33 results about "Causality" patented technology

The invention discloses a personalized information accurate pushing system and method based on artificial intelligence, and relates to the technical field of personalized recommendation, and the method comprises the steps: fusing user multi-platform behavior data and external space-time environment information, and generating a situation label with confidence through employing an improved space-time density clustering algorithm; constructing a causal directed acyclic graph by adopting a causal forest algorithm, quantitatively analyzing a heterogeneity causal effect, inverting a potential intention of the user, and outputting standardized intention inversion probability distribution; in combination with a historical intention and a behavior sequence, training a Transform intention state transition model constrained by causality of a causality directed acyclic graph, and performing multi-step probability deduction to generate an intention evolution path; information is retrieved from the dynamic knowledge graph according to the prediction path, a pushing copywriting matched with the situation is generated through the NLP technology, the optimal pushing opportunity is calculated in combination with the position track of the user, and accurate reaching of personalized information is achieved.

The invention discloses a cognitive disorder early screening and diagnosis system based on multi-modal data, and the system comprises the following modules: (1) a multi-modal data collection module which is used for obtaining image data, gene data, behavior data and clinical narrative information; the clinical narrative information comprises at least two of a patient chief complaint text, an interference factor hooking option and a symptom time axis; the causal purification module is used for filtering pseudo-correlation among the multi-modal data through clinical narrative anchoring and reverse intervention deduction, and comprises a narrative anchoring unit which is used for identifying data conflicts through a structured clinical narrative field based on a preset causal conflict rule base, and triggering freezing or weight descending operation; the intervention deduction unit is used for generating a reverse intervention verification packet containing a low-cost intervention measure and a review plan, and updating a causal rule base based on review data; according to the method, the statistical association limitation of the traditional technology is broken through, and the diagnosis and treatment normal form upgrading from correlation to causality is realized.

The invention discloses an anti-fact multi-mode dialogue emotion causal reasoning method based on a double-branch hypergraph. The method comprises the following steps: respectively extracting sentence level feature vectors of three modes of text, voice and vision from input multi-mode dialogue data; carrying out modeling on a high-order relationship in the modals and between the modals by utilizing a hypergraph structure, and constructing a dialogue hypergraph containing multi-modal nodes and emotion nodes; introducing a hypergraph attention network on the hypergraph, learning contribution weight of each modal node to a target emotion node, and selecting a candidate reason node set; the candidate reason nodes are intervened, an anti-fact branch is constructed, a fact situation and final node feature representation under the anti-fact situation are calculated, and a causal effect vector is obtained; and designing a joint optimization objective function, and carrying out joint training on emotion recognition loss and causal consistency loss to realize synchronous prediction of emotion categories and emotion reasons. According to the method, a high-order semantic relationship can be effectively modeled in a multi-modal dialogue scene, and a key reason for emotion formation is reasoned.

The invention discloses a time sequence prediction method based on cumulative causality and application, and belongs to the technical field of time sequence prediction.The method comprises the steps that firstly, a structural causality model is established for a power system containing observable reason variables, unobservable time-varying reason variables and to-be-predicted target variables; constructing an initial value and a time variation value of an encoder network characterization unobservable reason variable; and establishing a dynamic convolutional neural network prediction model by using the cumulative causal effect of a time-varying reason variable and a time-varying mechanism of convolutional expression, and outputting a result through a mask layer and accumulation. The prediction method based on the accumulative causal effect and the application are suitable for time sequence prediction problems such as metal component aging deformation prediction and the like, and have good potentials of stripping false correlation and improving time sequence prediction precision and stability.

The present invention makes it possible to estimate an integrated causal relationship between variables that span a plurality of datasets, and to estimate individual causal effects in each dataset.　A processing unit (12) acquires a plurality of pieces of first data, each of which includes a plurality of variable values that correspond to a plurality of variables, and which are used in estimating causal relationships and causal effects between variables based on the plurality of variable values. The processing unit (12) sets first information relating to an integrated causal relationship and causal effect in the entirety of the plurality of pieces of first data, and second information relating to weighting of the causal effect included in the first information for each of the plurality of pieces of first data. The processing unit (12) generates a plurality of pieces of second data that correspond to the plurality of pieces of first data on the basis of the first information and the second information. The processing unit (12) optimizes the first information and the second information so as to reduce the value of a loss function relating to the plurality of pieces of first data and the plurality of pieces of second data.

The application discloses a VFTO-induced partial discharge causality determination method based on time sequence characteristics, relates to the technical field of power equipment state monitoring, and comprises the following steps: acquiring a VFTO detection data set and an ultrahigh frequency partial discharge detection data set synchronously collected by an integrated sensing device; preprocessing each VFTO collection data and ultrahigh frequency partial discharge collection data; determining each causally related quantitative value; determining whether the collection data corresponding to each VFTO time sequence characteristic structure unit is partial discharge induction source data based on the causally related quantitative value; and outputting a VFTO-induced partial discharge causality determination conclusion based on the causality determination rule. After the integrated sensing device synchronously collects VFTO and ultrahigh frequency partial discharge multi-physical quantity data, the application can automatically mine the time sequence coupling correlation of the two, analyze the internal logic of insulation impact and discharge behavior, realize end-to-end intelligent analysis, and effectively improve the accuracy of VFTO-induced partial discharge causality determination.

The present application relates to the technical field of fault prediction and computer big data processing, and particularly relates to a generalized zero-shot composite fault diagnosis method, device and system based on counterfactual reasoning. The generalized zero-shot composite fault diagnosis method based on counterfactual reasoning proposed by the present application constructs a two-stage generalized zero-shot composite fault diagnosis model based on counterfactual reasoning. The model firstly points out the internal causal components of fault data from the perspective of causality theory, and then constructs a structural causal model to describe the decoupling and generation of fault features under the guidance of counterfactual reasoning. On this basis, the model improves the generative model by strengthening the discriminator in the first stage to realize the binary classification of single fault and composite fault. In the second stage, the supervised training of the classifier is used to predict the single fault category, and a traditional zero-shot learning method is designed to classify the composite fault. The present application greatly improves the diagnosis accuracy of the model and solves the problem of model diagnosis deviation on visible and invisible classes.

The invention provides a large language model causality enhancement method based on a causality inference theory. For intervention or anti-fact questions and answers in medical auxiliary diagnosis, educational evaluation and decision support, the problems of cause and effect direction errors, control condition omission, improper treatment of uncertain conclusions and the like are solved; according to the method, problems and facts are analyzed into measures, contrasts, control conditions and result indexes, the measures, the contrasts, the control conditions and the result indexes are mapped to a structural causal model, a causal subgraph is intercepted to execute intervention or anti-factual inference, result changes, key causal chains and uncertain marks are obtained, and a check list containing preconditions, assertable ranges and assertion rules which must be controlled and forbidden is generated; generating candidates and verifying the candidates, and constructing a preference sample to implement ORPO preference optimization to obtain a causal alignment model; during reasoning, a checking condition is injected, a consistency score threshold value is used for checking, and a consistent answer or a boundary answer is output; the verifiability and reliability of causal expression in the scene can be improved.

The invention relates to a computer-implemented method for simulating causality in production processes, wherein the method comprises the following steps: - Providing a structural causal model (10) for the production of products using a production line; - Initializing the structural causal model (10, S10) with the parameters with which the product is to be manufactured; - Performing a simulation for each product according to the initialized parameters (S16); and - Obtaining a simulated product sample (S26) for production from the simulation result.

The application discloses a kind of causality effect robustness inspection method based on counter disturbance, it is related to geological disaster risk analysis technical field, including: based on causal inference method obtains the causal factor of geological disaster prediction model, associated factor, and the causality effect index of corresponding factor;Factor disturbance space with physical rationality constraint is constructed, and the value range of factor disturbance amount is defined;Zero-order optimization counter attack method is used to generate factor-level counter disturbance samples in factor disturbance space;The change amount of model output before and after factor applies counter disturbance is calculated with the causality effect change amount, and factor-level counter robustness index is obtained;Causal robustness index is constructed, and the reliability evaluation and classification of causal factor are completed.The application solves the problems that the existing technology lacks robustness verification of causal effect, the causal factor may be affected by counter disturbance and fail, lacks causal robustness evaluation system of factor level and cannot identify pseudo-causality in causal inference result.

Embodiments of the present specification disclose a model training method and device based on feature selection and equipment. The method comprises the following steps: obtaining shared features Z of M tasks; for the kth task, determining a weight vector of features for the task according to the shared features Z, and determining a first prediction result of the kth task according to the shared features and the weight vector; for the ith feature, replacing the ith row in the shared features Z with a preset value to generate modified shared features, and determining a second prediction result of the kth task according to the modified shared features; determining a causal effect factor of the ith feature for the kth task according to the difference between the first prediction result and the second prediction result; determining the difference between the causal effect factor and the weight vector, generating a loss value according to the difference, and training the multi-task model, so as to selectively learn features with causal relationship for each task in the training process.

The application discloses a face feature decoupling representation method and device with causal effect transmission and a medium, relates to the technical field of causal discovery, image generation and decoupling representation learning. The method comprises the following steps: establishing a variational autoencoder, learning a latent feature distribution from a latent space based on the variational autoencoder in response to input face data; integrating a structural causal model into the variational autoencoder, modeling a causal effect to extract a causal feature from the latent feature distribution; establishing a graph attention network, inputting the causal feature into the graph attention network to decouple and transmit the causal effect; and designing a loss function, training the graph attention network by using a discriminator. The method can effectively mine and transmit the causal relationship between face features, improve the interpretability and transferability of feature representation, has strong application potential, and is especially suitable for face recognition, expression analysis and other tasks.

The present application relates to the field of biological identification, and provides a multi-modal impression identification method based on causality, which comprises obtaining first multi-modal data of a speaker and second multi-modal data of a listener; performing causality identification on the first multi-modal data and the second multi-modal data through a preset causality model to obtain first features; performing feature extraction on the second multi-modal data through a preset first BLSTM network to obtain second features; performing cross-domain fusion on the first features and the second features through a preset attention network to obtain first fusion features; and performing impression identification on the first fusion features through a preset full connection network to obtain a first impression identification result. The preset causality model is set to capture the causality between the speaker and the listener. The preset attention network is set to realize cross-domain fusion of the related information between the two, improve the accuracy of impression identification, and improve the performance of identifying impressions from a single aspect.

The invention relates to the technical field of industrial process monitoring, and particularly discloses an industrial abnormal root cause diagnosis method and system based on decoupling causal characterization. The objective of the invention is to solve the technical pain point that the existing anomaly detection technology stops alarming and cannot distinguish correlation and causality, so that root cause positioning is difficult. The core innovation of the invention lies in constructing a causal decoupling variational auto-encoder (CD-VAE) model, and learning a group of low-dimensional, independent and physical potential causal factor representations from high-dimensional industrial time series data. By introducing time sequence causal constraint and decoupling regularization, it is ensured that potential factors correspond to a key causal mechanism in the system. When an anomaly occurs, a fundamental causal factor, instead of a surface-related observation variable, which causes a fault is accurately positioned by calculating a variation score of posterior distribution of a potential factor and tracing a causal path of the potential factor. According to the method, the crossing from anomaly detection to root cause diagnosis is realized, and the operation and maintenance efficiency is remarkably improved.

The present invention includes: a preceding degree calculation unit (1) that calculates a degree of preceding of time series data xj of an item j with respect to time series data xi of an item i from a plurality of pieces of data; a similarity calculation unit (2) that calculates a semantic similarity between the time series data xi and the time series data xj; a surprise degree calculation unit (3) that calculates a degree of surprise indicating surprise of combining the item i and the item j on the basis of the degree of preceding and the semantic similarity; a causality testing unit (4) that tests causality of the item i and the item j; and a presentation unit (5) that presents the degree of surprise and presence or absence of the causality.

The present invention relates to a system (1) for enabling marketing teams to understand the reasons behind changes in subscriber"behavior better and to develop more effective campaign strategies by means of the technique of causality analysis.

The application discloses a method and system for improving video time retrieval performance based on counterfactual learning, inputting a video and a corresponding text query; extracting video features and text features; interacting and aligning the video features and the text features to obtain an encoder embedding; inputting the obtained encoder embedding into a counterfactual sample synthesis module to obtain a counterfactual encoder content embedding and a counterfactual encoder position embedding; obtaining a decoder output by using a Transformer decoder module; inputting the decoder output into a causality module to calculate a causal effect of the encoder embedding, and obtaining a causal representation. The causal table and the decoder output obtained from the encoder embedding are subjected to time sequence prediction to obtain a set prediction; the predicted result and the real label are subjected to supervised training, the influence of false correlation is effectively reduced, the generalization performance of the model on different distribution data is enhanced, and the model can more accurately locate a time segment related to a natural language query in the video.

The invention provides a network attack high-precision intelligent diagnosis method based on space-time causal fusion, which solves the problems of implicit feature interaction, sensitive noise, strong interference and the like in a traditional method through explicit space-time modeling, sub-tag feature optimization and hybrid factor dynamic suppression of a TAM matrix. Comprising the following steps: preprocessing network flow data, generating a space-time enhancement matrix, and explicitly coding a space-time causal relationship between features through a dynamic weight mechanism; based on a TAM matrix, spatio-temporal features are extracted through a time stream model and a spatial stream model, a time stream adopts a frame sequence differential capture attack evolution mode and extracts features through time sequence convolution, and the spatial stream analyzes a feature interaction structure through local convolution and an attention mechanism; an enhanced causal fusion module is designed, and in combination with hybrid factor suppression and adversarial training, false correlation is eliminated and model robustness is improved; spatial and temporal features are generated through double-flow feature extraction and a causal fusion mechanism, and a final attack diagnosis result is generated through DNN training.

The invention discloses a converter station important event diagnosis method based on correlation causal, comprising the following steps: collecting and preprocessing a converter station historical message, and carrying out SER event modeling; recording sequence events in the database, namely SER events occurring according to a time sequence, and mining association rules by utilizing an Apriori method according to the events, fault information and manual operation information; redundant rule pruning is carried out by using a confidence enhancement method, hybrid variable control is carried out on the pruned rule, and potential hybrid variables are eliminated; and finally, reducing the causal rule through an OR statistical causal method to obtain the causal rule of SER event occurrence during the fault occurrence period and the manual operation period. According to the method, redundant rule pruning and hybrid variable control links are introduced, the rules mined from the association rules are subjected to previous rule pruning, the event scale is reduced, the calculation pressure of OR during causal statistics is relieved, and the method is low in data demand and high in diagnosis accuracy.

The present application provides a method and device for dynamic rule adjustment of a digital human based on causality. The method comprises: obtaining historical data related to the interaction between the digital human and the user in a mixed reality scenario, wherein the historical data includes historical behavioral data and historical environmental data; determining the control step length and perception sliding window length of the digital human's behavioral decision based on the historical data, and constructing a behavior decision data matrix based on the control step length and perception sliding window length; performing causal structure extraction processing on the behavior decision data matrix to obtain a block matrix under causal constraints; generating a behavior adjustment rule set that satisfies the causal relationship based on the block matrix, and constructing a causality-driven multi-step behavior predictor based on the behavior adjustment rule set; and dynamically adjusting the behavior rules of the digital human based on the multi-step behavior predictor. The present application solves the technical problem that the digital human has poor adaptive behavior adjustment capabilities in complex interactive scenarios due to the lack of causal modeling.

The application provides a sequence-to-sequence text abstract generation method and system based on causality, and belongs to the field of natural language processing and automatic text abstract generation. The method is inspired by the causality theory, and studies the causality of various elements in the abstract task from the perspective of data generation. The method first introduces two unobservable variables to obtain a structural causal model of the abstract task; then, a corresponding sequence-to-sequence generation framework is obtained according to the structural causal model, which is used to model the generation process of the original text and the abstract. The framework includes three core modules: a double latent variable variational encoder, an original text reconstruction decoder and an abstract prediction decoder. The method not only has stronger explainability than existing end-to-end deep text abstract methods, but also has better abstract performance and stronger generalization ability. The method is a sequence-to-sequence framework with strong applicability, and therefore can be migrated to more model subjects, generation tasks and different data sets.

The application relates to the technical field of intelligent exploration, in particular to a gold mine target area prediction method and system based on metallogenic causality orientation, which is applied to gold mine target area prediction in a shallow coverage area and comprises the following steps: obtaining geophysical and geochemical data of a region to be predicted, inputting the geophysical and geochemical data into a target area prediction model, and obtaining a prediction result of whether the region to be predicted is a target area; wherein the target area prediction model is trained through the following steps: obtaining historical data of a target area; obtaining a historical metallogenic causality graph through a PCMCI algorithm based on a geological prior constraint set; performing causality feature extraction on the historical metallogenic causality graph to obtain corresponding causality orientation features; inputting the causality orientation features into the target area prediction model, optimizing model hyperparameters through a gradient descent algorithm, and obtaining a target area prediction model for predicting a gold mine target area in a shallow coverage area. The model has improved robustness and interpretability, and precise target area prediction in a shallow coverage area is realized.

According to the embodiments of the present disclosure, method and device for information processing are provided. This method comprises determining a group of target factors for a target object based on an unstructured text set about the target object. Each target factor represents an aspect of the target object. This method also comprises determining a causal-outcome event pair comprising a causal event and outcome event by analyzing the text in the text set. This method further comprises determining, based on the causal-outcome event pair, a first causality between a first factor in the group of target factors and a second factor of the target object. This scheme helps to improve the mining of causalities among the target object, thereby facilitating the improvement of the target object.

This invention discloses a method for discovering causal mechanisms based on time-series non-stationary causal mechanisms, comprising the following steps: S1: acquiring a dataset with known time-series non-stationary causal mechanisms and processing the dataset; S2: constructing a model for discovering time-series non-stationary causal mechanisms; S3: training the model for discovering time-series non-stationary causal mechanisms using the dataset to obtain a trained model for discovering time-series non-stationary causal mechanisms; S4: using the trained model for discovering time-series non-stationary causal mechanisms to discover causal mechanisms in data with unknown time-series non-stationary causal mechanisms. This invention utilizes state space and Gaussian processes to detect and discover causal mechanisms from time-series data containing non-stationary causal mechanisms, thus realizing the discovery of non-stationary causal relationships.

This invention relates to a method for interpolating missing values ​​in arch dam temperature field monitoring data based on causal and proximity effects. The method includes: distinguishing between complete temperature time series and temperature time series to be interpolated; determining whether each missing value segment of each temperature time series to be interpolated meets the linear interpolation criteria based on the location and relative change amplitude of the missing value segments; if it meets the criteria, performing linear interpolation; if it does not meet the criteria, establishing a prediction model that considers both causal mechanisms and proximity effects, and performing machine learning interpolation based on a multi-measuring-point stratification standard and a same-layer priority criterion. This invention can achieve efficient and accurate interpolation of missing values ​​in arch dam temperature field monitoring data.

The present invention describes a self-adaptive system capable of extracting correlations between multiple faults from net-work topologies, with the innovative component being the data preprocessing phase generating causality matrices to provide as an input to ML models. The proposed fault correlation system is responsible for, without any configuration, identifying the hierarchical relationships be-tween the multiple alarms, allowing for a better understanding of the causality and impact of each malfunction, hence assisting the implementation of RCA rules. This allows, not only for a huge dimensionality reduction of alarms needed to be processed by a TO's, but also significantly increases the knowledge about the topology, thus reducing downtime and increasing the quality of service of the network and services.

Embodiments of the present disclosure provide a method for determining causality, an apparatus for determining causality, an electronic device and a storage medium, and relates to a field of knowledge graph technologies. The method includes: obtaining event words expressing individual events and related words adjacent to the event words in a target text; inputting the event words and the related words into a graph neural network; and determining whether there is a causal relationship between any two events through the graph neural network.

The application discloses a method and device for realizing causality mask in large model inference, equipment and medium, relates to the technical field of self-attention mechanism, and the method comprises the following steps: after a vector-matrix operation is completed by VMPE, the operation result is sent to SFU; the input data is acquired by SFU receiving the cmd command sent by FW; the acquired input data is processed based on preset bit operation mask operation, and then the Softmax operation is performed; wherein, the hardware implementation architecture comprises VMPE responsible for processing vector-matrix operation, SFU responsible for processing other vector operation, and FW running on RISC-V CPU and used for controlling the work of DMA, VMPE and SFU. According to the application, the mask matrix does not need to be constructed in advance, so that the storage space is effectively saved.

The application discloses a kind of causality effect robustness test methods based on counter disturbance, it is related to geological disaster risk analysis technical field, including: based on causal inference method obtains the causal factor of geological disaster prediction model, associated factor, and the causality effect index of corresponding factor;Factor disturbance space with physical rationality constraint is constructed, and the value range of factor disturbance amount is defined;Zero-order optimization counter attack method is used to generate factor-level counter disturbance samples in factor disturbance space;The model output variation and the causality effect variation before and after factor applies counter disturbance are calculated, and factor-level counter robustness index is obtained;Causal robustness index is constructed, and the reliability evaluation and classification of causal factor are completed.The application solves the problems that the existing technology lacks robustness verification of causal effect, the causal factor may be affected by counter disturbance and fail, lacks causal robustness evaluation system of factor level and cannot identify pseudo-causality in causal inference result.

The invention discloses a traditional Chinese medicine intelligent tongue diagnosis method based on a causal relationship, a medium and equipment, and belongs to the technical field of intelligent medical treatment. The method comprises the steps that a causal generation type tongue diagnosis model is constructed, the causal structure of the model comprises a potential physiological state, a tongue picture feature and a tongue picture observation and diagnosis result four-element group, and a one-way causal direction from the potential physiological state to the tongue picture feature and then to the tongue picture observation and diagnosis result is preset; constructing a causal inference encoder, and inferring a first potential physiological state from the original tongue picture observation data along a causal reverse direction; constructing a mechanical decoder, and generating tongue picture characteristics and tongue picture observation data from the first potential physiological state along a causal positive direction in combination with the environmental noise; and constructing a diagnosis classifier, and generating a syndrome classification result according to the first potential physiological state. According to the method, through a cause and effect mechanism of explicit modeling tongue picture generation, model learning is guided to accord with real association of traditional Chinese medicine pathology, and reliability, robustness and interpretability of tongue diagnosis analysis can be effectively improved.