5784 results about "Autoencoder" patented technology

The invention provides a news scene three-dimensional reconstruction and visualization method based on multi-source remote sensing data, and relates to the technical field of three-dimensional reconstruction, and the method comprises the steps: extracting multi-modal data feature points through employing a spatial position weighted iterative nearest point algorithm and a tensor projection algorithm; after bidirectional attention deep neural network processing and local geometric consistency constraint screening, registration multi-source remote sensing data is generated, data enhancement is carried out through a variational auto-encoder network and a generative adversarial network, the enhanced data is used for depth information generation and texture feature migration, an initial three-dimensional grid model is generated based on a Poisson reconstruction algorithm, and the initial three-dimensional grid model is constructed; and carrying out topological optimization by combining multi-view projection consistency constraint and a grid optimization algorithm to obtain an optimized three-dimensional scene model, setting a space division function, carrying out space division, constructing a grade model and a depth region, generating a scene semantic segmentation map, and updating a visual scene.

The invention provides a dynamic health adaptive monitoring method and system using artificial intelligence, and relates to the technical field of health monitoring, and the method comprises the steps: carrying out the noise reduction through a hierarchical diffusion probability model through multi-source heterogeneous health data, extracting preliminary features through combining with an improved attention auto-encoder, learning discriminative features through a contrast learning network, and carrying out the recognition of the discriminative features; inputting the discriminative features into an adaptive wavelet neural network for multi-scale feature decomposition, inputting the discriminative features into a dynamic graph neural network to obtain a health feature tensor, obtaining time sequence features by using a hierarchical memory enhancement network, and generating a health knowledge graph in combination with a dynamic routing capsule network and a causal reasoning network; and inputting the time sequence characteristics and the health knowledge graph into a deep Bayesian network for health risk assessment, and obtaining an adaptive monitoring scheme through a model prediction control network by using a hierarchical reinforcement learning network and combining a multi-agent collaborative optimization system and a deep deterministic strategy gradient network.

The invention provides a home abnormal state signal detection method and system based on multi-modal sensing, and relates to the technical field of detection, and the method comprises the steps: collecting human body motion, acoustics and environment parameters through a millimeter wave radar, an acoustic sensor and an environment sensor, inputting the parameters into a deep fusion network, a spatio-temporal attention mechanism and a multi-scale convolutional neural network are used to extract a spatio-temporal feature sequence, and joint probability features are formed in combination with an acoustic feature spectrum analysis result. And inputting the joint probability features into a time sequence knowledge graph, and obtaining scene adaptive features after processing by a graph attention network and a double-flow auto-encoder network. And finally, the multi-task learning network is combined with the risk propagation neural network and the recursive neural network to carry out anomaly prediction and risk level evaluation, and is combined with historical early warning information to output an early warning strategy. According to the invention, multi-modal data can be effectively fused, the accuracy and reliability of home abnormal state detection are improved, and a more accurate risk assessment and early warning strategy is provided.

The invention provides a thermal power equipment real-time monitoring method and system based on edge computing, and relates to the technical field of thermal power equipment real-time monitoring, and the method comprises the steps: deploying an edge computing node array to collect multi-source heterogeneous data of thermal power equipment, and carrying out the preprocessing through data screening, multi-scale adaptive filtering and wavelet packet decomposition, a conditional variation auto-encoder is used to extract features, a hierarchical attention mechanism and a deep feature fusion network are combined to generate mixed feature representation, refined distribution estimation and abnormal mode recognition are performed on equipment states, cooperative monitoring modeling is performed based on a multi-scale spatial-temporal feature fusion network and a hierarchical depth deterministic policy gradient network, and a multi-scale spatial-temporal feature fusion network is established. The real-time monitoring accuracy and efficiency of the thermal power equipment can be effectively improved, the equipment failure rate is reduced, and safe and stable operation of a thermal power plant is guaranteed.

A method is provided for estimating the number of distinct tokens in a text stream using a modified text-to-text variational autoencoder (T5VQVAE) model. The method includes receiving a continuous input of a text stream; dynamically maintaining a buffer that stores a probabilistic subset of tokens from the text stream; calculating a sampling probability for each token based on a condition related to the current state of the buffer; updating the buffer based on the sampling probability to include or exclude tokens; encoding the buffered tokens into a latent space using the T5VQVAE model; and estimating the number of distinct tokens in the text stream based on the tokens in the buffer and the corresponding sampling probabilities.

The invention discloses an informatization project management system based on big data analysis, which belongs to the field of big data and comprises a data acquisition module, a time sequence modeling module, a task coupling analysis module, a risk clustering identification module, a resource allocation prediction module and the like. The data acquisition module asynchronously and parallelly acquires structured and unstructured data and uniformly encodes the structured and unstructured data; the time sequence modeling module constructs a multi-dimensional time sequence based on an autoregressive residual network; the task coupling analysis module fuses the task trajectory and the dependency relationship to generate a task influence directed graph; the risk clustering identification module identifies risks through variational graph auto-encoder mapping; the resource allocation prediction module constructs a dynamic resource priority based on a graph attention mechanism; a progress deviation traceability module identifies a deviation causal chain; the knowledge graph decision-making module corrects resource priorities and path strategies in a cross-graph manner; and the project global control module dynamically adjusts key paths and resource configuration and performs closed-loop self-correction. The beneficial effect is that the intelligent level and the risk response capability of project management are improved.

The invention discloses a self-adaptive operation and maintenance root cause positioning method and system based on deep learning. The method comprises the steps that firstly, multi-source data such as system logs, performance indexes, alarm events and configuration changes are collected, and time sequence features, text features and associated features are extracted; performing anomaly detection in combination with a 3-sigma criterion and an auto-encoder; when an exception is found, reasoning diagnosis is carried out by utilizing the fault knowledge graph, and fault diagnosis is realized by combining an XGBoost classification algorithm; and then fault propagation analysis and root cause positioning are carried out, and a fault processing flow is continuously optimized. The problems of incomplete fault features, low detection accuracy, limited diagnosis capability and the like in an existing operation and maintenance system are solved, more accurate fault detection and root cause positioning are realized through a mode of combining multi-source data fusion, deep learning detection and knowledge graph reasoning, and meanwhile, the method has adaptive optimization capability and is suitable for large-scale popularization and application. And the operation and maintenance fault processing efficiency is obviously improved.

The invention relates to the technical field of network security, in particular to a network security big data state evaluation method based on pattern recognition, which comprises the following steps of: extracting multi-modal features from a network flow log, a system event log, a host behavior log and threat intelligence data, generating a feature matrix, performing feature dimensionality reduction by adopting an auto-encoding network, and obtaining a network security big data state evaluation result; carrying out attack behavior classification and abnormal mode identification in combination with unsupervised clustering and a graph neural network; constructing an attack transition probability matrix based on a Markov model; forming a time sequence attack chain; predicting an attack development trend; and a dynamic protection instruction is issued to the safety equipment. According to the method, the unknown attack detection capability can be improved, the time sequence attack traceability is enhanced, the security situation assessment is optimized, and the method is suitable for security situation awareness in cloud computing, industrial internet and large-scale network environments.

The invention discloses a base station facility abnormity intelligent monitoring method and system, and the method comprises the steps: employing a multi-scale wavelet fusion pulse neural network to construct a dynamic signal perception topology according to the real-time data of a base station physical layer, and generating a space-time aligned base station full-dimension feature tensor; inputting the full-dimensional feature tensor of the base station into a fault mode confrontation distillation module, reconstructing a normal working condition manifold of the base station based on a physical constraint variational auto-encoder, and outputting an abnormal feature vector with a fault fingerprint identifier; fault propagation graph modeling is carried out on the abnormal feature vectors, and a base station fault root cause topological graph is generated in combination with back propagation credibility verification; and inputting the base station fault root cause topological graph into a toughness self-healing strategy generator, and finally outputting a base station facility self-healing strategy set meeting real-time constraint. By utilizing the embodiment of the invention, the accuracy and the real-time performance of abnormity monitoring can be improved, and the operation reliability and the communication service quality of the base station are improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an intelligent anomaly recognition and intervention processing method, device, equipment and medium. The method comprises the following steps: carrying out feature fusion by using a gating fusion network and generating a preliminary abnormal score, determining a reconstruction error through an auto-encoder and triggering abnormal early warning, calculating a causal effect value of key features in combination with a causal graph model and anti-factual reasoning, and calibrating the abnormal score to generate a final abnormal score and an intervention instruction. And executing an intervention action and recording a result. According to the method, the multi-dimensional feature information and the causal reasoning mechanism are fused, the self-encoder reconstruction error is combined to carry out anomaly judgment, the intervention instruction is generated and executed, closed-loop control of anomaly detection, reasoning analysis and intervention execution is achieved, and the recognition accuracy of complex events and the system response capacity are improved.

Systems / techniques that facilitate data drift detection for unstructured texts via deep learning autoencoders are provided. In various embodiments, a system can access a pre-trained natural language model and a set of unstructured texts on which the model is to be executed. In various aspects, the system can determine, via execution of a deep learning autoencoder, how different a first set of reconstruction errors associated with the set of unstructured texts are from a second set of reconstruction errors associated with a set of training unstructured texts on which the pre-trained natural language model was trained. In various instances, the system can generate, in response to a determination that the first and second sets of reconstruction errors differ by more than a threshold margin, a first alert indicating that data drift has occurred and that the model is thereby unable to confidently analyze the set of unstructured texts.

The invention discloses a multi-modal-based power equipment health state monitoring method, and relates to the technical field of power equipment detection.The power equipment monitoring method is based on multi-modal data and knowledge graph fusion, cross check, expert rule cleaning and label correction are implemented by collecting sensing data such as chromatography, temperature, current and vibration in oil, and the detection result is obtained. Outputting high-credibility data; a graph model is constructed based on equipment topology by adopting self-encoder dimension reduction fusion, early anomaly detection is realized by utilizing a graph neural network, and an anomaly alarm is generated; mechanism matching and consistency evaluation are carried out based on the fault mechanism knowledge graph, and interpretable diagnosis is output; and when the diagnosis result is significantly deviated from the actual operation and maintenance conclusion, triggering an online increment and transfer learning updating model and expanding the knowledge graph to form a closed-loop self-learning mechanism. According to the method, the fault detection accuracy is remarkably improved, false alarms and missing alarms are reduced, the operation and maintenance decision-making efficiency is improved, and meanwhile operation and maintenance intelligence and real-time alarm are enhanced.

A system and method for multi-scale temporal attention processing in multimodal technology deep learning systems. This system processes time-series, textual, sentiment, and structured tabular data across three hierarchically-organized temporal streams—quarterly, weekly, and intraday levels—with bidirectional cross-temporal information flow. Scale-specific attention mechanisms are optimized for respective temporal granularities, while an adaptive controller dynamically weights each temporal level based on real-time market volatility indicators. A multi-scale fusion processor integrates attention-weighted representations to generate temporally unified representations preserving both short-term market dynamics and long-term trends. This approach enables superior forecasting and risk assessment by leveraging temporal correlations across multiple time scales while automatically adapting to changing market conditions. The system facilitates interpretable AI analysis through attention visualization and enables synthetic scenario generation for model testing.

The invention discloses an electrical equipment fault diagnosis and prediction analysis system, which relates to the field of intelligent operation and maintenance of a power system and comprises an acquisition and preprocessing module, an extraction fusion module, a fault diagnosis modeling module, a prediction evaluation module and an update feedback module. According to the invention, through fusion of structured sensing data and unstructured image data, multi-modal depth feature joint representation is realized, and the accuracy and robustness of fault identification are significantly improved; a fusion time sequence prediction model is introduced, and a health degree scoring system is combined, so that accurate prediction of key parameter trends and quantitative estimation of the residual life of equipment are realized; a transfer learning and incremental learning mechanism is adopted, when a new fault or small sample data appears, model parameters can be quickly updated, and efficient adaptation to a new scene is achieved; a data alignment mechanism with time-space synchronization and an auto-encoder anomaly detection algorithm are constructed, and the multi-source heterogeneous data processing capacity and the real-time fault early warning capacity are remarkably improved.

The invention relates to the technical field of medicine quality management, in particular to a medicine quality management method and system based on big data and artificial intelligence, and the method comprises the steps: obtaining the quality influence parameters of a medicine product in the production, transportation and storage processes through a multi-modal data collection device; noise is removed through data cleaning, data dimension reduction is carried out through principal component analysis and an auto-encoder, the analysis efficiency is improved, and the efficiency problem of mass data processing of a traditional method is solved. Time sequence analysis is carried out through the long-short-term memory network, abnormal nodes are recognized in time, manual sampling inspection is replaced, and accurate early warning is achieved. The graph neural network constructs a path tracking model, analyzes the relevance between nodes, traces the quality problem, and reckons the batch of affected drugs. Based on a traceability result, an XGBoost model generates quality risk scores of all links by analyzing historical and real-time data and sets a threshold value, and quality risks are early warned in real time.

A method is provided for enhanced data routing in neural networks using Self-Organizing Maps (SOM) integrated with Autoencoder-GAN. The method comprises training an autoencoder to encode input data into a latent space representation; applying a Self-Organizing Map (SOM) to organize the latent space representation into a topological map; refining the latent space representation using a Generative Adversarial Network (GAN), wherein the generator generates enhanced latent space representations and the discriminator evaluates their quality; using the refined latent space representations to update the SOM topology dynamically; generating routing coefficients based on the updated SOM topology to guide data routing in a capsule network; and dynamically adjusting routing within the capsule network using the generated routing coefficients to enhance performance based on the refined latent representations.

A system and method for adaptive real-time multi-modal compression with dynamic resource allocation provides intelligent compression optimization based on continuously monitored device conditions. The system monitors battery level, CPU utilization, and memory availability while classifying incoming multi-modal data streams comprising image, audio, text, and sensor data to determine processing priorities. Multi-objective optimization balances compression efficiency, reconstruction quality, and energy consumption using evolutionary algorithms that generate optimal parameters for an adaptive variational autoencoder. The autoencoder features dynamically selectable processing complexity, adjustable latent space dimensionality, and modality-specific processing layers. The system automatically switches between operational modes including emergency mode triggered by resource constraints, which applies maximum compression settings and intelligent data triage. Continuous learning adapts compression parameters based on observed performance outcomes, improving future optimization decisions. The system enables homomorphic operations on compressed data and provides enhanced compression performance under varying resource constraints across diverse edge computing applications.

The invention relates to an underground equipment fault early warning and diagnosis method based on big data analysis. The method is suitable for equipment operation state monitoring and intelligent diagnosis in underground operation scenes such as mines. The method comprises the following steps: collecting multi-source data such as an equipment running state, environment parameters and operation behaviors and preprocessing the multi-source data; multiple signal features are extracted and fused to construct a unified feature vector; performing health modeling by using the residual self-encoder model to generate a health index; an early warning threshold value is dynamically set through clustering analysis and Bayesian reasoning, and anomaly recognition is achieved; after early warning is triggered, fault type identification is carried out by adopting the fusion discrimination model; performing causal reasoning and maintenance suggestion generation based on the equipment fault knowledge graph; and continuously optimizing the model in combination with operation and maintenance feedback information, and constructing a closed-loop diagnosis mechanism. The method has the characteristics of high recognition precision, high response speed, explainable result and sustainable optimization of the model.

The invention relates to a multi-modal AI data fusion processing method, device and equipment and a medium, and the method comprises the steps: firstly extracting visual, auditory and text modal features through a pre-training encoder, executing dimension alignment, and generating a standard data feature set with unified dimensions; a cross-modal semantic graph is constructed based on a cosine similarity algorithm, and the problem of semantic mismatch of heterogeneous data is solved; residual enhancement is carried out on the map nodes, and noise interference is eliminated; fusing the optimized features and the semantic topology in combination with a graph convolutional network to generate aggregation graph representation; the fusion features are mapped to a low-dimensional semantic space through a variational auto-encoder, and cross-modal correlation essence is captured; the key dimension contribution degree is quantified, a visual report is generated, and semantic association rules among modals are disclosed, so that the dimension isomerism limitation of a traditional fusion technology is broken through, quantifiable cross-modal semantic mapping is established, the whole process traceability from feature fusion to decision interpretation is realized, and the method is suitable for popularization and application. And the multi-modal decision black box problem in the fields of medical diagnosis, automatic driving and the like is effectively solved.

The invention discloses a power grid abnormal flow detection method based on multi-modal data fusion, and the method comprises the steps: collecting the multi-source heterogeneous data of a power grid through an edge calculation node, including the current waveform of an intelligent electric meter, the state variable of an SCADA system, network protocol metadata and an equipment log event; performing space-time alignment preprocessing on the original data, converting an unstructured log into a time sequence by adopting a sliding window mechanism, and eliminating sensor noise through an LSTM auto-encoder; constructing a multi-dimensional feature space which comprises a frequency domain feature, a spatial-temporal feature and a protocol feature, and obtaining a feature vector; the feature vectors are input into a hybrid detection model, the model is composed of an isolated forest algorithm, an improved CNN-LSTM classifier and an information entropy-based rule engine which are connected in parallel, and a dynamic weight fusion strategy is adopted to output an abnormal probability; and when the abnormal probability exceeds a dynamic threshold, triggering a multi-level response mechanism: sending a traffic shaping instruction to the edge device, generating a device fingerprint portrait on the cloud platform, and storing abnormal event features through a block chain.

A system and methods for processing diverse financial data types using a jointly trained Vector-quantized Variational Autoencoder (VQ-VAE) and neural upsampler. This system efficiently handles time-series, textual, sentiment, and structured tabular data through specialized encoding modules. A novel fusion module integrates these encodings, capturing cross-modal relationships via attention mechanisms and gated fusion units. The fused representation is compressed into a discrete latent space by the VQ-VAE encoder, then reconstructed and enhanced by the VQ-VAE decoder and neural upsampler, respectively. Joint training optimizes all components simultaneously, using a comprehensive loss function that balances reconstruction quality across modalities with upsampling performance. This approach enables superior data compression, reconstruction, and analysis, leveraging inter-modal correlations to improve financial forecasting, risk assessment, and decision-making. The system's ability to explore the latent space facilitates generation of new, synthetic financial scenarios for robust model testing and strategy development.

A system and methods for implementing adversarial-robust compression and reconstruction using a vector quantized variational autoencoder (VQ-VAE) with secure latent space management. The system provides comprehensive protection against adversarial attacks through multi-channel threat detection, adaptive defensive parameters, and coordinated response mechanisms. Input data is continuously monitored for potential threats, and defensive parameters are dynamically adjusted based on detected threat levels. The system implements bounded constraints and hierarchical projections to maintain latent space security while preserving compression efficiency. Multi-stage reconstruction with progressive validation ensures reliable data recovery even under adversarial conditions. The system coordinates defensive responses across all compression and reconstruction processes, implementing various recovery mechanisms when security violations are detected. This approach enables robust compression and reconstruction of time-series data while maintaining protection against various forms of adversarial manipulation.

The invention discloses an inspection method, device, equipment and medium based on a digital airspace system, and the method comprises the steps: carrying out the feature extraction and calibration of multi-source sensing monitoring data of a to-be-inspected region through a pre-trained neural network model; obtaining a structured semantic description and a time sequence measurement value to be combined with external meteorological spatial data to be input into a digital airspace expert model based on an MoE framework for multi-modal fusion; carrying out enhancement processing on the generated multi-modal fusion representation through a variational auto-encoder so as to input the multi-modal fusion representation into a multi-modal transformer decoder for decoding, and obtaining an entity triple set to construct a digital spatial domain knowledge graph; node characterization in the knowledge graph is enhanced by adopting an attention enhancement mechanism based on a graph neural network, the node characterization is input into a conditional generative adversarial network model for multi-task prediction, and an inspection decision suggestion is generated to be executed by the unmanned aerial vehicle, so that the utilization rate of multi-source sensing data is effectively improved, and the inspection efficiency of the unmanned aerial vehicle is improved.

The present disclosure relates to the technical field of videos. Disclosed are a video anomaly event detection method, apparatus and device, and a storage medium. The method comprises: acquiring the current video frame of an industrial site, and reconstructing, by means of an anomaly detection model, a current reconstructed frame corresponding to the current video frame, wherein the anomaly detection model is a model constructed on the basis of a two-stream autoencoder network, the two-stream autoencoder network being used for extracting a spatial feature and a temporal feature; calculating the current dynamic threshold of the current video frame, wherein the current dynamic threshold is used for performing anomaly detection on the current reconstructed frame; and on the basis of the current dynamic threshold and the current reconstructed frame, detecting abnormal events in the industrial site. In the present disclosure, whether abnormal events occur is detected by means of an anomaly detection model and a dynamic threshold value; therefore, the reconstruction capability of the model on the abnormal events can be suppressed, and an auto-encoder is encouraged to produce a higher reconstruction error for the abnormal events, thus reducing the problems of false detection or missed detection, and improving the accuracy of video anomaly event detection.

The invention discloses an intelligent monitoring system for a municipal drainage pipe network, and particularly relates to the technical field of drainage pipe network monitoring. The node operation mode identification module carries out real-time classification and confidence evaluation on the operation state of the pipe network, constructs a multi-attribute pipe network weighted graph based on pipe diameter difference, gradient and confluence density, and extracts multi-scale features through graph Fourier transform. A hybrid anomaly detection link is constructed in combination with an LSTM self-encoder, an isolated forest model and chemical oxygen demand and turbidity water quality verification, and the problems that traditional single-index monitoring is prone to false alarm and missing alarm and inaccurate in positioning are solved; sensor data compensation is realized through cooperation with digital twinning, a rapid detection mode is started during rainstorm early warning, key nodes are processed preferentially, and drainage scheduling is controlled in a closed-loop mode; and target nodes which are easy to accumulate grease are screened based on pipe network topology connectivity, accumulation risks are predicted by fusing multi-sensor data, and a preventive clearing instruction is triggered.

A method is provided for mapping the latent space of a Vector Quantized Variational AutoEncoder (VQ-VAE) to polynomial basis vectors. The method includes training a VQ-VAE model on a dataset to obtain a set of codebook vectors representing the latent space; defining a polynomial basis for the latent space, the polynomial basis containing terms up to a predetermined order; mapping each codebook vector to the polynomial basis by determining polynomial coefficients that represent each codebook vector in terms of the polynomial basis; and using the polynomial coefficients to reconstruct and manipulate latent space representations.

The invention discloses a box-type substation state monitoring and early warning method based on artificial intelligence, relates to the technical field of intelligent power grids, and aims to solve the problems of missing report, false report and response lag caused by the fact that an existing static threshold ignores multi-physical coupling and a depth model highly depends on scarce fault samples. According to the scheme, sliding window kernel density estimation is carried out on a multi-channel time sequence signal, a dynamic coupling matrix is constructed through recursion Copula decomposition, a three-level threshold surface is generated through time-varying quantile regression, abnormal samples and graph attention network extraction state representation are generated in combination with a conditional variation auto-encoder, lightweight recursion pruning is carried out, and the dynamic coupling matrix is obtained. An abnormal score is generated through a multilayer Bayesian network and particle filtering, a multi-step risk trend is discriminated through a Gaussian kernel derivative slope, and finally unscented Kalman filtering is used for smoothing and online threshold correction; according to the method, the detection sensitivity and the early warning recall rate of the box-type substation to the transient coupling fault are remarkably improved, the response speed is improved, and the false alarm frequency is effectively reduced.

The invention relates to the field of road traffic, in particular to a multi-feature fusion fatigue driving detection method and a fatigue driving detection system. The method comprises the following steps: extracting facial features from a face image of a driver; extracting vehicle features from the vehicle driving parameters of the vehicle driven by the driver; and fusing the facial features and the vehicle features to judge whether the driver is in fatigue driving. Extracting facial features by designing a CNN model; extracting basic convolution features; extracting local convolution features; extracting global convolution features; performing pooling operation; aggregating global features; and carrying out dimensionality reduction mapping. A self-encoder is designed to extract vehicle characteristics; a symmetric deep neural network structure is adopted, and high-dimensional time sequence data is compressed to a low-dimensional potential space through nonlinear mapping; through combination and matching of the CNN model and the auto-encoder, the technical defects of feature redundancy, noise interference, information loss and suboptimal decision existing in an existing multi-feature fusion fatigue driving detection system are thoroughly solved.

A method for structuring the latent space of an autoencoder is provided. The method includes analyzing natural language descriptions related to input data; creating language-guided libraries that categorize and abstract data features based on the analyzed descriptions; mapping input data into the categorized and abstracted features within the latent space of the autoencoder; and training the autoencoder to minimize reconstruction loss while adhering to the structure imposed by the language-guided libraries.

The invention discloses a high-resolution radar echo extrapolation prediction method fused with satellite data, and the method specifically comprises the following steps: firstly, inputting historical radar echo sequence preprocessing at a previous T moment, including denoising, normalization processing and data set segmentation, and obtaining cleaned data; then, through a deterministic modeling method (SimVP), a fuzzy prediction sequence of a future T duration is obtained, then a variational auto-encoder (VAE) maps an original radar echo image and the fuzzy prediction sequence to a low-dimensional potential space, and two-stage diffusion modeling is carried out on the basis; in the first stage, a space-time converter (ST-Translator) is used to extract space-time evolution characteristics of radar echoes; in the second stage, satellite data at the corresponding time of the previous T moment is input, preprocessing including normalization processing, feature selection and data set segmentation is carried out, cleaned data is obtained, and the influence of the satellite data is dynamically adjusted in the diffusion process by adopting a multi-source fusion denoising network Fsrform so as to make full use of satellite information; and finally, inversely transforming output results of the two stages into a pixel space to obtain a high-resolution radar echo extrapolation prediction result of the future T duration. According to the invention, computing resource consumption can be effectively reduced, and the precision and detail fidelity of short temporary rainfall prediction are improved.