence interval so as to trigger manual annotation. An efficient, low-cost, high-quality, flexible and extensible data set labeling process is realized, so that the labeling capability and the service quality of an AI model service platform are remarkably improved.

The invention provides a network node classification method based on a multilayer graph neural network model, and the method comprises the steps: constructing a graph according to network nodes, carrying out the preprocessing of initial node features in the graph, and obtaining an initial embedded vector; according to the initial embedding vectors of the node and the neighbor node thereof, updating the node representation by adopting a layered message passing mechanism; according to the initial embedded vectors of the nodes and the neighbor nodes thereof, the graph attention network uses an attention mechanism to calculate weights for the neighbor nodes of each node and then dynamically updates feature vectors of the nodes; a multi-head attention mechanism is adopted to splice and merge the feature vectors of the nodes output by the graph attention network and the updated node representation, and the comprehensive feature vector of each node is obtained; the comprehensive feature vectors are further optimized through graph contrast learning and a node embedding module, and optimized features are obtained; and obtaining predicted node classification according to the optimization features. According to the method, complex features of heterogeneous graph data can be effectively captured, the method has good robustness for an over-smoothing problem, more accurate heterogeneous network representation learning is realized, and the method has advanced performance and robustness in a node classification task.

The invention discloses a classroom behavior identification method based on a deformable multi-scale adaptive detection network. The classroom behavior identification method comprises the following steps: building the deformable multi-scale adaptive detection network; dividing the classroom behavior sample data set into a training set sample data set, a verification set sample data set and a test set sample data set, extracting student behavior characteristics from pictures in the training set through a deformable multi-scale adaptive detection network, and performing model training; verifying the verification set by using a model obtained from the training set; obtaining the optimal model parameters of the verification set, inputting the photos in the test set for testing to generate a prediction image, and completing the detection of the classroom behaviors of the students. According to the invention, high-accuracy classroom behavior recognition is realized by using the feature extraction module, the multi-scale feature fusion module and the regression detection module. By dividing the sample data set into the training set, the verification set and the test set, efficient and scientific model training is ensured, and the over-fitting risk is reduced.

The invention provides a hysteresis loop prediction model establishment method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out a hysteresis characteristic experiment on a ferromagnetic material, setting hysteresis loop related characteristics comprising magnetic induction intensity waveform data and magnetic field waveform data under the excitation of preset sine waves under different magnetic induction intensity peak values, establishing a hysteresis loop prediction model comprising an improved convolutional neural network model and a K-nearest neighbor algorithm model, training the improved convolutional neural network model, inputting a magnetic induction intensity peak value and magnetic induction intensity waveform data, and outputting magnetic field waveform data; and adjusting the magnetic field waveform data based on the feature data by using a K-nearest neighbor algorithm model to obtain a final magnetic field waveform result. According to the method, the hysteresis loop prediction model is established based on the improved convolutional neural network in combination with the K nearest neighbor algorithm, the overfitting phenomenon can be prevented, the training speed is higher, the resource consumption is lower, and rapid iteration and adjustment in practical application are facilitated.

The invention relates to a Transform and RF fused power load prediction method, which comprises the steps of obtaining short-term power load data to be predicted in a target area, inputting the short-term power load data into a trained random forest network RF after clustering and decomposition, and outputting a power load prediction result. The RF training process comprises the following steps: acquiring power load historical data and corresponding historical weather data of a specific area, and preprocessing to obtain a first training data set and a second training data set with labels respectively; clustering and decomposing the first training data set with the label and the second training data with the label based on the power load historical data and the time sequence characteristics of the corresponding historical weather data; respectively inputting the clustered and decomposed power load data into a multi-modal time sequence prediction converter to obtain a feature sequence; and the feature sequence is transmitted to RF for regression prediction, regression loss is calculated, and the random forest network is iteratively optimized through the regression loss. The accuracy of a power load prediction result can be obviously improved.

The invention discloses a wind turbine generator fault early warning method based on machine learning, and relates to the field of wind turbine generator fault early warning. The method comprises the following steps: preprocessing data; the method comprises the following steps: preprocessing historical sample data of a healthy fan, dividing the preprocessed historical sample data of the healthy fan into a training set and a test set, respectively inputting the training set into a Stacking fusion model and a Blending fusion model for training, carrying out comprehensive testing through the test set to obtain a Stacking offline model and a Blending offline model, respectively sending verification data to the Stacking offline model and the Blending offline model, and carrying out comprehensive testing through the test set to obtain a Blending offline model and a Stacking offline model; selecting an optimal model through a self-adaptive threshold value; and inputting actual data of the wind turbine generator into the optimal model to obtain whether the wind turbine generator has a fault or not. According to the method, on the premise that the prediction effect is guaranteed, fault early warning can be carried out early, and for the conditions that the operation range of a draught fan is wide, data is diversified and missing exists, the problems that the model precision and stability are reduced due to data missing, and overfitting is caused due to the fact that the model is too complex can be effectively solved.

The invention provides a whole blood donor low hemoglobin delayed blood donation risk prediction method, which comprises a data normalization and abnormal value processing module, a classification feature coding module, a category balance and model fitting module, a hyper-parameter adjustment module and a model interpretation and deployment module. According to the prediction method provided by the invention, data normalization and targeted feature coding are carried out on blood donation records and hemoglobin detection data, an SMOTE oversampling algorithm is used for class balance and then fitting of a Light GBM model is carried out, and a Hyperband hyper-parameter adjustment method is used for adjusting and optimizing SMOTE and Light GBM parameters. And storing the tuning model for feature importance interpretation, model packaging and network deployment, thereby realizing the effects of optimizing the whole blood donor invitation strategy and enhancing the continuity and stability of blood supply.

The invention discloses a CNN-based pump station fault prediction method, and particularly relates to the field of industrial equipment fault prediction, and the method comprises the following steps: S1, deploying a sensor in a pump station, obtaining the operation state data of the pump station in real time, removing the noise and abnormal values in the data, and carrying out the normalization processing of the data; s2, extracting features related to pump station faults by using a multi-layer convolutional network, and independently performing convolution operation on each time sequence; s3, processing the time sequence data by using a bidirectional GRU network and introducing an Attention mechanism, so that the model can automatically learn different time steps and features; s4, training the model by using historical data, and optimizing the performance of the model by adjusting the parameters and the structure of the model; according to the invention, through the advanced deep learning algorithm and multi-source data fusion, efficient prediction and early warning of the pump station fault are realized, the operation efficiency and safety of equipment are significantly improved, and the method has important application value and popularization prospect.

The invention relates to a transfer learning-based power distribution network measurement data super-resolution sensing method. The method comprises the steps that a high-frequency time sequence is acquired and preprocessed, and training sample data is obtained; a cascade model is constructed based on a graph attention network and a transformer network, the training sample data and an incidence matrix are input into the cascade model, the cascade model is pre-trained, and the incidence matrix represents the topological connection relation of the power distribution network; the cascade model after pre-training is divided into a learning device part and a decision-making device part, transfer learning training is carried out, model parameters reaching a training target are reserved, a final super-resolution perception model is obtained, the learning device part comprises all layers except a transformer linear output layer, and the decision-making device part comprises a transformer linear output layer; and inputting real-time measurement data into the super-resolution sensing model to obtain a super-resolution measurement generation result.

The invention relates to the technical field of computers, in particular to a hyperspectral compressed sensing reconstruction method based on depth double-prior progressive fusion, which comprises the following steps of: 1, shooting to obtain an original compressed measurement image, and normalizing the original compressed measurement image to obtain a normalized compressed measurement image; 2, constructing an objective function based on a compressed sensing reconstruction problem, and optimizing the objective function to obtain a final optimized objective function; 3, establishing a self-supervised learning model for hyperspectral compressed sensing reconstruction according to the normalized compressed measurement image; the self-supervised learning model comprises outer loop iterative optimization and two pieces of inner loop network training; and 4, solving the optimized final objective function by using a self-supervised learning model, and obtaining a final reconstructed image by fusing depth priori items obtained in two internal loop network training processes. The problem that an existing self-supervised spectrum reconstruction method is low in imaging quality is solved.

The invention discloses a method for realizing tobacco field yield prediction based on multi-source data analysis, and particularly relates to the technical field of tobacco yield prediction. Firstly, a tobacco planting area is divided into monitoring areas, multi-source data such as weather, soil, remote sensing images and actual yield are obtained in real time, the collected data are preprocessed, space-time consistency characteristics and information integrity characteristics are extracted, a comprehensive matching degree index is generated through calculation and weighting, on the basis, a yield prediction model is established, and a tobacco yield prediction result is obtained. The prediction value and the actual yield are compared and analyzed, if the deviation is large, model parameters are dynamically adjusted through fuzzy logic based on the comprehensive matching degree index and the actual yield data, and a data processing and fusion algorithm is optimized, so that the prediction precision is remarkably improved, and the field management risk caused by data isomerism is reduced.

The invention belongs to the technical field of biological feature recognition, and relates to a Transform-based gene data mining method, which comprises the following steps of: loading gene expression data from a file, and preprocessing; inputting the data into a designed model for training and evaluation; the designed model comprises a CNN (Convolutional Neural Network) and an improved Transform model; the improved Transform model comprises an encoder and a classifier; the encoder adopts a multi-head self-attention mechanism, a convolutional self-attention mechanism and a feedforward neural network; processing the data by using the trained model, and storing the fusion attention weight obtained by the coding layer in the data processing process; and finally, averaging the fusion attention weights of all batches, calculating the comprehensive attention weight of each gene at different time points, and identifying the most important gene by calculating and analyzing the attention score of each gene. According to the method, the problems of scarcity and imbalance of gene data can be solved, the risk of overfitting is reduced, and the precision of gene data analysis is improved.

The invention provides a hydropower station floating object detection method based on global relation modeling, and aims to improve the detection precision and efficiency of hydropower station water surface floating objects, and the method comprises the steps: collecting hydropower station water surface scene data through a multi-view device; extracting shallow multi-scale features through a lightweight convolutional network; modeling a global relationship between the floaters through a multi-head self-attention mechanism; carrying out the classification and positioning of floating objects through a target detection head; network training is performed through a multi-task loss function to optimize the model; and reasoning by using the trained floating object detection network, inputting a to-be-detected water surface image into the network, outputting the category and the position of the floating object, and finally generating a detection result. According to the method, the global relation modeling method is introduced, the detection precision of the hydropower station water surface floating objects is effectively improved, detection errors caused by insufficient local features in a traditional method are reduced, and the method has low calculation complexity and is suitable for real-time detection in practical application.

The invention belongs to the technical field of image recognition, and relates to a small sample learning method for task-adaptive association learning, which comprises the following steps of: S1, assisting the original prompt by using a specific prompt word of a task; s2, enhancing the discrimination of the training features by using comparative learning; s3, using diversified image enhancement means to enhance the contrast of the image; according to the method, the generalization ability of the model is enhanced through rich description of a natural language, so that the CLIP can be more efficient even if the CLIP faces the unmet category or complex concept. Therefore, the method not only reduces the dependence on a large-scale annotation data set, but also improves the learning ability of the model under the condition of small samples and even zero samples, enhances the adaptability and generalization ability of the model to a new environment, greatly simplifies the deployment process of the model, and improves the deployment efficiency of the model. The method becomes a powerful tool for solving a series of challenges in image recognition and description tasks.

The invention relates to a container number and container threshold weight identification method and device based on deep learning. The method comprises the following steps: acquiring a side image of a container body; inputting the side image of the box body into a target detection model, and detecting the coordinates of the area where each target is located and the corresponding target type; cutting out a target image from the box side image, inputting transverse box number images into a box number character block detection model, correspondingly outputting a prediction set by each transverse box number image, detecting character blocks in the prediction sets by adopting non-maximum suppression to obtain a detection set of the character blocks, cutting out character block images, and splicing the character block images to obtain a detection set of the character blocks; obtaining a transverse box number spliced image; and inputting the transverse box number spliced image and other target images into a trained character recognition model, and recognizing the box number, the ISO number and the box threshold weight limiting character. The method has the advantages that the container number and the container threshold weight can be automatically and accurately recognized, the recognition accuracy is high, the method is suitable for various complex container images, and the good recognition effect can be achieved.

The invention discloses a semi-supervised multi-modal data classification method based on shared feature alignment. The method comprises the following steps: S101, inputting labeled and unlabeled hyperspectral images and laser radar images, and extracting domain sharing features and domain private features; s102, splicing domain sharing features of the hyperspectrum and the laser radar, generating fusion features of domain sharing, and supplementing semantic information in the fusion features; s103, aligning the feature distribution of the label data and the feature distribution of the label-free data; s104, identifying a label sample and a label-free sample, and selecting a valuable label-free sample; s105, designing a sample labeling strategy based on a class adaptive threshold value, designing different threshold values for each class according to the classification difficulty of the classes, and selecting a pseudo label sample with high confidence coefficient to re-train the model; and S106, training the established semi-supervised joint classification network model. According to the method, the domain self-adaption thought is introduced to capture the shared features of the label data and the label-free data, and the classification precision of the model is improved by iteratively selecting the high-value pseudo labels.

The invention discloses a calculation method of an automatic processing tool based on abnormal link identification. The method comprises the steps of S1, receiving network flow data, S2, analyzing the data to determine a reference mode, S3, detecting an abnormal link in a network based on the reference mode, and S4, generating and executing a corresponding repair instruction to process the abnormal link. According to the calculation method of the automatic processing tool based on abnormal link identification, new threats can be found and dealt with in time, the defect of response lag in the face of unknown anomalies in the prior art is overcome, the safety of the system is improved, and the method is suitable for popularization and application. The problems that in the prior art, threshold adjustment is not timely, data preprocessing lags behind, multi-dimensional feature selection is inaccurate, automatic coping strategies are insufficient, and the unknown anomaly recognition capacity is limited are solved.