463 results about "Bayesian inference" patented technology

The invention discloses a fatigue life simulation evaluation method for a lightweight aluminum alloy material of a new energy automobile, and relates to the technical field of material life evaluation. A microstructure image is collected, coupling features are extracted through machine learning, and heterogeneous data fusion and enhancement are completed; generating a topological optimization structure based on a GAN, introducing a VPSC model to describe anisotropy according to a stress gradient dynamic grid, and constructing a dynamic finite element model; fusing vehicle driving data, predicting a load by using LSTM, performing VMD decomposition and environment correction, and realizing space-time correlation load spectrum reconstruction; a phase field model is used in a microcosmic mode, cracks are tracked in a macroscopic mode through XFEM, damage parameters are transmitted in a bidirectional coupling mode, and multi-physics field coupling simulation is carried out; fusing simulation and test data by adopting Bayesian reasoning, calculating life probability distribution, and correcting parameters when errors exceed the limit; according to the method, the fatigue life prediction error is finally reduced, the time consumption of single simulation is reduced, full-life-cycle evaluation and visual early warning are realized, an efficient scheme is provided for lightweight design, and industrial technology upgrading is promoted.

The invention belongs to the crossing field of environmental engineering and hydrology and hydrodynamics, and particularly relates to a traceability method based on coupling hydrodynamics and a pollutant degradation equation, which comprises the following steps: firstly, acquiring and preprocessing multi-source heterogeneous monitoring data, then selecting a one-dimensional Saint-Venant equation or a two-dimensional shallow water equation according to a water body form to solve a hydrodynamic field, and finally, determining the hydrodynamic field. A multi-component convection-diffusion-reaction equation is coupled to simulate pollutant migration and transformation; an LSTM module is introduced to identify suspected pollution events, pollution source parameters are inverted through a two-channel framework of PDE constraint optimization and Bayesian inference, uncertainty is quantified, model parameters are updated online in combination with data assimilation, and finally the uncertainty is quantified and verified. The method considers traceability precision, efficiency and compliance, supports multiple water bodies and multiple data sources, and is suitable for complex water body pollution traceability.

The invention provides an automatic processing method for real-time observation data of an ocean station, and belongs to the technical field of ocean observation data processing. A wavelet packet decomposition multi-scale noise separation algorithm is established to distinguish environmental noise and real signals, dual-sensor redundancy configuration is combined with Bayesian inference to identify sensor drift, and a calibration coefficient is updated in real time through a recursive least square method. A one-dimensional time sequence is mapped to a high-dimensional phase space by utilizing a phase space reconstruction algorithm to realize high-precision prediction of a chaotic signal, a hierarchical data storage architecture is established, and a data migration strategy is iteratively optimized through a hierarchical correlation degree function; the technical problem that time synchronization signals are difficult to reconstruct accurately according to asynchronous sampling data of multiple sensors of an ocean station is solved.

The invention discloses a watershed water resource supply and demand risk prediction and evaluation method based on a multilevel Bayesian causal network, and relates to the technical field of water resource supply and demand risk management.The watershed water resource supply and demand risk prediction and evaluation method comprises the steps that a water resource supply and demand risk diagnosis knowledge graph is constructed according to key variables and interrelations input by a user; constructing a multi-level Bayesian causal network structure; estimating conditional probability distribution among the nodes, and performing parameter learning and structure training on the Bayesian causal network; carrying out risk path identification through a reverse Bayesian reasoning method; outputting a posterior probability of water resource supply and demand risk prediction; based on a preset fuzzy character string matching algorithm, typical risk events and risk features are extracted; and according to the posterior probability and the risk characteristics, comprehensively evaluating the water resource supply and demand risk level. The method can improve the systematicness and scientificity of risk identification, is suitable for multi-link and multi-scale risk assessment and scheme comparison and selection in a complex drainage basin, and has high practical value and popularization prospect.

The invention relates to a circuit board on-line defect detection method and system, and the method comprises the steps: carrying out the synchronous collection and structural integration of multi-source technological parameters such as production line environment temperature and humidity, equipment operation states, material batches and the like, and defect detection images, and achieving the construction of large-sample original data in a production process; through standardization and de-noising preprocessing, multi-modal features are fused, and a distribution mapping model of process and defect features is established by using algorithms such as mutual information analysis and principal component analysis. Based on a feature distribution model and real-time data, a dynamic anomaly detection threshold is adaptively generated, Bayesian inference and evidence reasoning are combined, multi-level confidence levels and risk response suggestions are output, and self-learning evolution of the model and the threshold is realized through a closed-loop feedback mechanism. According to the scheme, the accuracy of anomaly detection, the response timeliness and the risk disposal intelligent level are improved, the method adapts to complex working conditions and batch changes, and the closed-loop optimization and safety control capability of the production process is remarkably enhanced.

The invention relates to the technical field of task scheduling, and provides a metropolitan area network privacy protection computing migration task scheduling optimization method, the resource state of a computing node is processed in real time through Bayesian inference to determine a dynamic trust value in real time, and compared with static trust evaluation in the prior art, real-time risk changes of the computing node can be captured in real time, and the real-time trust value of the computing node is determined in real time. The privacy leakage risk is obviously reduced; the privacy risk estimation value, the task completion time delay and the task execution energy consumption are jointly used as optimization objectives of a multi-objective optimization function, and constraint conditions of the multi-objective optimization function are defined to ensure that the generated optimization scheduling scheme not only meets the privacy security requirement, but also can meet the time delay and energy consumption requirements; according to the method, actual behavior data of the computing nodes are continuously monitored, privacy compliance auditing is carried out, privacy compliance expression is used as new evidence to be fed back to Bayesian inference, dynamic trust values of the nodes are corrected, and long-term reliability and flexibility of task scheduling are remarkably improved.

The invention relates to the technical field of image processing, and discloses a pulmonary embolism focus segmentation method and system based on image recognition, and a storage medium. The method comprises the following steps: extracting a multi-level blood vessel topological structure of a CTPA image through blood vessel diameter gradient analysis; modeling blood vessel density distribution by using a Weibull mixed model to obtain embolism characteristic parameters; the pixel embolism probability is estimated through variational Bayesian reasoning, and a focus distribution diagram is generated; performing multi-scale feature fusion on the lesion probability graph to obtain a segmentation boundary; and obtaining a final embolism focus segmentation result based on the vascular connectivity constraint optimization boundary. The problems that blood vessel level differentiation processing cannot be achieved, and accurate probability modeling and anatomical constraint verification are lacked are solved. The accuracy of pulmonary embolism focus segmentation is improved.

The mold injection control method comprises the steps that three-dimensional point clouds of a current injection molding part and an adjacent previous injection molding part are obtained, the global difference degree between the current injection molding part and the adjacent previous injection molding part is calculated through overall registration, if the global difference degree exceeds a threshold value, a difference mask is generated and covers a real-time image of a cavity, a difference image is formed, and the difference image is subjected to injection molding. And performing hybrid clustering on the difference image and a known defect type database to obtain candidate defect types and membership degrees, calculating posterior probability contribution degrees of the sensing nodes to the candidate defect types by taking the membership degrees as input and combining a Bayesian reasoning algorithm, if the contribution degree of any sensing node exceeds a threshold value, outputting a defect root cause report, and if the contribution degree of any sensing node exceeds the threshold value, outputting a defect root cause report. And a machine table or a mold execution mechanism is driven to carry out correction. According to the invention, the problems of low detection efficiency, large subjective deviation and lagging root cause judgment due to the fact that automobile part defect detection and root cause analysis depend on manual visual detection or single-dimensional automatic detection are solved.

The invention relates to a reclaimed water reuse regulation and control method and system based on artificial intelligence and digital twinning, and the method comprises the steps: collecting initial data in a water treatment system, and carrying out the data preprocessing of the initial data to generate preprocessed data; constructing a digital twinning virtual model, and updating model parameters of the digital twinning virtual model based on the preprocessed data through a Bayesian reasoning algorithm to obtain a target digital twinning virtual model; outputting a water quality prediction result in a future preset time period through a pre-constructed water quality prediction model in the decision-making layer, and performing a rehearsal control strategy in the target digital twin virtual model based on the water quality prediction result to generate an optimization control instruction; performing data anomaly detection and fault diagnosis processing based on the preprocessed data through an anomaly detection model and an isolated forest algorithm to generate a fault diagnosis report; and issuing the optimization control instruction to an execution mechanism. The system response speed is improved, the control strategy perspectiveness is enhanced, and the equipment operation and maintenance intelligent level is improved.

The invention discloses an intelligent education robot question answering system based on voice recognition and a knowledge graph, and particularly relates to the technical field of artificial intelligence. The method comprises the following steps: performing feature extraction on a user voice signal to obtain a text sequence and a multi-modal context feature; recognizing subject domain judgment and question answering intentions based on supervised classification and keyword rule fusion, and outputting a subject domain prior probability and a question answering target vector; determining polysemy words in the text sequence by using a context window, generating a semantic item sequence and semantic item confidence, constructing a subject domain sub-graph based on a subject domain prior probability, and obtaining a candidate reasoning path and a path scoring vector; determining a target teaching concept and an optimal reasoning path by combining Bayesian inference and consistency verification; generating a personalized question answering result aiming at the question asked by the user through fact retrieval and knowledge derivation in combination with the question answering target vector; accurate and efficient intelligent teaching question answering can be realized, and question answering accuracy and intelligent interaction capability of the education robot are effectively improved.

The invention relates to the technical field of elevator safety monitoring, in particular to a fault early warning method based on an intelligent elevator. The fault early warning method comprises the steps that multi-dimensional operation parameters of a target elevator are obtained; multi-modal fusion is conducted on the vibration signal component, the noise signal component, the equipment static attribute data and the working condition environment data, and a health degree evaluation matrix of elevator operation is generated through a space-time attention encoder; according to the health degree evaluation matrix, a preset historical fault knowledge base is combined, the dynamic fault probability is calculated through a Bayesian inference model, and the early warning grade is generated. A historical fault knowledge base and a Bayesian inference model are further combined, a self-adaptive maintenance strategy triggered according to an early warning level from static threshold value alarm to dynamic fault probability prediction is realized, on-demand accurate maintenance is realized, and the maintenance efficiency and the resource utilization rate are improved.

The invention relates to the technical field of financial risk assessment, in particular to a financial risk assessment method and system fusing multi-dimensional indexes and combined weights, and the method comprises the steps: constructing a financial cooperation risk index system containing multi-dimensional heterogeneous data; executing a combined weight calculation process based on Bayesian inference logic; performing weighted aggregation on the standardized index data and the posterior combination weight, and calculating a comprehensive financial risk index of the target assessment object; and based on the comprehensive financial risk index, in combination with a preset risk threshold model, generating a systematic risk assessment result and a structural risk distribution map for a specific financial cooperation scene. According to the method, complex risk factors are converted into visual quantitative indexes, and macroscopic decisions in transnational financial cooperation are directly supported.

The invention discloses a virtual simulation and security evaluation method and system based on a network security target range, and the method comprises the steps: constructing a network asset knowledge graph for describing a virtualized target range environment through information collection; secondly, based on an attack strategy grammar rule base, adopting a Monte Carlo Tree Search (MCTS) algorithm to carry out intelligent attack simulation on the knowledge graph so as to discover a nonlinear and multi-stage attack path; thirdly, constructing a Bayesian attack graph (BAG) based on the knowledge graph, and performing probabilistic and systematic quantitative evaluation on the security risk of each asset node in the network through Bayesian reasoning; and finally, integrating the attack path and the quantitative risk value, and generating a comprehensive assessment report containing a visual path, a risk sequence and a reinforcement suggestion. According to the target range simulation method and device, the problems that existing target range simulation is insufficient in confrontation authenticity, one-sided in safety evaluation and lack of predictability are solved by combining the strategy simulation of the MCTS and the global quantitative analysis of the BAG.

The invention provides a multi-mode photovoltaic panel subfissure fusion detection method and device. Acquiring multi-source sensing data of the photovoltaic module under different physical detection principles; based on the detection characteristics of each sensor, carrying out preprocessing and defect identification on the multi-source sensing data, and respectively obtaining a subfissure detection result corresponding to each sensor and an initial confidence coefficient of the subfissure detection result; carrying out space coordinate alignment on the detection results of the sensors, and carrying out dynamic fusion calculation on the confidence coefficients of the detection results by adopting a Bayesian reasoning algorithm to obtain a comprehensive defect detection probability; and comparing the fused comprehensive defect detection probability with a preset threshold value, judging the existence and severity of the subfissure in combination with a rule fusion strategy, and outputting a detection result. According to the method, the limitation of a single detection method can be effectively overcome, the high-precision and full-scene coverage detection of the hidden crack defect of the photovoltaic module is realized, the omission ratio and the false alarm rate are remarkably reduced, and the reliability and the adaptability of a detection system are improved.

The invention relates to the technical field of geotechnical engineering and geological disaster monitoring, in particular to a rockburst tendency dynamic discrimination method, and aims to solve the limitation caused by the fact that a dynamic evolution process is simplified into a quasi-static attribute in traditional rockburst tendency evaluation. According to the method, rockburst tendency is defined as a hidden state variable evolved along with time, a physical constraint state space model containing a hidden state kinetic equation and a multi-modal observation equation is constructed, continuous stress-strain and discrete acoustic emission data are fused, hidden state probability distribution is estimated in real time through online Bayesian inference, and the probability distribution of the hidden state is estimated in real time. And in combination with adaptive information weight updating and physical consistency constraint, predicting a future state trajectory, calculating a risk probability exceeding a critical threshold, and outputting a dynamic rockburst tendency level. According to the scheme, continuous, dynamic and prospective judgment of the rockburst tendency is realized, and the accuracy and reliability of early warning are improved.

The invention discloses a bridge structure crack real-time monitoring and progress analysis system based on deep learning, and belongs to the technical field of bridge structure health monitoring. The system comprises a time sequence image acquisition and multi-modal data fusion module, a self-adaptive crack feature extraction and identification module, a dynamic evolution tracking and trend prediction module and a closed-loop feedback optimization and early warning decision module, and innovatively introduces feature fusion of time sequence consistency constraint and mutual information maximization based on Riemannian manifold. Deep fusion of multi-modal data is realized; a multi-scale convolutional neural network and an attention mechanism are adopted to accurately extract crack features; predicting a crack development trend by using a long short-term memory neural network and Bayesian inference; a closed-loop feedback mechanism is designed to dynamically optimize system parameters, the four modules are deeply coupled to form a complete closed loop of data forward transmission, performance evaluation and parameter reverse feedback, real-time monitoring, dynamic tracking and intelligent early warning of cracks are realized, and a scientific decision basis is provided for bridge safety management.

The invention relates to the technical field of power system equipment state monitoring and fault diagnosis, in particular to a GIS basin-type insulator operation state evaluation method and system, and the system comprises an asset information and baseline modeling module which is used for building a high-fidelity multi-physics field finite element reference model and generating a defect state-external representation mapping data set; the physical information driven agent model generation module is used for constructing a neural network agent model fusing physical law constraints; the real-time data acquisition and feature extraction module is used for acquiring and processing online monitoring data such as UHF, gas, temperature and vibration; the state inversion and digital twinning calibration module is used for inverting internal defect parameters by adopting a Bayesian inference and MCMC method so as to realize real-time calibration of the model; and the evaluation diagnosis and life prediction module carries out fault mode identification and residual life prediction based on the calibration model.

The invention discloses a bridge health monitoring system which comprises a sensing layer, a transmission layer, a processing layer and an application layer which are in communication connection in sequence. The sensing layer synchronously collects structural mechanics, environmental influence and traffic load data through multi-source heterogeneous sensing nodes, and the sensing nodes adopt a solar energy and vibration energy double-source energy supply and low-power-consumption mechanism; the transmission layer adopts a'wireless private network + edge gateway 'mixed mode, and has data caching and breakpoint resuming functions; the processing layer analyzes data through a deep learning fusion algorithm based on an attention mechanism, and realizes dynamic early warning threshold adaptive adjustment in combination with a Bayesian reasoning model; and the application layer provides a visual interface, graded early warning and targeted maintenance decision suggestions. The system achieves the precise monitoring of the full life cycle of the bridge, improves the evaluation accuracy and system stability, reduces the operation and maintenance cost, provides scientific support for the safe operation and maintenance of the bridge, is suitable for the health monitoring scenes of various bridge types, and greatly improves the accuracy of the evaluation of the health state of the bridge.

The invention discloses an industrial network fault intelligent diagnosis method and system based on multi-source data, and the method comprises the steps: synchronously collecting data from a plurality of data sources of an industrial network, and extracting a time sequence statistical feature, a flow entropy feature and a protocol conformity feature to form a multi-dimensional feature vector; establishing a dynamic baseline model by adopting a sliding window online learning method, and calculating a comprehensive anomaly score for anomaly detection; the fault suspicion degree is calculated based on the equipment incidence matrix and the fault propagation model to realize fault source positioning; carrying out fault type identification and root cause analysis by adopting Bayesian reasoning and a knowledge rule base; and outputting a structured diagnosis report containing the fault source, the type, the root cause and the disposal suggestion. According to the invention, early warning, accurate positioning and intelligent diagnosis of industrial network faults are realized, and the operation and maintenance efficiency, safety and reliability of the industrial control network are significantly improved.

The invention provides an emission reduction intelligent accounting expansion method and system based on scene recognition, and relates to the technical field of carbon emission reduction accounting, and the method comprises the steps: obtaining energy consumption, production activity and environment monitoring data, carrying out the fusion, constructing a scene vector, carrying out the scene division, extracting an accounting node from an accounting knowledge base, and calculating the initial emission reduction; coding the environmental monitoring data to construct a causal relationship graph, and calculating anti-fact emission reduction to obtain a causal enhancement scene vector; and a plurality of accounting paths are selected based on vector matching to calculate the integrated emission reduction and perform Bayesian inference, and the final emission reduction and confidence interval are output, so that the accuracy and reliability of emission reduction accounting are improved.

The invention discloses a multi-modal training data desensitization and traceability management method, which comprises the following steps of: firstly, carrying out structured preprocessing on original multi-modal data, and then generating text weighted image features, image weighted text features and a key cross-modal attention graph through cross-modal feature extraction and collaborative attention fusion; on the basis of the attention graph and a privacy strategy library, entity identity priori detection is carried out innovatively in combination with a knowledge graph, and self-adaptive collaborative prediction is carried out on sensitivity by utilizing Bayesian inference; and finally, a refined desensitization plan is generated through variational optimization, and accurate desensitization of the original data is realized. By means of the mode, the defects of inconsistent desensitization and one-step desensitization in the aspect of multi-modal data privacy protection in the prior art are overcome, it is ensured that sensitive information is fully protected, meanwhile, the inherent value and training availability of data are reserved to the maximum extent, and the data privacy protection efficiency is improved. And a high-quality, compliant and valuable training data set is provided for the artificial intelligence large model.

The invention discloses an underground safety level intelligent evaluation response method and system fusing fuzzy credibility weighting and Bayesian reasoning, and relates to the technical field of underground safety monitoring. According to the method, a multi-source heterogeneous sensor is deployed to collect data, a fuzzy membership matrix is obtained through fuzzy membership function normalization, a credibility factor matrix is constructed by combining time sequence stability, spatial neighborhood consistency and node long-term health weight, and the two are subjected to weighted fusion to obtain a fusion index vector. And inputting the Bayesian network fused with the credible nodes, reasoning to obtain security level posterior probability distribution, and triggering a linkage response. The system correspondingly comprises a plurality of modules for implementing the steps. According to the method, the dynamic evaluation and credibility quantification of the data quality of the underground multi-source sensor are realized, and an intelligent evaluation mechanism for deeply integrating the credibility of the data source into a reasoning structure is constructed, so that the risk evaluation robustness and accuracy are improved, the closed-loop management from evaluation to response is realized, and the underground safety is guaranteed.

The invention provides an engineering construction monitoring method and system based on multi-source data fusion, and relates to the technical field of engineering construction monitoring. Structural vibration, wind power and multi-dimensional environment data are fused, a wind load modulation function and an environment correction model are constructed, the influence of a wind load nonlinear amplification effect and environment disturbance on vibration signals is effectively eliminated, and the accuracy of the vibration signals is improved. The accuracy and sensitivity of damage feature extraction are improved; meanwhile, in combination with a signal decomposition technology and multi-layer Bayesian reasoning, probabilistic evaluation and real-time risk early warning of the structural damage state are realized, the response capability and the discrimination capability of the monitoring system to structural state changes under complex working conditions are enhanced, and the precision and the reliability of health monitoring of the engineering building structure are improved.

The invention belongs to the technical field of agricultural traceability information, and provides an agricultural ecological industry chain traceability system based on GIS and AI technologies, which comprises an acquisition module, an identification and evidence storage module, a risk assessment module, a pollution propagation analysis module and a visualization module, and is characterized in that GIS spatial data of an agricultural ecological industry chain is acquired, and real-time streaming data of the Internet of Things is acquired; a unique digital identifier is given to a material minimum physical unit, a traceability relation chain is generated, a business process in an agro-ecological industry chain is defined and identified, production links are marked, risk feature engineering is extracted, and a risk probability prediction model is constructed and adopted to output a risk probability value of cross contamination of the production links. And if a terminal product is obtained and pollutants are detected, carrying out probability inversion calculation by adopting a Bayesian reasoning algorithm to mark candidate pollution sources, identifying corresponding pollution propagation paths, and constructing a pollution source tracing situation map based on the candidate pollution sources and the corresponding pollution propagation paths.

The invention discloses a springback compensation control system for a metal stamping part, and belongs to the technical field of metal plate forming. The system comprises a stress memory prediction module, a fractal compensation analysis module, a phase change compensation regulation and control module, a compensation decision fusion module and an execution feedback optimization module. The stress memory prediction module extracts stress evolution characteristics of the stamping process through a multi-scale memory network and a time decay attention mechanism; the fractal compensation analysis module adaptively adjusts the compensation grid density based on the fractal dimension to realize optimal configuration of computing resources; the phase change compensation regulation and control module predicts the phase change behavior of the material through the thermal-mechanical coupling constitutive model and calculates the compensation correction amount caused by phase change; the compensation decision fusion module intelligently fuses three compensation strategies by adopting Bayesian reasoning and a spatial modulation function; and the execution feedback optimization module realizes continuous optimization of the system through online learning. According to the method, the influence of three dimensions of stress history, geometric complexity and material phase change is comprehensively considered, accurate prediction and compensation of the springback behavior are achieved, and the forming precision and production efficiency of the metal stamping part are remarkably improved.

The invention discloses an allergic rhinitis diagnosis and allergen traceability system based on dynamic text guidance, and belongs to the technical field of intelligent medical treatment. According to the method, the problems that in the prior art, patient description is inaccurate, allergens are various in variety and have differences, and allergens are difficult to accurately determine and trace are solved, the initial situational sub-graph is verified by introducing periodic features of the patient, the causal contribution degree of the initial situational sub-graph is evaluated through a Bayesian reasoning algorithm, and a mode association result library is formed; according to the method, the crossing of the allergic rhinitis diagnosis and tracing from the traditional static judgment to the dynamic accurate inference is realized, and a personalized and scientific allergen avoidance scheme is provided for patients; through similarity retrieval, environmental information injection verification and calculation of a mode goodness-of-fit score, under the condition that patient symptoms are in multi-factor mixing, a mixed causal graph is created through a graph fusion technology, and the mode goodness-of-fit score is calculated again, so that the accuracy of obtaining an allergen traceability result in practical application is ensured.

The invention discloses a tower full life cycle multi-objective optimization decision-making system in a typhoon disaster scene, and relates to the technical field of power transmission tower disaster prevention and reduction, and the system comprises a multi-source data collection module, an analysis construction module, a calculation risk assessment module, a multi-objective optimization decision-making module and a block chain coordination module. Complementation and standardization are realized through federated learning and a generative adversarial network; generating a fault probability result through data driving and mechanism model dual-channel fusion; in the risk assessment stage, combining Monte Carlo and Bayesian inference to dynamically update the risk, and outputting a survival rate thermodynamic diagram and collapse probability distribution; an improved NSGA-III algorithm is adopted in the decision optimization stage, and a reinforcement scheme, a first-aid repair path and a recovery time sequence are generated; and the block chain coordination module realizes credible linkage through a distributed account book and knowledge graph reasoning, and realizes second-level response in combination with multi-level early warning and edge calculation. And closed-loop management of data fusion, risk assessment and emergency collaboration is realized.

The invention provides a biomedical causal relationship inference method and system based on a Bayesian knowledge graph, and relates to the technical field of biomedical data mining and artificial intelligence, and the method comprises the steps: carrying out the multi-source evidence fusion of biomedical data, and obtaining a structured triple containing Bayesian confidence; analyzing the triple by using priori knowledge and obtaining a conditional probability table through parameterized filling; carrying out posteriori updating by using the Bayesian theorem; and analyzing the updated knowledge graph state by using a graph neural network model to obtain an inference result. Wherein the Bayesian inference module is combined with the graph neural network model, the former provides priori knowledge with confidence, the latter provides a fine path dependency relationship, and the accuracy and robustness of inference are remarkably improved. According to the method, the problems of evidence isomerism fragmentation, causal inference subjectization and knowledge discovery inefficiency are solved, and intelligent and automatic inference of the causal relationship is realized.

The invention discloses a poplar catkin flying intensity prediction method based on meteorological data, and relates to the technical field of forestry prediction, and the method comprises the steps: obtaining meteorological factor data, carrying out the preprocessing, and generating a meteorological factor sequence; carrying out change point identification based on the meteorological factor sequence, constructing Poisson prior distribution, inverse gamma prior distribution and a Gaussian likelihood function, generating posterior distribution by applying Bayesian inference, carrying out sampling to obtain a sampling set, generating credible intervals based on the sampling set, and carrying out merging to generate a credible interval set; backtracking is carried out based on the credible interval set, fitting cost values of corresponding meteorological factor data calculation intervals are obtained, iteration-updating is carried out in combination with a PELT algorithm, during iteration-updating, a hybrid optimization strategy is introduced to obtain optimal parameters of the PELT algorithm for feedback, and an optimal candidate catastrophe point position set is output; according to the method, the accuracy and stability of poplar catkin flying intensity prediction are greatly improved.

The invention belongs to the field of building environment control, and provides a thermal comfort dynamic adaptive control method based on multi-modal wave analysis and AI driving. According to the method, environmental parameters, user physiological signals (HRV) and subjective thermal comfort data are synchronously collected in real time, time-frequency characteristics of the physiological signals are extracted through continuous Morlet wavelet transform, high-order dynamic characteristics are constructed, the thermal comfort state is predicted in combination with deep learning, a deep reinforcement learning strategy is optimized through an NSGA-II algorithm, a multi-target optimal strategy set is generated, and the optimal thermal comfort state is obtained. And finally, a multi-arm bandit model with Bayesian inference is utilized to realize strategy online adaptive updating. By applying the method, the thermal comfort prediction precision can be expected to be greater than or equal to 90%, the net energy conservation is greater than or equal to 32%, the limitation of the existing thermal comfort regulation and control method in a dynamic situation is effectively solved, and the dynamic balance of personalized thermal comfort and system energy conservation is realized.