586 results about "Dynamic learning" patented technology

The invention relates to a multi-modal dynamic optimization educational resource recommendation system and method, and the system comprises the following modules: a multi-modal data collection module integrates video behaviors, answer tracks, physiological signals and other data through edge calculation, and constructs a learning feature map; the student portrait module adopts an LSTM-Attention network in combination with a graph neural network to dynamically model knowledge mastery and learning styles; the resource matching engine realizes multi-objective optimization of knowledge gain, cognitive load and interest matching based on reinforcement learning and knowledge graph analysis; the tag adaptive module dynamically adjusts resource weights through causal inference and comparative learning, the personalized recommendation module generates a dynamic learning path and pushes adaptive resources based on student portraits and real-time behavior data, and the learning progress tracking module monitors a learning state in real time and feeds back the learning state to the resource matching engine to optimize a recommendation strategy in a closed loop mode. The technical defects that resource recommendation of a traditional education platform is rigid and personalized adaptation is lacked are overcome.

The invention discloses a user behavior prediction system and method based on multi-modal data fusion, and particularly relates to the field of user behavior prediction, and the system comprises a multi-modal data collection module, a preprocessing and feature extraction module, a cross-modal fusion module, a user behavior prediction module, and a model optimization and feedback module. According to the system, multi-dimensional original data such as visual sense, auditory sense, text, physiological signals and environment context of a user are acquired in real time through a multi-modal data acquisition module; then, deep networks such as ResNet, VGGish and BERT are adopted to extract high-dimensional feature vectors of all modals, and contribution weights of features of different modals are dynamically learned through an attention mechanism; and finally, based on a time sequence model of Transform and LSTM, analyzing fusion features, and outputting probability distribution of future behavior intentions. And parameter joint optimization and continuous learning are realized through a multi-objective loss function and end-to-end back propagation.

The present application relates to the technical field of power plant optimization, and discloses a thermal power plant auxiliary power system optimized dispatching method and system considering a wind-solar-storage system, and a device and a storage medium. The method specifically comprises: collecting thermal power plant auxiliary power system data, and establishing an auxiliary power system multi-objective function on the basis of the thermal power plant auxiliary power system data and a wind-solar power generation cluster model in an auxiliary power system; introducing constraint penalties and constraint conditions to the auxiliary power system multi-objective function, and constructing a thermal power plant auxiliary power system optimized dispatching model; and processing the thermal power plant auxiliary power system optimized dispatching model by using a dynamic learning factor-based particle swarm algorithm to obtain an optimized dispatching result, and completing thermal power plant auxiliary power system optimized dispatching on the basis of the optimized dispatching result. According to the present application, the optimal interactive output among wind turbine units, photovoltaic units, energy storage units, and a generating set can be determined on the basis of the optimized dispatching result, auxiliary power system low-carbon optimized dispatching is implemented, and the problem in the prior art of lacking dispatching in which new energy and thermal power plant auxiliary loads are integrated for analysis is solved.

The invention relates to the technical field of urban infrastructure intelligent detection, and discloses an urban drainage pipe network damage detection system based on intelligent analysis. A multi-source data acquisition module acquires pipe network static structure parameters and real-time operation monitoring data through a distributed sensor network; generating a topological characteristic value, a dynamic operation state characteristic value and a dynamic detection threshold set of each damage type; the data preprocessing module filters noise of the monitoring data, eliminates abnormal values and extracts time domain and frequency domain feature vectors; the feature fusion module fuses and generates a multi-dimensional fusion feature matrix based on the topology and operation feature values; the intelligent analysis engine calculates and outputs a damage type diagnosis result through mode matching; the spatial positioning module generates three-dimensional coordinate positioning data of the damaged area in combination with the topological characteristic value; and the dynamic learning module optimizes the detection rule according to the maintenance data. The system realizes intelligent damage detection and accurate positioning, improves the detection accuracy and efficiency, adapts to a complex environment, and is high in intelligent level.

The invention belongs to the technical field of speech recognition. The invention provides a low-resource language self-adaptive speech recognition method based on AdLoRA Plus. The low-resource language self-adaptive speech recognition method comprises the following steps of: obtaining a speech According to the embodiment of the invention, the AdLoRA Plus fine tuning technology is introduced, so that the speech recognition precision of the Whisper model is remarkably improved in a low-resource language environment. Through a low-rank adapter layer and dynamic learning rate adjustment, efficient parameter updating is realized under limited training data. According to the method, a strategy of freezing basic parameters is adopted, only an AdLoRA Plus adapter layer is trained, calculation overhead and training time are remarkably reduced, pre-training knowledge is kept, and overfitting is prevented. The method has wide adaptability and expansibility, and is ensured to be outstanding in practical application. The voice recognition precision, the reasoning efficiency and the training efficiency are effectively improved, multiple challenges in application in small languages and specific fields in the prior art are solved, and the method has important practical application value.

The invention discloses a temperature control management method for an electric oven, and relates to the technical field of intelligent household appliance control, and the method comprises the steps: carrying out the offset correction of a pre-stored mode mapping table based on a calibration matrix, loading a target temperature interval and a three-dimensional temperature field partition parameter according to a cooking mode selected by a user, and triggering a dynamic learning mark; according to the dynamic learning mark, the furnace chamber temperature and the environment temperature change rate are collected in real time, the power compensation amount is calculated through a thermal inertia compensation model, and a partition power control matrix is generated in combination with the three-dimensional temperature field partition parameters; and distributing the power compensation amount and the partition power control matrix to the heating pipe according to a preset topology, dynamically adjusting power output, and implementing temperature early warning and no-load identification based on an acoustic emission spectrum entropy value. The temperature gradient change rate is calculated through the Fourier heat conduction law, the three-dimensional temperature field partition parameters are dynamically generated, and accurate control over the temperature field in the complex three-dimensional space is ensured so as to cope with environment changes and user demand changes.

The invention relates to the field of deep learning and emotion recognition, in particular to an EEG emotion recognition system and method based on multi-scale space-time diagram convolution and comparative learning, and the method comprises the steps: carrying out the preprocessing of an EEG signal; constructing positive and negative sample pairs based on the emotion categories and the identities of the subjects; extracting hidden space representation of the electroencephalogram signal by adopting a stack auto-encoder, and dividing the electroencephalogram signal into a plurality of functional brain regions to obtain a brain source signal after dimension reduction; constructing an undirected graph structure of the brain source signal; constructing a multi-scale space-time diagram convolutional network as a feature extraction network, inputting an undirected graph structure, dynamically learning and updating an adjacent matrix, expressing features of brain source signals in the undirected graph structure, and extracting emotion related features; based on a multi-scale space-time diagram convolution and comparative learning framework, an EEG emotion recognition model is built and trained to eliminate individual differences. According to the method, the multi-dimensional information of the EEG signals is fully utilized, and the accuracy, robustness and generalization performance of emotion recognition are remarkably improved.

The invention belongs to the technical field of medical artificial intelligence, and discloses an artificial intelligence-based auxiliary diagnosis and treatment system, which comprises a multi-modal data acquisition module, a dynamic learning module, a diagnosis reasoning module, a privacy protection module, an interactive decision module and an early warning monitoring module, the output end of the multi-modal data acquisition module is connected with the input end of the privacy protection module, the output end of the privacy protection module is connected with the input end of the dynamic learning module, the output end of the dynamic learning module is connected with the input end of the diagnostic reasoning module, and the output end of the diagnostic reasoning module is connected with the input end of the interactive decision module. And the early warning monitoring module monitors abnormal data in real time and performs bidirectional interaction with the diagnosis reasoning module. According to the method, multi-source medical data are integrated, and high-precision real-time auxiliary diagnosis is realized by adopting a dynamic incremental learning and privacy encryption technology; the medical worker cooperation efficiency is improved through an interactive interface, the safety is guaranteed in combination with real-time monitoring and early warning, and the system can remarkably improve the diagnosis and treatment efficiency and accuracy.

The invention provides a privacy protection method for multi-modal pedestrian behavior monitoring, and relates to the field of information security, and the method comprises the following steps: 1, carrying out the multi-modal pedestrian spatial-temporal feature fusion through a multi-modal pedestrian data fusion method based on spatial-temporal hybrid Mama; step 2, effectively protecting fusion features based on a differential privacy protection method of adaptive feature density perception; 3, a multi-modal pedestrian behavior pre-training method based on a double-flow dynamic Transform is adopted, and the pre-training precision of the model is improved; 4, a sparse gradient privacy protection method oriented to adaptive space-time correlation is adopted to ensure the safety of the model; and step 5, performing efficient monitoring based on a multi-modal pedestrian behavior monitoring method of a dynamic learning rate. According to the method, high-accuracy pedestrian behavior monitoring is realized, # imgabs0 # differential privacy is met based on the differential privacy property, and the safety and effectiveness of multi-mode pedestrian behavior monitoring are improved.

The invention relates to the technical field of evaluation and management, in particular to a classroom learning dynamic evaluation and management system, which comprises a multi-source heterogeneous data acquisition module, an acoustic sensor array, an optical motion capture unit, an intelligent writing track acquisition device and a brain wave monitoring terminal, the data preprocessing and feature fusion module is used for eliminating environment interference signals and generating preprocessed data; the dynamic learning state evaluation module is used for extracting three-dimensional features and outputting a dynamic evaluation matrix; the group learning portrait generation module is used for generating a multi-dimensional learning portrait in combination with a preset knowledge graph topological structure; the self-adaptive management strategy generation module is used for dynamically generating a management strategy set; and the intelligent feedback execution module is used for driving the self-adaptive illumination system, the wearable vibration reminding device and the AR enhancement projection equipment to execute physical environment regulation and control. According to the invention, personalized strategy dynamic generation is realized, and adaptive regulation and control of the classroom environment and the teaching rhythm are realized in combination with the intelligent Internet of Things equipment, so that an intelligent collaborative feedback closed loop is formed.

The invention discloses a scenic spot accompanying service method and a scenic spot accompanying service system based on linkage of a generative AI and a knowledge base, particularly relates to the technical field of artificial intelligence and smart tourism, and is used for solving the problems that core knowledge is forgotten and the answer accuracy is reduced due to dynamic knowledge updating of a generative AI model in an existing scenic spot guide system. The method comprises the following steps: extracting tourist question keywords in real time and retrieving a knowledge base to generate associated data; dynamically weighting the associated data priority based on the tourist aggregation density; generating an initial answer through real-time parameter adjustment; fusing the spatial-temporal clustering and the knowledge graph structure entropy to generate a weight factor; correcting the answer coverage defect and evaluating the result; outputting a final answer after directional addition of core knowledge iterative training; it is guaranteed that core knowledge of the scenic area is stably reserved in the dynamic learning process of the generative AI, meanwhile, the real-time scene requirement is accurately responded, and the reliability, accuracy and individuation level of the navigation service are remarkably improved.

The invention provides a natural language text data intelligent classification method and system based on deep learning, and relates to the technical field of natural language processing, and the method comprises the steps: 1, employing a context awareness mechanism to analyze the real semantics of a target vocabulary according to an antagonistic variant existing in a text, and obtaining a target vocabulary; in combination with a word meaning library and a pre-training process of a dynamic learning rate adjustment strategy, generating a candidate replacement vocabulary set with consistent semantics; and step 2, based on the candidate replacement vocabulary set, performing multi-dimensional semantic similarity calculation and emotional tendency discrimination, determining applicable vocabularies conforming to an original culture background through a context adaptation strategy, and generating a standardized text sequence. According to the method, through multi-dimensional semantic analysis, cultural context fusion, cross-granularity feature construction and dynamic parameter correction, the accuracy and adaptability of natural language text classification are realized.

The invention discloses an automatic driving decision-making method and system based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: obtaining the initial positioning and destination information of a target vehicle, and generating a target driving route; the method comprises the following steps: acquiring multi-source environment sensing data through an intelligent sensing module, and performing multivariate feature extraction to generate environment feature information; based on the environment characteristic information, a dynamic learning optimization technology is adopted to carry out real-time adjustment on the target driving route, and a driving strategy adapting to a complex traffic scene is generated; and finally, realizing automatic driving control of the target vehicle according to the real-time dynamic driving strategy. According to the method, the technical problems of incomplete environment perception, static path planning and insufficient decision real-time performance of the existing automatic driving technology in a complex traffic environment are solved, and the technical effects of comprehensive perception and real-time dynamic path planning in the complex environment are achieved through multi-source data fusion and dynamic learning optimization.

The invention provides a medical decision support method and system based on big data. The method comprises the following steps: integrating and fusing patient information from different medical institutions, personal health monitoring equipment and a public health database to obtain a dynamic update library; a graph neural network algorithm is applied to analyze the relation between the patients and the relation between the patients and the environmental factors in the dynamic update library so as to predict the individualized disease development trend, and dynamic risk early warning signals are generated; based on the dynamic risk early warning signal, through feature importance analysis and a local interpretable model, revealing key factors and an interaction mechanism influencing disease progression, and applying a health economics evaluation method to generate a medical suggestion report; and in combination with the medical suggestion report, establishing a dynamic learning and feedback mechanism, optimizing personalized suggestions in the medical suggestion report, and constructing a medical decision support system. According to the technical scheme provided by the invention, the credibility of medical decision making is remarkably improved.

The invention provides a personalized learning content recommendation method and system based on neighborhood and hypergraph collaboration, and relates to the technical field of content recommendation. The method comprises the following steps: constructing a hypergraph view and a neighbor graph view by obtaining user session sequence data; extracting global high-order relation features based on the hypergraph view; extracting local co-occurrence relation characteristics based on the neighbor graph view, and generating enhanced co-occurrence relation characteristics; embedding and splicing a sequence position code of a user learning path and learning content semantics, fusing context information through a gating dynamic attention mechanism, and generating a dynamic learning interest embedding expression; based on a global-local contrast learning strategy, performing nonlinear projection on dynamic learning interest embedding and global semantic embedding, and optimizing semantic consistency of the two types of embedding by comparing loss; and combining the cross entropy loss and the contrast learning loss of the recommendation task, constructing a combined optimization objective function, generating a personalized recommendation result, and realizing the technical effect of capturing dominant and implicit relationships between learning contents.

The invention relates to the field of computer accessories, and discloses a computer accessory intelligent recommendation system and method based on user behavior analysis, and the method comprises the steps: collecting interaction data of a user in an e-commerce platform, and constructing a behavior feature data set of user preference and a current equipment state through a behavior semantic deconstruction algorithm and an equipment configuration recognition mechanism; performing multi-dimensional feature extraction on the behavior feature data set, constructing a user equipment ecological model based on an accessory dependence modeling method, and introducing a behavior context sensing mechanism to perform dynamic learning training on the model; judging whether the recommendation model reaches a stable state or not according to the change trend of the fitting dependence path in the model training process; based on the optimized equipment ecological model, adopting a heterogeneous relation fusion recommendation strategy; and generating a personalized accessory recommendation scheme according to a sorting result, and performing feedback verification on the scheme in combination with a preset recommendation rationality evaluation model. The method has the advantage of improving the precision and experience of accessory recommendation.

The invention belongs to the technical field of artificial intelligence education, and particularly relates to a student learning behavior prediction method based on artificial intelligence, and the method comprises the steps: obtaining student learning data and teacher teaching task data; constructing a student agent according to the student learning data, and constructing a teacher agent according to the teacher teaching task data; a dynamic teaching strategy generated by the teacher agent is input into the student agent, and the student agent predicts possible learning behavior change of the student based on a learned behavior mode in combination with a strategy-behavior causal model; the prediction result is linked with a teaching management mechanism, a dynamic learning file is generated, the teacher intelligent agent matches personalized learning resources through an intelligent recommendation algorithm according to the dynamic learning file, and the student intelligent agent receives feedback of students on the learning resources and performs targeted intervention actions in combination with feedback information. Therefore, the problems of insufficient causal reasoning ability, weak calibration ability, insufficient data fusion ability and the like in the prior art are solved.

The invention discloses an intelligent recognition system for urban and rural building styles and features based on multi-source data fusion. According to the invention, by fusing the emotion feedback and objective visual features of the user on the building, the system not only can accurately judge the style type of the building, but also can understand the subjective feeling difference caused by different styles. For example, when the Hui-style building is identified, the system can synchronously capture the worry emotion generated by the user on the'whitewashing and yerba ', so that the characteristics of the building can be displayed and the emotion demand of the tourist can be matched during tourism recommendation. The dynamic learning mechanism enables the system to continuously absorb fresh feedback of users in various regions and automatically correct cognitive deviation of an original model to regional characteristic buildings, for example, the detail distinguishing standard of southern Fujian red brick placing and Lingnan wok ear house is updated in time, the adaptive capacity to continuously changing urban and rural styles is kept, and in a cultural heritage protection scene, the system can be used for protecting cultural heritage. In combination with double dimensions of professional surveying and mapping data and public emotion evaluation, recent modern buildings with collective memory value can be positioned more accurately.

The invention belongs to the technical field of automatic driving vehicle identification, and discloses an automatic driving vehicle point cloud identification method and system based on a laser radar. According to the method, an automatic driving vehicle point cloud recognition model is built, modular dynamic edge convolution based on a feature sensitivity layer number selection strategy is provided in the model, local geometric information is better captured by dynamically learning a local geometric structure, and the extraction capability of geometric feature information is enhanced. In order to prevent the problem of insufficient information extraction caused by layer number simplification of modular dynamic edge convolution, a selective kernel attention mechanism is introduced, a feature fusion mode is adjusted, residual connection is added, more comprehensive statistical information is captured while original information is reserved, and the multi-scale feature capture capability is improved, so that the classification performance of the model is improved. Especially in the face of noise, sparse data and complex object shapes, high classification accuracy can still be kept, and a more accurate environment perception capability is provided for an automatic driving system.

The invention relates to the technical field of intelligent monitoring, and discloses an intelligent archival repository monitoring system based on Internet of Things, comprising: a plurality of edge sensing units deployed in a repository, monitoring parameter drift in real time and triggering a local perturbation event by dynamically learning a personalized stable state baseline of environmental parameters; cooperative judgment is achieved among the units through perturbation wake-up signals, concerned events are reported to a central platform only when preset conditions are met, and full-spectrum perception of slowly changing and sudden risks is formed through baseline learning and a cooperative wake-up mechanism of the edge units in combination with instantaneous event template matching and targeted enhanced monitoring; based on the dynamic health fingerprint analysis of the perturbation resonance characteristic spectrum, the stability degradation trend of the archive microenvironment can be pre-warned in a prospective manner, and the intelligent level and the preventive protection capability of the monitoring system are remarkably improved.

The invention discloses a layered energy management method of a fuel cell hybrid tramcar with self-adaptive working condition perception. In the recognition layer, a sliding window mechanism is adopted to extract time domain and frequency domain features of load conditions, feature data are clustered based on a spectral clustering algorithm driven by a deep auto-encoder, a data set with category labels is obtained, and a deep dynamic learning vector quantization neural network classifier is trained; in the strategy layer, a double-delay depth deterministic strategy gradient reinforcement learning algorithm is adopted, a reward function is constructed, and lithium battery SOC fluctuation penalty term limit parameters in the reward function are adaptively adjusted according to the real-time load working condition category output by the recognition layer; training the reinforcement learning agent to obtain an optimal power distribution scheme between the multi-stack fuel cell power generation system and the lithium battery; and according to the performance degradation degrees of different fuel cell stacks, a distributed cooperative control strategy considering performance difference is adopted to distribute the output power of each stack, so that the coordinated control of the running state of the multi-stack fuel cell power generation system is realized.

The invention relates to the technical field of data governance, and discloses a data governance method based on an intelligent decision engine, which comprises the following steps: carrying out business semantic classification and marking on preliminarily processed real-time streaming data, and constructing a data portrait library; constructing a dynamic topological graph, learning an abnormal propagation rule based on a graph neural network, analyzing an influence range and establishing an influence grading mechanism; performing multi-dimensional quality evaluation on the data, and generating a dynamic data quality score and a grading strategy; constructing a data quality historical problem and reason case library, and generating a quality anomaly root cause judgment and influence quantification report by using a large language model agent; generating a candidate strategy set, and selecting an optimal governance strategy from the candidate strategy set by establishing a multi-objective optimization model; and performing compliance test and conflict identification on the optimal governance strategy by using a large language model agent, and dynamically adjusting the decision weight of a rule engine by using a reinforcement learning algorithm to realize a closed loop of data governance and dynamic learning.

The invention relates to the technical field of multi-view clustering, in particular to a multi-view clustering method and device, and can solve the problem that the overall effect of an existing method in a large-scale clustering task is limited due to the fact that the existing method has problems in the aspects of calculation efficiency, robustness and multi-view information integration to a certain extent. The method comprises the following steps: dynamically learning an anchor matrix and a projection matrix for each view, and constructing a bipartite graph to generate a similarity matrix; calculating a graph Laplacian matrix based on the similarity matrix of each view, and extracting spectrum embedding; the spectrums of multiple views are embedded and stacked into a third-order tensor, and cross-view shared information is extracted by using a low-rank tensor constraint; multi-view atlas embedding is aligned through a spectrum rotation technology, and a discrete clustering indication matrix is directly output.

The invention belongs to the technical field of control valve adjustment, and particularly relates to a military and civilian dual-purpose ship electric control valve actuator which comprises a target analysis module, a dynamic compensation module, a parameter transmission module, a closed loop calibration module and an emergency braking module. Valve displacement increments and initial motor rotating speed parameters are distributed for all the sub-windows, the comprehensive influence of gear return difference, thermal deformation, friction and vibration interference on valve displacement is effectively considered in the execution process of the sub-windows, a mechanism coupling compensation factor with a dynamic learning optimization mechanism is generated, displacement errors are combined to be superposed to the rotating speed parameters of the next window, and a dynamic learning optimization mechanism is generated. According to a double-layer correction framework of child window dynamic compensation and tail end closed-loop calibration, technical closed-loop from local interference suppression to global precision guarantee is achieved, an emergency braking module is additionally arranged to avoid the risk of out-of-control displacement caused by sudden load impact, and efficient and safe operation of a ship is effectively guaranteed.

A dynamic learning server-based logistics system includes a node-based logistics receptacle operative to receive a delivery item as part of a logistics transaction and also includes a backend server maintaining a management profile related to operation of the node-based logistics receptacle. The node-based logistics receptacle includes a plurality of monitored receptacle components, a wireless accessory sensor node having a plurality of sensors, and a bridge node operative to retrieve event information from the wireless accessory sensor node. The backend server receives the retrieved event information, compares the retrieved event information with the management profile, identifies a threshold change condition from the comparison, dynamically revises the management profile when the threshold change condition is identified, and transmits an adjustment message to the bridge node. The adjustment message is based upon the revised management profile, and the adjustment message initiates a timing change to operation of the bridge node.

The invention relates to the technical field of defect detection systems, and discloses a titanium alloy surface crack defect detection system based on deep learning. According to the system, a crack feature extraction module is used for collecting a titanium alloy surface image and extracting multi-scale crack features including crack trend distribution features and micro-crack density features; the multi-modal data fusion module is used for receiving the multi-scale crack features and performing space-time alignment on the multi-scale crack features and ultrasonic reflection wave features collected in real time to generate a fusion defect feature matrix; the dynamic learning engine module is used for constructing a crack propagation prediction model according to the historical change trend of the fusion defect feature matrix and outputting a dynamic defect response vector; the defect positioning module is used for mapping the dynamic defect response vector to a titanium alloy surface three-dimensional coordinate space to generate a defect position thermodynamic diagram; and the self-adaptive scanning control module is used for analyzing the defect confidence of each area in the defect position thermodynamic diagram and dynamically adjusting the scanning path and the focal length parameter of the industrial camera.

The invention discloses a Chinese herbal medicine intelligent drip irrigation regulation and control system based on end-cloud cooperation, and relates to the technical field of agricultural intelligent irrigation, and the system comprises an edge equipment end which is deployed in a Chinese herbal medicine planting area, comprises a multi-mode sensor module, a communication module and an irrigation execution mechanism, and is used for collecting soil humidity, illumination intensity and meteorological data in real time, and sending the collected data to a cloud server; and the drip irrigation valve is controlled through the irrigation executing mechanism. According to the Chinese herbal medicine intelligent drip irrigation regulation and control system based on end-cloud collaboration, through an end-cloud collaboration architecture and a hierarchical decision-making mechanism, the drip irrigation regulation and control accuracy and real-time performance in a Chinese herbal medicine planting environment are improved. A local AI inference engine of the edge equipment end is combined with a dynamic learning module, an optimization instruction can be automatically generated during network fluctuation, dependence on real-time communication of the cloud end is reduced, and continuity and reliability of irrigation operation in complex terrains are ensured.

The invention discloses an extreme weather photovoltaic power prediction method, system and device, and a medium. The method comprises the steps of obtaining related data of a power plant and performing first processing; constructing a first neural network to extract spatio-temporal features of the cloud picture, and realizing adaptive classification of extreme weather and non-extreme weather through a double-branch discriminator; guiding a conditional diffusion model to generate a non-extreme weather accurate cloud picture by taking the cloud picture spatial-temporal characteristics as constraint conditions; generating an extreme weather accurate cloud picture based on a cloud picture spatio-temporal feature guidance condition generative adversarial network; constructing a second neural network to capture global and local dynamic change characteristics of photovoltaic power and related meteorological data of the power plant; constructing a cross attention module to fuse the weather accurate cloud picture and the dynamic change features; and inputting the fusion features into a third neural network, and dynamically learning mapping from the fusion features to power. According to the invention, through a cloud picture generation framework and a multi-modal fusion mechanism, the problem of failure of a traditional prediction model in extreme weather is effectively solved.

The embodiment of the invention provides a multi-element deep learning correction method and device for numerical mode forecasting. The method is applied to the technical field of data processing, and comprises the following steps: marking observation points, and performing loss function construction on the positions of the observation points to obtain a model optimization target; carrying out iterative updating on model parameters, and carrying out training process optimization by adopting a dynamic learning rate adjustment strategy to obtain a forecast field correction model; and applying the prediction field correction model to target numerical mode prediction data acquired in real time, performing prediction effect evaluation, and performing standardization processing and anti-standardization processing to obtain a correction prediction result. According to the method, the information extraction capability of a deep learning visual algorithm model is utilized, fine deviation correction of data of a numerical mode forecast space grid by meteorological station observation data is completed, meanwhile, multiple types of meteorological elements are fused, the deep learning model is utilized to learn mutual influences and restrictions between related elements, and the prediction precision of the numerical mode forecast space grid is improved. And finer deviation correction is completed.

The invention relates to the field of network security, in particular to a root cause analysis method, system and device based on large model causal reasoning, and aims to improve the positioning precision of an attack entry node. The root cause analysis method comprises the following steps: extracting a network entity and an attack event chain from a network traffic log; constructing a first causal graph based on a pre-trained graph neural network according to the network entity and the attack event chain; wherein nodes of the first causal graph represent network entities or security events, and edge weights of the first causal graph represent causal dependence intensity dynamically learned through an attention mechanism; performing logical reasoning on the first causal graph by using a pre-trained large language model, and optimizing the first causal graph into a second causal graph; and calculating the root cause probability of each node in the second causal graph based on Bayesian inference, and positioning the attack entry node with the highest abnormal value. According to the method, emerging threats can be detected without frequently updating the rule base, and the positioning precision of the attack entry node is effectively improved.