99 results about "Conditional probability table" patented technology

The invention provides a pressure-bearing equipment damage mode identification and risk assessment method and system, and relates to the technical field of safety engineering, and the method comprises the steps: collecting multi-source sensor data and image data, inputting the data into a deep neural network after preprocessing and feature extraction, extracting spatial features through a convolutional layer, and extracting time sequence features through a recurrent neural network. And using the attention mechanism to fuse the features to identify an injury pattern. And then, constructing a multi-level evaluation index system, performing combined weighting by adopting an analytic hierarchy process and an entropy weight method, inputting weights into an improved Bayesian network model based on a D-S evidence theory, dynamically updating a conditional probability table by the model by utilizing a deep neural network and a fuzzy inference rule, and finally obtaining a risk evaluation result. According to the invention, the damage mode of the pressure-bearing equipment can be effectively identified, risk assessment is carried out, and assessment precision and reliability are improved.

The invention discloses a building equipment fault rapid attribution and self-optimization method, which relates to the field of intelligent operation and maintenance of building equipment, establishes a multi-dimensional association relationship among equipment, building space, sensors and fault modes, and deeply combines a fault attribution engine with system dynamics. Data driving flexibility and physical logic preciseness are simultaneously realized in fault attribution, and reasoning from abnormal data to root cause analysis is realized. According to the method, the optimization efficiency is remarkably improved through a specific incremental learning / local updating mode, the weight of the knowledge graph and the Bayesian network conditional probability table are adjusted according to the maintenance result, physical equation parameters are calibrated, and dynamic updating of node attributes of the knowledge graph is achieved; through dynamic weight optimization, the adaptive ability of real-time reasoning confidence evaluation and scene context is improved; a physical equation is used as an executable knowledge unit to be embedded into a knowledge graph through establishment and deep integration of a system dynamics model, and a safety and reliability mechanism is designed for verification.

The invention discloses a fault diagnosis method and system for an electric power centralized communication control device, which are used for accurately identifying cascade faults so as to improve the safety and stability of an electric power system. The method comprises the following steps: acquiring operation data of the power centralized communication control device, and extracting a frequency feature set from the operation data; calculating association strength among variables in the frequency feature set by using a conditional probability table, and screening out a key feature vector set to generate an interactive topology among different devices in the power system; calculating propagation paths and propagation speeds of the key feature vectors in the interactive topology according to a path reasoning algorithm, and screening out a candidate fault propagation path set based on the propagation paths and the propagation speeds; calculating fault propagation probabilities of the candidate fault propagation paths to determine a cascade fault propagation feature set; and constructing a high-dimensional space classification boundary according to the cascade fault propagation feature set so as to perform fault mode classification and obtain a fault diagnosis result.

The invention provides a landslide risk dynamic early warning method and system based on a Bayesian network, and belongs to the field of geological disaster intelligent prediction, and the method comprises the steps: constructing a disaster-inducing factor data set, and screening key factors based on a Pearson's correlation coefficient and an information gain method; an FP-Growth algorithm is further utilized to extract association rules among high-confidence factors, a Bayesian network structure is guided to be optimized, and a Bayesian network model with a causal relationship is constructed; the model supports an incremental learning mechanism based on a newly added landslide sample, can dynamically update a conditional probability table, and realizes landslide probability prediction and risk grade division in combination with a Bayesian forward reasoning result. The method has the advantages of being high in causal reasoning ability, high in model structure expression ability, excellent in prediction precision and capable of supporting real-time updating and risk partition, and is suitable for an intelligent risk assessment and early warning system for landslide disasters.

The embodiment of the invention provides a dynamic risk assessment management method and system based on business risk control, and belongs to the technical field of business risk monitoring. Comprising the following steps: acquiring behavior data of a user, and performing statistical feature extraction on the behavior data; constructing a dynamic Bayesian network according to the statistical characteristics of the behavior data; performing incremental updating on a conditional probability table of a dynamic Bayesian network according to the real-time behavior data; constructing and training an LSTM model and a random forest model by adopting the behavior data; acquiring a current comprehensive risk assessment result according to the real-time behavior data, the dynamic Bayesian network, the LSTM model and the random forest model; a multi-model fusion mode is adopted, so that the risk assessment precision can be effectively improved; and finally, an adversarial sample is constructed, and the dynamic Bayesian network and the LSTM model are trained offline according to the adversarial sample, so that the generalization ability for an unknown attack mode can be improved, and the security is higher.

The invention provides a dam safety monitoring system abnormity diagnosis method, system and device and a medium, and relates to the technical field of hydraulic engineering safety monitoring, and the method comprises the steps: evaluating a diagnosis object to which measuring point data of an abnormity label belongs through a knowledge graph engine, generating an abnormity alarm grouping list through employing a diagnosis object-monitoring abnormity format, and carrying out the abnormity alarm grouping list; searching an abnormal phenomenon entity matched with the alarm description in the knowledge graph through Cypher; and positioning matched abnormal phenomenon nodes in the Bayesian network, extracting associated abnormal reason nodes by using directed edges, obtaining a prior probability and conditional probability table of the abnormal reason nodes, performing probability reasoning, and outputting an abnormal reason diagnosis list. Through multi-source data fusion and knowledge graph driven intelligent reasoning and Bayesian network probabilistic reasoning, scientific and operable root cause diagnosis and disposal suggestions are provided, and the reliability and intelligent level of a dam monitoring system are enhanced.

The invention discloses an initiating explosive device processing safety assessment and early warning method based on a Noisy-OR Bayesian network. According to the method, a Noisy-OR model and a Bayesian network are combined, and an initiating explosive device processing process safety evaluation model is constructed. According to the method, a Noisy-OR model can be used for carrying out quantitative processing on expert evaluation information endowed with weight, a corresponding CPT (conditional probability table) is generated, and the risk probability of the initiating explosive device processing process is generated through a Bayesian network by combining real-time monitoring data of a dangerous point and simulation data of an initiating explosive device processing finite element model through a multi-source information fusion method. According to the method, subjectivity of traditional initiating explosive device processing safety evaluation and singleness of a safety monitoring method are avoided, the Noisy-OR model and the Bayesian network are fused and applied to the field of initiating explosive device processing safety monitoring, the problems that safety evaluation is not objective and not real-time, and the monitoring method is local are solved, and the safety of initiating explosive device processing is improved. The method has a practical guiding significance for monitoring the actual processing safety of the initiating explosive device.

The invention discloses a vehicle fault diagnosis method, system and device based on a Bayesian network and a medium, and the method comprises the steps: constructing the Bayesian network according to preset vehicle data variables and fault root cause description, and initializing a conditional probability table of each node and the attention weight of each connection edge; inputting preset multi-source sensor sample data into the Bayesian network for parameter learning, and optimizing the conditional probability table of each node and the attention weight of each connection edge to obtain a vehicle fault diagnosis model; inputting the target multi-source sensor data into the vehicle fault diagnosis model to obtain target probability distribution of a plurality of target fault root causes, and determining the contribution degree of each input variable to each target fault root cause according to the attention weight; and generating a fault diagnosis thermodynamic diagram according to the target probability distribution and the contribution degree, and marking a key input variable and a corresponding causal chain in the fault diagnosis thermodynamic diagram. The method improves the intuition and interpretability of the diagnosis result, and can be applied to the technical field of fault diagnosis.

The invention discloses a method for establishing a risk management model of a hydrogen-doped natural gas pipeline. Firstly, a Bow-Tie model system is used for analyzing a failure reason and an accident consequence development scene of the hydrogen-doped natural gas pipeline; then, the model is mapped into a Bayesian network by utilizing GeNIe software; and calculating the prior probability of the basic event through an expert evaluation method and a fuzzy set theory. Setting a conditional probability table of the Bayesian network by using a fault tree mapping method and a historical data calculation method; on the basis, simulating an equipment component failure process through a Markov model, introducing hydrogen corrosion and hydrogen-assisted fatigue crack propagation models to carry out hydrogen-related dynamic analysis, and finishing parameter setting of a dynamic Bayesian network; and finally, calculating the failure probability of the hydrogen-doped natural gas pipeline and a potential life loss result when an accident occurs in combination with a model output result. The method adopts the dynamic Bayesian network to predict the pipeline failure probability, is more in line with the actual operation condition, and can be widely applied to the risk management process of the hydrogen-doped natural gas pipeline.

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 relates to a cable tunnel bridge fire prediction method and device, electronic equipment and a storage medium. The cable tunnel bridge fire hazard prediction method comprises the following steps: establishing a cable tunnel bridge fire hazard numerical simulation model, establishing a cable tunnel bridge fire hazard simulation model based on FDS software, obtaining key parameters such as heat release rate, temperature distribution and flame spread boundary under different working conditions, and constructing a multi-time sequence sample data set; performing state discretization on continuous variables such as temperature and a spreading range, and estimating a node prior probability in combination with a statistical frequency; constructing a dynamic Bayesian network topological structure according to a causal relationship among a heat source, temperature and spread, and setting a cross-time slice node dependence path to realize time sequence modeling; inputting a training sample and performing parameter learning to generate a conditional probability table; in the prediction stage, multi-step reasoning is achieved through forward propagation, flame spreading range probability distribution and interval estimation of multiple time steps in the future are obtained, and the specific position where the flame arrives is predicted.

The invention discloses an uncertainty reasoning state scoring and early warning system for gear machining equipment, and relates to the technical field of gear machining monitoring. Data are collected in real time through an industrial Ethernet, time synchronization is realized based on an IEEE1588PTP protocol, and a data cleaning sub-module is designed to repair an abnormal value and keep a record; the method comprises the following steps of: extracting 128-dimensional potential features of a vibration signal by adopting a variational auto-encoder, fusing a temperature drift coefficient and a current harmonic component, quantifying feature uncertainty through Monte Carlo dropout, and marking low-reliability features; and constructing a Bayesian network containing 5 state nodes and 12 observation nodes, calculating a posterior probability through a Markov chain Monte Carlo algorithm, dynamically adjusting a conditional probability table, and fusing multi-feature scores. According to the method, the state evaluation accuracy and the early warning timeliness are improved, the resource consumption is optimized, full-link monitoring is realized, the fault handling efficiency is enhanced, and reliable support is provided for precision manufacturing.

A flight control equipment reliability allocation iterative optimization and dynamic prediction method comprises the following steps: constructing a Bayesian network through a system reliability block diagram of FMEA at an offline stage, expanding the Bayesian network, updating the network by taking a failure probability as a prior probability, and performing system reliability check to obtain a Bayesian network considering weight nodes; setting a conditional probability table and prior distribution of weight nodes; in the online stage, reliability is obtained through calculation according to the service life data of the parts, then the reliability is updated to be the prior probability in the Bayesian network, upward reasoning is conducted through the Bayesian network, and a real-time reliability predicted value is obtained. The Bayesian network is used for integrating prior knowledge and sample data, the variable dependency relationship is expressed through the conditional probability table, joint probability distribution is simplified, and the method is suitable for complex causal relationship modeling in reliability analysis.

Computer-implemented methods of providing a clinical predictor tool are described, comprising: obtaining training data comprising, for each of a plurality of patients, values for a plurality of clinical variables comprising a variable indicative of a diagnosis or prognosis and one or more further clinical variables; and training a clinical predictor model to predict the variable indicative of a diagnosis or prognosis using said training data, wherein obtaining the training data comprises obtaining synthetic clinical data comprising values for a plurality of clinical variables for one or more patients by obtaining a directed acyclic graph (DAG) edges corresponding to conditional dependence relationships inferred from real clinical data comprising values for the plurality of clinical variables for a plurality of patients, and obtaining values for each node of the DAG using a machine learning model and multivariate conditional probability table. Computer-implemented methods of obtaining synthetic clinical data are also described.

The invention provides a construction interruption risk reasoning and plan generation method and device. The method comprises the following steps: acquiring multiple types of risk factors influencing construction interruption and a historical data set; taking a Bayesian information criterion as a scoring function, and constructing a directed acyclic graph structure based on the scoring function, a historical data set and a constraint set determined by domain knowledge; the constraint set is used for limiting whether edges between nodes exist or not in the construction process of the directed acyclic graph structure; based on the directed acyclic graph structure and the historical data set, a conditional probability table of the directed acyclic graph structure is determined, and the directed acyclic graph structure and the conditional probability table form a Bayesian network model; determining the risk probability of the target construction interruption event based on a Bayesian network model; and optimizing a preset construction plan combination based on the risk probability, and determining an optimal plan combination. According to the directed acyclic graph structure, objective data and domain knowledge are considered, and the accuracy of subsequent risk reasoning and plan generation is improved.

The invention discloses an electricity consumption anomaly detection method and system based on a Bayesian model, and the method comprises the steps: obtaining multi-mode electricity consumption data, carrying out the preprocessing of the collected multi-mode electricity consumption data, carrying out the preprocessing of an innovative preprocessing frame which comprises dynamic mode alignment and multi-mode missing value processing, and achieving the deep cooperative processing of data through a progressive architecture; initializing a Bayesian network model, defining nodes and a structure, and initializing a conditional probability table; learning the structure and parameters of the Bayesian network by using the sample data, and adjusting the structure and parameters of the network; and performing multivariable joint probability fault reasoning by using the trained dynamic Bayesian network DBN, namely predicting and classifying new data. According to the method, a closed-loop technology covering a sensing-inference-decision link of electricity consumption anomaly detection is formed, and compared with the prior art, the method has remarkable advantages.

The invention discloses a Bayesian reasoning method for high-voltage power supply reliability under common cause failure influence, and belongs to the technical field of high-voltage power supply reliability analysis. Constructing a dynamic fault tree of the high-voltage power supply; acquiring the proportion of common cause failure in each pair of bottom event failures, and collecting evaluation suggestions for the proportion of the bottom event to construct a fuzzy matrix; determining common cause failure factors of common cause failure of each pair of bottom events; the dynamic fault tree of common cause failure is converted into a discrete time Bayesian network, and a Bayesian network graph, a conditional probability table and a marginal probability table are obtained respectively; and performing bidirectional reasoning on the dynamic reliability of the high-voltage power supply, and calculating reliability and maintainability indexes of the high-voltage power supply in each time period. According to the method, the common cause failure factor is determined through the fuzzy theory, and the dynamic fault tree considering common cause failure is mapped into the Bayesian network for reliability analysis, so that the problems that the common cause failure factor is difficult to determine and the reliability analysis calculation amount is too large are solved, and the high-voltage power supply reliability analysis precision and calculation efficiency are effectively improved.

This invention discloses a method for fire risk assessment of LNG storage tank areas based on Bayesian networks, comprising the following steps: S1, determining the initial accident tanks and fire scenarios in the LNG storage tank area, and calculating the intensity of thermal radiation generated by the fire; S2, determining the safety barriers set for each target tank, evaluating the performance parameters of each safety barrier, and calculating the failure probability of each target tank under thermal radiation; S3, constructing a Bayesian network model, and setting the conditional probability table for each node based on the failure probability of each target tank under thermal radiation; S4, determining the probability of a domino effect accident through forward reasoning of the Bayesian network; and identifying the most likely accident propagation sequence through backward reasoning of the Bayesian network, providing decision support for emergency response.

The application discloses a fault diagnosis method and system of a power centralized communication control device, which is used for accurately identifying cascading faults to improve the safety and stability of a power system. The method comprises the following steps: obtaining operation data of the power centralized communication control device, and extracting a frequency feature set from the operation data; calculating the correlation strength between each variable in the frequency feature set by using a conditional probability table, screening out a key feature vector set, and generating an interaction topology between different devices in the power system; calculating the propagation path and propagation speed of each key feature vector in the interaction topology according to a path reasoning algorithm, and screening out a candidate fault propagation path set based on the propagation path and propagation speed; calculating the fault propagation probability of the candidate fault propagation path, determining a cascading fault propagation feature set, constructing a high-dimensional space classification boundary according to the cascading fault propagation feature set, and performing fault mode classification to obtain a fault diagnosis result.

The invention provides an electric power system state evaluation and early warning method based on a dynamic Bayesian network, which relates to the technical field of electric power, and comprises the following steps: obtaining time sequence historical data and topological relation data of an electric power system, extracting time sequence characteristics from the time sequence historical data based on a hierarchical sliding window method of an alarm level, and calculating the state of the electric power system according to the extracted time sequence characteristics; on the basis of the topological relation data, constructing a domain structure in a topological conversion mode; performing dynamic Bayesian network modeling according to the time sequence characteristics and the domain structure; according to the dynamic Bayesian network, constructing a conditional probability table and a state transition matrix by using a cross-domain prior probability in combination with a maximum likelihood estimation method; calculating a prediction state of the domain structure based on the conditional probability table and the state transition matrix in combination with monitoring data of each node in the domain structure; and performing power system state evaluation and early warning according to the prediction state of each domain structure in the power system. According to the invention, a new methodology is provided for fault prediction and operation state management of the intelligent power grid.

The invention provides a fault identification method and device and a program product, and relates to the technical field of data processing, the method comprises the following steps: obtaining at least one first node state parameter of a network node, the network node being a network node having a fault; calculating posterior probabilities of a plurality of fault types based on a conditional probability table and the at least one first node state parameter through a preset network model, the conditional probability table comprising prior probabilities and conditional probabilities between each fault type in the plurality of fault types and different node state parameters, the preset network model is used for calculating a posterior probability of a fault type according to a prior probability, and the plurality of fault types are a plurality of fault types when the network node fails; and determining a first fault type based on the posterior probability, wherein the first fault type is the fault type with the maximum posterior probability in the plurality of fault types. According to the invention, the fault identification accuracy can be improved.

This invention discloses a method for optimizing the operating parameters of a vacuum adsorption system based on transfer learning. Specifically, the method includes: aligning historical and current adsorption condition data by time and dimension to form a sequence of operating condition features; extracting material, roughness, load, pressure, flow rate, leakage, and cycle time features to form a set of node vectors; constructing an initial structure of a semi-naive Bayesian network to generate a set of candidate parent sets; performing parent set competition explicitness calculations to determine the dominant parent set identifier; statistically analyzing the evidence quantity of historical, current, and conflicting samples to generate a local evidence concentration sequence and form a conditional probability table; performing parameter inference to generate vacuum pressure values, pressure holding time values, valve switching time values, and leakage compensation amplitude values; and performing constraint verification to output a set of operating parameters. This invention achieves adaptive optimization of the operating parameters of a vacuum adsorption system under the combined influence of historical and current operating conditions.

The invention discloses a premature infant retinopathy risk prediction method and system based on a Bayesian network. The method comprises the following steps: S1, data acquisition and grouping; s2, performing quality control and standardization processing on clinical variables, and preprocessing microbiome data; s3, based on a structure learning algorithm, constructing a directed acyclic graph Bayesian network model which jointly reflects a dependency relationship between clinical variables and microbiome variables, optimizing the structure in combination with clinical prior medical knowledge, generating a conditional probability table of each variable, and realizing multi-factor joint risk reasoning and interpretation; s4, model training and performance evaluation; and S5, inputting data, analyzing, outputting the risk probability of occurrence of ROP of the child patient, and visually displaying the risk probability. By integrating multi-dimensional clinical variables and intestinal microbiome characteristics, a Bayesian network model which is reasonable in structure, high in interpretability and high in prediction accuracy is constructed, and early layered prediction and individualized intervention suggestions on the retinopathy risk of the premature infant are achieved.

The application discloses a unified probability propagation prediction method and system suitable for WUI fire, and the method comprises the following steps: constructing a unified state space and discretizing; constructing an external driving model of building layer fire propagation; constructing a building layer dynamic Bayesian network with each building as a node, parameterizing a conditional probability table of the building layer dynamic Bayesian network based on a physical driving mechanism; establishing a mapping relationship between an internal state of the building layer and an external observation category; realizing state correction and rolling prediction based on Bayesian updating; when external observation is obtained, the system state is updated based on Bayesian updating in combination with observation information, a posterior state distribution is obtained, the posterior state distribution is taken as an initial state of the next time step prediction, a rolling assimilation closed loop is formed, and finally a multi-state probability risk field of building scale evolution over time is output. The application can realize unified coupling of a landscape, a building and a flying fire, obtain state probability output over time, and can be assimilated and corrected.

The invention discloses a distribution network new energy facility disaster chain coupling transmission model construction method, and relates to the technical field of novel power system disaster modeling, simulation analysis and risk assessment, and the method comprises the steps: obtaining the type, intensity and influence range of a disaster faced by a distribution network new energy facility under a typhoon and rainstorm coupling scene, and recognizing a key disaster chain scene element; determining key nodes in the disaster chain according to the identified elements; constructing a topological relation of a disaster chain network based on the key nodes to form a disaster chain network structure; constructing a conditional probability table for the constructed topological relation; and simulating a disaster transmission process according to the constructed model, and introducing case backtracking verification to evaluate the accuracy of the model and optimize model parameters. According to the method, the coupling fault transmission process of the distribution network new energy facility under the typhoon and rainstorm coupling scene is effectively simulated, and accurate risk assessment and decision support can be provided for formulation of disaster prevention and reduction measures and optimization of emergency response strategies.

The soil and groundwater pollutant toxic effect risk diagnosis and control method and system of the present application relate to the field of soil pollution analysis technology. By collecting emission data and toxicological parameters, calculating partial correlation coefficients, and constructing a pollutant causal relationship diagram; dividing pollutants into samples, adding toxic effect nodes, and extracting sub-causal relationship diagrams, determining the pollutant parent node set and the toxic effect parent node set; calculating the first conditional probability of the pollutant node, calculating the second conditional probability and the third conditional probability of the toxic effect node, and obtaining the conditional probability table of the pollutant node and the conditional probability table of the toxic effect node; constructing a Bayesian network, obtaining the joint probability distribution of the pollutant combination, obtaining the emission concentration to form an evidence vector, and calculating the posterior probability distribution; obtaining the probability of the toxic effect node being in different states, taking the state corresponding to the maximum probability as the severity of the toxic effect, and selecting the pollutant node with the highest pollution weight for priority treatment.

The invention provides a human activity interference risk assessment method and system based on a Bayesian network, and relates to the field of ecological environment protection, and the method comprises the steps: obtaining risk assessment data corresponding to a preset risk factor in a to-be-assessed geographic region; determining risk state levels corresponding to different risk evaluation data according to a preset risk state level interval; matching risk probability distributions corresponding to different risk factors from a preset conditional probability table according to the risk state levels; and loading the risk probability distribution and the risk factor to a preset Bayesian network model for probabilistic reasoning calculation to obtain posterior probability distribution of the to-be-evaluated geographic area under one or more risk probability levels, and then generating and outputting a risk evaluation result of human activity interference in the to-be-evaluated geographic area. By implementing the method, the accuracy and reliability of ecological risk assessment can be improved.

The application discloses a constellation core network test fault positioning method and device, the method comprises the following steps: when the test task of the constellation core network fails, the path label chain of the test task is extracted as a fault label path; a directed dependency graph representing a fault propagation path is constructed according to the directed dependency relationship between network elements in the fault label path; a Bayesian network is constructed with the fault phenomenon corresponding to the fault label path as an observation node, the directed edges in the directed dependency graph as propagation nodes, and the network elements in the directed dependency graph as root cause network elements; a conditional probability table is constructed according to the causal relationship between the root cause network element anomaly, the propagation node anomaly and the fault phenomenon in the Bayesian network; the multi-dimensional evidence fusion score of each root cause network element is calculated according to the conditional probability table; and whether the root cause network element with the highest multi-dimensional evidence fusion score is a fault node is judged according to the confidence of the root cause network element with the highest multi-dimensional evidence fusion score. The application has high accuracy and high efficiency in fault positioning.

The application discloses a learner intelligent diagnosis method based on a Bayesian network, and belongs to the technical field of intelligent education. Knowledge points are modeled as binary random variables, a Bayesian network with a conditional probability table is constructed, and a bidirectional weighted graph is constructed through forward sampling and mutual information; a triple encoding Transformer that fuses node centrality, the shortest weighted path and edge encoding is used to generate node embedding; from the perspective of information theory, intelligent diagnosis is equivalent to a maximum decoding information path search problem, and the optimal diagnosis path is searched based on node embedding; through offline construction of a K-neighbor graph index and online greedy search, efficient diagnosis is realized with one training and multiple inferences. The application can accurately model knowledge level dependency, provide an interpretable diagnosis conclusion with causal tracing capability, and significantly improve the computational efficiency in multiple diagnosis scenarios, and can be used for personalized learning diagnosis and teaching intervention in an intelligent education system.

This invention discloses a method for coal mine terminal risk scoring based on Bayesian networks, comprising the following steps: Step 1: Collecting coal mine terminal risk data to form a terminal risk dataset; Step 2: Extracting risk variable nodes, barrier variable nodes, and terminal scoring nodes, constructing a Bayesian network, and forming a node conditional probability table; Step 3: Performing deontization, triangulation, and clique partitioning to form a connection tree and a partition set; Step 4: Calculating the probability estimate of clique nodes and the barrier state description term; Step 5: Constructing propagation messages using an improved Shafer-Shenoy algorithm to form a penetrating residual component; Step 6: Performing state enhancement marginalization to form a partition set propagation message; Step 7: Forming the terminal residual posterior risk distribution; Step 8: Forming the coal mine terminal risk scoring result. This invention improves the ability to characterize coal mine terminal residual risk and the reliability of risk scoring.