2058 results about "Prediction probability" patented technology

The invention discloses an intelligent management method and system for IT equipment asset maintenance, and relates to the technical field of intelligent management. During system operation, multi-dimensional parameters of IT equipment are collected in real time and transmitted to a data processing module, the collected data are preprocessed, the current state of the equipment is comprehensively analyzed, and the health state coefficient Hstate of the equipment is calculated; the method comprises the following steps: acquiring a current equipment operation state, performing baseline establishment on historical operation data of the equipment, comparing the current state with the historical data, analyzing the performance trend and change of the equipment, calculating to obtain a trend analysis coefficient Ttend, and identifying potential problems and performance reduction trend of the equipment through long-term data accumulation. And calculating a final fault prediction probability index Pfault, comparing the final fault prediction probability index Pfault with a set threshold value, obtaining a grade prediction scheme, generating early warning information, prompting a system administrator to sort and distribute according to the urgency and priority of tasks, automatically generating a comprehensive report by the system, and providing decision support for the administrator.

The invention provides a knowledge and data fused medical content image-text generation system and method. Relates to the technical field of digital medical treatment and artificial intelligence. The multi-modal feature extraction module is used for extracting multi-modal features from the multi-modal data; the multi-modal feature fusion module is used for carrying out cross-modal dynamic fusion on the multi-modal features to generate cross-modal high-consistency fusion features; the model training optimization module is used for configuring a soft and hard target loss function and a parameter optimizer; the information analysis and reasoning module is used for carrying out semantic matching on the fusion features, the disease classification and the clinical path based on a dynamic medical knowledge network, and generating disease prediction probability distribution and a semantic reasoning path; and the image-text report generation module is used for generating an image-text report containing a diagnosis conclusion and an interpretation basis according to the prediction probability and the semantic reasoning path. According to the invention, intelligent and precise generation of medical contents can be realized.

In some embodiments, at a first time, a computing system receives a classification request specifying query content. The system executes a first pre-trained AI-generated content classifier in the set of AI-generated content classifiers on the query content to compute a set of confidence scores proportional to predicted probabilities that the query content includes content data produced by a generative AI model. The set of confidence scores is generated based on parameters learned by the first pre-trained AI-generated content classifier during a training stage. The classification results are output based on the set of confidence scores at approximately the first time.

The invention relates to a drug-disease relationship prediction method and system based on a dual-channel fusion knowledge graph. The method comprises the following steps: S1, constructing a biomedical fusion knowledge graph; s2, constructing a drug-disease sub-graph based on the biomedicine fusion knowledge graph; s3, constructing a dual-channel adaptive fusion feature module, and embedding a drug-disease sub-graph; s4, performing enhanced splicing on the drug-disease sub-graphs in the dual-channel fusion knowledge graph pre-embedded network, importing an edge-node iterative updating learning mechanism, training a spliced sub-graph relation perception learning network, and obtaining enhanced sub-graph feature embedding; and S5, utilizing the trained enhanced subgraph features to embed, calculate and output the prediction probability of the drug-disease relationship. According to the method, the semantic representation capability of the knowledge graph and the topological modeling advantages of the graph neural network are integrated, and efficient and accurate prediction of the drug-disease relationship is realized through multi-modal feature interaction, sub-graph enhancement and a dynamic sub-graph learning mechanism.

The invention relates to the technical field of cold-chain logistics monitoring, and discloses a temperature prediction method and system for a multi-modal AIGC cold-chain logistics monitoring platform, and the method comprises the steps: carrying out the multi-modal data collection and data fusion of a cold-chain logistics transportation process based on a cold-chain logistics monitoring platform, and obtaining a multi-modal fusion data matrix; inputting an AIGC model to carry out feature extraction and inter-modal feature weight calculation to obtain a multi-modal feature importance vector; performing cross-modal weighted fusion calculation and associated feature map construction to obtain a temperature state feature sequence; inputting a multi-modal deep belief network to carry out probability distribution modeling to obtain a temperature prediction probability distribution sequence; performing time sequence characteristic analysis to obtain a temperature prediction interval sequence; and performing dynamic threshold judgment to obtain a multi-stage temperature early warning trigger signal. According to the invention, the temperature prediction accuracy of the cold-chain logistics monitoring platform is improved.

The invention relates to an automatic data labeling method of an ISP image signal processing visual sensor. The method comprises the following steps: carrying out noise reduction and signal enhancement on an original image data stream acquired by an ISP image signal processing visual sensor to obtain a standardized image sequence; performing time sequence feature extraction to obtain a time sequence feature tensor; performing spatial feature extraction to obtain spatial-temporal feature representation; inputting a double-fold teacher-student network for semi-supervised training to obtain an initial image annotation model; performing quality evaluation based on the prediction probability distribution and the time sequence consistency to obtain a labeling result with a quality score; and storing a high-quality sample in the labeling result with the quality score into a sample buffer pool, carrying out sample screening based on entropy and distance measurement, and carrying out parameter updating on the initial image labeling model through an incremental learning strategy to obtain a target image labeling model. According to the invention, the reliability evaluation of the labeling result is realized, and the accuracy of automatic labeling is ensured.

The embodiment of the invention provides an image semantic segmentation method and device fused with Fourier transform, and the method comprises the steps: constructing a segmentation model based on a U-shaped network, and carrying out the feature extraction through employing a four-layer convolution pooling network as an encoder; constructing a Fourier transform module, performing two-dimensional discrete Fourier transform on the input image to obtain a spectrogram, and performing amplitude spectrum and phase spectrum decomposition on the spectrogram to obtain an initial frequency domain feature; performing preset size scaling and pixel normalization processing on the input image to obtain a pre-processed image, and inputting the pre-processed image into a Fourier transform module to obtain four groups of adjusted frequency domain features; a bilinear interpolation algorithm is adopted to adjust the size of the prediction probability graph to the size of an original input image, pixel points with probability values larger than 0.5 in the prediction probability graph are marked as foreground areas, and a final semantic segmentation result is obtained; according to the method, the semantic segmentation task in a complex scene can be better processed, and the segmentation precision and the model robustness are improved.

The invention discloses a dynamic weight correction and path deviation probability prediction method for a vehicle track, which comprises the following steps of: acquiring vehicle data and multi-source dynamic data of the vehicle track in real time through an optical sensor, a radio wave sensor and an inertial navigation sensor, carrying out space-time calibration, extracting obstacle characteristics and road structure characteristics, and predicting the path deviation probability of the vehicle track. The obstacle movement trend is quickly captured through a space-time diagram sequence and a diagram convolutional neural network, real-time obstacle avoidance is realized in combination with dynamic weight adjustment, a driving intention is predicted by using a Bayesian neural network, a trajectory planning strategy is adjusted through weight correction, and uncertainty is reduced by using multi-source data fusion and probabilistic prediction. A closed-loop feedback mechanism continuously optimizes the model, and efficient operation is kept in complex scenes such as intersections and roundabout through real-time weight adjustment and closed-loop feedback, so that the purpose of quickly responding to dynamic obstacles or driving behavior changes can be achieved, and the precision of the path deviation prediction probability is improved.

Provided are a method and an apparatus for constructing a road congestion prediction model, a device, a medium, and a product. A road traffic network is defined as a directed weighted graph. Historical dynamic traffic features of each road segment in the road traffic network are obtained as sample data, including recent dynamic traffic features and periodic dynamic traffic features. The sample data is input into a mixture of adaptive graph learners (MAGL) model for learning, and a probability prediction vector is output. The sample data is input into a trend expert model, and a trend distribution vector of a predicted probability of future traffic conditions is output. The periodic dynamic traffic features are fused to determine a periodicity prediction vector. An aggregated logit vector is obtained. An objective function is determined based on the aggregated logit vector. Congestion prediction training is performed to obtain a road congestion prediction model.

The invention, which relates to the technical field of fire protection and security management, discloses an intelligent fire protection and security integrated big data platform system comprising a data acquisition module, a data storage and preprocessing module, an intelligent analysis module and a linkage control module. The data acquisition module integrates fire-fighting and security sensors and equipment, and transmits data to the convergence unit in a wired and wireless communication mode, so that one-stop acquisition of fire-fighting and security basic data is realized; according to the invention, the intelligent analysis module can carry out fire prediction probability evaluation in combination with security video image features, carries out comprehensive analysis on security videos and time series data through CNN and LSTM technologies, analyzes the internal relation of fire protection and security data through an association rule mining algorithm, and generates a risk early warning report; according to the intelligent analysis method, the accuracy and timeliness of safety early warning are improved, potential safety threats can be found and processed in time, and safety accidents such as fire disasters and the like are effectively prevented.

A method for training and using a field machine learning (ML) model to classify emission data is presented. The method includes generating synthetic data by a large language model (LLM) by prompting the LLM with emission classes and few shot examples. The synthetic data includes multiple synthetic data instances and corresponding instance labels. A training dataset is obtained from the synthetic data. The method further includes training the field ML model with training instances which are synthetic data instances from the training dataset and corresponding training labels. The field ML model generates a predicted probability distribution of a training output class corresponding to a training instance. The method further includes adjusting a model parameter weight of the field ML model to minimize a categorical cross-entropy loss function calculated based on the generated predicted probability distribution. The trained field ML model is used to classify emission data.

Techniques are discussed for predicting an occupancy of visible region of an environment. For instance, a vehicle may generate sensor data representing an environment. The vehicle may then analyze the sensor data to determine an occluded region of the environment a visible region of the environment. Additionally, the vehicle may determine at least one prediction probability associated with occupancy of the visible region over a future period of time. In some instances, the vehicle determines the at least one prediction probability by inputting data representing at least the occluded region and the visible region into a machine learned model and receiving the at least one prediction probability from the machine learned model. Using the at least one prediction probability, the vehicle may then determine and perform one or more actions.

The invention relates to the field of industrial intelligent control, in particular to a real-time production efficiency optimization system based on an artificial intelligence technology, and the system comprises an equipment fault prediction module which is used for collecting multi-modal time sequence data, and predicting the equipment fault probability based on a deep learning network; the process parameter adjusting and optimizing module is in communication connection with the equipment fault prediction module and is used for receiving the fault prediction probability and dynamically adjusting process parameters based on a reinforcement learning algorithm; the federated learning and incremental training module is in communication connection with the equipment fault prediction module and the process parameter tuning module, and is used for realizing collaborative optimization and privacy protection of a local model and a global model, greatly improving the fault prediction accuracy, reducing the false alarm rate from 20% to 5% or below, prolonging a prediction window from 10 minutes to 30 minutes or above, and improving the prediction efficiency. A sufficient preventive maintenance time window is provided for a production system; and the process parameter optimization effect is remarkably improved, and the comprehensive efficiency improvement space of the equipment is expanded to 8-12% from the traditional 5%.

The invention discloses a drug and target interaction prediction method based on multi-scale convolution feature fusion, which comprises the following steps: acquiring drug molecule data, target protein data and drug and target interaction data, constructing a drug molecule map according to the drug molecule data, and coding a target protein sequence according to the target protein data; inputting the drug molecular map into a model, and obtaining drug features through a multi-scale map convolutional network and a dynamic gating attention mechanism; inputting a target protein sequence into the model, and obtaining target features through hierarchical cavity convolution and a bidirectional gating cycle unit; through multi-head cross attention, the drug features are aligned with the target features, local and global cross-modal fusion is carried out, and drug target fusion features are obtained; based on the drug target fusion features, outputting a drug and target interaction prediction probability; and training the model according to the drug and target interaction data and the prediction probability, and applying the trained model to drug and target interaction prediction.

The invention relates to the technical field of unit detection, in particular to a unit magnetic variable on-line monitoring method and system, and the method comprises the steps: carrying out the multi-source data collection through a sensor, carrying out the correction of the multi-source data through a multi-dimensional calibration mechanism, synchronizing a timestamp through a dual-synchronization system, and carrying out the frequency-band-divided conditioning and standardization processing; environmental noise in the standardized multi-source data is eliminated through an intelligent algorithm, feature vectors are extracted, and purified feature vectors are obtained; screening effective abnormal features through an isolation forest algorithm; and inputting the effective abnormal features into an LSTM prediction model to obtain a corrected prediction value, substituting the corrected prediction value into a logistic regression formula to obtain a fault prediction probability of fault occurrence, calculating a health degree score, and performing graded early warning according to the health degree score. According to the scheme, through multi-dimensional calibration, working condition adaptive feature extraction and graded early warning, the unit monitoring data precision, the fault feature recognition accuracy and the operation and maintenance decision efficiency are improved.

The invention discloses a multi-module collaborative rapid electrocardiogram automatic diagnosis method and system, and belongs to the technical field of automatic diagnosis. The method comprises the following steps: preprocessing an original ECG signal; the preprocessed ECG signals serve as input, and after the preprocessed ECG signals are sequentially processed by a lightweight convolution sub-module, a deformation convolution sub-module and a non-local attention sub-module, multi-level features containing local details and global time sequence dependency are output; fusing the multi-level features, and sending the fused multi-level features into a classifier to complete prediction of heart rhythm types to obtain prediction probabilities of all categories; a sliding window mode is adopted, the ECG signal fragments with the fixed length are sent to the diagnosis model for reasoning, the diagnosis model continuously outputs diagnosis results, and alarm or diagnosis prompt information is output in time according to the diagnosis results. According to the method, by designing a lightweight network structure, the parameter quantity and calculation complexity of a diagnosis model are effectively reduced, and real-time online ECG signal automatic diagnosis is realized on the premise of ensuring high diagnosis accuracy.

The invention relates to the technical field of energy consumption prediction, in particular to a building envelope energy-saving effect prediction method, which specifically comprises the following steps: deploying a sensor in a building maintenance structure to collect related data, and constructing a data set; marking the collected data to form a training set; a physical constraint decoupling normalization method is adopted for the data in the training set to generate features after decoupling normalization; a weighted feature vector is generated by adopting an attention mechanism guided by physical prior; constructing an energy-saving effect prediction network, and inputting the weighted feature vectors into the network for prediction; optimizing the network to obtain a trained network; newly-collected data is processed and then input into the trained network, the final prediction probability of each energy-saving grade is output, and the grade with the maximum probability is taken as a prediction result. According to the method, the collected data is preprocessed and then input into the network, so that the defects of inaccurate data processing, unreasonable feature selection and the like can be overcome, and the accuracy of a prediction result is improved.

A method and apparatus for training a few-shot event detection model based on multilingual prompt learning are provided, which includes: acquiring a training data set, applying a multilingual prompt model to any instance to obtain a predicted probability distribution of a trigger tag, so as to obtain a first loss; generating a contrastive instance and a bilingual instance, and performing multilingual prompt and cross-lingual encoding according to the input instance and the bilingual instance by applying the multilingual prompt model to obtain joint event characterization; performing event tag prediction on the joint event characterization by applying a two-level hierarchical prototype network model, and calculating a second loss; performing contrastive learning on respective instances by applying a quaternary contrastive learning module to obtain a third loss; determining a total loss of the few-shot event detection model according to respective losses, and performing model training optimization based on the total loss.

The invention discloses a fine-grained multi-modal prompt-guided visual relation identification method and device, and the method comprises the steps: carrying out the modeling of a plurality of groups of obtained relation weight vectors through multivariate Gaussian distribution, deducing the relation classification loss based on a small number of training samples in combination with the features of an output composite image, and calculating the semantic diversity loss, optimizing the text prompt by minimizing the total training loss; taking a relation average weight vector, respectively calculating similarity with the composite image features of the target object pair, carrying out weighted fusion, and carrying out normalization operation to obtain relation prediction probability distribution; and verifying the relation predicate with the maximum prediction probability, and detecting the abnormal behavior of the large public place in real time by the intelligent monitoring system according to the output relation category. The device comprises a processor and a memory. According to the method, the visual language model is accurately adjusted to the visual relation detection task, and the visual relation is accurately detected, so that the abnormal behavior detection capability of the intelligent monitoring system is improved, and an alarm is timely triggered to inform related personnel.

The system comprises a data acquisition layer, a data processing layer, a model layer and an application layer, the data acquisition layer is used for acquiring multivariate heterogeneous data in real time, the data processing layer is used for processing the acquired data, the model layer is used for training the processed data, and the application layer is used for applying the trained data to the data processing layer. And the application layer is used for performing dual drive by adopting a time sequence processing block and point prediction and probability prediction, the time sequence processing block is a double-branch parallel backbone network integrating a Decoder-Only Transform network and a multi-scale graph neural network, and the application layer is used for evaluating the running state of the electric energy metering device according to a predicted value and a predicted probability calculated by the model layer at a certain moment. According to the charging pile operation state prediction system based on time sequence analysis, the operation state of the electric energy metering device can be monitored more comprehensively and accurately, potential abnormity and fault hidden dangers can be found in time, early warning is carried out in advance, and economic losses caused by metering errors and equipment faults are effectively reduced.

The invention discloses a prostate cancer three-classification risk layering method based on an integrated learning model, and relates to the technical field of data processing and analysis. The method comprises the following steps: collecting clinical information and pathological data of a patient with increased PSA, and dividing the data into a training set and a test set; the training set is preprocessed, and prediction features are screened through LASSO regression; constructing a plurality of machine learning base models based on the features, and training and optimizing through cross validation; soft voting is constructed through an integration strategy, and an integration model is stacked; setting double thresholds according to the integrated model prediction probability, and establishing a layering rule; combining an integrated model and rules to form a three-classification model, and judging low, high and medium risks according to probabilities; and finally verifying the model diagnosis performance in the test set. According to the method, through cross-modal feature integration and ensemble learning, the method is PSAlt; accurate risk stratification is provided for 30 ng / mL people, biopsy decision-making efficiency is optimized, and excessive puncture and missed diagnosis risks are reduced.

The invention discloses an emergency patient intelligent pre-examination triage system, and particularly relates to the field of emergency patient pre-examination triage, comprising: a data processing module performs standardization processing on patient chief complaint text and sign data, and constructs a pre-examination data set; the disease prediction module inputs the pre-examination data set into a multi-label disease prediction model, and outputs a potential disease set and a prediction probability thereof; the probability adjustment module performs confidence correction on the prediction result in combination with the historical medical history of the patient; the graph construction module constructs a potential disease semantic adjacency graph according to the semantic similarity; the detection item determination module performs co-occurrence path compression on the basis of the semantic graph structure, extracts a minimum detection item set and generates an auxiliary detection item list; the triage guidance module schedules and ranks the detection items according to the real-time states of the detection resources, triage detection guidance is generated, and efficient and flexible emergency treatment primary screening planning is achieved.

The invention provides a road tunnel traffic incident real-time prediction method based on multi-model fusion, and the method comprises the steps: S1, collecting traffic data from a plurality of data sources, carrying out the data preprocessing of the traffic data, dividing the processed data into a training set, a verification set and a test set according to a specific proportion, carrying out normalization processing on data of the training set and the test set; s2, designing and training the processed data to obtain M models; and S3, constructing a stack model from the M models obtained in the S2 by adopting a stack ensemble learning strategy, and inputting the prediction probability of each model as feature input into the stack model for prediction to obtain a final prediction result. The problems that the prediction accuracy and reliability are insufficient due to the fact that complex traffic data features are difficult to fully capture in the prior art, the characteristics of various models cannot be effectively fused, the advantages of an integrated model cannot be fully played, and the prediction effect is uneven in hierarchy are solved.

The invention relates to the technical field of pharmacology and artificial intelligence, and provides a compound-target interaction prediction method and system, and the method comprises the steps: constructing a knowledge graph containing compounds, target entries and disease entities, and the correlation of the compounds, the target entries and the disease entities; inputting the knowledge graph into a multi-modal feature extraction model, and extracting topological information and internal semantic information in the knowledge graph; wherein the multi-modal feature extraction model comprises an ICD2Vec layer, a graph Transformer, a gene ontology embedding layer and an attention mechanism-based graph neural network, and the ICD2Vec layer, the graph Transformer, the gene ontology embedding layer and the attention mechanism-based graph neural network are respectively used for extracting disease semantic features, compound semantic features, protein target semantic features and topological features of a knowledge graph; performing knowledge fusion on the extracted semantic features and topological features of the knowledge graph through a feature fusion module, and obtaining a compound-target prediction probability matrix through a knowledge graph embedding method; and according to the compound-target prediction probability, performing descending sorting on the input compound-target interaction, and outputting a target recommendation list.

The invention provides an intelligent machine room multi-dimensional dynamic monitoring management method and system based on digital twinning, and relates to the technical field of machine room monitoring, and the method comprises the steps: collecting a three-dimensional point cloud set and an RGB image set of a machine room space, and building a space mapping table; mapping the access control event data to a corresponding position in a digital twin space, generating an access control event space positioning set, identifying access control abnormal events, and constructing an access control abnormal event space positioning set; performing abnormal behavior recognition, and constructing an abnormal event graph structure; reconstructing and visualizing an abnormal track based on the abnormal event graph structure; in combination with the access control abnormal event space positioning set, the abnormal behavior category prediction probability distribution and the track risk level, executing a grading early warning mechanism, and generating an access control abnormal event log; according to the invention, intelligent positioning, track visualization and risk grading early warning of access control abnormal events in the intelligent machine room are realized, and the method is suitable for digital operation and maintenance management systems such as the intelligent machine room.

The invention relates to a meteorological disaster prediction method and system based on an improved BERT-RG-TGA model. The method comprises the following steps: constructing a dynamic spatio-temporal knowledge graph joint feature vector; processing is carried out through a graph attention component, a dynamic time gating circulation component, a static semantic constraint component and a key node screening component in the improved BERT-RG-TGA model, and a trained BERT-RG-TGA model is obtained; and obtaining to-be-predicted time period data, performing convolution operation on the fused data features through the trained BERT-RG-TGA model, and capturing time sequence interaction information and a dependency relationship by using a self-attention mechanism to obtain a meteorological disaster prediction probability distribution result. By fusing meteorological text data and time-space sensor data and processing through a graph attention component, a dynamic time gating circulation component, a static semantic constraint component and a key node screening component in the improved BERT-RG-TGA model, the prediction accuracy can be improved.

The invention provides a data label classification method and system based on artificial intelligence, and the method comprises the steps: obtaining a text data feature and an image data feature, and fusing the two features to form a multi-modal feature; modeling the label hierarchy graph by using a graph neural network, and training the model by taking the multi-modal features as the output to obtain a trained complex model; performing knowledge distillation on the complex model, and compressing the complex model into a lightweight model; correcting the label prediction probability distribution of the lightweight model according to the label hierarchy graph; newly input data are obtained, the newly input data are input into the label hierarchy diagram to be dynamically updated, meanwhile, consistency regularization is designed during updating to adaptively adjust label prediction probability distribution, and finally the weight of the lightweight model is optimized according to the updated label hierarchy diagram. The invention provides an efficient label classification system which can adapt to diversified application scenes on the premise of keeping classification precision.

The invention relates to the technical field of medical artificial intelligence, in particular to a pulmonary nodule malignant risk dynamic prediction method and system based on space-time attention and multi-modal data guide fusion. Clinical features are obtained based on clinical data, and a lung CT slice image is obtained based on a lung CT image; the method comprises the following steps: extracting general medical visual features in an image by using an open-source medical large model, extracting image features in a lung CT slice image through a visual Transform model, and performing feature guide optimization on the image features based on clinical features and the general medical visual features to obtain patient image specific features; performing joint mapping on the specific features of the patient image by using a space-time attention mechanism to obtain space-time enhancement features of the patient image; and performing weighted fusion on the clinical features, the general medical visual features and the space-time enhancement features of the patient by using a gating mechanism, and obtaining the risk prediction probability of the malignant pulmonary nodules of the patient by using a classifier. The method can predict the malignant probability of the pulmonary nodule, and facilitates the realization of auxiliary diagnosis such as pulmonary nodule screening.

A QUIC encrypted traffic classification method based on multi-model fusion belongs to the field of communication, and comprises the following steps: a model training stage: dividing a data set, training each model in a high-precision model group and a high-recall-rate model group by using a training set, evaluating model performance by using a verification set, if a dynamic weight mechanism is started, calculating the weight of the model according to a model evaluation result, and if the dynamic weight mechanism is started, calculating the weight of the model; carrying out normalization processing on the weight, and searching an optimal decision threshold by using a plurality of candidate thresholds; in the model prediction stage, prediction data are input, each model generates a respective prediction probability, and if a dynamic weight mechanism is started, the prediction probability of each model is subjected to weighted averaging according to the weight obtained in the training stage so as to perform probability calibration; and combining the calibration probability of each model, judging the calibration probability through an optimal decision threshold, and generating a final classification prediction result. According to the method, the risks of overfitting and poor generalization ability of a single model are reduced, and QUIC encrypted traffic classification with high accuracy and stability is realized.

The invention discloses an analysis method and system for a dynamic recrystallization structure form of a titanium alloy based on machine learning and a medium, and belongs to the technical field of metal material microstructure quantitative characterization, a Gleeble thermal compression test is processed on a titanium alloy to be tested, multi-modal data is collected, a DRX probability graph is output based on a DRX segmentation model, and then the characteristics of DRX are extracted. And respectively inputting the DRX features into the first-level classifier, carrying out PCA dimension reduction processing, splicing and fusing the prediction probability and the features after dimension reduction, and inputting the spliced and fused features into a second-level classifier to output a two-dimensional DRX segmentation map. Based on the FIB-SEM tomography sequence image, reconstructing a three-dimensional model of the DRX crystal grain so as to carry out consistency verification on the two-dimensional DRX segmentation image; and evaluating a correlation coefficient of the three-dimensional model and the two-dimensional DRX model, and finally carrying out three-dimensional visualization on the space aggregation of the DRX crystal grains. According to the method, the automation degree and efficiency of dynamic recrystallization proportion and type identification are remarkably improved.