103 results about "Disease characteristic" patented technology

The invention relates to a road dielectric constant inversion and disease discrimination method based on a neural network. The method comprises the following steps: expanding the number of jump connections based on a TransUNet baseline, introducing a gating attention mechanism, and additionally arranging a multi-scale feature fusion module, an asymmetric depth-space attention module and a deep supervision solution terminal; an AdamW optimizer and a Warmup-cosine annealing learning rate scheduling strategy are adopted to construct an adaptive region weighted loss function so as to amplify dielectric constant mutation boundary loss weight. After a model is trained through a road GPR simulation data set and parameter adjustment of the set is verified to be convergent, a to-be-detected road GPR-B-scan image is input, dielectric constant distribution is output, and according to dielectric constant characteristics of different diseases, accurate discrimination of hidden diseases such as cavities, voids, loose bodies and water-rich bodies is achieved. By adopting the method, high-resolution dielectric constant end-to-end inversion can be realized, and multi-scale disease characteristics can be accurately captured.

The invention relates to the field of biological medicine, and discloses a method and system for analyzing cough sound by using disease characteristics to diagnose respiratory diseases, and the method comprises the steps: deploying a six-microphone annular array to achieve the precise positioning and triggering of a sound source; self-adaptive spectral subtraction and Wiener filtering cascade are adopted to enhance the audio; segmenting a cough segment based on energy envelope; fusing the Mel-cepstrum, the linear prediction residual error, the harmonic energy ratio and the transient zero-crossing rate to construct a pathological feature matrix; extracting local, medium-range and global time sequence features through a three-branch parallel convolutional network; inputting a disease specific classifier to discriminate asthma, pneumonia and laryngitis respectively, and applying a feature decoupling regular term to improve interpretability. The system correspondingly realizes the modularized processing flow. According to the method, the cough sound collection quality and the disease subtype recognition accuracy in a complex environment are improved, meanwhile, the thermodynamic diagram is output to assist clinical decision making, and the diagnosis credibility and practicability are enhanced.

The invention relates to the technical field of bridge disease diagnosis and maintenance, in particular to a bridge disease diagnosis and maintenance measure recommendation method which comprises the following steps: constructing a bridge disease database which comprises feature data and cause data of various types of bridge diseases and maintenance measure data matched with the various types of diseases; receiving field disease information of a target bridge input by a user, wherein the field disease information comprises a disease type and a disease characteristic parameter; performing matching analysis on the field disease information and data in the bridge disease database, and diagnosing a disease cause of the target bridge based on a matching result; according to the diagnosed disease causes, one or more maintenance measures corresponding to the disease causes are called from the bridge disease database and output as recommended schemes, and a complete data link from disease detection to maintenance decision is established by constructing the standardized bridge disease database and a matching mechanism.

The invention provides a drug-disease association prediction method and system, computer equipment and a medium, and belongs to the technical field of computers. The method comprises the following steps: constructing a drug-protein-disease heterogeneous network, and extracting a plurality of element path sub-graphs; inputting the meta-path sub-graph into a multi-scale diffusion graph convolution module, executing learnable multi-step graph diffusion on the basis of graph convolution, synchronously capturing local adjacency and high-order topological information, and generating node embedding; and performing dynamic weighted fusion by utilizing meta-path attention to obtain unified representation. In order to relieve imbalance of positive and negative samples, implementing difficult negative sampling in the embedding space, and constructing a balance training set with the positive samples; medicine-disease features are spliced, a regularization XGBoost classifier is trained, and unknown correlation accurate prediction is achieved. By adopting the method, the drug-disease association prediction precision and efficiency are improved, multi-scale topology and priori knowledge are fused, and a powerful calculation tool is provided for drug relocation.

The embodiment of the invention provides a tunnel disease detection method and system based on an unmanned aerial vehicle, and belongs to the technical field of defect optical detection. The method comprises the steps that an unmanned aerial vehicle is controlled to fly along a tunnel to collect multichannel image data of the surface of a structure, and the flight attitude is adjusted based on environment illumination information to execute image illumination compensation; performing image alignment of each target anchor point based on a structure anchor point atlas constructed based on historical acquisition images in combination with the flight pose information of the unmanned aerial vehicle and the multi-channel image data after illumination compensation; identifying a disease area in the aligned image, extracting disease features of each target anchor point at this time, and updating the disease of each target anchor point at this time into a time sequence feature data sequence corresponding to each target anchor point; and based on the updated time sequence characteristic data sequence of each target anchor point, Bayesian point change detection is adopted to analyze the disease evolution trend of the tunnel. According to the scheme, the alignment precision, the time sequence comparability and the risk judgment capability of tunnel disease detection are integrally improved.

The invention discloses a brain disease risk prediction method and system based on big data analysis, and belongs to the technical field of brain disease risk prediction. The method comprises the following steps: carrying out standardized preprocessing and tagged classification on brain disease related big data to generate a feature data set; mining specific disease characteristics and risk factors in the set, and carding an association rule; training a risk prediction sub-model for each disease type based on the data, and building a multi-sub-model hierarchical prediction system; and collecting to-be-predicted object data, matching a disease type, and calling the corresponding sub-model to complete risk assessment. The system comprises multiple modules for collaborative operation, and a full-process closed loop of data storage, feature processing, model management and result output is realized. According to the scheme, the pertinence, the accuracy and the efficiency of risk prediction are improved, the traceability of the whole process and the dynamic optimization of the model are realized, and reliable technical support is provided for early screening and risk early warning of brain diseases.

The invention relates to a road infrastructure full-automatic inspection method, device and equipment based on an unmanned aerial vehicle group, and a medium thereof. The method aims at the problem that disease characteristics collected by unmanned aerial vehicles in traffic flow and vegetation shielding scenes are broken, and the method comprises the following steps of: decoupling texture and motion characteristics of a dynamic shielding area; feature maps of the effective area and the shielding area are separated; performing cross-frame splicing and continuous repair on the fracture features by using an optical flow constraint generation network, and reconstructing the geometric integrity of a shielded region; infrared data are fused to correct thermal deformation errors, and a high-precision continuous curved surface model is generated; and finally, based on a disease quantitative feature vector matching maintenance strategy, realizing full-process automation from data acquisition to decision output. According to the method, the continuous modeling precision and the maintenance decision reliability of pavement disease detection in the shielded environment are remarkably improved.

The invention discloses a pathogen transmission rapid early warning and traceability analysis method based on multi-source data fusion. The method comprises the steps of S1, collecting multi-source data such as drug sales, network behaviors, social media, outpatient diagnosis and traffic time and space; s2, through cleaning and standardized preprocessing, social text disease features are extracted by adopting BERT; s3, mining a comprehensive weak signal through single-source anomaly detection and multi-source correlation analysis; s4, fusing the features by using an Attention-LSTM model, and outputting a regional risk index; s5, training an early warning model based on historical data, and setting a three-level threshold to trigger early warning; and S6, positioning a propagation starting point in combination with the spatio-temporal data, and constructing a propagation chain through a graph neural network. The early warning is advanced by 3-7 days, the traceability precision reaches the community level, and the prevention and control precision is improved.

The invention discloses a Chinese patent medicine prescription intelligent assistance method and system, and the method comprises the steps: determining a possible traditional Chinese medicine diagnosis range through disease information / patient information, carrying out the further analysis, obtaining the disease feature information / patient feature information which needs to be obtained for determining the traditional Chinese medicine diagnosis, and determining the traditional Chinese medicine diagnosis according to the related information. The Chinese patent medicine prescription intelligent auxiliary system comprises a demand acquisition module, a feature information analysis module, an information acquisition module and a traditional Chinese medicine diagnosis analysis module. According to the Chinese patent medicine prescription intelligent assistance method and system, doctors and patients can be helped to accurately select Chinese patent medicines, and damage caused by misuse of the medicines is prevented.

The invention discloses a tumor patient portrait construction method and system based on multi-source heterogeneous data. The method comprises the following steps: collecting heterogeneous data related to a tumor patient; preprocessing the heterogeneous data, including format standardization, missing value completion, time sequence alignment and privacy desensitization processing, to obtain a data set which can be used for unified modeling; respectively extracting disease features, psychological features, behavior features, social features and regional features, and generating corresponding feature vectors for various features; mapping the feature vectors to a unified feature space by using a heterogeneous graph neural network based on an attention mechanism, dynamically calculating contribution degrees of different features to patient portraits, and establishing a multi-dimensional feature association graph of the tumor patients; and generating a structured tumor patient portrait including a disease dimension, a psychological dimension, a behavior dimension, a social dimension and a regional dimension. According to the method, high-precision, multi-dimensional and explainable patient feature description is realized, and a data basis is provided for precise service.

The invention provides a multi-element machine learning model-based cross-species lung disease characteristic gene screening method and system, an electronic system and a storage device. The method comprises the following steps of: acquiring single cell / transcriptome data related to mouse lung diseases from a public database and preprocessing the single cell / transcriptome data; training the model by adopting six machine learning algorithms and outputting a gene importance score; calculating the weight according to the model performance and normalizing the score; and integrating the cross-species scores through a weighted fusion formula, and outputting a feature gene list and a visual report. The system comprises a data acquisition and preprocessing module, a multi-element machine learning model training module, a weight calculation and normalization module, a cross-species comprehensive scoring module and a result output module. The screening accuracy, stability and generalization ability are improved through multi-algorithm integration and cross-species fusion, and the method can be widely applied to the fields of mechanism research of lung diseases, diagnosis marker development and drug target verification.

The invention relates to the technical field of tunnel safety, and discloses a safety detection method and system for a large-span multi-arch tunnel, and the method comprises the following steps: a preventive monitoring step: carrying out the dynamic monitoring of a middle rock pillar, a double-hole junction section and a vault region of the multi-arch tunnel through a monitoring device, and collecting the deformation data and stress data of surrounding rock and a structure; a disease detection step: detecting the tunnel lining and the surrounding rock by adopting a mode of combining surface detection and hidden detection to obtain surface disease characteristics and hidden disease characteristics; and a data fusion step: carrying out fusion processing on the deformation data, the stress data, and the surface disease characteristics and the hidden disease characteristics obtained in the disease detection step. The deformation data and the stress data are obtained by dynamically monitoring the middle rock pillar, the double-hole junction section and the arch crown area, and the problem that the tunnel safety state evaluation is not comprehensive due to the fact that a single-dimension monitoring or detection mode is mostly adopted in traditional tunnel safety detection is solved.

The invention discloses a lung function evaluation method for a patient in a pneumonia rehabilitation period, and relates to the technical field of rehabilitation management. Extracting a lung function feature set based on the image data; analyzing based on multi-dimensional parameter association, and establishing a dynamic mapping relationship between the lung function feature set and associated physiological parameters; identifying abnormal associated parameters through a dynamic mapping relation between the lung function feature set and the associated physiological parameters, and when the deviation between the image feature recovery degree and the corresponding physiological parameter recovery degree exceeds a preset threshold value, judging that functional abnormal parameters exist; and matching a potential complication database based on the abnormal parameter type, analyzing the relevance between the abnormal parameter and a preset disease feature model, and outputting secondary disease risk early warning. The method has the advantages that through cross-modal fusion of the lung image features and the dynamic physiological parameters, the early recognition precision of the pneumonia convalescence complication is remarkably improved.

The invention provides a plant disease feature extraction and classification method and system based on deep learning, and relates to the technical field of plant disease identification, and the method comprises the steps: mining the interdependence rule of different disease features through constructing a disease feature symbiosis wake-up network, and setting wake-up conditions; inputting a to-be-analyzed plant disease image into the network, capturing initial disease features, triggering associated feature wakeup, and generating a disease feature symbiotic set; conducting the characteristic information according to the hierarchical relationship to generate enhanced symbiotic disease characteristics; recording morphological change details to construct a disease characteristic evolution sequence; and inputting the disease characteristic evolution sequence into a pre-trained deep learning classification model, analyzing disease essential characteristics, and generating a classification result containing a disease type and a matching basis. The method can comprehensively and accurately extract features, and improves the accuracy and reliability of plant disease classification.

The invention relates to the technical field of intelligent disease and insect pest recognition, and discloses an improved ResNet50-based agricultural disease and insect pest recognition method and system, and the method comprises the steps: recognizing the crop variety of an agricultural crop and the corresponding disease and insect pest type; an intelligent monitoring network of agricultural planting crops is set, and pest and disease damage characteristics of the agricultural planting crops are extracted; inputting the pest and disease damage characteristics and the pest and disease damage types into a pre-trained ResNet50 network model as input data, so as to identify disease crop characteristics of the agricultural planting crops through an attention mechanism in the ResNet50 network model; according to the characteristics of the diseased crops, extracting key disease areas of the agricultural planting crops by using a disease and pest behavior detection mechanism of a ResNet50 network model, and analyzing disease causes of the diseased crops; and in combination with the key disease areas and disease causes, generating disease and pest identification results of the agricultural planting crops. The accuracy and efficiency of agricultural pest identification can be improved.

The invention relates to the technical field of medical data management, and discloses a GIST special disease database intelligent management system, which comprises a multi-source data acquisition module, a standardized processing module, an intelligent analysis module and a security sharing module, the multi-source data acquisition module is in communication connection with a hospital information system H IS, a laboratory information system L IS, an image archiving and communication system PACS and a patient end application, and is used for acquiring electronic medical records, inspection reports, image data and patient active report data; a standardized data model is built in the standardized processing module, and the standardized processing module is used for performing field mapping and format conversion on the acquired multi-modal data; the intelligent analysis module comprises a machine learning algorithm engine. According to the medical data management system, the multi-source data acquisition module is in communication connection with the hospital information system and the laboratory system, so that the problem that most traditional medical data management systems can only acquire single-source or single-mode data, and consequently disease characteristics cannot be comprehensively reflected is solved.

The invention belongs to the technical field of disease detection, and discloses a rice multi-disease detection method based on improved YOLOv11n, a novel model MSAF-YOLO obtained by improving a YOLOv11n model structure is adopted, the novel model MSAF-YOLO uses a CSPC module to replace an SPPF module in a backbone network part, uses an ACM module to replace a C3k2 module in the backbone network part, and constructs a CSMS-BiFPN as a neck architecture; the rice multi-disease detection method comprises the following steps: S1, image acquisition; s2, preprocessing the image and constructing a data set; and S3, inputting the data set into the novel model MSAF-YOLO for training, and evaluating the model. According to the invention, the capturing capability of the model for disease characteristics of different scales is enhanced, the sensitivity of the model to tiny disease spots is improved, and background noise is effectively inhibited. While the high and low layer feature fusion efficiency is optimized, the number of parameters and the calculation overhead are greatly reduced.

The invention discloses a drug-disease association prediction method, system, device and medium, and relates to the technical field of drug relocalization, and the method comprises the steps: constructing a drug similarity network and a disease similarity network; obtaining a binary adjacency matrix through k-neighbor graphs of different nodes in the two similarity networks, carrying out weighted fusion on the binary adjacency matrix through an attention coefficient to obtain a soft adjacency matrix, and carrying out fine-grained graph convolution updating to obtain drug features and disease features; extracting heterogeneous node representations of drugs and diseases in the biochemical heterogeneous network, and carrying out dynamic weight distribution on different representations to obtain final embedding of drug nodes and disease nodes; and splicing the final embedding of the drug nodes and the final embedding of the disease nodes, and performing prediction according to the spliced features to obtain the drug-disease association probability. According to the method, the potential complementary relationship between the two is fully mined, and the heterogeneous feature fusion effect is improved, so that the performance and robustness of drug-disease association prediction are integrally enhanced.

The invention provides a disease portrait generation method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: constructing a feature association map according to multi-source data; inputting the atlas into a hierarchical graph attention network, learning a direct association and combination relationship of feature nodes by using a hierarchical structure, and obtaining an attention weight; candidate key feature nodes are screened accordingly; performing causal effect estimation on the candidate key feature nodes to obtain a causal effect value representing real causal intensity; and finally, based on the attention weight and the causal effect value, determining an association level and generating a disease portrait. According to the method, the depth feature mining capability of the hierarchical graph attention network and the counterfeit elimination and true storage capability of causal inference are fused, so that automatic discovery of the high-order combination relationship of the disease features and quantitative verification of the true causal are realized, and a dynamic disease portrait with depth correlation information and high-credibility causal interpretation can be generated.

The application relates to the technical field of pest and disease identification, in particular to a dynamic early warning and prevention and control system based on forestry pest and disease identification, which obtains crown layer leaf attribute data of target forest area tree species and excitation source physical characteristic parameters of a patrol unmanned aerial vehicle, determines aerodynamic pressure required for turning over of the crown layer leaves according to the leaf attribute data, determines aerodynamic excitation control parameters in combination with the excitation source physical characteristic parameters and a final parameter mapping model, controls the unmanned aerial vehicle to force the leaves to turn over by using a downward airflow to obtain leaf back image data, and adaptively corrects the control parameters according to an effective leaf back exposure rate; image recognition is performed on the leaf back image data to obtain pest and disease characteristic data, and a leaf stiffness index is calculated through time domain analysis; pest and disease severity is generated according to the pest and disease characteristic data and the leaf stiffness index, and a graded early warning is performed; the application can effectively obtain leaf back image information, and realizes early and accurate identification and dynamic early warning of pests and diseases.

The invention relates to a crop disease identification method based on wavelet transform and residual network fusion. According to the method, a CBAM attention mechanism, wavelet transform and a residual network are fused, and a disease identification model (CropNet) for non-specified crop types is provided. According to the CropNet, firstly, Haar wavelets are utilized to perform four-stage decomposition on disease images, frequency domain features are deeply extracted, and the frequency domain features and spatial features extracted by a residual network are continuously fused; then different weights are given to the fused feature layer by using CBAM, and the attention of the model to a disease area is increased; and finally, a dual transfer learning training model is utilized to improve the accuracy and generalization of the model for identifying diseases of non-specified crop types. The identification accuracy of the CropNetA is 99.76%, the identification accuracy of the CropNetA is 99.85%, and the identification accuracy of the CropNetA is 99.86% on the PlantVillage data set, the identification accuracy of the CropNetA is 99.85% on the AI Challenger 2018 data set and the identification accuracy of the CropNetA on the self-built data set. The result shows that the method can obtain clearer and more sufficient disease characteristics while reducing the noise, improves the disease recognition precision, and provides reference for intelligent agriculture and precise recognition, prevention and control of crop diseases.

The present disclosure describes systems configured to recognize indicators of a medical condition within a diagnostic image and predict the progression of the medical condition based on the recognized indicators. The systems can include neural networks trained to extract disease features from diagnostic images and neural networks configured to model the progression of such features at future time points selectable by a user. Modeling the progression may involve factoring in various treatment options and patient-specific information. The predicted outcomes can be displayed on a user interface customized to specific representations of the predicted outcomes generated by one or more of the underlying neural networks. Representations of the predicted outcomes include synthesized future images, probabilities of clinical outcomes, and / or descriptors of disease features that may be likely to develop over time.

The invention discloses a neurosurgery patient data management method, and relates to the technical field of big data management, and the method comprises the steps: defining a special disease library body and a data extraction rule, and distributing the special disease library body and the data extraction rule to all medical branch centers; performing regularized extraction on medical data in the local medical data source to generate special disease feature data, and performing scanning comparison on medical record texts in the local medical data source through a large language model to generate clinical feature suggestions; traceability auditing information is added to all special disease feature data to form a special disease data pool, and clinical feature suggestions are incorporated into local ontology evolution suggestions; and encrypting and transmitting the local ontology evolution suggestions to a coordination center, integrating all the local ontology evolution suggestions by the coordination center, and generating a global ontology updating instruction through a federated collaborative evolution mechanism. According to the method, the large language model is deployed in the local medical branch center, and semantic comparison is performed in combination with the special disease library ontology, so that supplementary recognition of clinical information which is not regularly extracted and covered in the medical record text is realized.

The invention belongs to the technical field of data processing, and particularly relates to an internet-based traditional Chinese and western medicine intelligent diagnosis and treatment method and system and a storage medium, and the method comprises the steps that a user fills in different disease feature data through a mobile terminal module, and the mobile terminal module preprocesses the different disease feature data; the preprocessed different disease feature data are sent to the diagnosis and treatment server module through the internet module; the diagnosis and treatment server module pre-trains a diagnosis and treatment model 1, a diagnosis and treatment model 2, until a diagnosis and treatment model N. The diagnosis and treatment server module receives different disease feature data from the mobile terminal module, selects a proper diagnosis and treatment model from the diagnosis and treatment model 1, the diagnosis and treatment model 2, until the diagnosis and treatment model N, and sends the selected diagnosis and treatment model to the diagnosis and treatment server module. And inputting the different disease feature data into the selected diagnosis and treatment model, and outputting disease names corresponding to the different disease feature data by the diagnosis and treatment model. According to the invention, the disease identification accuracy can be improved.

The invention belongs to the technical field of road surface detection, and relates to a multi-dimensional radar map construction method based on electromagnetic signals, which comprises the following steps: S1, scanning a target area through high-frequency three-dimensional ground penetrating radar equipment, acquiring electromagnetic reflection signals, and preprocessing the acquired signals; s2, converting the time domain data of the preprocessed electromagnetic reflection signal into spatial domain data, and generating a three-dimensional data model; s3, blank data in the three-dimensional data model are complemented through an interpolation method, and high-resolution three-dimensional grid data are generated; s4, extracting a disease area based on a reflection intensity threshold value and performing type identification; and S5, constructing a three-dimensional disease visualization model, and mapping disease characteristic parameters by adopting color coding. According to the method provided by the invention, the depth resolution and the spatial positioning precision of disease detection are improved, and the real distribution and form of the diseases in the pavement can be reflected more comprehensively.

To provide a device which improves accuracy of infection risk determination of an infection disease.SOLUTION: The infection risk estimation system comprises: means for acquiring positional information of a user; means for acquiring biological information of the user and information on an affecting disease; estimation means for estimating a disease infection risk (possibility of infection from a patient of an infection disease) of the user; and reporting means for reporting the disease infection risk of the user. The estimation means determines from the history of the positional information of a first user affected by a disease a second user who was in contact with the first user, estimates the active state of the first user in a period when the first user was in contact with the second user from the biological information of the first user, and estimates the infection risk of the second user from the active state of the first user and the feature of the disease. When it is estimated that the risk of the second user having infected by the disease is high, the reporting means gives a report on high possibility of the infection by the disease.SELECTED DRAWING: Figure 6

The application belongs to the technical field of pest and disease identification, and discloses a pepper pest and disease identification method and system based on a disease grading detection double-task model. 2 The sample image is subjected to enhancement processing by using a saliency target detection model U 2 The sample image is subjected to foreground and background segmentation by using U 2 The main body of the leaf in the image is retained, the authenticity and integrity of the disease characteristics are ensured, and the diversity of the data is increased to achieve the purpose of data enhancement.

The application discloses a disease pre-examination triage auxiliary method and system, relates to the technical field of disease pre-examination triage, collects patient treatment data to generate a data group, extracts features of the data group to obtain a disease feature vector, constructs a dynamic routing layer to convert the disease feature vector into a plastic weight matrix, constructs a processing cluster layer including a quick response cluster and a deep analysis cluster, inputs the plastic weight matrix into the processing cluster layer to obtain an analysis result, and outputs a treatment guide report by fusing analysis results of multiple clusters through a decision fusion layer.

The present application relates to the technical field of intelligent wearable medical equipment, in particular to an intelligent bracelet for monitoring neurological diseases, which comprises a wristband body and an electronic monitoring system, the electronic monitoring system comprising a multi-modal physiological signal acquisition module, a microprocessor control unit, a disease characteristic analysis module, an early warning feedback module, a wireless communication module and a power management module. By collecting multi-dimensional physiological signals, Parkinson's disease targeting features, epilepsy targeting features and double disease auxiliary features are extracted, then through the basic differentiated contribution weight of the convolution long short-term memory network model and the dynamic output distribution weight adjustment strategy triggered by the pathological threshold, the spatio-temporal fusion analysis is realized and the risk probability of the two diseases and the normal state probability are output, the early warning feedback module outputs differentiated prompts according to the risk probability, the wireless communication module synchronizes data or sends emergency alerts through dual-mode communication, and the power management module realizes power supply and low power reminder.

The invention belongs to the field of bioinformatics, and relates to a circRNA-disease association prediction method based on an attention fusion graph-hypergraph convolutional network. The method comprises the following steps: firstly, constructing a circRNA-disease incidence matrix and a plurality of similarity matrixes based on a database; secondly, respectively constructing a graph adjacent matrix and a hypergraph adjacent matrix based on the similarity matrix, extracting circRNA and disease low-order local features by using a graph convolutional network, and extracting circRNA and disease high-order global features by using a hypergraph convolutional network; then, dynamically fusing circRNA and disease low-order local features obtained from the graph convolutional network and circRNA and disease high-order global features obtained from the hypergraph convolutional network through an attention aggregation mechanism, and enhancing feature interaction by means of comparative learning; then, using a variational auto-encoder to extract circRNA and disease nonlinear characteristics from the incidence matrix; and finally, integrating a plurality of circRNAs and disease characteristics, and predicting a circRNA-disease association score. According to the method, multi-level features can be effectively fused, and the prediction accuracy and robustness are improved.