556results about How to "Improve discrimination ability" patented technology

The invention provides a three-dimensional point cloud data segmentation method and system based on multi-scale point features, and relates to the technical field of point cloud processing, and the method comprises the steps: obtaining original point cloud data, constructing a three-dimensional Hash index table, carrying out the self-adaptive hierarchical division through a local maximum value of a density distribution curve, and obtaining a local maximum value of a density distribution curve; noise point elimination is carried out based on a region density count value and a geometric distribution coefficient, an enhanced feature vector containing a main feature direction, a main curvature value and the like is constructed for non-eliminated points, a local geometric descriptor is constructed by adopting four spherical search regions with increasing radiuses, a three-branch space attention network is input to extract spatial features, and the spatial features are extracted; and fused feature data are obtained through a multi-level geometric feature extraction network and a bidirectional feature propagation network. And obtaining a final segmentation result through segmentation energy function optimization and a region merging strategy.

The invention relates to the technical field of image classification, and discloses a breast image classification evaluation method and system based on deep learning, and the method comprises the steps: carrying out the preprocessing of sample breast image data, and obtaining comprehensive feature data; performing feature enhancement based on the comprehensive feature data to obtain enhanced feature data; performing multi-modal bidirectional feature fusion on the enhanced feature data to obtain multi-modal fusion feature data; based on the multi-modal fusion feature data, constructing and training a semi-supervised local feature reservation dense connection context-aware graph convolutional network to obtain a graph volume integral class model; according to the multi-modal fusion feature data, constructing and training a multi-branch residual attention reconstruction network to obtain a multi-scale feature fusion model; through the image volume integral class model and the multi-scale feature fusion model, classification evaluation and prediction result integration are carried out on the real-time mammary gland image data to obtain a target mammary gland image classification result, and the method improves the accuracy and reliability of mammary gland image classification.

The invention relates to the technical field of video stitching, and discloses a monitoring video stitching method, device and equipment and a storage medium, and the method comprises the steps: carrying out the video framing of a monitoring video collected by a monitoring terminal, and obtaining a plurality of target video frames; performing human shape detection to obtain a human shape detection result; aligning and cutting a face region in the human shape detection result to obtain a standardized face image, and extracting a face feature vector; performing motion prediction and trajectory extrapolation to obtain a multi-target human shape tracking result; inputting the multi-target human shape tracking result into a distributed computing framework for task allocation and cross-node feature matching to obtain a global human shape tracking result; and performing double-flow network processing on the plurality of target video frames according to the global human shape tracking result, calculating to obtain video stitching parameters, and performing stitching operation on the plurality of target video frames to obtain a stitched video, thereby effectively improving the quality and visual effect of the stitched video.

The invention discloses an aggregation neighborhood embedding image text matching method based on clustering prototype guidance, relates to the technical field of computer vision and natural language processing, and provides a full-granularity prototype guidance neighborhood embedding framework. The framework dynamically learns a unified representation space through clustering prototype momentum contrast learning, and relieves a soft positive sample problem; global and local feature joint extraction and an adaptive aggregation network are introduced, so that the global information understanding capability is improved; an intra-modal correlation degree matrix and an inter-modal correlation degree matrix are constructed, and the neighborhood relation of sample instances is deeply mined; and by adopting a momentum contrast learning technology, the negative sample capacity is expanded, and the feature discrimination capability is improved. Experimental results show that the performance of the FPNE on Flickr30K and MS-COCO data sets is superior to that of an existing most advanced method, the image-text matching precision and efficiency are remarkably improved, and high robustness and wide applicability are shown.

The invention relates to a tumor image segmentation method. Performing multi-scale feature extraction on the image by using a convolutional neural network (CNN) to capture different-scale information of the tumor; introducing a self-attention mechanism to enhance the attention capability of the model on the tumor area and the accuracy of feature extraction; performing image segmentation through the improved model based on the U-Net architecture; according to the method, the advantages of a CNN and a VisionTransform are combined, local and global features are extracted by using a hybrid architecture, and position codes are added into the Transform so as to enhance the perception capability of spatial position information; adopting a comparative learning strategy to improve the discrimination capability of the model by comparing positive and negative sample pairs, and performing multi-task learning in combination with a tumor classification task and a segmentation task; designing a combination of a weighted cross entropy loss function and a Dice loss function, and improving the sensitivity to a small tumor region; and performing post-processing by using a conditional random field (CRF) to optimize a segmentation boundary, and eliminating small noise points and filling holes of a segmentation region by applying morphological operation to further optimize a segmentation result.

The invention relates to a multi-modal implicit sentiment analysis method based on a multi-granularity attention mechanism, which belongs to the field of artificial intelligence, and comprises the following steps: S1, extracting visual features in image information by using a visual feature extraction strategy of multi-scale attention fusion; s2, generating a text description of the image information by adopting an image translation engine, splicing the text description with an original text, and extracting text features through a hierarchical attention mechanism; s3, carrying out normalization processing; s4, performing multi-modal fine-grained correlation fusion on the visual features and the text features by adopting a bidirectional cross attention mechanism, and extracting fine-grained features in the visual features and the text features through a multi-head attention mechanism and residual connection; and S5, fusing the fine-grained features by using an adaptive multi-modal classification module to complete sentiment classification. The multi-modal sentiment analysis method solves the problems that multi-modal sentiment analysis is insufficient in inter-modal correlation mining, insufficient in fine-grained information capture and large in noise interference.

The invention provides a forged voice detection method and system based on multi-task learning, and the method comprises the steps: carrying out the preprocessing of original audio data, and extracting a primary feature through a pre-training model; then, inputting the primary features into a forged voice detection model, and carrying out multi-task learning; thirdly, jointly optimizing classification loss and reconstruction loss, and training the forged voice detection model until convergence; and finally, performing authenticity detection on to-be-detected audio data by using the trained forged voice detection model, and distinguishing whether the to-be-detected audio data is forged voice or not. The method is suitable for acoustic scenes in which the number of real voices and the number of counterfeit voices are unbalanced, is also suitable for detecting counterfeit voices of unknown counterfeit types, and has good universality and generalization.

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 provides a remote sensing image target detection method based on an improved FCOS, and relates to the technical field of target detection, and the method comprises the following steps: carrying out the convolution and pooling operation of a remote sensing target image based on a pre-trained convolutional neural network, generating a preliminary feature, and carrying out the enhancement processing of the preliminary feature through a twin multilayer perceptron; carrying out fusion processing on different levels of feature information in the multi-level feature map through a feature map splicing mode and a feature map enhancement mode; and determining the position of the remote sensing image target according to the analysis result to obtain a target detection result. According to the method, the feature pyramid network is combined with an innovative coordinate attention mechanism, fusion of high-level semantic information and low-level detail information is realized, an enhanced multi-scale feature map is generated to cope with diversity of target scales in a remote sensing image, multi-scale fusion and an anchor-frame-free design are combined, false detection is effectively reduced, and the detection accuracy is improved. Therefore, the method shows efficient, accurate and wide application potential in the field of remote sensing image target detection.

The invention relates to the technical field of intelligent lock recognition, in particular to an intelligent lock image feature recognition method and system based on deep learning. The recognition method comprises the following steps: constructing a multi-branch deep neural network model, wherein the multi-branch deep neural network model comprises a backbone network, a feature extraction branch and a feature fusion branch; a framework training model is used to learn identity recognition, attitude estimation and environment perception tasks; and identifying the comprehensive feature representation by using a trained framework training model, and generating a control instruction of the intelligent lock according to an identification result. According to the intelligent lock image feature recognition method based on deep learning provided by the invention, comprehensive analysis of multi-dimensional information such as identity, posture and environment is realized by constructing the multi-branch deep neural network model.

The invention relates to the technical field of image analysis and processing, in particular to a high-precision detection method based on image analysis, which comprises the following steps: acquiring an original image to be detected, performing preprocessing operation on original image data, including normalization processing, de-noising processing and brightness adjustment, performing multi-scale feature conversion on the preprocessed image to generate feature matrixes of different scales, calculating the correlation degree between the feature matrixes through a correlation self-adaptive fusion module, and generating a fusion feature map; calculating a significance score of each pixel point in the fused feature map, generating an abnormal score matrix, and determining a significant abnormal region in combination with the deviation matrix; original image information is decomposed into different scales through a multi-scale feature conversion module, local and global abnormal features of an image are captured by using comprehensive information of feature matrixes of different scales, information redundancy among the features of the scales is eliminated, and the identification degree and the detection accuracy of an abnormal region are improved.

The invention relates to the technical field of financial data processing, in particular to a data processing method and system based on financial information bills. The data processing method comprises the following steps: acquiring multi-modal financial information bill data; and performing bill modal decomposition on the multi-modal financial information bill data to generate financial information bill modal decomposition data. Bond information price income prediction needs a large amount of financial data, such as market interest rate, bond expiration date, face interest rate and the like, the data are similar to the data form of bill modal decomposition, and a more accurate model can be obtained through standardization and feature extraction of multi-modal data. Therefore, valuable input is provided for bond price and income prediction. According to the invention, through multi-modal data fusion, counterfeited feature comparison modeling, abnormal bill clustering analysis and dynamic risk assessment, the security and accuracy of financial bill identification are improved.

The invention discloses an electrocardiosignal open-set identity recognition method based on a hybrid network and a cross attention mechanism, and belongs to the technical field of identity recognition. The electrocardiosignal open-set identity recognition method comprises the steps that electrocardiosignals are preprocessed to obtain standardized input; constructing a hybrid network model to extract a long-time dependency relationship between multi-scale local space information and a time sequence; fusing different types of information by using a cross attention mechanism; and establishing an Openmax classification layer to realize identity tag identification in an open set environment. By means of the method, the known individual identity can be effectively recognized, unfamiliar persons are rejected, and the accuracy of electrocardiosignal identity recognition and the applicability in the practical application scene are improved.

The invention provides a mining equipment fault diagnosis method based on multi-parameter change monitoring. The mining equipment fault diagnosis method comprises the following steps: firstly, constructing a fault diagnosis model through a neural network; digital signals of the running state of the mining equipment are obtained in real time through a plurality of sensors; the digital signals are preprocessed through a data preprocessing module; then, features capable of representing the running state of the equipment are extracted from the preprocessed digital signals through a feature extraction module based on a neural network, and then the extracted features are spliced and fused through a feature fusion module; and finally, analyzing the fused features through a fault diagnosis training model, carrying out fault diagnosis, generating fault information according to a fault diagnosis result, and sending out a fault alarm. According to the method, various parameter data of the operation state of the mining equipment are fully considered, feature extraction and feature splicing fusion are performed based on the twin neural network, the feature discrimination is effectively enhanced, and the intelligent fault diagnosis accuracy and efficiency of the mining equipment are improved.

The invention provides a traditional Chinese medicine abnormal state recognition method, system and device and a storage medium, and relates to the field of abnormal recognition. The method comprises the following steps: acquiring product information of a to-be-detected traditional Chinese medicine, and determining a data acquisition standard of the to-be-detected traditional Chinese medicine based on the product information of the to-be-detected traditional Chinese medicine and a preset detection rule; based on a data acquisition standard of the traditional Chinese medicine to be detected, inputting the image data into a preset image anomaly detection model to obtain a preliminary image anomaly region; performing feature fusion on the visual feature data and the spectral feature data to obtain an abnormal feature vector; and inputting the abnormal feature vector into a preset abnormal state judgment model, outputting abnormal state data, and performing abnormal state judgment based on the abnormal state data and a preset abnormal state judgment threshold to obtain an abnormal state detection result of the to-be-detected traditional Chinese medicine. Through the scheme, the abnormal state of the traditional Chinese medicine can be identified timely and accurately.

The invention provides a medical image classification unsupervised domain self-adaption and multi-granularity alignment system and a medical image classification unsupervised domain self-adaption and multi-granularity alignment method. According to the method, a coarse-to-fine progressive feature optimization strategy is provided, that is, a fine-grained feature encoder is initialized by using the training weight of a coarse-grained feature encoder, and alignment optimization of fine-grained features is guided while original semantic information is reserved. Specifically, a staged and layer-by-layer unfreezing fine adjustment method is adopted, and the adaptive capacity of fine-grained features is enhanced on the premise that the invariance of a coarse-grained domain is not damaged. According to the strategy, the generalization and convergence efficiency of the model on target domain data is remarkably improved. And experimental verification is carried out on a plurality of cross-domain medical image classification data sets. Results show that no matter on a small-scale data set or a large-scale data set, the method provided by the invention can obtain performance obviously superior to that of an existing method, and generalization ability and robustness are stronger.

The invention relates to the technical field of battery management, in particular to a new energy vehicle battery data analysis method and system, and the method comprises the following steps: merging a state feature set of a battery based on the charging and discharging period and use environment data of the new energy vehicle battery, extracting the voltage, current and temperature features of the state, and obtaining a state feature set; and carrying out feature combination on the battery degradation state, classifying and associating feature items and temperature features in the feature combination, and obtaining a state feature merging result. According to the method, through merging the new energy vehicle battery charging and discharging period and the use environment data, the battery state characteristics are accurately extracted, refined classification and correlation analysis are realized, the discrimination capability and adaptability of the state data are improved, and the state transition trend is flexibly captured based on the linkage trend of the state transition frequency and the current observation data; and dynamic evaluation is realized through correlation of periodic temperature and current, an accurate and reliable state change evaluation scheme is provided, and the dynamic response of battery management and the full-life periodic performance regulation and control quality are optimized.

The invention relates to a post-stack seismic section super-resolution reconstruction method comprising the steps that a generative network and an adversarial network are constructed, the generative network is used for improving the resolution of a post-stack seismic section, and the adversarial network is used for judging whether an input image is an original high-resolution seismic section or a high-resolution seismic section reconstructed through the generative network. A generative network composed of a multi-scale residual module, a double-attention module, a residual D module and the like is designed, and the ability of the network in the aspect of extracting important feature information is improved; a Markov discriminator-based adversarial network is also designed, so that the discrimination capability of the network on seismic images is improved; a conventional loss function of the generative adversarial network is improved by introducing total variation loss and edge information retention loss functions. According to the method, the resolution of the post-stack seismic section can be effectively improved, meanwhile, noise signals are better removed, more geological structures and features are reserved, and the sensing quality of the seismic image is improved.

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

The invention provides a zero sample image classification system and method, and the system comprises a teacher model and a student model which are the same in architecture, and each of the teacher model and the student model comprises a visual encoder, a semantic encoder, a visual-semantic alignment module and a zero sample classification module; a visual encoder of the teacher model is constructed in a manner of cascading a CNN (Convolutional Neural Network) and a Transform; selecting a BERT network as a semantic encoder of the teacher model; the visual-semantic alignment module is used for constructing a teacher model and a student model based on a cross-modal attention mechanism; a full connection layer is adopted as a zero sample classification module of the teacher model and the student model; a visual encoder of the student model is constructed by adopting a lightweight EnviroNet network; and a semantic encoder of the student model is constructed by adopting a Core-BER network. The method has the advantages that under zero sample setting, the high unseen category classification performance can be kept, meanwhile, the model complexity is reduced, and deployment on actual equipment is better facilitated.

The invention relates to the technical field of big data processing, in particular to an online state grid user classification method, system and device based on a graph convolutional neural network and a storage medium. The invention discloses an online state grid user classification method based on a graph convolutional neural network. The method comprises the following steps: extracting user explicit and implicit features; the method specifically comprises the following steps: firstly, constructing a user graph model by taking online state grid user data as input, extracting feature information in graph data by using a stack network formed by a convolutional neural network, and propagating vector representations of aggregated users and neighbor users thereof by using a cyclic convolution operation; classifying users; according to the method, the graph convolutional neural network model is used for constructing the portrait of the state grid user on the Internet, dominant and implicit features of the user are deeply mined, and an accurate user feature vector is formed. Meanwhile, user vector subdivision is achieved according to probability representation output by the full connection layer, and potential user groups are effectively recognized.

The invention discloses a speech emotion recognition method based on multi-modal feature fusion, and the method comprises the steps: designing a multi-modal speech emotion recognition model, enabling an audio to serve as a main mode, employing the function of wav2vec2.0, and combining a text mode with a visual mode to enhance the performance of emotion recognition based on the audio; the self-attention mechanism, the GRU and the LVC are combined to extract global and local information from a visual mode, the global information is extracted only from text features, visual clues and text clues related to emotion can be comprehensively understood, the extracted text and visual features are integrated into a wav2vec2.0 model, multi-mode representation of multi-level audio information is formed, and the multi-mode representation of the multi-level audio information is realized. And meanwhile, the discrimination capability of the model is enhanced by utilizing multi-modal homogeneous feature difference learning, and the proposed model is evaluated on two data sets, so that the model is proved to have excellent robustness and generalization compared with the existing most advanced model.

The invention relates to a staged-based adaptive multi-target tracking method, and provides a staged association thought and an adaptive weight strategy, when a to-be-tracked target in a video sequence has complex conditions such as long-time shielding, deformation and illumination change, target trajectories are classified according to the target shielding degree, and the target tracking accuracy is improved. A reasonable track detection frame association sequence is set in combination with the actual situation, and meanwhile, different association strategies are designed for each association, so that the tracking accuracy is further improved; a confidence coefficient difference value and speed direction information are used as a weak clue to assist a strong clue in matching between a target track and a detection frame, so that the correlation success rate is further improved; and the appearance feature updating module designs different appearance feature updating strategies for the targets with different shielding degrees so as to improve the discrimination of the appearance features. The tracking method provided by the invention can still keep track continuity and tracking stability in a complex scene.

The invention discloses a lightweight unmanned aerial vehicle target tracking method and system based on dual cross-correlation fusion. The method comprises the following steps: acquiring a video stream of a target area; adding an initial target frame to a first frame image of the video stream to calibrate the initial position of a target, taking the first frame image as a template image, and taking other frame images of the video stream as search images; preprocessing the template image and the search image; inputting the preprocessed template image and the search image into a pre-trained target tracking model to obtain a predicted position of the target in a certain frame of image of the video stream, thereby realizing target tracking; a twin network is adopted as an overall framework, a backbone network is a lightweight network, the real-time performance of an algorithm is improved while the network parameter quantity and the calculation quantity are reduced, a dual cross-correlation fusion module is adopted, the nonlinearity of fusion features is enhanced, target feature information is highlighted, an anchor-free position prediction head is used, and the tracking speed is improved. And the network parameter quantity is reduced.

The invention provides a zero sample image classification system and method, and the system comprises a visual feature extraction module which is used for obtaining image visual feature data according to an input unseen category image; the semantic information extraction module is used for obtaining image semantic information data according to the input text information corresponding to the unseen category image; the cross-modal feature fusion module is used for obtaining aligned visual-semantic feature data according to the input image visual feature data and image semantic information data; and the classification module is used for obtaining a classification result of the image category according to the input aligned visual-semantic feature data. Compared with the prior art, the method has the advantages that image information, auxiliary information and shared information between the image information and the auxiliary information can be better utilized, and under the setting of zero samples, the classification precision of visible categories can be kept at a high level, and the classification performance of unvisible categories can be effectively improved.

The invention discloses a photovoltaic power station supervised data generation method based on a generative adversarial network, which is used in the technical field of data augmentation, and comprises the following steps: initializing a generator and a discriminator, and randomly extracting training samples; training a generator and a discriminator by using the training sample, and generating a synthetic data set conforming to photovoltaic power station data set distribution through the generator; and clustering the features of the synthetic data set and the photovoltaic power station data set through a K-means clustering algorithm, observing a clustering center and feature distribution, evaluating the feature distribution difference between the generated data set and the real photovoltaic power station data set through an unsupervised clustering method, and evaluating the quality of the generated data set. According to the method, through the steps of density value sorting, initial center selection and the like, fine division of clustering is achieved, and initial center selection deviation in the clustering process is effectively avoided by combining density value calculation and a grid division method.

The invention discloses a thromboembolism occurrence risk assessment method and assessment system. The method comprises the following steps: acquiring a blood vessel image map of a to-be-assessed patient; inputting the blood vessel image map of the patient to be assessed into a pre-trained risk assessment model; wherein the pre-training of the risk assessment model is based on a ResNet-50 model, and self-supervised contrast learning iteration is carried out by inputting positive and negative samples so as to update model parameters; extracting a feature embedding vector in the blood vessel image; according to the feature embedding vector, calculating probability distribution of embolism occurrence risk levels through a model classification head; and according to the probability distribution, selecting a risk level label and outputting the risk level label as an evaluation result. According to the method based on the time axis symmetry, the image data of the patient is collected before and after the embolism occurrence time point, the positive and negative sample pairs are generated, the problem that the embolism sample is difficult to obtain is solved, and meanwhile the sample collection cost is reduced through self-supervised learning.

The invention discloses an image classification method based on intra-class difference suppression dictionary learning. The method comprises the following steps: S1, selecting an image data set; s2, preprocessing the image by using a feature extraction method to generate an image sample set; s3, constructing a supervised dictionary learning model; s4, constructing a category label matrix; s5, constructing a Laplacian matrix by using the sample data; s6, carrying out regularization on the training sample by adopting Laplacian feature mapping; s7, calculating an intra-class sparse mean vector; s8, optimizing the dictionary model by using intra-class deviation between minimum sparse coefficients; s9, solving the objective function by adopting an analytical method, and performing iterative updating on the sparse coefficient and the dictionary; s10, calculating an error according to the updated sparse coefficient and the dictionary; s11, judging whether an iteration convergence condition is met or not, if yes, outputting an optimal discrimination dictionary, and if not, executing a step S7; and S12, carrying out image classification by adopting a kNN classifier. The method is good in generalization performance and robustness and high in image classification accuracy.

The invention relates to the technical field of medical information, and discloses a pancreatic cancer risk prediction method based on machine learning and multi-modal data, and the method comprises the steps: obtaining the multi-modal data of a target user; performing time sequence deduction on the molecular biological detection data to generate a virtual molecular time sequence; time sequence signals are extracted from the virtual molecule time sequence and the time sequence behavior monitoring data; calculating the dynamic coupling strength between the two time sequence signals to obtain a space-time coupling coefficient; weighted fusion is carried out on the features, and unified multi-modal feature representation is constructed; carrying out multi-modal feature representation training to obtain a special risk prediction model for the target user; and obtaining a risk quantitative score, and identifying a key risk driving factor which contributes to the score most. According to the invention, through multi-modal time sequence fusion and personalized modeling, early-stage, dynamic and explainable and evaluable pancreatic cancer risks are realized.