161 results about "Domain prediction" patented technology

The invention discloses a wind-solar power generation power prediction method based on meteorological feature screening and transfer learning, and belongs to the field of new energy power prediction. The method comprises the following steps: firstly, establishing a combined credibility index for screening sensitive meteorological characteristic factors, and obtaining the sensitive meteorological characteristic factors; constructing a source domain prediction model, and pre-training the source domain prediction model by using the sensitive meteorological characteristic factors; then acquiring historical power generation data of a photovoltaic power station to be subjected to wind-solar power generation power prediction, constructing a target domain data set, and performing transfer learning and parameter fine tuning on the pre-trained source domain prediction model based on the target domain data set to obtain a target domain prediction model for predicting wind-solar power generation power; and utilizing the target domain prediction model to predict the wind-solar power generation power. The method not only effectively solves the problem of insufficient generalization ability of the model, but also has stronger adaptability and robustness, and significantly improves the prediction precision and stability.

The invention relates to the field of data visualization, in particular to a visual scheduling method and system for a scientific and technological achievement evaluation system. The method comprises the following steps: identifying system access behavior data of a user; performing attention hotspot field prediction on system access behavior data of the user, performing deep personalized demand evolution, and constructing a personalized scientific and technological achievement demand graph; real-time data flow matching retrieval is carried out according to the personalized scientific and technological achievement demand graph, semantic feature analysis is carried out, and deep semantic features of each text item and visual semantic features of each image and table item are extracted; and performing dynamic clustering processing according to the deep semantic features of each text item and the visual semantic features of each image and table item, and performing multi-dimensional scientific and technological achievement item aggregation to construct a scientific and technological achievement display library. According to the invention, comprehensive, dynamic, accurate and personalized scientific and technological achievement evaluation visualization is realized.

The invention discloses a lithium battery SOH prediction method and device based on fusion features, equipment and a medium, and relates to the technical field of lithium battery SOH prediction. The lithium battery SOH prediction method comprises the following steps: A1, acquiring a first data set of a target domain and a second data set of a source domain; a2, performing data preprocessing and feature extraction on the first data set and the second data set to obtain a source domain feature data set and a target domain feature data set; and A3, constructing a cross-domain prediction model. And A4, according to the source domain feature data sets of different source domains and the cross-domain prediction model, training a source domain prediction model for each source domain. And A5, fusing the source domain prediction model of each source domain to obtain a fused prediction model. S1, acquiring to-be-predicted data of a target domain; s2, performing preprocessing and feature extraction on to-be-predicted data to obtain to-be-predicted features; and S3, inputting to-be-predicted features into the fusion prediction model to obtain an SOH prediction value.

Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

According to an aspect, there is provided method performed by a user equipment, UE The UE is being served by a first cell of a source network node. The method comprises transmitting (602), to the source network node, a first message comprising time-domain prediction information for a second cell; receiving, from the source network node, a conditional handover, CHO, configuration comprising a CHO execution condition and a CHO candidate configuration for the second cell; and evaluating the CHO execution condition associated with the second cell.

The invention discloses a defect detection method and a model migration method. The model migration method comprises the following steps: obtaining a source domain image and a corresponding label, and obtaining a baseline model from a source domain; obtaining a target domain image, wherein the target domain image is completely labeled or partially labeled or completely unlabeled; inputting the annotation of the source domain image into a de-noising device to obtain a de-noised annotation; inputting the initial baseline model into an unlabeled target domain image to obtain a second target domain prediction result, performing data expansion on the unlabeled target domain image to obtain a second target domain expansion image, and taking the second target domain prediction result as a pseudo label of the second target domain expansion image; and training a baseline model by using the source domain image and the corresponding de-noised annotation, the annotated target domain image and the corresponding annotation and / or the second target domain expansion image and the corresponding pseudo annotation to obtain a migration model. According to the method, training can be completed with a small number of labeled target domain images, and the problem that the model migration performance is poor under the condition that the target domain images are insufficient is solved.

The invention discloses a confrontation trajectory prediction method, a readable storage medium, electronic equipment and a vehicle, and belongs to the field of automatic driving. The prediction method comprises the following steps: constructing a trajectory prediction model; inputting a historical track, a real track and environment context information; track features are obtained through feature extraction and a space-time attention mechanism; constructing a confrontation model of the explicit space; mapping the track features to a submerged space; disturbance is carried out on the submerged vectors, and the submerged vectors are regularized to specific distribution; and mapping the latent vector to the explicit space, and generating a confrontation trajectory of the target driving vehicle. The readable storage medium stores a program of the method. A program including the method is stored in the electronic equipment. The vehicle comprises the intelligent system for executing the method. According to the method, the explicit space and the implicit space are emphasized for multi-space collaborative optimization, the pertinence and the real concealment of attacks are remarkably improved, the prediction precision is improved, and then the target driving vehicle track can resist surrounding vehicles and cope with complex vehicle conditions.

The invention discloses a rolling bearing life prediction method based on a dynamical model and a cross-domain graph network, and the method comprises the steps: building a simulation model based on a five-degree-of-freedom dynamical model of a rolling bearing, and combining a multi-target particle swarm optimization algorithm with a bearing actual measurement signal to dynamically update the parameters of the dynamical simulation model. And the defect evolution process of the simulation model in different degradation stages is explored, and the full-life-cycle simulation data of the rolling bearing are generated, so that the defect that the full-life-cycle data of the bearing are difficult to collect in actual engineering is overcome. Designing a multi-layer cross-domain graph neural network model, performing nonlinear transformation on graph node features to extract space information of neighbor nodes, and extracting time dependence of the neighbor nodes by combining a hidden layer state at a previous moment; and taking the complete labeled simulation data as source domain data, taking the incomplete label-free actual measurement data as target domain data, reducing the distribution difference between the source domain data and the target domain data through a multi-layer domain adaptation mechanism, and finally realizing cross-domain prediction of the service life of the bearing.

The invention particularly relates to a time sequence mapping knowledge domain prediction method based on continuous features and a large model. The method comprises the following steps: acquiring mapping knowledge domain data; constructing a knowledge graph prediction model, wherein the knowledge graph prediction model comprises a historical coding module, a continuous time neural network module, a feature fusion module and a training loss module; the historical coding module outputs a historical entity matrix, a historical relationship matrix and a historical matrix based on the knowledge graph data; the continuous time neural network module obtains a time continuous entity matrix and a time continuous relation matrix according to the historical entity matrix and the historical relation matrix; the feature fusion module generates probabilities of all candidate entities based on the time continuous entity matrix and the time continuous relation matrix; and the training loss module calculates final loss and generates probabilities of all final candidate entities so as to predict the time sequence knowledge graph. According to the method, continuous time dynamic modeling and multi-scale feature fusion are realized, and the prediction precision and generalization ability of the time sequence knowledge graph are remarkably improved.

The invention discloses a power electronic device fault early warning method based on multi-physics field coupling, and the method comprises the steps: (1) collecting aging data of a power electronic device under the condition of electric field and thermal field coupling, and dividing the aging data into a source domain data set and a target domain data set; (2) establishing a power electronic device aging parameter screening method, selecting a parameter which can best represent an aging rule as an aging precursor, and converting discrete voltage and current signals into time sequence signals which can be accepted by a neural network; (3) compressing the time sequence signal set into sliding window graph nodes, calculating a distance relationship between the graph nodes, and obtaining a graph matrix containing data structure information; (4) building a space-time fusion fault predictor, wherein the space-time fusion fault predictor comprises a feature extractor, a time sequence predictor and a domain discriminator; and (5) a weak supervision adversarial learning strategy is adopted, a small amount of target domain label data participates in the model training process, and the source domain prediction loss, the target domain prediction loss and the discrimination loss are combined for training.

The invention discloses a few-sample traffic flow prediction method and system based on a diffusion model, and a terminal, and the method comprises the steps: obtaining the traffic flow data of a city, and enabling the city to comprise a source city and a target city; constructing a space-time prediction model, and training the space-time prediction model according to the traffic flow data to obtain a high-dimensional vector; acquiring spatial-temporal characteristic data of a city, and processing the spatial-temporal characteristic data to obtain a spatial-temporal characteristic embedded vector; constructing a diffusion model, and training the diffusion model according to the high-dimensional vector and the spatio-temporal feature embedded vector to obtain a trained diffusion model; and based on the trained diffusion model, performing traffic flow prediction on the target city according to the traffic flow data to obtain a traffic flow prediction result. According to the method, the diffusion generation model is introduced before target domain prediction to generate the adaptive model parameters more conforming to the target domain characteristics, so that the future traffic flow is predicted in combination with the traffic flow characteristics of the target domain, and the traffic flow prediction accuracy is improved.

The invention discloses a remote sensing image cross-scene classification method, device and equipment based on collaborative learning, and the method comprises the steps: training and generating an initial classification model through employing source domain data with noise labeling, predicting unlabeled target domain data based on the initial classification model, generating a target domain pseudo-label, and carrying out the recognition of the target domain pseudo-label through a collaborative learning mechanism. Performing bidirectional knowledge migration on the target domain pseudo-label and the data with the noise source domain, and training the initial classification model to obtain a target domain prediction entropy value; screening a high-confidence pseudo label according to the target domain prediction entropy value, replacing the target domain pseudo label, and returning to the step of executing bidirectional knowledge migration on the target domain pseudo label and the data with the noise source domain through the collaborative learning mechanism until the model is converged to obtain a target classification model; and classifying the to-be-classified remote sensing image by using the target classification model to obtain a classification result. By adopting the method, the accuracy of cross-scene classification of the remote sensing image is improved.

The invention discloses an adverse drug reaction prediction method and system based on multi-source heterogeneous modal dual-channel fusion interaction, and relates to the technical field of multi-modal data fusion and self-supervised learning. The prediction method comprises the following steps: S1, performing multi-source heterogeneous modal feature extraction and representation optimization, and constructing feature engineering for multi-source heterogeneous data; and S2, performing dual-channel fusion interaction collaborative prediction. In the step S2, based on the hierarchy and heterogeneity of modal features, a spatial fusion module with gated deep convolution is provided, a representation learning space is constructed, a dual-channel fusion interaction mechanism including multiple fusion strategies is provided, local and global features are dynamically fused, and the fusion speed is improved. Efficient information interaction and collaborative optimization among multi-source heterogeneous modal data are realized; and finally, realizing collaborative prediction based on the matching degree of the fused feature representation and the adverse reaction embedding. The method is easy to implement, a lightweight architecture is adopted, but performance indexes can be greatly improved, and efficient screening and prediction can be achieved in the early stage of drug research and development.

The invention relates to a data set distribution difference-oriented electronic medical record data representation learning method and system, and the method comprises the steps: pre-training a source domain teacher model through a source domain data set of an existing disease, and extracting the health state representation information of a source domain disease patient; training a domain invariant feature extractor as a transition model, modeling general features through an adversarial training strategy, and establishing an independent extraction channel for private features to realize feature alignment among different domains; and migrating parameters of the transition model to a target domain emerging disease prediction model, and performing fine tuning in combination with target domain data to realize accurate prediction of emerging diseases. Through domain invariant feature extraction and model migration optimization, the generalization ability and prediction precision of the model on different data sets are significantly improved, clinical results of patients can be accurately predicted, accurate support is provided for medical decision, and a reliable foundation is laid for the cross-domain prediction problem in medical data analysis.

The invention discloses a vehicle fine granularity detection method based on a three-dimensional grid and YOLOv11 transfer learning. The method mainly comprises three components: a source domain prediction network structure, a target domain prediction network structure and a transfer learning module. Wherein the source domain prediction network and the target domain prediction network are dual-channel deep networks fusing two-dimensional images and three-dimensional grids, and efficient migration of source domain knowledge in a target domain is realized by aligning feature distribution of the source domain and the target domain. Through deep fusion of three-dimensional grid information and two-dimensional image features, the method can maintain robust detection performance under adverse conditions of vehicle attitude change, illumination interference, shielding and the like, can effectively reduce large-scale data annotation and training cost, improves the rapid adaptation capability of the model in a new scene or a new vehicle type, and improves the robustness of the model. And a high-precision, extensible and rapid-iteration fine-grained identification and detection solution is provided for intelligent traffic monitoring, unmanned driving perception, military equipment identification and digital twin systems.

The invention relates to the field of health detection, and particularly discloses an intelligent wearable device sleep state monitoring system based on time-frequency analysis, and the system comprises a data collection module which is used for collecting all physiological information data of a user from the beginning of sleep to the end of sleep, and collecting the data into a data set; the data preprocessing module is used for preprocessing the data set; the time domain analysis module is used for extracting time domain features of the data set A by using the constructed LSTM time domain prediction model; the frequency domain analysis module is used for extracting frequency domain features of the data set B by using the constructed PSO-XGBoost frequency domain prediction model; the data classification module is used for classifying and identifying the data set according to classification results of the time domain analysis module and the frequency domain analysis module; according to the method, the LSTM is utilized to predict the time domain features, the XGBoost is utilized to predict the frequency domain features, and then the prediction results of the two parts are weighted and fused, so that the breathing events in sleep are accurately identified and classified.

The invention provides an event monitoring model training method and an operation video anomaly detection method, which can be applied to the technical field of video processing. The method comprises the following steps: training a feature extraction module, an event memory unit and a source domain classifier by using a source domain sample video set to obtain a pre-training model; inputting the target domain sample video into a feature extraction module and outputting target domain sample features; inputting the target domain sample features and the source domain sample features into a scene memory unit and an event memory unit, and respectively outputting mixed domain event enhancement features and scene enhancement features; inputting the mixed domain event enhancement feature, the target domain sample feature and the source domain sample feature into a target domain classifier, and outputting a target domain prediction result; and iteratively adjusting the event feature prototype, the scene feature prototype and the network parameters according to the target domain prediction result and the pseudo tag until a first iteration stop condition is met, and obtaining a trained event monitoring model.

The invention discloses an aircraft body surface acoustic load time domain prediction method and system, and belongs to the technical field of aircraft detection. In order to solve the problem of high-precision solving calculation of the sound scattering problem of the aircraft, an aircraft flow field calculation grid and a sound field grid are established; the grids are initialized; calculating a Jacobian determinant and grid cell measurement, and completing grid coordinate system conversion; judging the convergence of the numerical solution of the grid unit; a Runge-Kutta method is adopted to iteratively solve a linear Euler equation under each time step; obtaining flow field data and sound field data of each grid unit; filtering processing is carried out by adopting a spatial filtering format, numerical pseudo waves are eliminated, and flow field data and sound field data of each grid unit after filtering processing are obtained; and performing time updating iteration on the flow field data and the sound field data until the obtained acoustic load data is stable, and outputting aircraft surface acoustic load time domain data, a watershed sound field cloud picture and a flow field cloud picture. The method gives consideration to calculation efficiency and precision.

The invention provides a turbine engine residual life prediction method based on cross-domain migration. The method comprises the following steps: training a residual life original prediction model by using source domain training data; the residual life original prediction model is composed of a multi-scale feature extraction module and a prediction module, and the multi-scale feature extraction module comprises a Transform network, a CNN network and a feature coupling unit; performing cross-domain learning on the pre-training prediction model by using the target domain data to obtain a residual life target prediction model corresponding to the target domain; and acquiring operation data corresponding to a to-be-predicted turbine engine, and inputting the operation data into the residual life target prediction model for residual life prediction to obtain the residual service life corresponding to the to-be-predicted turbine engine. Through the method and the device, the problem of performance reduction caused by data distribution difference in cross-domain prediction is effectively relieved, and accurate prediction of the residual life result of the target domain is realized.

The invention provides a multi-source domain invariant acoustic feature extraction method and system for an equipment operation state, and belongs to the technical field of equipment maintenance, and the method comprises the steps: constructing a multi-source domain invariant acoustic feature extraction network based on a DANN model, and the network comprises a feature extractor, a classifier, a domain discriminator and a multi-domain acoustic feature class boundary constraint module; the feature extractor extracts high-dimensional features of sound signals, the classifier carries out fault mode recognition, and the domain discriminator realizes domain prediction. The multi-domain constraint module generates an embedding space, and calculates the maximum mean value difference, the local maximum mean value difference and the Euclidean distance among different source domain features. The network constructs a loss function by taking minimization of inter-domain difference and classification loss and maximization of inter-domain distance and domain discrimination loss as targets, and carries out adversarial training through multi-source tagged acoustic data. According to the method, domain invariant features are extracted by using adversarial learning and hidden space constraint alignment of multi-source domain acoustic features, so that the influence of feature offset under a cross-working-condition condition is effectively reduced, and the fault mode recognition accuracy is improved.

The invention discloses a whole blood donation adverse reaction risk prediction method and system, and relates to the technical field of medical informatization and intelligent risk prediction. The prediction method comprises the following steps: performing data import and integration on demographic information, blood donation history and adverse reaction records of blood donors; performing preprocessing and variable definition on the data; the method comprises the following steps: respectively establishing a plurality of machine learning models by taking a serious blood donation adverse reaction as a main outcome variable and an adverse reaction type as a secondary outcome variable, screening an optimal main outcome variable prediction model and an optimal secondary outcome variable prediction model through a plurality of evaluation indexes, and verifying the models by adopting a cross validation method. And finally, realizing risk prediction and hierarchical management of blood donation adverse reactions by using the selected optimal model. According to the method, layered identification and multi-model training of the primary and secondary result variables can be realized, the accuracy and intelligent level of blood donation adverse reaction prediction are effectively improved, and the method is suitable for risk prevention and control and management of large-scale blood donation crowds.

According to an aspect, there is provided a method performed by a user equipment, UE The UE is being served by a first cell. The method comprises receiving (702) a conditional handover, CHO, execution condition. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

The invention discloses an enzyme kinetic parameter and domain label prediction method and device, equipment and a medium, and relates to the technical field of enzymes, and the method comprises the steps: training an initial enzyme kinetic parameter prediction model comprising a feature extraction sub-model and a domain adversarial neural network through employing an intra-domain data set and an extra-domain test set, obtaining a target enzyme kinetic parameter prediction model; inputting the target reaction substrate and the target enzyme sequence into a target enzyme kinetic parameter prediction model so that the target enzyme kinetic parameter prediction model performs enzyme kinetic parameter prediction to map to a corresponding enzyme kinetic parameter prediction value, and performing domain tag mapping to obtain a corresponding domain prediction tag, outputting an enzyme kinetic parameter prediction value and a domain prediction tag corresponding to the target reaction substrate and the target enzyme sequence. Through a special training process, the characteristics of a substrate and an enzyme sequence can be extracted more accurately, so that the prediction accuracy of enzyme kinetic parameters and domain tags is improved.

A defect detection method and a model transfer method. The model transfer method comprises: acquiring a source-domain image and a corresponding annotation, and a baseline model obtained from a source domain; acquiring target-domain images, which are fully annotated, partially annotated, or unannotated; inputting the annotation of the source-domain image into a denoiser to obtain a denoised annotation; inputting the unannotated target-domain images into an initial baseline model to obtain second target-domain prediction results, performing data augmentation on the unannotated target-domain images to obtain second target-domain augmented images, and using the second target-domain prediction results as pseudo-annotations of the second target-domain augmented images; and using the source-domain image and the corresponding denoised annotation, the annotated target-domain images and the corresponding annotations, and / or the second target-domain augmented images and the corresponding pseudo-annotations to train the baseline model, so as to obtain a transfer model. The method can complete training by using a small number of annotated target-domain images, thereby solving the problem of model transfer performance being poor in the case of insufficient target-domain images.

A decoder for decoding a digital time-varying signal from a data stream is presented. The decoder is configured to decode the digital time-varying signal from the data stream in non- overlapping temporal blocks by decoding each of transform-coded temporal blocks of the non-overlapping temporal blocks of the digital time-varying signal by predicting the respective transform-coded temporal block using a selected prediction mode out of a set of prediction modes to obtain a prediction signal, decoding coefficients from the data stream, the coefficients representing a prediction residual signal of the respective transform-coded temporal block in a transform domain, subjecting the coefficients to a predetermined re-transformation from the transform domain to time domain to obtain a time-domain prediction residual signal representing a prediction residual signal of the respective transform-coded temporal block in a time domain, and correcting the prediction signal using the time-domain prediction residual signal, wherein the predetermined re-transformation is a non-overlapping transform.

The invention relates to a prediction modeling method of a multi-source migration adaptive enhancement network, which comprises the following steps of: source domain modeling: after samples of a multi-source domain and a target domain are respectively subjected to deep migration learning based on confrontation, extracting consistency information of the multi-source domain, and inputting the information into a domain discriminator to distinguish whether data is from the source domain or the target domain; inputting the source domain features into a nonlinear regression device to complete a source domain prediction task; simultaneously training an adversarial-based deep transfer learning network, a domain discriminator and a nonlinear regression device based on a domain discrimination error and a regression prediction error, and stopping training when the domain discriminator cannot correctly divide received data into source domain features or target domain features and the nonlinear regression device can predict source domain data; and target domain prediction: performing prediction by using the prediction network trained by the source domain and inputting new information of the target domain, performing transfer learning on data of each source domain, constructing a multi-source transfer prediction model, and better performing accurate prediction by using low-value density data.

The invention relates to a self-adaptive cross-domain battery pack health state probability prediction method, and belongs to the technical field of battery health management. The method comprises the following steps: S1, data preprocessing and trajectory normalization; s2, carrying out adaptive step length difference modeling based on local curvature; s3, multi-modal noise modeling; and S4, cross-domain migration probability prediction based on GMM-UT. Quantizing the nonlinear characteristics of the degradation track through local curvature, and dynamically adjusting the difference step length so as to accurately extract the degradation characteristics; a Gaussian mixture model is adopted to fit multi-modal noise, and accurate quantification of uncertainty is achieved; multi-modal noise statistical characteristics and unscented transformation are fused, cross-domain migration and uncertainty propagation are optimized, and battery pack degradation track multi-modal probability distribution is output. According to the method, the defects that an existing method is poor in fixed step length adaptability, inaccurate in noise modeling and insufficient in cross-domain prediction robustness are overcome, the health prediction precision and reliability of the battery pack are improved, and the method is suitable for health management of the battery pack under complex working conditions.

The invention discloses a quality parameter detection model construction method based on multi-source domain adaptation, and relates to the technical field of spectral analysis, the method comprises the following steps: constructing a quality parameter detection basic model, and constructing a multi-source spectral data set for training the quality parameter detection basic model; during model training, extracting source domain features and domain invariant features of the spectral data, and respectively predicting to obtain a source domain prediction result and a domain invariant prediction result; dynamically adjusting the contribution weight of each source domain training set to model training based on the performance of the domain invariant prediction result on each source domain training set; and determining a loss function of model training based on the domain invariant feature, the source domain prediction result and the domain invariant prediction result in combination with the contribution weight, and training by using the loss function to obtain a quality parameter detection model. According to the method, the problem of multi-source spectrum cross-domain regression prediction can be effectively solved under the condition of no target domain spectral data, and the robustness and accuracy of quality parameter detection are improved.

This invention provides a medical ultrasound image recognition method based on generator domain alignment, relating to the field of image classification technology. The method includes: creating labeled generated medical ultrasound image samples for fine-tuning using a conditional diffusion model, where labels characterize the category corresponding to the generated medical ultrasound image sample; aligning each labeled generated medical ultrasound image sample to the generator domain using an unconditional diffusion model of the generator domain, obtaining a generator domain medical ultrasound image set; fine-tuning the source domain model using the generator domain medical ultrasound image set, obtaining a generator domain model; aligning a target medical ultrasound image to the generator domain using the unconditional diffusion model of the generator domain, obtaining a generator domain target medical ultrasound image; and inputting the generator domain target medical ultrasound image into the generator domain model to obtain a first predicted classification result for the target medical ultrasound image. This transforms a cross-domain task into an intra-domain prediction task, aligning both the source domain model and the target data to the same generator domain, thereby achieving accurate predicted classification results.

The invention belongs to the technical field of biological computing, and relates to a TADs structural domain prediction method and system based on attribute graph node clustering. The method comprises the following steps: comparing Hi-C sequencing data with a reference genome, constructing and preprocessing a Hi-C contact matrix, constructing a chromatin attribute graph model, taking chromatin equal-length segments as graph nodes, taking interaction among the nodes as edges, and splicing node attributes by A / B compartment structures and DNA sequence features; the node attribute values serve as new nodes to be inserted into the graph, node amplification is carried out, and an extended attribute graph is formed; performing node clustering on the extended attribute graph, and dividing closely connected structural nodes into the same cluster to serve as a preliminary TADs structural domain; and according to biological prior knowledge, carrying out continuity and size constraint processing on the preliminary TADs, and finally obtaining a predicted TADs structural domain. According to the method, various characteristic information of chromatin is fused through a graph model, and biological priori knowledge is combined, so that the TADs structural domain is effectively predicted.