573 results about "Single model" patented technology

The invention discloses a maritime accident prediction method and device based on interpretable integrated machine learning, and relates to the technical field of maritime affair safety risk analysis, and the method comprises the steps: obtaining accident investigation data, carrying out the preprocessing, balancing the data through a ten-fold layered oversampling method, and carrying out the cross verification training, and determining a performance optimal model by using the test set and carrying out interpretable analysis to explain the influence of the characteristics on the accident prediction result. By constructing a closed-loop'data processing-model optimization-explanation output 'process and adopting SMOTE oversampling and ten-fold layered cross validation training and a heterogeneous base model ensemble learning strategy, the processing capacity of the data imbalance problem of accident categories is improved, the data leakage problem of oversampling is avoided, and the possible bias of a single model is overcome. The interpretability analysis of the model prediction result can quantitatively display the contribution degree of each feature to prediction globally and locally, reveal the nonlinear relationship and interaction effect between the features, and provide transparent interpretation of model decision.

The invention relates to the crossing field of hydraulic engineering hydrological monitoring technology and machine learning prediction technology, discloses a sediment concentration prediction method based on deep learning, and aims to solve the problems that in existing sediment concentration prediction, hyper-parameter manual tuning is low in efficiency, key feature attention is insufficient, local and time sequence information is difficult to consider by a single model and the like. Accurate prediction is realized through five core modules: a data preprocessing module performs missing value filling, abnormal value processing and derivative feature generation on hydrological data; the feature selection module screens key features based on mutual information; the time sequence construction module generates time sequence data through a sliding window; the hyper-parameter automatic optimization module adopts Bayesian optimization iteration to obtain an optimal hyper-parameter; the CNN-LSTM-attention prediction module fuses CNN local feature extraction, bidirectional LSTM time sequence dependence capture and multi-head self-attention mechanism key feature focusing capability, is suitable for scenes such as river channels and channels, and provides efficient decision support for hydrological regulation and control.

The invention discloses a deep learning and machine learning fused soil moisture inversion construction method, and relates to the technical field of measurement of physical properties of materials, and the method comprises the steps: capturing complementary information and spatial context of multi-source data through a multi-source heterogeneous data space-time adaptive fusion step by using a cross-modal attention mechanism and a graph neural network; through a deep learning and machine learning dual-path collaborative inversion step, advantage complementation is realized by combining data-driven nonlinear modeling and a physical constraint interpretable model; according to the method, the defects of single data source, insufficient model generalization ability and incomplete physical mechanism consideration in the prior art are overcome, the inversion precision is improved by 12%-18% under the complex earth surface condition, and the method has the advantages that the method is suitable for large-scale popularization and application. And a high-precision, strong-generalization and reliable technical means is provided for precise monitoring of soil moisture.

The invention relates to the technical field of geological disaster monitoring, and discloses a landslide dynamic simulation monitoring and early warning method based on multi-source sensing fusion, and the method comprises the steps: collecting multi-source data of a landslide body through a plurality of heterogeneous sensors, and enabling the multi-source data to be in space-time alignment after preprocessing; building a multi-parameter fusion model fusing a displacement field, a mechanical field and an environment field based on the preprocessed data, enabling the multi-parameter fusion model to output a deformation rate and a stability coefficient, and dynamically adjusting the weights of the displacement field, the mechanical field and the environment field according to a landslide evolution stage; predicting a future deformation trend of the landslide mass in combination with a geological structure and historical data, comparing a stability coefficient with a dynamic safety threshold to judge a risk level, and generating early warning information; and dynamically correcting a reference weight coefficient in the model based on the deviation between the monitoring data and the model output, so that the model is adaptively optimized. The problems of single monitoring dimension and static model solidification in the prior art are solved, and accurate and adaptive monitoring and early warning of the risk state of the landslide mass are realized.

The invention discloses a knowledge graph completion method based on combined prediction of large and small models, which comprises the following steps: 1, constructing and preprocessing a knowledge graph completion reference data set, and training by adopting a RotatE model to obtain candidate entities generated by the model and confidence scores; 2, constructing a related triad, an adjacent triad and entity long text description based on the query to form a context prompt, inputting the context prompt and the query into a large language model, and performing semantic reordering and scoring by the large language model; and 3, constructing a fine tuning data set, and performing fine tuning on the large language model to obtain the KGC task optimization-oriented large language model. And based on the KGC score, the LLM score and the dynamic weight, outputting a complementation result through joint prediction of a fusion result. According to the method, the structured reasoning ability of the small model and the deep semantic understanding of the large language are effectively combined, the prediction accuracy, robustness and specialty are remarkably improved, and the defects that a single model is weak in generalization ability and insufficient in semantic utilization are overcome.

The invention relates to the technical field of disaster prevention and reduction of a power system, and discloses an icing risk early warning method based on multi-model fusion and residual time sequence characteristic analysis, which comprises the following steps: collecting meteorological data of a line area in real time, removing abnormal values through secondary judgment of a Pauta criterion and a trend, and standardizing; adopting a TEROL algorithm to screen high-weight key features; running SWD-BP, MUL-GRNN and ELM models in parallel, constructing a dynamic weight by combining DSI, an independence weight method and an entropy weight method, and calculating a final meteorological predicted value; generating a prediction residual signal, extracting time domain features such as a mean value and a peak value, and constructing a residual feature matrix through a sliding window; and inputting an LSTM model to process a time sequence dependency relationship, and judging an icing risk level. According to the method, meteorological prediction is optimized through multi-model dynamic fusion, and deviation is analyzed and corrected in combination with residual time sequence characteristics, so that the problem of weak generalization ability of a single model is effectively solved, and the accuracy of icing risk early warning is obviously improved.

The invention relates to the technical field of genome data analysis, and discloses an intelligent system, method and equipment for assisting multi-step genome data analysis, and the system comprises a dialogue agent which is used for generating a corresponding answer according to a question of a user, or reading an analysis plan file generated by a workflow agent, generating an analysis interpretation text for the analysis plan file; the workflow agent is used for generating a structured task execution plan according to the to-be-executed analysis task and executing the to-be-executed analysis task; and the modeling analysis agent is used for generating a configuration file and a script based on the user request, constructing a model and generating an analysis result corresponding to the user request in combination with the workflow agent. Through multi-agent cooperation, task division and cooperative scheduling are realized, each agent independently completes task planning, execution control, model analysis and other functions, the bottleneck problem of processing of a traditional single model in a complex process is avoided, error accumulation is reduced, and the execution efficiency and stability of the whole process are improved.

The invention discloses a total primary productivity estimation method and system based on multi-model coupling deep learning, and the method comprises the steps: obtaining the multi-source data of meteorological data, remote sensing images, latent heat flux, sensible heat flux and solar radiation, carrying out the quality control, missing value processing and nearest neighbor interpolation of different data sources, and carrying out the prediction of the total primary productivity. Unifying to a target spatial resolution and a time resolution; in a light energy utilization rate (LUE) model family, a solar radiation phase factor is introduced into a photosynthetically active radiation absorption ratio (FPAR) to obtain a phase modulation type FPAR, drought duration is introduced into a water stress function f (W) to obtain an exponential decay type f (W), and a GPP time sequence of a plurality of improved mechanism models is calculated according to the exponential decay type f (W); extracting spatial texture features from a remote sensing image stack by using a convolutional neural network (CNN), and performing cross-modal fusion on the spatial features and the GPP estimated by the plurality of improved mechanism models in a gating mode to form fusion representation; carrying out learning and collaborative optimization on the fusion representation of the GPP and CNN spatial features estimated by the plurality of improved mechanism models by adopting a gradient lifting tree model; and high-precision estimation of the GPP is realized through multi-model collaborative optimization. The method aims at solving the problem that a traditional light energy utilization rate model is insufficient in response under the extreme environment conditions of drought and intense radiation, the adaptability limitation of a traditional single model under the complex environment is broken through, and therefore high-precision GPP estimation under the complex environment is achieved.

The invention discloses an interpretable false news detection method and system based on retrieval evidence enhancement, the interpretable false news detection method combines a big language model with an external knowledge base retrieval mechanism, that is, factual supplementary evidence is provided for the big language model to generate final reasoning through a retrieval module. Screening candidate text evidences by utilizing a clustering algorithm, and performing credibility scoring and filtering on the candidate evidences in combination with a large language model; a unified reasoning Prompt is constructed to input a plurality of large language models, true and false judgment is output respectively, and detailed explanatory texts are generated with the assistance of natural language explanation, so that the false news detection method with factual support, language expression and user understandability is realized. And the judgment results of the models are fused through a majority voting mechanism, and explanation is generated from multiple perspectives, so that the risk caused by reasoning deviation of a single model is reduced, and the accuracy and stability of system output are effectively improved.

The invention discloses an intelligent monitoring and evaluating system for the metal health state of a generator set, and belongs to the technical field of state monitoring of power generation equipment. The system comprises a data acquisition and preprocessing module, a data fusion and feature extraction module, a metal health state evaluation module, a residual life prediction and fault tracing module and a visual intelligent decision support module. The method comprises the following steps of: extracting cross-scale damage characteristics by fusing macroscopic operation data and microscopic nondestructive testing signals; calculating a comprehensive health index by adopting a physical mechanism model and data-driven model adaptive weighted fusion mode; dynamic residual life prediction and failure reason intelligent traceability are realized; and finally, graded early warning and maintenance decision suggestions are provided through a three-dimensional visual interface. According to the method, the problems of single monitoring dimension, model isolation and static prediction in the prior art are solved, and comprehensive, high-precision and interpretable evaluation and predictive maintenance support of the health state of the metal part are realized.

The invention belongs to the technical field of artificial intelligence and multi-modal emotion calculation, and discloses a multi-modal emotion recognition method based on a Mama state space model and cross-modal self-distillation. Through the organic combination of the efficient sequence modeling capability of the Mamba state space model and the knowledge sharing mechanism of cross-modal self-distillation, the advantages of the state space model in the aspects of time sequence modeling and calculation efficiency are fully played, and meanwhile, the limitation of a single model architecture is made up through a cross-modal attention mechanism; the technical bottlenecks of an existing multi-modal emotion recognition method in the aspects of long sequence processing efficiency, cross-modal information fusion and knowledge transfer sufficiency are effectively solved, and an efficient and reliable technical solution is provided for further development and practical application of the multi-modal emotion recognition technology.

The invention discloses a wind power prediction method and system based on DIRMO and a differentiated objective function, and relates to the field of wind power prediction. In order to solve the defects that time sequence modeling and feature processing are difficult to consider at the same time, the prediction precision is reduced, the model robustness is insufficient and the search efficiency is low due to the fact that a single model is adopted for prediction in existing multi-step power prediction, denoising, normalization and feature extraction are carried out on preprocessed power and wind speed data, and multi-scale features are obtained; performing time sequence modeling on the normalized power and wind speed data to generate a future preliminary prediction result; dividing a multi-step prediction task into a plurality of groups, and converting a multi-output problem into a single-output problem for training and prediction; and carrying out automatic optimization on hyper-parameters of the LightGBM models, training each group of LightGBM models by using the optimized hyper-parameters, and carrying out final power prediction based on a GRU preliminary prediction result and multi-scale features. The method is mainly used for predicting the wind power.

The present application discloses a method for determining a degree of matching prediction model and a related apparatus. For a target search scenario comprising two types of correlation tasks, hybrid training is performed on an initial model by using training samples from the two types of correlation tasks. In the hybrid training, model parameters are shared, and for the shared model parameters, weights are adjusted to distinguish different types of correlation tasks, so that the initial model can learn the shared model parameters so as to participate in prediction of a first type of correlation task using first weights and participate in prediction of a second type of correlation task using second weights. On this basis, in a finally obtained degree of matching prediction model, the shared model parameters have two sets of weights corresponding to the two types of correlation tasks, so as to be compatible with different requirements of semantic matching of different types of correlation tasks, so that a single model has a capability of covering the two types of correlation tasks. Accordingly, only one model needs to be deployed in the target search scenario, thereby improving the deployment efficiency of the model and reducing resource overhead.

The invention provides a large model reasoning acceleration method and device based on speculation sampling, equipment and a medium, and the method comprises the steps: building a lightweight and adaptive fusion dual-order N-Gram draft model framework, capturing a long sequence dependence mode in a local context through a high-order N-Gram model, and obtaining a large model reasoning acceleration model; meanwhile, robust probability prior is provided with the help of a low-order N-Gram model to relieve the problem of data sparseness, on this basis, interpolation weights are dynamically determined based on context semantic intensity perception, and the interpolation weights are used for conducting dynamic weight fusion on probability distribution output by the high-order N-Gram model and probability distribution output by the low-order N-Gram model respectively; the hybrid probability distribution is generated by effectively combining the complementary advantages of high-order and low-order N-Gram models, and the candidate lexical element sequence is generated by using the hybrid probability distribution, so that the prediction deviation caused by improper order setting of a single model is avoided, and the prediction efficiency is improved while extremely low calculation overhead and storage requirements are maintained. Semantic rationality and verification passing rate of candidate sequences are improved, and large model reasoning acceleration is realized.

The invention relates to the technical field of medical health information services, in particular to a cerebral apoplexy knowledge question-answering system construction method and system based on a knowledge graph and a large language model. Natural language input of a user is analyzed through a query agent, a query intention and constraint conditions are recognized, and a structured execution plan is generated; a user state management tool is forcibly activated, a static clinical portrait and a dynamic rehabilitation log are loaded, and a personalized context is constructed; a plurality of tools such as knowledge graph query, authoritative literature retrieval and rehabilitation plan generation are scheduled, and accurate retrieval and reasoning of heterogeneous knowledge are completed; through double verification of fact consistency and clinical risks, error or high-risk suggestions are intercepted and replaced with risk early warning. The problems of'illusion 'risk, insufficient individuation, poor interpretability and the like of a traditional single model are solved to a large extent, high-credibility, individuation and traceable rehabilitation knowledge service can be provided for the stroke patient and a caregiver of the stroke patient, and rehabilitation safety and effect are guaranteed.

The invention discloses an electric power total-factor unified load prediction method and system based on a time sequence large model, and relates to the technical field of machine learning, and the method comprises the steps: triggering a prediction process through a timed task, and obtaining historical load data and external covariable data; constructing a time sequence sample required by training and prediction according to a time window, and performing batch pulling and processing according to a fixed number of days when the data size exceeds a single-batch threshold value; performing data standardization and data cleaning on the data, and generating structured time sequence input; loading a time sequence large model as a unified prediction engine, and inputting a load sequence and an external covariable into a covariable fusion component for collaborative modeling; and outputting fine-grained prediction results of the electric power elements in the target time period at the same time under a single model framework, and post-processing and storing the prediction results. Through the technical scheme of the invention, the model fragmentation and maintenance cost is reduced, the generalization and stability are improved, and the operation stability and the engineering availability are improved.

The embodiment of the invention provides a model training method, an information recommendation method, equipment, a storage medium and a program product. According to the embodiment of the invention, a multi-encoder-multi-sub-decoder-total decoder hybrid model architecture is provided, sample data of different information modes correspond to different encoders-sub-decoders, and a mode of processing all training sample data by a single model is converted into a divide-and-conquer mode. The internal complexity of each encoder-sub-decoder is relatively low, the complexity of model training can be reduced, resource consumption can be saved, and different encoder-sub-decoders can be trained in parallel, so that the model training time can be shortened; and furthermore, by utilizing a dual decoding mechanism of the sub-decoder and the global decoder, parameters of the encoder can be continuously adjusted through local optimization and global optimization, the performance of the model is optimized, the accuracy of a reasoning result is improved, the convergence speed of the model is accelerated, the model training efficiency is further improved, and the model training time is saved.

The invention discloses a physical feature perception large language model construction method for flow field understanding and generation, and belongs to the technical field of intelligent aerodynamics, multi-modal deep learning and computer vision crossing. High-level aerodynamic semantics and bottom-level physical feature learning of a flow field are decoupled through a double-codebook sharing mapping mechanism, and alignment of the high-level aerodynamic semantics and the bottom-level physical feature learning is kept at the same time. The discrete unified representation obtained through the token device is combined with a large language model, high-precision physical reconstruction and deep aerodynamic semantic understanding of the flow field image can be achieved at the same time under a single model framework, and the core problems that in the prior art, perception and generation tasks are split, and the fidelity of physical characteristics is low are effectively solved.

The invention relates to the technical field of mechanical equipment intelligent operation and maintenance and state monitoring, and discloses a health monitoring method for bearing state evaluation and residual life and degradation trend prediction, which comprises the following steps of: firstly, extracting time domain, frequency domain and time-frequency domain characteristics from original vibration signals of a bearing under different working conditions; according to comprehensive evaluation indexes and known bearing degradation characteristics, features having good characterization capability and trend consistency for bearing degradation performance are screened out, a novel backbone network model is constructed, deep features are mined, effective features are enhanced, meanwhile, a time dependency relationship in a long sequence is captured, and then a multi-task learning mechanism is introduced, so that the bearing degradation performance is evaluated. Through parameter sharing and joint optimization, bearing state identification, residual life prediction and performance degradation trend prediction can be synchronously completed only by training and deploying a single model. According to the method, multi-task collaborative prediction under complex working conditions is realized, and the accuracy and robustness of bearing state recognition and service life prediction are improved.

The invention discloses a 10kV overhead line adaptive evaluation method and system for non-power-cut operation, and the method comprises the following steps: obtaining the field data of a target line, and constructing the field data into a multi-dimensional evaluation feature vector according to a preset evaluation dimension system for non-power-cut operation; inputting the multi-dimensional evaluation feature vector into a non-power-cut operation adaptability evaluation model to obtain a comprehensive evaluation score and an optimization suggestion of the target line; outputting the comprehensive evaluation score and the optimization suggestion; wherein the non-power-cut operation adaptability evaluation model is constructed by the following steps: training to obtain an initial machine learning model; simulating a preset non-power-cut operation task flow in the digital twinborn body; and performing incremental training and parameter optimization on the initial machine learning model by using operation effect data fed back after actual operation of the simulation data vector. The problems of single evaluation dimension, model stiffness and the like in the prior art can be solved.

The invention discloses a load prediction method and system based on error division multiple tasks, a medium and equipment, and the method comprises the steps: combining an error division task with a continuous learning mechanism, firstly calculating a sample relative error in a training process, classifying low-error data into a data set corresponding to a learned load feature mode, and carrying out the calculation of a data set corresponding to the learned load feature mode; the high-error data is delimited as a new task to be learned; measuring model parameter importance through a Fisher information matrix of EWC, introducing an L2 regularization item to constrain core parameter updating, and avoiding forgetting a learned old mode; and circularly executing task division and model training, so that a single model gradually masters various load characteristic modes in continuous learning. A division basis does not need to be set manually, a multi-mode learning process is simplified, and prediction accuracy and robustness in a complex load scene are improved.

The invention relates to a thermal power generating unit coal consumption prediction method and device and a program product. Comprising the steps of determining a target prediction time period, a target prediction moment and a target time scale; screening out a target operation data set matched with the target time scale and the target prediction time period from a preset operation data set corresponding to the target thermal power generating unit according to the target prediction moment; and inputting the target operation data set into a pre-trained target coal consumption prediction model to obtain the coal consumption corresponding to the target thermal power generating unit under the target time scale in the target prediction time period. Thus, the problem that a traditional single model is difficult to consider multi-time-dimension prediction precision can be effectively solved, meanwhile, errors caused by manual scale conversion are avoided, and full-cycle decision support from real-time level to strategic level is provided for fuel scheduling of a power plant.

The invention provides an automatic homework evaluation method and system based on multi-agent parallel voting, and the method comprises the steps: receiving a to-be-corrected target homework answer, and distributing a converted task to a parallel scoring agent cluster for processing; performing parallel scoring operation on the target homework answers, and respectively outputting respective correction scores and corresponding confidence indexes; collecting a correction result from each agent, and calculating to obtain a final correction score of the target job according to a preset dynamic weight distribution mechanism and an abnormal value elimination mechanism; and returning the calculated final correction score and an interpretable report including the scoring details of each scoring model to the terminal. According to the method, multiple scoring models are adopted for parallel scoring, and the voting aggregation technology is combined, so that the scoring variance of a single model is effectively reduced, and the overall accuracy is improved; and the model weight is dynamically adjusted according to the historical accuracy and the real-time confidence, so that the adaptability and robustness to different question types and different answers can be improved.

The invention provides an intelligent prediction and dynamic optimization distribution method for computer network traffic, which relates to the technical field of computer networks and comprises the following steps of: acquiring and preprocessing network traffic data; constructing a multi-model fusion network traffic prediction model; generating a dynamic optimization distribution strategy based on a prediction result; and allocation strategy execution and dynamic feedback adjustment: executing the allocation strategy through the SDN controller, monitoring the network state in real time and feeding back the network state. A multi-model fusion strategy is adopted, the time sequence capturing capability of the improved LSTM, the feature fitting capability of the XGBoost and the long dependence processing capability of the time sequence attention Transform are combined, and the weight is optimized through PSO, so that compared with a single model, the prediction error is reduced, the burst flow and periodic flow features can be accurately captured, and the problem that in the flow distribution link, the flow distribution efficiency is greatly improved is solved. Most methods only aim at maximizing the bandwidth utilization rate, and ignore the problem of QoS demand difference of different services.

The invention relates to the technical field of mold machining, and discloses a process parameter determination method and system, terminal equipment and a storage medium, and the process parameter determination method comprises the steps: obtaining model training data, carrying out the labeling processing of the model training data, and obtaining the processed model training data; performing model training based on the processed model training data to obtain a process parameter model, the process parameter model comprising a meta learner and a plurality of base learners; inputting the process processing data into each base learner to obtain initial process parameters; and inputting each initial process parameter into the meta-learner to obtain a target process parameter. According to the method, the target technological parameters are automatically determined through the technological parameter model, the problem that determination of the mold technological parameters depends on artificial experience is solved, the technological parameter model predicts the final target technological parameters based on the multiple base learners and the meta learners, single model deviation is avoided, and the accuracy and stability of technological parameter prediction are remarkably improved.

The invention relates to the field of water quality prediction, and particularly discloses a water supply pipe network water quality prediction method and system based on big data analysis. The input mixed water quality signal is decoupled into a plurality of independent component branches in one-to-one correspondence with the water sources on the characteristic level. And then, through a time-space diagram convolutional network sharing parameters, parallel and independent evolution derivation is carried out on each component flow, so that pervasive transportation and attenuation laws followed by different source water in a pipe network can be respectively captured, and the fundamental defect that a traditional single model cannot be distinguished and processed is overcome. Finally, all independently predicted future component states are subjected to self-adaptive nonlinear fusion with definite physical significance according to the accurate volume ratio of the future component states at the target point, so that a final mixed water quality prediction result with physical interpretability and high precision is generated.

The invention relates to a multi-agent cooperation-based language model reasoning resource scheduling method and system, and the method achieves the intelligent simulation of multi-view iterative thinking in a complex reasoning task through the construction of a multi-agent system which is clear in division of labor and is provided with a special knowledge base. View limitation and decision deviation of a single model in long-sequence and multi-step reasoning are effectively overcome; depending on the fusion of the general capability of the large language model and the task special knowledge base, the professionality and accuracy of the reasoning result are improved. Meanwhile, the problems of resource waste, redundant calculation and unstable convergence caused by cognitive overload in the cooperation process are solved by combining multi-round dynamic cooperation with a convergence mechanism of cognitive load perception and a dynamic token number limitation and low-confidence branch pruning strategy; therefore, on the premise that the reasoning quality is guaranteed, the utilization efficiency of computing resources is remarkably optimized, peak value occupation is reduced, the overall reasoning time delay is shortened, and reliable technical support is provided for efficient and stable deployment of a large language model in a complex task.

The invention relates to the technical field of natural language processing, in particular to a multi-agent-based question number reply method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: determining a corresponding target query task according to a natural language text currently input by a user in response to a received query instruction; analyzing and disassembling the target query task to obtain a plurality of atomized sub-tasks; matching the plurality of atomization sub-tasks with each agent, so as to enable each atomization sub-task to be matched with a corresponding target agent; executing the corresponding atomization sub-task based on each target agent to obtain an execution result; and according to each execution result, generating a natural language reply text. Therefore, the query instruction in the natural language form of the user is disassembled into the atomization sub-tasks, the problem that a traditional single model is difficult to efficiently process complex and multi-dimensional question requirements is solved, and the processing capacity of complex question tasks can be improved.

The invention provides a Bohai sea temperature prediction model based on a fusion model, the previous research mainly carries out prediction through single models, and the single models have corresponding limitations more or less. In order to solve the problem, a Bohai sea temperature prediction model based on a fusion model is provided. According to the method, through fusion of an Informer model and an LSTM model, and through feature optimization and XGBoost correction, the model obtains better prediction performance. According to the model, the prediction precision of the sea surface temperature of the semi-closed sea area is improved, and high-reliability data support is provided for ocean decisions such as storm surge early warning, fishing ground scheduling and ecological management.

The embodiment of the invention provides a user risk identification method and device, electronic equipment and a storage medium, and relates to the technical field of computers. According to the method, multi-source time series data are fused, local space correlation characteristics of user behaviors are extracted by using a convolutional neural network in sequence, a long-term and short-term memory network captures a long-range time dependency relationship of a behavior sequence, a Transformer encoder mines deep correlation characteristics among key behavior segments, and risk decision is carried out by integrating the three characteristics. According to the method, multi-dimensional collaborative recognition of a complex and hidden risk mode in digital right operation is achieved, the accuracy and robustness of risk recognition are improved, the false alarm rate and the missing report rate are reduced, the limitation of a traditional risk control method or a single model in space-time-semantic joint modeling is overcome, and the method has higher generalization ability and practical application value.