51 results about "Causal strength" patented technology

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a multi-modal causal reasoning and interpretation method, device, equipment and medium, and the method comprises the steps: obtaining original data streams of at least two different modals, and extracting modal features; a cross-modal attention mechanism is utilized to fuse modal features, and causal features are extracted through feature distillation; constructing a dynamic causal graph based on causal features, and updating an edge weight through a causal intensity function; identifying the causal relationship in the dynamic causal graph and performing anti-factual reasoning verification to evaluate the reliability of the causal relationship; and generating a causal interpretation result in combination with the dynamic causal graph and the causal relationship reliability. According to the method, the multi-modal data are fused, the causal features are extracted, and dynamic causal graph updating and anti-factual reasoning verification are combined, so that reliable modeling and explanation of the causal relationship in a complex scene are realized, the defects of single modal or simple fusion in the prior art are overcome, and the accuracy and interpretability of causal reasoning are improved.

The invention relates to the technical field of aircraft fault diagnosis, in particular to a vertical take-off and landing aircraft diagnosis generalization enhancement method based on causal weight. Firstly, a directed acyclic graph between flight features and fault types is established through an information flow causal discovery method, the causal relationship between the flight features and the fault types can be clearly presented, and a basis is provided for subsequent analysis. Then, mutual information between nodes is calculated and converted into causal strength for causal enhancement, and expression of the causal relationship in the data is enhanced; in the convolutional neural network, causal weights are used for dynamic weighting to extract local features, causal features of a directed acyclic graph are combined, and feature information of different types is fully utilized. According to the method, features are fused through a graph convolutional network to obtain high-order features, adversarial training is completed through a full-connection network, the constructed fault prediction model integrates various technical advantages, the generalization ability of the model is effectively improved, the model can better adapt to different working conditions and data changes, and aircraft faults are accurately diagnosed.

The embodiment of the invention provides a causal knowledge constraint-based event extraction method and device. The method comprises the following steps of: constructing a causal graph of an event text to obtain a causal intensity matrix of feature data of the event text; constructing a problem template of an event argument according to the type of the event; the question template and the event text are combined and coded, and a coded sequence is input into a BERT model so that the hidden state of the last layer can serve as semantic representation of the input sequence; weighting the semantic representation of the input sequence by applying a self-attention weight matrix to obtain a weighted output; comparing the causal intensity matrix with the self-attention weight matrix to obtain a causal loss item; and defining a loss function in combination with the causal loss item to obtain an answer to the question according to the weighted output. Through the processing scheme disclosed by the invention, the interpretability of the model is improved.

A method includes generating a causal graph based on a plurality of values, each value corresponding to a causal relationship between two or more sensors of a plurality of sensors in one or more manufacturing systems. The method further includes determining a causal strength index matrix. The method further includes responsive to identifying an anomalous behavior in at least one of the plurality of sensors, determining a root cause of the anomalous behavior using at least one of the causal strength index matrix or the causal graph. The method further includes causing a recommended corrective action to be issued based on the root cause of the anomalous behavior.

The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis model construction method based on distributed causal discovery and federated learning. According to the method, a covariance tensor containing statistical association information of an observation variable and an agent variable is obtained, a global causal graph is obtained by combining a federal causal discovery method introducing the agent variable, then a converted causal intensity matrix is embedded into a graph convolutional neural network, and finally a personalized and global diagnosis model is trained by using a FedAvg framework fused with a Dito algorithm. According to the method, distributed heterogeneous data can be effectively processed while data privacy is protected, model interpretability is improved by mining a causal relationship between variables, global generalization and client personality requirements are considered, the accuracy and generalization ability of fault diagnosis are remarkably improved, and the fault diagnosis efficiency is improved. The method is especially suitable for fault diagnosis of industrial bearings and other scenes needing dispersed sensitive data processing.

The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method for causal characterization decoupling and causal strength embedding between data. The method comprises the following steps: firstly, acquiring multi-source-domain bearing historical fault data acquired by a plurality of data acquisition units; thirdly, performing causal characterization decoupling processing on the historical fault data of the bearing, and decoupling causal features and non-causal features of each data collector; then, performing causal intensity embedding processing by using all the causal features to obtain comprehensive causal features; and finally, fault prediction is carried out on the comprehensive causal features, and a corresponding bearing fault type is predicted. Therefore, the cross-domain bearing fault diagnosis method can effectively improve the accuracy of cross-domain bearing fault diagnosis by separating the causal features related to the fault from the non-causal features of environmental interference and fusing the causal information of the multiple data collectors.

A method includes generating a product knowledge causal graph based on causal relationships between multiple sensors in one or more manufacturing systems, parts data of a plurality of parts of the manufacturing system, and equipment constant data of a plurality of equipment constants of the manufacturing system. The method further includes determining a causal strength index matrix. The method further includes, responsive to identifying an anomalous behavior in at least one of the plurality of sensors, determining a root cause of the anomalous behavior using at least one of the causal strength index matrix or the product knowledge causal graph. The method further includes identifying, based on at least a subset of the parts data corresponding to the root cause of the anomalous behavior, or a subset of the equipment constant data corresponding to the root cause of the anomalous behavior, at least one corrective action for the anomalous behavior.

The invention discloses an industrial multi-source data fusion method based on causal inference in the technical field of computer data processing, and the method is applied to an aero-engine, and comprises the steps: obtaining the original performance data of the aero-engine, carrying out the normalization processing of the original performance data, and obtaining a target variable, the original performance data comprises rotating speed, exhaust temperature, oil pressure, oil temperature and metal abrasive particle component data; constructing a causal inference algorithm to calculate a dynamic threshold value; the causal intensity of each variable pair is calculated from the candidate causal set, variables with the first M ranks of the causal intensity are selected to form an optimization condition set, and a test algorithm is constructed; constructing a symmetric causal intensity matrix; and on the basis of the target variable and the feature matrix, performing quadrature to obtain a new data set after dimension reduction. By constructing the causal inference algorithm, the interpretability and generalization ability of the model can be enhanced, the performance stability is improved, the application range in the industrial field is expanded, and the calculation burden is relieved.

The invention discloses a drug relocation prediction method based on causal inference. The method comprises the following steps: 1) constructing a multi-modal heterograph; 2) obtaining a medicine functional embedding expression; 3) calculating a causal intensity weight of a drug-disease edge based on Do-calculation, and constructing a causal perception heterograph; 4) constructing a structural causal model, and calculating the average treatment effect of the drug on the disease; 5) designing a causal heterogeneous graph convolutional network, and learning node deep causal characterization; 6) identifying and correcting bias and errors; (7) What-if analysis is conducted through an anti-fact reasoning module, and the difference between an anti-fact result and the effect is calculated; and 8) fusing node deep causal characterization, a causal intervention result and an anti-fact reasoning conclusion, outputting a drug-disease causal association probability, and tracing a key causal path and an action mechanism. According to the method, the problem that the causal effect and the false correlation are difficult to distinguish in a traditional drug relocation method is solved, and the reliability, the interpretability and the generalization ability of a prediction result are improved.

The present application relates to a power distribution network grounding fault accurate positioning method based on fusion of multi-source data analysis, aiming at the problems of insufficient accuracy of causal relationship modeling and poor transparency of result reliability in existing methods, by fusing power distribution network topology, equipment parameters and historical fault data, combining with relay protection action logic, applying causal discovery and time series analysis, a weighted directed causal graph with causal strength interval is constructed. Further, based on the minimum strong causal path set, simulation intervention is implemented to form structured counterfactual experimental data, realize intermediate node role identification and causal reasoning link construction. Finally, through the reliability grading and feedback correction mechanism, a fault positioning report with logical interpretability and dynamic optimization ability is output. The scheme improves the accuracy, interpretability and self-adaptive evolution ability of power distribution network fault diagnosis.

The application discloses a large language model log analysis method based on relationship inference, comprising: taking a prefix parsing tree as the core, pre-processing the input log, and then traversing the prefix tree to realize template matching. If the matching is successful, the structured log is output, if the matching is unsuccessful, the relationship between the unmatched log and other logs is evaluated from the syntax and semantics. The syntax similarity between the unmatched log and the candidate log set is calculated at the syntax level, the causality strength and the number of shared entities between the unmatched log and the logs in the historical log window are evaluated through LLM at the semantic level, and the semantic correlation log is screened out by combining the semantic composite score; the screened syntax similar and semantic related log is taken as an example to construct a complete prompt containing a task instruction, a demonstration example and a log to be parsed, and a large language model is called to generate a structured template of the unmatched log; the newly generated template is adapted to the prefix parsing tree, the tree structure is perfected through dynamic updating, and more comprehensive template support is provided for subsequent log analysis.

The embodiment of the invention provides a causal relationship-based reservoir group multi-objective optimization scheduling method and system. The method comprises the steps of determining a multi-source decision factor stationary time sequence involved in reservoir group scheduling; scheduling-driven causal correlation analysis is carried out based on the multi-source decision factor stationary time sequence, and a scheduling causal network atlas is constructed based on an analysis result; based on the scheduling causal network map, through quantitative analysis of the hysteresis effect and causal intensity of each potential path, after path logic rationality verification, an effective driving path set is obtained; based on the effective driving path set, constructing a reservoir group scheduling mapping model; a multi-objective optimization algorithm is adopted to collaboratively optimize structural parameters of the model and input causal driving factors, so that good scheduling benefits and causal consistency can be generated during subsequent reservoir group scheduling planning based on the model. The implementation of the scheme can improve the scientificity and interpretability of scheduling.

The invention relates to a data root cause analysis method, system and equipment based on dynamic causal graph and large model collaboration, and relates to the technical field of artificial intelligence, the method, system and equipment form a dynamic causal graph by adding time sequence information and causal intensity weight in a blood relationship graph, and when a user performs abnormal query, the user can perform abnormal query on the basis of the dynamic causal graph. According to the method, the large model and the dynamic causal graph are combined to obtain the root cause hypothesis, so that the root cause hypothesis is verified, and the accuracy and the quickness of root cause determination are improved due to the addition of the time sequence information and the causal strength weight.

This disclosure provides a method and apparatus for interpretability evaluation that combines causal knowledge and attention. The method includes: dividing a dataset into a training set and a test set; constructing a causal graph of event data on the training set to obtain a causal strength matrix between event arguments; training a model using the causal graph to obtain a trained model; inputting test data into the trained model to obtain prediction results and attention weights; visualizing the attention weight vectors to obtain a directed graph; and comparing the similarity between the directed graph and the causal graph to determine interpretability. Through the processing scheme of this disclosure, the interpretability of the model is achieved.

The invention discloses an attribution analysis method and device, equipment, a storage medium and a computer program product, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the causal structure learning of a target data set, obtaining a target causal relationship in the target data set, and constructing a causal knowledge graph based on the target causal relationship; in response to a selection instruction of a main analysis index of a target user, querying a node set having causal association with the main analysis index from the causal knowledge graph, and determining a recommended association node based on causal strength; performing intervention effect calculation on the main analysis index based on the main analysis index and the recommended association node to generate anti-fact deduction result data; and performing multi-dimensional confidence assessment on the anti-fact deduction result data to obtain an attribution path credibility score. And through causal structure learning and multi-dimensional confidence assessment, the problem that attribution analysis depends on experience hypothesis is solved, and the analysis reliability is improved.

The invention relates to an enterprise information security management method, system and device and a medium. The method comprises the following steps: acquiring heterogeneous security data of a physical environment and a network environment, and performing standardized analysis and element extraction on the heterogeneous security data to obtain a physical event and a network event; based on a preset unified event model, carrying out cross-domain association analysis on the physical event and the network event, and calculating space-time proximity and semantic correlation between the physical event and the network event to obtain an association candidate pair set; inputting the associated candidate pair set into a pre-trained causal inference model to obtain the causal intensity of the influence of the physical event on the network event, and identifying the associated candidate pair of which the causal intensity exceeds a preset threshold value from the associated candidate pair set as a cross-domain event pair to obtain a visual attribution map; and triggering an enterprise dual prevention mechanism to perform linkage response based on the visual attribution map. By adopting the method, the overall capability of active defense and risk management and control of an enterprise can be improved.

This invention relates to the field of fault diagnosis technology, specifically disclosing a cross-operating-condition fault diagnosis method based on a stable causal graph convolutional domain generalization network. The method acquires multi-channel observation data of equipment under different operating conditions and explicitly introduces operating condition variables to label the corresponding operating conditions. Based on the multi-channel observation data and operating condition variables, a cross-operating-condition stable causal graph is constructed. The causal strength between adjacent observation variables in the cross-operating-condition stable causal graph is quantified to generate a causal strength matrix. Using the causal strength matrix as the graph topology weight, the multi-channel observation data is input as node features into a graph convolutional network for feature extraction to obtain graph-level embedding vectors. A diagnostic model including a classification branch and a domain generalization branch is constructed and trained. The trained diagnostic model is used to diagnose faults in equipment data under the target operating condition. This invention improves the generalization performance and fault diagnosis accuracy of the diagnostic model when facing unknown operating conditions.

The application relates to the technical field of fault diagnosis, in particular to a fault diagnosis method for decoupling and embedding of causal representation and causal strength between data. First, bearing historical fault data of a multi-source domain collected by multiple data collectors is acquired; then, the bearing historical fault data is subjected to decoupling processing of causal representation, and causal features and acausal features of each data collector are decoupled; then, all the causal features are used for embedding processing of causal strength to obtain comprehensive causal features; finally, the comprehensive causal features are subjected to fault prediction to predict corresponding bearing fault types. Thus, the application can effectively improve the precision of cross-domain bearing fault diagnosis by separating the causal features related to faults from the acausal features of environmental interference and fusing the causal information of multiple data collectors.

A method includes generating a causal graph based on a plurality of values, each value corresponding to a causal relationship between two or more sensors of a plurality of sensors in one or more manufacturing systems. The method further includes determining a causal strength index matrix. The method further includes responsive to identifying an anomalous behavior in at least one of the plurality of sensors, determining a root cause of the anomalous behavior using at least one of the causal strength index matrix or the causal graph. The method further includes causing a recommended corrective action to be issued based on the root cause of the anomalous behavior.

The application discloses a railway freight car configuration history management method, device, medium and equipment, and the method comprises the following steps: acquiring history basic information, including the attributes and attribute fields of each configuration item. An association matrix is constructed according to the correlation intensity of each attribute field, the penetration probability between each attribute field is determined based on the association matrix, the attribute grouping and the history type identification of the attribute field are determined according to the penetration probability. Each classified attribute field is taken as a node to construct a causal reasoning graph, and the causal strength and the causal path between each classified attribute field are determined according to the causal reasoning graph. The classified attribute fields are established into a hierarchical data structure according to a preset configuration level, the causal strength and the causal path between the classified attribute fields are marked in the hierarchical data structure, and the attribute configuration result of each configuration item is obtained. The application is helpful for the effective management and tracing of the attribute information of the railway freight car configuration item.

The application relates to the technical field of industrial automation and safety control, and particularly discloses a control loop dynamic reconstruction method and system for abnormal event stream causal inference. The application collects multi-source abnormal events in real time, identifies a driving propagation path through lightweight causal discovery, and calculates comprehensive causal strength according to path length, confidence and time coupling. A four-layer nested judgment mechanism is adopted to ensure that reconstruction is triggered only for a continuously high-threat path. The system combines reconstruction strategies based on an atomic action library, realizes smooth migration of new and old control structures through an S-shaped function after pre-performance verification by digital twinning, and continuously monitors and supports abnormal freezing and rollback in the process. The application realizes a closed-loop autonomy from abnormal perception, causal diagnosis to safety reconstruction, and significantly improves system resilience.

The invention discloses a service system fault prediction method based on causal analysis, which is used for fault prediction of a service system comprising a plurality of service nodes, and comprises the following steps: establishing a directed graph according to a calling relationship of the plurality of service nodes; according to multi-class service index data acquired by historical acquisition, mining a causal relationship of a plurality of connected service nodes in the directed graph to obtain a causal graph, and establishing corresponding edge strength in the causal graph in combination with causal relationship strength and a calling relationship distance; the method comprises the following steps: predicting a plurality of service system fault nodes according to multiple types of service index data collected in real time in combination with a causal graph, obtaining corresponding confidence probabilities one by one, adjusting the confidence probabilities according to corresponding edge strength, and determining a final service system fault node. Based on the directed graph structured service dependency relationship, the causal relationship is mined, the edge strength is established in combination with the causal strength and the calling distance, the confidence probability is dynamically adjusted to predict the fault node, and the prediction accuracy is improved.

The invention discloses a federal causal portrait and teaching intervention optimization method for a multi-school online education scene. The method comprises the following steps: constructing a local sample set and a local variable matrix; correlation calculation is carried out on education variables in the local variable matrix, and a local candidate neighborhood matrix is constructed; constructing a local candidate father node set; constructing a father variable set and a target variable, and performing linear least square fitting on the relationship between the father variable set and the target variable; obtaining a first residual dependency degree between the residual and the parent variable matrix; constructing a local causal adjacency matrix according to the local direction score; obtaining a global causal direction score by adopting federal causal structure weighted aggregation; constructing a global causal skeleton matrix; mining a causal path set pointing to the learning result node from a teaching related node set, and obtaining path causal intensity; calculating an overall causal influence score of learning result nodes of the teaching action set; and sorting according to the overall causal influence scores to obtain an intervention strategy.

Disclosed is a causal relation extraction method, specifically relating to a method and a device for denoising causal relation extraction based on multi-task collaborative learning. The method includes: inputting a text to be processed into a task-sharing layer of a denoising causal relation extraction model based on multi-task collaborative learning for feature extraction to obtain an extraction result; inputting the extraction result into the task-specific layer of the denoising causal relation extraction model based on multi-task collaborative learning to perform part-of-speech tagging, chunking analysis, and causal extraction tasks, to obtain feature labels corresponding to the tasks; performing causal strength classification and causal relation extraction tasks; conducting causal strength representation learning based on counterfactual negative sample contrastive learning, using a gating generator to obtain channel gains and temperature control coefficients, which are applied to gated attention calculation, to realize causal strength classification and guide extraction of causal relations through causal strength.

The invention discloses a causal feature recognition method and device associated with the curative effect of an immune checkpoint inhibitor, equipment and a medium, and relates to the technical field of biomedical detection, and the method comprises the steps: screening a candidate feature set meeting a preset screening condition from an original data set; performing conditional independence test based on a folded residual on each target data feature in the candidate feature set to obtain a false positive controlled candidate feature set; performing cross validation prediction comparison to obtain a causal strength index, outputting the data features with the causal strength index greater than a preset index threshold, and constructing a candidate causal feature set; calculating an out-of-fold prediction residual error of a candidate curative effect label corresponding to a candidate causal feature in the candidate causal feature set, obtaining a dependency detection value between the out-of-fold prediction residual error and the candidate causal feature, if the dependency detection value is smaller than a preset detection value threshold value, reserving the candidate causal feature and outputting the candidate causal feature as a target causal feature, and it is ensured that the output target causal features are robust and core driving factors.

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 the technical field of industrial automation and safety control, and particularly discloses a control loop dynamic reconstruction method and system for abnormal event flow causal inference. According to the method, multi-source abnormal events are collected in real time, a driving propagation path is found and recognized through lightweight causality, and the comprehensive causality intensity is calculated according to the path length, the confidence coefficient and the time coupling. And a four-layer nested judgment mechanism is adopted to ensure that only the continuous high threat path is triggered and reconstructed. The system is based on an atomic action library combination reconstruction strategy, after digital twinborn rehearsal verification, smooth migration of a new control structure and an old control structure is achieved through an S-type function, and in the process, continuous monitoring is conducted, and abnormal freezing and rollback are supported. According to the method, closed-loop autonomy from abnormal perception and causal diagnosis to safe reconstruction is realized, and the system toughness is remarkably improved.

The invention discloses an SER event diagnosis method based on causal verification and semantic generalization, and the method comprises the steps: firstly collecting historical event records of a converter station, and carrying out the priority division and dynamic time window aggregation; then, the events are constructed into a time-space-description triple, and a frequent item set is mined through correlation analysis; redundant rule pruning is carried out through confidence coefficient improvement, and false correlation is eliminated by adopting hybrid variable control; the causal intensity is verified based on ratio statistics, and reliable causal rules are screened; calling an intelligent language model to perform semantic analysis and tagging on the rule, extracting a core factor and generating a cross-scene generalization template; and finally, importing events, rules, tags and factors into a graph database, and constructing a visual causal knowledge graph. According to the method, the defects of redundancy and false association of the traditional association rule are effectively overcome, and the accuracy, interpretability and cross-scene migration capability of fault root cause positioning are remarkably improved.

The invention provides an electricity sales risk prediction method, device and system based on causal interpretation and online self-learning, and the method comprises the steps: obtaining historical electricity sales records and associated power grid operation observation data, building a sample data set containing a time stamp, carrying out the causal recognition of the sample data set, and carrying out the prediction of the electricity sales risk. Analyzing direct causal association and indirect causal association among variables through a structural causal model, generating a causal path weight set, performing Bayesian network fusion on the causal path weight set and time sequence pattern features in a sample data set, constructing a time sequence representation vector with causal logic constraints, and inputting the time sequence representation vector into a meta-learning framework model to obtain a meta-learning framework model; and generating an initial risk predictor through parameter fine tuning, obtaining a deviation value between the real-time power sale quantity observation value and the probability distribution sequence so as to adjust parameter configuration of the initial risk predictor, updating a causal intensity quantized value in the causal path weight set, and generating a power sale quantity risk assessment result. The accuracy and long-term stability of the risk prediction result can be improved.

The invention discloses a multimodal transport-oriented freight demand causal relationship graph construction method, and relates to the field of intelligent logistics, and the method comprises the steps: carrying out the collection and causal perception fusion processing of multi-source heterogeneous data from a multimodal transport service, and obtaining a time-space aggregation data table; based on the space-time aggregation data table, performing preliminary discovery of a causal structure by adopting a causal discovery algorithm fusing prior knowledge in the multimodal transport field to obtain a preliminary causal directed acyclic graph; and outputting the preliminary causal directed acyclic graph to a spatial-temporal heterogeneity causal effect estimation model based on a graph neural network and a super network, and calculating a personalized causal effect changing along with a space unit and a time context to obtain a spatial-temporal heterogeneity causal graph. According to the method, the causal atlas which can quantify causal intensity, reflect space-time heterogeneity and embed market game behaviors and has dynamic deduction capability is constructed, and decision support is provided for multimodal transport strategy optimization through visual integration.