56 results about "Causal link" patented technology

The invention relates to the technical field of power system measurement, and discloses a current transformer error dynamic monitoring method and system.The current transformer error dynamic monitoring method comprises the steps that current transformer time sequence data and a system event log are obtained; constructing a time sequence causal graph to represent the time correlation between the event and the error change; identifying potential causal links by applying a counter causal model; designing a multi-world simulation engine to generate an anti-fact scene; quantifying a causal effect by comparing actual observation with an anti-fact simulation result; establishing a monitoring mechanism to track key trigger events in real time; generating a dynamic causal interpretation report and adjusting a compensation strategy; according to the method, the limitation of traditional correlation analysis is broken through, the causal relationship and the correlation can be accurately distinguished, the real triggering factor of the error change of the current transformer can be accurately identified, the false alarm rate and the missing report rate are reduced, and the accurate dynamic monitoring of the error of the current transformer is realized.

The invention discloses an intelligent automobile interpretable abnormity diagnosis method and system, and relates to the technical field of intelligent traffic. The method comprises the steps of collecting multi-dimensional sensor data based on an intelligent automobile test platform, and constructing a directed causal graph and a causal adjacency matrix which are used for describing a causal relationship between the sensor data; designing a causal constrained graph attention mechanism based on the causal adjacency matrix, and constructing a causal constraint enhanced graph attention anomaly diagnosis model; and based on the directed causal graph and the graph attention anomaly diagnosis model, constructing a hierarchical anomaly diagnosis strategy integrating a feature reconstruction error, a variable causal relationship and a graph attention network weight, positioning an anomaly root cause and identifying a propagation path of the anomaly in the sensor network. According to the invention, the problems of false correlation and lack of exception explanation ability of graph attention network learning in the prior art can be overcome, and reliable exception detection and root cause diagnosis of intelligent automobile multi-sensor data are realized.

The invention provides an accident consequence simulation calculation method based on mathematical physical model coupling solution, and the method comprises the steps: constructing an accident chain knowledge graph and a physical trigger graph, and building a causal relationship and physical constraints among equipment, states, events and consequences; gathering and mapping historical records, expert rules and online observation data into map entities and relationships, forming a baseline accident scene and calculating a baseline index; generating candidate paths by utilizing graph reasoning and coupled multi-physics field simulation, and realizing a closed loop of graph reasoning and physical solution through consistency check; performing scoring and disturbance simulation analysis on the candidate paths, and screening robust target paths; and carrying out high-fidelity simulation on the target path, identifying key nodes in combination with sensitivity analysis and a minimum cut-off set, and generating disposal suggestions and action priorities. According to the method, high-credibility prediction of accident evolution and emergency response closed-loop linkage are realized, and the method has high precision, high robustness and engineering implementability.

The invention provides a causal relationship and time sequence characteristic-considered cascading failure rapid screening method and system, and relates to the technical field of power grid cascading failures, and the method comprises the steps of obtaining cascading failure scene data; based on cascading failure scene data, extracting a causal relationship between an initial short-circuit fault and a subsequent fault by using logistic regression and a neural network model; different states of the fault event are converted into graph structures, time delays between the different states of the fault event are obtained based on cascading fault scene data statistics, and time sequence features in the transient evolution process of the cascading fault event are extracted; the probability that the initial fault causes a subsequent fault event is obtained based on a causal relationship, the duration of different states of the fault event is generated by adopting a Monte Carlo sampling method based on time sequence characteristics, and a cascading fault scene is generated; and carrying out risk assessment and probability assessment on the cascading failure scene generated based on the causal relationship and the time sequence characteristics, and finally screening to obtain a high-risk cascading failure scene.

The present disclosure provides a method and system for quickly screening cascading failures that consider causal relationships and timing characteristics, and relates to the technical field of cascading failures in power grids. The method comprises the following steps: obtaining cascading failure scenario data; extracting the causal relationship between an initial short-circuit fault and subsequent faults using logistic regression and a neural network model based on the cascading failure scenario data; converting different states of a fault event into a graph structure, and obtaining time delays between different states of the fault event based on statistics of the cascading failure scenario data, and extracting timing characteristics during the transient evolution of the cascading failure event; obtaining the probability of an initial fault triggering a subsequent fault event based on the causal relationship, and generating a cascading failure scenario using a Monte Carlo sampling method based on the timing characteristics; and performing risk assessment and probability assessment on the cascading failure scenarios generated based on the causal relationship and timing characteristics, and ultimately screening out high-risk cascading failure scenarios.

The embodiment of the invention discloses a safety assessment method and device for a receiving station, equipment and a medium, and the method comprises the steps: determining a risk event according to a hazard source in a to-be-assessed receiving station, and enabling the risk event to represent a hazard source out-of-control event; determining a safety index of the to-be-evaluated receiving station according to historical data associated with the risk event of other receiving stations and the technological process of the to-be-evaluated receiving station; a comprehensive influence matrix is determined according to the index scores of the safety indexes, a safety evaluation graph of the to-be-evaluated receiving station is determined based on the comprehensive influence matrix, and the safety evaluation graph is used for investigation operation of risk events of the receiving station and characterization of the causal relationship and the hierarchy of the safety indexes. Based on the safety assessment diagram provided by the embodiment of the invention, accident cause factors, causal relationships and levels can be determined, the accuracy of risk disposal can be improved, and meanwhile, through the safety indexes and the safety assessment diagram, the accident occurrence mechanism can be known, the accident prevention capability can be improved, and the occurrence of accidents can be avoided.

The application provides an accident consequence simulation calculation method based on mathematical physical model coupling solution, which comprises the following steps: constructing an accident chain knowledge graph and a physical trigger graph, establishing the causal relationship and physical constraints among equipment, state, event and consequence; mapping the historical records, expert rules and online observation data into graph entities and relationships to form a baseline accident scene and calculate baseline indicators; generating candidate paths by using graph reasoning and coupled multi-physical field simulation, and realizing the closed loop of graph reasoning and physical calculation through consistency checking; scoring and perturbation simulation analysis on the candidate paths, screening the robust target path; carrying out high-fidelity simulation on the target path, identifying key nodes combined with sensitivity analysis and minimum cut set, and generating disposal suggestions and action priority. The application realizes high credible prediction of accident evolution and closed loop linkage of emergency response, and has high precision, high robustness and engineering implementability.

The invention discloses a controllable flight ground collision risk judgment method and system based on a Bayesian network model, and relates to the technical field of controllable flight ground collision risk judgment. And carrying out classification identification on causes of controllable flight ground collision (CFIT) unsafe events. The complex and disordered cause factors are sorted through an interpretation structure model (ISM), and a hierarchical relation schematic diagram capable of clearly showing the mutual causal relation and hierarchy of the cause factors is obtained. A Bayesian network model is established, and key factors in a CFIT event are sorted out from three different angles. According to the analysis result, various external factors and unit capability defects have influences on the CFIT, and the last defensive line for judging key links and preventing and controlling CFIT events can be found. More detailed guidance and training are provided for the key links, and more standardized supervision is carried out.

The application provides an enterprise resource planning system data flow conversion monitoring method, relates to the technical field of abnormal cause analysis in an enterprise resource planning system, and aims to solve problems such as difficult extraction of abnormal propagation causality, unexplainable traceability path, and low efficiency of quasi-real-time cause analysis in a multi-node complex business process. The core technical scheme includes the following steps: collecting and standardizing time series data of business key state indicators, establishing a local causal correlation cache by using a sliding window and a causal reasoning algorithm, recursively tracing back to an abnormal node as a terminal to form a preliminary causal path, screening high-confidence causal links through multi-dimensional time consistency evaluation, generating a simplified dynamic path by using a node semantic aggregation mechanism, and finally embedding the path in an operation and maintenance interface in the form of a visual trajectory to realize interactive cause analysis verification. The scheme improves the accuracy and explainability of abnormal cause analysis, realizes full-process automation and man-machine fusion optimization from data to root cause links, and significantly enhances the intelligent level of system abnormality handling.

To comprehensively derive the causal relationships between multiple factors. [Solution] The processing device 100 classifies a plurality of causal exploration factors, which include an influencing factor and influencing factors that may influence the influencing factor, into one of a plurality of hierarchy levels according to the causal order of the plurality of causal exploration factors, and derives the causal relationships of the causal exploration factors belonging to multiple hierarchy levels that are different from each other.

The invention discloses a highway bridge engineering construction safety monitoring method. The highway bridge engineering construction safety monitoring method comprises the steps of obtaining highway bridge construction historical accident data; extracting structured information from the accident report text to determine an accident label and risk factors associated with the accident label; processing co-occurrence data of the risk factors in the accident case by using a preset association rule mining algorithm, and generating a risk factor association rule set representing a potential causal relationship among the risk factors according to the co-occurrence data; constructing a probability graph model of the risk factors based on causal semantics of the risk factor association rule set, wherein the probability graph model represents a dependency relationship among the risk factors; based on the probability graph model, determining sensitivity values of at least part of risk factors by using a preset importance degree measurement algorithm; determining a key risk factor according to the sensitivity value of the risk factor and a preset sensitivity threshold; and determining safety monitoring indexes of highway bridge engineering construction according to the key risk factors.

The application discloses a cross-region synchronous power monitoring system and method based on a time series database, and relates to the technical field of data analysis.The method comprises the following steps: acquiring historical abnormal events and storing them into a time series database, extracting first and second event features therefrom, calculating a perception response duration and a recovery treatment duration, and taking the two as third event features; step-by-step construction of corresponding event sequence models to obtain a complete event sequence model set of all abnormal events; screening of event pairs by traversing the set, analysis of causality based on the event pairs, determination of a causal relationship, and generation of a causal link pair set; traversal of the causal link pair set, marking of associated causal chain pairs and grouping; establishment of a mapping and storage into a knowledge base, marking of consequence types and average recovery durations of each situation element; real-time monitoring of situation element abnormalities, query of the knowledge base to find common consequences, calculation of an estimated maximum recovery time, and early warning if the estimated maximum recovery time exceeds a threshold value.The application realizes cross-region synchronous power monitoring.

To improve the accuracy of root cause analysis.SOLUTION: A root cause analysis system 1 that recommends a root cause of an abnormality occurring at an analysis target based on normal data and abnormal data obtained by measuring the analysis target with a plurality of sensors includes: a causal relationship information processing part 351, a significance level calculation part 352, and a recommendation result calculation part 3531. The causal relationship information processing part, based on the normal data, calculates a causal structure that links a plurality of sensors through causal relationships and an influence level of each of the plurality of sensors. The significance level calculation part, based on the normal data and the abnormal data, calculates the significance level of each of the plurality of sensors. The recommendation result calculation part, based on the causal structure and the significance level, extracts a plurality of recommended sensors as a target of recommendation, and determines a recommendation ranking of each of the plurality of recommended sensors based on the causal structure and the influence level to calculate recommendation results in which the plurality of recommended sensors are arrayed in order of the recommendation ranking.SELECTED DRAWING: Figure 1

The invention relates to the technical field of mechanical fault diagnosis, and discloses a small sample fault diagnosis method based on a causal relationship and a terminal. According to the method, a fault diagnosis model of a causal small sample relation measurement network is constructed, and the fault diagnosis model is mainly composed of a feature coding module, a causal intervention module, a causal decomposition module and a relation measurement module. In the causal intervention module and the causal decomposition module, causal factors are extracted from input, then factorization loss is designed to reconstruct an invariant causal mechanism, the invariant causal mechanism is converted into independent features with a sufficient causal relationship, and finally a feature coding module and a relationship measurement module train a plurality of meta-tasks to obtain a plurality of meta-tasks. And a trainable similarity measurement space is established to learn the feature distance between the sample pairs. Therefore, the model can capture the causal characteristics of the distribution differences among the components, the interpretability and generalization ability of the model are remarkably improved, and the accuracy of fault diagnosis is ensured.

The invention provides a power grid accident automatic submission method and system based on AI semantic understanding and event chain tracking, and relates to the technical field of intelligent power grid monitoring. The method comprises the following steps: constructing an event chain model through event time alignment and equipment topological association, and deducing a causal relationship between events to generate an electrical law causal graph; identifying a root cause event in combination with the in-degree, out-degree and confidence weight of the node; and automatically judging and generating an accident submission text and an evidence packet according to the accident severity and the confidence threshold. According to the invention, intelligent diagnosis and automatic submission of electrical accidents can be realized, and the analysis accuracy and response efficiency are improved. The problem that in the prior art, cross-system time alignment and automatic power grid accident submission based on causal constraints cannot be achieved under the multi-source heterogeneous data condition is solved.

The present invention discloses a system and method for identifying unsafe factors in the process of new energy infrastructure construction. The specific technical solution is as follows: constructing a feature database of unsafe factors in different construction stages and different accident types, calculating the similarity between the unsafe factor feature vectors collected in real time and the unsafe factor feature vectors in the feature database, and when the calculated similarity exceeds a set similarity threshold, preliminarily identifying the current unsafe factor, and then analyzing the causal relationship, temporal sequence, and spatial relationship between the current unsafe factor and other unsafe factors associated with it, constructing a factor association network model, determining the unsafe factor chain, and mining potential unsafe factors. By analyzing the mutual influence between the current unsafe factor and the potential unsafe factor and deeply mining the complex relationship between the data, it can help staff fully understand the root causes and development trends of unsafe factors and formulate more effective response measures.

A causal device, which includes a causal module and a causal feature learning module coupled to the causal module, and a causal method thereof is disclosed to ensure accurate fusion of hybrid imaging or improve priority triage of imaging tests. The causal module is configured to identify or utilize causal relationship(s) between a plurality of variables; the causal feature learning module is configured to extract at least one first causal feature of one of the plurality of variables.

The application relates to the technical field of power system measurement, and discloses a current transformer error dynamic monitoring method and system, wherein the current transformer error dynamic monitoring method comprises the following steps: obtaining current transformer time sequence data and system event logs; constructing a time sequence causal diagram to represent the time correlation between events and error changes; applying a counter causal model to identify potential causal links; designing a multiple world simulation engine to generate counterfactual scenarios; quantifying causal effects by comparing actual observations with counterfactual simulation results; establishing a monitoring mechanism to track key trigger events in real time; generating a dynamic causal explanation report and adjusting a compensation strategy; the application breaks through the limitations of traditional correlation analysis, can accurately distinguish between causality and correlation, accurately identifies the real trigger factors of current transformer error changes, reduces the false positive rate and the false negative rate, and realizes accurate dynamic monitoring of current transformer errors.

The application relates to the field of artificial intelligence models and discloses a method, system, device and storage medium for evaluating content causality of a generative engine based on a structured causal model. The method comprises the following steps: obtaining a structured causal graph of a target industry field, user query information and to-be-evaluated content information; inputting the user query information and the to-be-evaluated content information into a causal enhancement model, performing causal link analysis on an original answer after the original answer is generated, extracting causal inference information and mapping the causal inference information to nodes of the structured causal graph, generating causal path data, quantifying causal necessity of the to-be-evaluated content information, obtaining a causal necessity index, a path causal contribution degree and a counterfactual influence index of the to-be-evaluated content information, and then outputting an evaluation result of the to-be-evaluated content information. The method provided in the application embodiment improves the stability of a model, thereby reducing the probability of redundant information in a model output result.

The application discloses a kind of based on causal event extraction model's causal event extraction method, comprising the following steps: based on event extraction and causal relationship identification two subtasks, construct causal event extraction model;Acquire input sentence;Based on pre-training language model, input sentence is encoded, based on sequence labeling decoder, the coded input sentence is decoded, and the event of existence causal correlation is extracted;Based on causal event extraction model, construct initial background graph;Event is inserted into initial background graph, and updated background graph is obtained;Using graph neural network, the representation of extracted event is obtained by encoding and updating to updated background graph;Based on classifier and the representation of extracted event, the causal relationship between events is obtained, realizes the extraction of causal event.The experimental results of the sentence of different causal event pairs prove the ability of the method of the application to extract complex causal relationship.

The invention discloses a multi-modal model-based fuel gas use abnormal behavior identification method and system, and belongs to the technical field of intelligent fuel gas safety and artificial intelligence. According to the method, an explicit gas use structure causal model is constructed, and a causal relationship graph among hidden variables such as basic gas consumption, high-power equipment start and stop, leakage events and environment temperature influences is defined. The method comprises the following steps: acquiring multi-modal time series data, training a decoupling representation learning model combining a variational auto-encoder and causal constraints, and decomposing observation data into independent feature components of hidden variables in a corresponding structural causal model; when an anomaly occurs, a root variable causing the anomaly is positioned by comparing the change of each hidden variable component in a normal state and an abnormal state, and a father node influence path is traced along a structural causal model causal graph, so that anomaly detection and explainable root cause diagnosis are realized. According to the invention, the accuracy of abnormity identification is improved, an operable diagnosis conclusion of equipment fault or behavior abnormity and the like is provided, and the intelligent level of gas safety operation and maintenance is improved.

The invention discloses a method for identifying an event causal relationship by combining a knowledge base and a spreading model, and relates to a causal relationship identification task in the field of natural language processing, which comprises the following steps of: extracting events, sentences, relationships among the events and the like from an event document set; inquiring common sense information of each event in an external knowledge base to enrich event representation; extracting feature representations of the events through an encoder technology, carrying out feature fusion on the feature representations and common sense information, and splicing the two event representations into event pair representations; gaussian noise is gradually added into the event causal tag representation to obtain tag representation with noise; performing feature fusion on the noisy tag representation, the event pair feature representation and the current time step information, and calculating the noise in the tag representation by using a diffusion model; and obtaining potential representation through predicted noise, time step information and label representation with noise, splicing the potential representation and event pair features, and inputting the spliced new features into a classifier to calculate the causal relationship of the event pair. By exploring the external knowledge of the event and the conversion process of the diffusion model to the causal label, the accuracy of event causal relationship identification is improved.

This specification relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer equipment, and storage medium for processing causal event pairs. The method comprises: extracting an event dataset from text data; extracting event data from the event dataset without replacement as first event data; matching a corresponding first node in a causal knowledge graph based on the first event data; obtaining the cause node and / or result node of the first node as a second node in the causal knowledge graph; extracting matching event data from the event dataset without replacement as second event data based on the second node; constructing candidate causal event pairs based on the first event data and the second event data; determining the causal relationship strength of the candidate causal event pairs; and performing causal relationship annotation on the constructed candidate causal event pairs based on the causal relationship strength of the candidate causal event pairs. The embodiments of this specification can improve the annotation efficiency of causal relationships.

The application discloses a mine accident simulation training method and device based on VR technology and a medium, relates to the technical field of mine safety intelligent training, and comprises the following steps: collecting typical mine accident types, constructing accident causality, mapping accident elements in the accident causality with risk nodes in a mine semantic twin scene, and forming an accident causality structure; comparing accident perception delay data with a perception delay threshold, outputting a delay level judgment result, adjusting an accident evolution state according to the delay level judgment result, and outputting an adaptive accident evolution state; comprehensively analyzing the adaptive accident evolution state and a student operation track, reconstructing the accident causality structure, and obtaining a personalized accident retraining scene. The application realizes a VR safety training system by constructing a mine digital twin scene that integrates spatial semantics and accident causality logic, and improves the authenticity, teaching pertinence and training effectiveness of mine accident simulation.

The invention discloses an identification system and method for unsafe factors in a new energy infrastructure construction process, and the specific technical scheme is as follows: constructing a feature database of unsafe factors in different construction stages and different accident types; carrying out similarity calculation on unsafe factor feature vectors collected in real time and unsafe factor feature vectors in a feature database, and when the calculated similarity exceeds a set similarity threshold value, preliminarily identifying a current unsafe factor; and analyzing a causal relationship, a time sequence and a spatial relationship between the current unsafe factor and other unsafe factors associated with the current unsafe factor, constructing a factor association network model, determining an unsafe factor chain, and mining potential unsafe factors. By analyzing the mutual influence between the current unsafe factors and the potential unsafe factors, the complex relationship between the data is deeply mined, so that workers can be helped to comprehensively understand the root and development trend of the unsafe factors, and more effective countermeasures can be formulated.

The invention discloses a general aviation flight accident cause chain identification method and device, a medium and a terminal, relates to the technical field of safety management, and mainly aims to solve the problem that a clear accident cause chain cannot be constructed due to the fact that the internal mechanism of accident occurrence is complex and general aviation flight accident cause analysis is difficult to comprehensively carry out. Comprising the following steps: firstly, identifying an unsafe action and indirect reasons from an accident investigation report, and then selecting an indirect reason matched with the unsafe action from the indirect reasons as a dominant indirect reason; further, based on a mapping relationship between a plurality of accident cause sub-types and type descriptions, according to the unsafe action, a hidden indirect cause is determined; and further, upper-layer reasons of the dominant indirect reasons and the recessive indirect reasons, namely safety management system deficiency and safety culture deficiency, are traced respectively, and are linked according to a causal relationship to obtain an accident cause chain.

The present invention relates to a method, device, and medium for improving an event knowledge graph based on data-driven. The method includes: collecting and preprocessing numerical data; using the Markov boundary discovery algorithm to learn event causal relationships and constructing an event causal relationship set; screening events directly related to the target event through conditional independence tests; quantitatively evaluating the causal strength of event pairs and verifying the triples in the event knowledge graph, adding the triples with causal strength lower than the preset threshold to the set to be verified; for event pairs with insufficient causality but significant correlation, retaining the events that meet the significance conditions based on correlation tests; complementing the event pairs with significant causal relationships in the data but missing in the knowledge graph, generating and bidirectionally verifying the complemented event triples; integrating the verified and complemented triples to update the event knowledge graph, and this method effectively improves the accuracy and efficiency of causal inference.

The invention relates to a big data-based METTL14 action mechanism analysis method and system, and provides a multi-modal omics data-oriented causal structure modeling and intelligent prediction method for the problem of causal inference of a regulation relation of METTL14 and a target gene (such as PTEN) thereof in gastric cancer. The method comprises the following steps: firstly, acquiring a transcriptome, an m6A methylation modification group and clinical phenotype multi-modal original data from a public database, marking and pre-processing the data, unifying the data to a potential space through high-dimensional feature mapping, and constructing and optimizing cross-modal causal embedding representation and a graph structure; the causal link mining is realized by combining the variational self-encoding and the graph convolutional network, and the signal-to-noise ratios of different modes are dynamically weighted, so that the structural analysis precision is improved. Anomaly detection and adaptive correction are further introduced to ensure the credibility of the causal chain. Integrating external biological experiment data to carry out model fine tuning, and supporting dynamic introduction of new features. And finally, outputting an interpretable regulation and control prediction result. According to the scheme, the reliability and generalization ability of causal inference under multi-modal data are improved, and mechanism support is provided for targeted intervention.

Automatically generating a fault tree on the basis of the causal relationship of defects to events to be analyzed, and calculating a priority degree (score) for the individual events in the generated fault tree by means of the number of co-occurrences of “events” and “event-related information” in past defect information on the basis of “event-related information” in which a component is used. A scored fault tree to which the scores have been applied is presented.