20 results about "Bayes analysis" patented technology

The invention relates to the technical field of intelligent customer service, and discloses an intelligent customer service dialogue generation method and system based on user intention recognition, and the method comprises the steps: obtaining an input first user text from an intelligent customer service system, and carrying out the feature decomposition and attention fusion of the first user text, and obtaining a fusion intention feature matrix; performing intention migration analysis and dynamic Bayesian analysis on the dialogue sequence data in the historical dialogue corpus to obtain an intention state transition probability matrix; an improved Transform network model is input for joint training, and a dialogue generation model is obtained; a newly input second user text in the intelligent customer service system is decoded and generated based on the dialogue generation model, meanwhile, the intention state transition probability matrix serves as a constraint condition, a reply text conforming to the dialogue intention is obtained, the accuracy and robustness of intention recognition are improved, the reply smoothness is guaranteed, and meanwhile the user experience is improved. And the generated content is ensured to conform to an expected intention transfer rule.

The invention discloses an energy-saving early warning control method and system in a casting process, and the method comprises the steps: obtaining casting environment data, power consumption data, fuel consumption data and emission data, carrying out the data cleaning and normalization operation, and obtaining the preprocessed multivariable time series data; inputting the multivariable time series data into a pre-trained multivariable prediction model to obtain a predicted value of each variable, and performing comparison calculation on the predicted value and an actual measurement value to obtain a predicted residual error; according to the prediction residual error, sequential Bayesian analysis is carried out, the abnormal event probability of each variable is obtained, probability fusion calculation and comprehensive evaluation are carried out, and an abnormal score is obtained; and when the abnormal score is judged to be greater than a preset abnormal threshold value, generating an early warning signal, and sending the early warning signal to the casting equipment, so that the casting equipment automatically adjusts the operation parameters according to the early warning signal. According to the method, accurate environment-friendly early warning and real-time control in the casting process can be achieved.

The embodiment of the invention discloses a GBIC-based multi-electric aircraft starting power generation system DBN model lightweight method, and relates to the technical field of reliability design and modeling of an equipment complex system.The GBIC-based multi-electric aircraft starting power generation system DBN model lightweight method comprises the steps that a DBN model of a starting power generation system is established, nodes in the DBN model correspond to key components and working states of the starting power generation system, and the nodes in the DBN model correspond to the key components and the working states of the starting power generation system; directed edges in the DBN model are used for describing the mutual relation between the nodes, a redundant structure in the DBN model is recognized, lightweight processing is carried out, and the fault state of the starting power generation system is recognized through the DBN model subjected to the lightweight processing. Aiming at the problems of complex reasoning calculation and low efficiency in the use process of the dynamic Bayesian analysis method of the equipment complex polymorphic system, the grey system theory and the Bayesian information criterion are introduced, the lightweight of the dynamic Bayesian network of the complex polymorphic system is realized, the redundant structure is eliminated, and the accuracy of the result is ensured.

The invention provides a serum tumor marker detection array optimization method and system.The method is applied to a control module of an array device.The method comprises the steps that when a multi-needle detection platform conducts serum tumor marker detection on a preset sample, preliminary expression information sent by the multi-needle detection platform is obtained; acquiring patient medical history information, iconography information and pathology information corresponding to the preset sample; inputting the preliminary expression information, the patient medical history information, the iconography information and the pathology information into a pre-constructed Bayesian analysis model, and outputting a prediction weight, a prediction disease progress direction and a correlation marker corresponding to each tumor marker to generate target information; wherein the target spot information comprises a plurality of target markers; and controlling the multi-needle detection platform to perform serum tumor marker detection on the preset sample again according to the target spot information to complete array optimization of serum tumor marker detection. Therefore, an efficient and innovative solution is provided for early diagnosis and monitoring.

The invention discloses a construction method of a malignant pleural effusion prediction model, a marker combination and application, equipment and a medium. The construction method comprises the following steps: S1, obtaining characteristics of a biomarker combination; the biomarker combination is composed of three biomarkers of NGAL, CEA and CA50; s2, based on the characteristics of the biomarker combination, adopting Logistic regression analysis to respectively construct regression models corresponding to the three biomarkers, and respectively outputting parameters alpha NGAL, beta NGAL, alpha CEA, beta CEA, alpha CA50 and beta CA50; and S3, based on the output parameters in the step S2, adopting Bayesian analysis to construct a malignant pleural effusion prediction model. The method can be used for predicting the MPE probability in the pleural effusion patient, the identification and prediction accuracy is high, and compared with pleural biopsy and thoracoscopic sampling biopsy, the method has the advantages of being rapid, minimally invasive and the like.

The invention discloses a film scoring system and method based on big data. The film scoring system comprises a data acquisition layer, a data storage and processing layer, a model construction layer, a service layer and a user interface layer, wherein the data acquisition layer is used for performing data acquisition; the data storage and processing layer is used for carrying out data cleaning and preprocessing on the collected data and extracting features from the preprocessed data; the model construction layer is responsible for processing and analyzing big data, generating movie scores, analyzing user behavior data by using naive Bayes, quantifying positive / negative emotions, reducing weights of easy-to-classify samples by using focus loss when emotional tendency distribution of a specific group is imbalanced, and constructing a classification model based on movie features, multi-dimensional features and time features; according to the method, multiple XGBoost models are trained through multi-task learning, scores of different dimensions are predicted respectively, input of emotional tendency is provided for different dimensions through naive Bayesian analysis results, and meanwhile personalized scores are provided for different groups in combination with group characteristics.

The invention relates to the technical field of water resource allocation, in particular to a Copula function-based runoff abundance and dryness compensation evaluation method and system for a water diversion project. The method comprises the following steps of: acquiring long-time sequence actually-measured runoff data of representative hydrometric stations of a water source region and a water receiving region of the water diversion project; constructing a Copula function-based runoff abundance and dryness encounter probability model of the water diversion project, and fitting parameters by using a mixed evolution MCMC algorithm based on Bayesian analysis; using 37.5% and 62.5% of cumulative frequencies as runoff runoff-runoff runoff-runoff runoff-runoff runoff-runoff runoff-runoff runoff-runoff runoff-runoff runoff-runoff runoff According to the method, the magnitude of the runoff abundance and dryness compensation of the water diversion project can be quantitatively evaluated by taking the probability of abundance and dryness synchronization, abundance and dryness asynchronization, favorable water diversion and unfavorable water diversion as runoff abundance and dryness compensation evaluation indexes, and a conclusion whether the abundance and dryness compensation exists or not is accurately obtained.

The invention provides a PI coating machine precision motion control method based on combination of a magnetic encoder array and a neural network, and the method comprises the steps: obtaining the historical substrate vibration data and historical substrate displacement images of a coating machine, carrying out the preprocessing, inputting a processing result into a constructed SSD single-shot multi-frame neural network detection model for training, and obtaining a motion detection result; obtaining a trained SSD single-shot multi-frame neural network detection model; real-time substrate vibration data and real-time substrate displacement images in the coating process of the coating machine are collected and input into the trained SSD single-shot multi-frame neural network detection model, and a detection result is output; and calculating the motion trail of the coating machine substrate according to the detection result by adopting an extended Kalman filtering algorithm, correcting the motion state by applying a Bayesian analysis method to obtain the corrected motion trail of the coating machine substrate, and inputting the corrected motion trail into a coating machine air suspension control unit. And outputting a control adjustment signal to control a coating machine compressor to inflate an air spring or control an exhaust valve to release air. The coating precision of the coating machine can be improved, and the coating stability is improved.

The invention provides an intrinsic measurement method and device for thorium. The intrinsic measurement method comprises the following steps: recording detection time of alpha particles released by decay of to-be-measured < 220 > Rn gas and daughter < 216 > Po in a measurement chamber; performing Bayesian analysis according to the detection time, and calculating a 220Rn-216Po true coincidence count; and according to the < 220 > Rn count, the < 216 > Po count and the < 20 > Rn-< 216 > Po true coincidence count, calculating the activity concentration of the thorium. According to the intrinsic measurement method and device, two alpha particles emitted by successive decay of 220Rn and 216Po are utilized to form an intrinsic characteristic conforming to a signal, so that the detection efficiency is reduced; the detection efficiency is reduced, so that the method and the device do not need to measure the detection efficiency of the standard scale from the outside, and have self-traceability; meanwhile, the influence of the change of the detection efficiency on the measurement accuracy is avoided, and the measurement accuracy is improved.

The invention discloses a PD motion subtype classification method based on transcranial Doppler and Bayesian analysis, and relates to the technical field of medical diagnos.The method comprises the steps that S1, cerebral blood flow velocity signals of a subject in different physiological states are collected through transcranial Doppler equipment, and arterial blood pressure signals are synchronously collected through continuous non-invasive blood pressure monitoring equipment; s2, processing the signals collected in the S1, and extracting characteristic indexes reflecting the dynamic cerebral blood flow automatic adjusting function; s3, combining the feature indexes with the basic hemodynamic parameters to form feature vectors; s4, inputting the feature vector into a pre-trained Bayesian discrimination model; and S5, classifying the subjects into different Parkinson's disease motion subtypes according to the output of the Bayesian discrimination model. The method has the advantages of improving classification objectivity, capturing dynamic physiological signal features, achieving accurate subtype identification and the like.

The present invention discloses an energy-saving early warning control method and system for a casting process. The method comprises: obtaining casting environment data, power consumption data, fuel consumption data, and emission data, and performing data cleaning and normalization operations to obtain preprocessed multivariate time series data; inputting the multivariate time series data into a pretrained multivariate prediction model to obtain predicted values ​​for each variable, and comparing the predicted values ​​with actual measured values ​​to obtain prediction residuals; performing sequential Bayesian analysis based on the prediction residuals to obtain abnormal event probabilities for each variable, and performing probability fusion calculations and comprehensive evaluations to obtain an anomaly score; and generating an early warning signal when the anomaly score is determined to be greater than a preset anomaly threshold. The early warning signal is sent to the casting equipment, causing the casting equipment to automatically adjust operating parameters based on the early warning signal. This method can achieve accurate environmental early warning and real-time control during the casting process.

The application discloses a kind of original light element abundance prediction and parameter estimation method, including setting cosmological parameter and the sampling range of rigid phase correction factor, batch generation structured data set containing multiple light element theoretical abundance using numerical calculation code;Deep network model integrating multi-head attention mechanism and deep residual block is constructed, and the nonlinear mapping from parameter space to abundance space is established by supervised training;The model is encapsulated as a likelihood function interface, integrated into the Cobaya Bayesian analysis framework, and the forward inference is performed using the computing kernel;Combined with the actual observation data constraint, the parameter space is automatically sampled using the Markov Chain Monte Carlo algorithm, and the posterior probability density distribution of each physical parameter is output.The application effectively solves the problem of low efficiency in solving high-dimensional rigid equation set in original nucleosynthesis, and can quantitatively analyze the tension between lithium abundance observation data, and reveal the potential physical path of rigid phase correction parameter to alleviate the lithium problem.

The present invention discloses a method and system for detecting anomalies in the construction of pumped storage power stations based on drone image analysis, which relates to the field of engineering construction monitoring technology, including constructing a hybrid knowledge model; planning the acquisition path of the construction area, acquiring multi-view images, processing multimodal sensor data, and generating a construction site feature tensor; inputting the construction site feature tensor into a densely connected convolutional network for processing, combining a heterogeneous graph attention module and a gated recurrent unit with causal reasoning capabilities to establish a four-dimensional construction dynamic model; using a two-layer contrastive learning network to calculate the feature distance between the hybrid knowledge model and the four-dimensional construction dynamic model, calibrating the abnormal area and its uncertainty; performing causal reasoning and tracing analysis on the detected abnormal area, and screening the optimal compensation solution through a case-enhanced Bayesian analyzer. The present invention realizes the effective integration of CAD drawings and expert knowledge through a deep cross-modal knowledge distillation network, providing a more comprehensive and standardized knowledge foundation for anomaly detection.

This invention relates to an improved CBBA (Continuous Computational Bayes Analysis) task allocation method for unmanned surface vessels (USVs) based on MOAWC-Kmeans clustering, belonging to the field of unmanned autonomous collaborative control technology. The method first uses the MOAWC-Kmeans algorithm to intelligently pre-cluster tasks, employing adaptive weight calculation, intelligent initialization, constraint-optimized allocation, and a boundary task secondary optimization mechanism to achieve task grouping. Second, distributed task allocation is performed based on the improved CBBA algorithm, with each USV prioritizing bidding for tasks within its pre-clustered cluster. This method introduces a hard time window constraint mechanism, dynamically pruning to remove non-compliant tasks. During path construction, a two-layer strategy combining greedy construction and local search is used to optimize the path structure in real time. After negotiation convergence, unassigned tasks are greedily inserted according to the time window urgency index, and the Or-opt path reconstruction mechanism is used for deep path reconstruction. Finally, load balancing adjustments further optimize cluster efficiency. Compared with existing technologies, this invention significantly improves the task completion rate, path efficiency, and load balancing of heterogeneous USV clusters, making it suitable for complex application scenarios such as maritime search and rescue and patrol monitoring.

The embodiment of the application discloses a DBN model lightweight method of a multiple-electric aircraft starting power generation system based on GBIC, relates to the technical field of reliability design and modeling of complex equipment systems, and comprises the following steps: a DBN model of a starting power generation system is established, nodes in the DBN model correspond to key components and working states of the starting power generation system, directed edges in the DBN model are used for describing mutual relations between nodes, redundant structures in the DBN model are identified and lightweight processing is performed, and a fault state of the starting power generation system is identified by using the DBN model subjected to the lightweight processing.The embodiment of the application introduces a grey system theory and a Bayesian information criterion aiming at the problems of complex and low efficiency of reasoning calculation in the process of a dynamic Bayesian analysis method of a complex polymorphic system, realizes lightweight of the dynamic Bayesian network of the complex polymorphic system, eliminates redundant structures, and guarantees the accuracy of results.

The invention relates to a radionuclide gamma energy spectrum analysis method and device based on sequential Bayesian analysis. The method comprises the following steps: generating an energy sequence and a time sequence of a radiation event based on a Monte Carlo sampling principle; discriminating the energy sequence and the time sequence of the radiation event based on a preset energy interval and an average arrival time interval; filtering the energy information in the energy sequence of the radiation event passing the discrimination and the arrival time information of the time sequence in the radiation event; and calculating the posterior probability of a radiation event for the filtered energy information and time information, judging whether the radiation event is generated by a radionuclide gamma or not through the posterior probability, and judging whether a target nuclide exists or not in real time according to a Wald sequential probability ratio test rule of the posterior probability.

This invention discloses a method, apparatus, computer-readable storage medium, and product for identifying liver lobule regions based on spatial transcriptome sequencing data, relating to the field of liver lobule region technology. The method includes: normalizing the spatial transcriptome data matrix of the liver and performing regression analysis to identify highly variable genes; performing principal component analysis on the highly variable genes to determine principal components; performing Bayesian analysis on the principal components to perform unsupervised clustering of cells / regions in the spatial transcriptome data matrix to obtain cell / region cluster information; and identifying liver lobule regions based on the cluster information. This invention achieves rapid identification of liver lobule regions based on spatial transcriptome sequencing data by spatial clustering, limiting the number of clusters, and combining this with the expression abundance distribution of specific biomarkers.

The application discloses a kind of movie rating system and method based on big data, including data acquisition layer, data storage and processing layer, model construction layer, service layer and user interface layer: data acquisition layer: carry out data acquisition;Data storage and processing layer: the data cleaning and pretreatment to the data collected, extract features from the data after pretreatment;Model construction layer: responsible for processing and analyzing big data, generating movie rating, using naive bayes analysis user behavior data, quantifying positive / negative sentiment, when the sentiment of a particular group is imbalanced, use focal loss to reduce the weight of easily classified samples, based on movie features, multi-dimensional features and time features, use multi-task learning to train multiple XGBoost models, predict ratings in different dimensions respectively, naive bayes analysis results provide sentiment input for different dimensions, at the same time, combined with group characteristics, provide personalized ratings for different groups.

The invention provides a multi-change point threshold ARMA model with exogenous input and a Bayesian analysis method thereof. Firstly, an MB-TARMAX time series model is constructed based on the ARMA model; two groups of collected time series data are pre-processed and rearranged according to time domain change points and value range change points, and the likelihood function of the model is obtained according to the rearranged data; then, based on the prior distribution of all unknown parameters of the MB-TARMAX time series model of the invention, a joint prior distribution of all unknown parameters is obtained, and a joint posterior distribution of all unknown parameters is obtained according to the Bayesian theorem combined with the likelihood function; finally, based on the joint posterior distribution, a fully conditional posterior distribution of all unknown parameters and a corresponding fully conditional posterior distribution form are obtained, and for different fully conditional posterior distribution forms, a Monte Carlo Markov chain sampling method is applied under the Bayesian framework to conveniently obtain the estimated values ​​of the parameters of the MB-TARMAX time series model.

The application discloses a PD movement subtype classification method based on transcranial Doppler and Bayesian analysis, and relates to the technical field of medical diagnosis, and comprises the following steps: S1, collecting the cerebral blood flow velocity signals of a subject under different physiological conditions through a transcranial Doppler device, and synchronously collecting the arterial blood pressure signals through a continuous noninvasive blood pressure monitoring device; S2, processing the signals collected in S1, and extracting characteristic indexes reflecting the dynamic cerebral blood flow automatic regulation function; S3, combining the characteristic indexes with basic hemodynamic parameters to form a characteristic vector; S4, inputting the characteristic vector into a pre-trained Bayesian discriminant model; and S5, according to the output of the Bayesian discriminant model, classifying the subject into different Parkinson's disease movement subtypes. The application has the advantages of improving classification objectivity, capturing dynamic physiological signal characteristics, and realizing precise subtype identification.