51 results about "Causal knowledge" patented technology

The present invention provides a system and method for causality-augmented generative intelligence capable of autonomously discovering non-obvious actionable insights from heterogeneous and multimodal data sources. The system integrates a data ingestion unit for semantic and temporal harmonization of structured and unstructured datasets, a causal inference processor for constructing a dynamically evolving directed causal knowledge representation using perturbation-based validation, a latent representation processor that combines multimodal semantic embeddings with causal parameters to generate fused latent vectors, and a generative insight processor utilizing causally constrained generative reasoning to synthesize hypotheses anchored to verified cause-effect dependencies. A validation processor performs counterfactual assessment and observational verification to ensure retention of only those insights that remain consistent with causal ground truth.

The invention belongs to the technical field of automatic driving testing, and particularly relates to an interpretable automatic driving decision-making method based on causal knowledge. Comprising the following steps: step 1, discovering causals oriented to automatic decision knowledge; 2, constructing an interpretable automatic driving decision model; 3, evaluating the interpretability of the automatic driving decision-making system; and 4, evaluating the performance of the automatic driving decision-making system. The method comprises four steps of causal discovery for automatic driving decision-making knowledge, construction of an interpretable automatic driving decision-making model, evaluation of the interpretability of the automatic driving decision-making system, and evaluation of the performance of the automatic driving decision-making system. Based on a causal discovery model of decision observation data, key variables of a causal relationship influencing self-vehicle driving behaviors are found from the data, an interpretability standard and a decision performance evaluation index are defined, the interpretability and decision performance of an automatic driving decision system are evaluated, and the automatic driving decision system is continuously optimized and iterated.

The invention discloses a beneficiation process intelligent optimization control method and system based on a knowledge graph, and relates to the technical field of beneficiation process control, and the method comprises the steps: collecting static attribute data and dynamic operation data, constructing a causal knowledge graph, and obtaining a causal relationship between nodes in the causal knowledge graph and an optimization target constraint; based on a causal relationship between nodes in the causal knowledge graph and optimization target constraints, screening data from a historical database to form a high-value historical data set; according to the high-value historical data set, a reward function model is constructed, a strategy function is trained, and a reinforcement learning control strategy is obtained; running the reinforcement learning control strategy, generating a control instruction, and issuing the control instruction to the target equipment to obtain dynamic optimization control; and performing real-time monitoring on the dynamic optimization control, and performing anti-fact reasoning based on a causal knowledge graph when abnormal deviation of the running state is detected to obtain an anti-fact reasoning result.

The computer fault diagnosis method based on the causal reasoning and mapping knowledge domain hybrid architecture comprises the steps of obtaining and processing multi-source heterogeneous data of an embedded computer, constructing a system mapping knowledge domain integrating the multi-source data of the embedded computer, and forming a knowledge base containing components, functions, fault phenomena and association relationships thereof; the method is characterized in that a causal reasoning engine is designed, domain knowledge constraints are utilized, a real cross-level fault propagation causal chain is mined from atlas association, and root causes are verified through anti-fact reasoning. And the engine dynamically feeds back the mined causal knowledge to the atlas, so that the causal knowledge is continuously optimized. According to the hybrid architecture, accurate and rapid tracing with causal explanation from a fault phenomenon to a root cause is realized, and the diagnosis capability in high-reliability fields such as aerospace and industrial control is remarkably improved.

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.

The invention relates to the technical field of Internet of Things monitoring, and provides an Internet of Things monitoring system and method, and the method comprises the steps: synchronously obtaining a valve position signal, a current signal and a vibration signal, extracting features, combining a valve position change rate as a weight, fusing the features of multiple signals, and carrying out the mapping output of a health feature vector; embedding the health feature vector into a causal knowledge graph, reasoning the causal knowledge graph through a graph neural network, and outputting a fault occurrence probability, residual life and a causal path; a part degradation model is integrated in digital twinning, different candidate maintenance strategies are simulated and deduced, and multi-target cooperation is realized through a target optimization algorithm, so that maintenance strategy one-sidedness caused by single dimension and fixed working conditions is avoided; after the maintenance strategy is executed, the actual performance track is generated and compared with the change track of the residual life to obtain the track deviation, parameters of the graph neural network and the component degradation model are adaptively corrected based on the track deviation, long-term stable operation of monitoring is guaranteed, and the manual operation and maintenance cost is greatly reduced.

The invention belongs to the technical field of knowledge graph construction, and particularly relates to a transformer operation inspection-oriented causal relationship enhanced knowledge graph construction method and system. According to the method, information in a transformer fault processing text is deeply mined, a natural language processing technology and a deep learning algorithm are utilized, and accurate recognition and relation extraction of key entities such as fault description, reasons, phenomena, detection methods, detection results and operation and maintenance suggestions are achieved. Structured knowledge is organized and stored in a graph database, and a comprehensive, deep and easy-to-query transformer fault operation and maintenance knowledge graph is formed. By introducing a causal scientific theory, the causal relationship in the knowledge graph is remarkably enhanced, fault operation and maintenance causal knowledge with a more stable causal effect is formed, the accuracy and robustness of the causal relationship in the knowledge graph are improved, and operation and maintenance personnel can more intuitively understand complex association between fault phenomena and reasons.

The invention discloses a geological mineralization causal knowledge extraction method, a storage medium, equipment and a product, and relates to the field of geological mineralization, and the method comprises the steps: constructing a causal hypothesis of a causal role from an unstructured geological text; constructing a causal data set based on causal hypothesis, and training the natural language inference model by using the causal data set; wherein the input vector of the causal data set and the vector of the causal role are fused to form the input vector of the model; a bias matrix of a causal role is introduced to calculate a self-attention weight; obtaining gating weights of the causal role and the global context based on [CLS] embedding, and performing weighted summation on embedding of the causal role and [CLS] embedding by using the gating weights to obtain a final fusion representation; and identifying a high-confidence causal chain from the geological text by using the trained model to obtain a typical causal mode related to the specific mineralization. According to the invention, the chain type identification of the complex mineralization mode can be realized.

The invention discloses an accident scene reasoning method and device. The method comprises the following steps: extracting a causal relationship mention from historical data and constructing a causal relationship mention data set; the historical data records cause events and result events of historical accidents; the causal relationship mention represents a text containing a causal relationship pair; the causal relationship pair comprises a cause event and a result event which are associated with each other; analyzing the causal relationship mentions in the causal relationship mention data set into causal events; based on the causal events, integrating at least two common causal events to form a generalized causal event network; and reasoning an accident to be analyzed based on the generalization causal event network. According to the accident scene reasoning method constructed by the invention, valuable causal knowledge can be mined from a large number of English accident reports, and a useful tool capable of predicting future accidents can be formed.

The invention relates to the technical field of intelligent exercise training, and particularly discloses a causal knowledge-driven man-machine collaborative personalized exercise training case reasoning method, which comprises the following steps of: constructing a case library containing a plurality of cases, and performing causal knowledge reconstruction at different levels; searching a case most similar to the target case from a case library based on the weight of each description variable; the difference of training scheme variables between the target case and the retrieved similar cases is recognized, anti-fact intervention and inference of any training scheme variable are conducted on the target case, and one or more new cases are screened out; when an actual result generated after the new case is executed does not conform to expectation, executing an attribution process, and generating different processing suggestions according to attribution types; new cases which do not conform to expectation are stored in a case library, and causal knowledge reconstruction is periodically carried out. According to the method, causal science and human-computer interaction can be deeply fused to carry out personalized training scheme reasoning.

The invention discloses a causal knowledge graph construction and question-answering system based on retrieval enhancement generation and a large language model. The system comprises a multi-source heterogeneous knowledge base construction module, a retrieval enhancement generation module, a named entity recognition and causal triple extraction module and a knowledge fusion reasoning module, according to the method, a high-quality named entity annotation data set and a causal data set are constructed, and normalization and integrity of input knowledge are guaranteed; a mixed retrieval strategy (keyword + vector + sparse embedding) is provided, and the evidence coverage rate and recall precision are improved. Under RAG driving, LLM is combined, two rounds of causal triple extraction are achieved, and the causal relationship coverage degree and the direction judgment confidence degree are improved; a conflict detection and atlas fusion mechanism is designed to ensure the unity and consistency of new and old causal knowledge; a question answering system based on a causal atlas is also established, multi-hop causal reasoning is supported, and answers with controllable credibility and explainable are output.

The invention discloses a fine tuning method, system and equipment for an electric power intrinsic safety analysis model based on knowledge distillation, and a medium, and belongs to the technical field of electric power safety analysis. The method comprises the following steps: collecting professional knowledge data in the field of electric power intrinsic safety analysis, and performing professional knowledge supervision fine tuning to obtain a distillation model; and guiding an output thinking process and a root cause based on problem description through the distillation model, and introducing a super model and a causal knowledge graph for evaluation to obtain an evaluation result. Through combination of knowledge distillation and the causal knowledge graph, the accuracy and interpretability of an electric power intrinsic safety analysis inference model are remarkably improved, the thinking process and the root cause of problem description are generated through the distillation model, output is evaluated by using the super model and the causal knowledge graph, the causal inference ability is enhanced, and the accuracy and the interpretability of the electric power intrinsic safety analysis inference model are improved. The problem that the causal relationship of a traditional model is fuzzy in complex power accident analysis is effectively solved.

This application discloses a data prediction method, apparatus, device, storage medium, and computer program product, relating to the fields of artificial intelligence and data processing technology. Embodiments of this application can be applied to fields such as mapping and transportation. The method includes: acquiring a universal causal graph to characterize causal knowledge prevalent in different regions, whereby the causal knowledge characterizes causal relationships between attributes of different regions; based on the universal causal graph and observation data of a target region, acquiring the full range of regional attributes corresponding to each region in the target region, including unobserved regional attributes; and based on the full range of regional attributes corresponding to each region in the target region, acquiring predicted values ​​for object flows between regions in the target region. This application solves the problem of inaccurate object flow prediction in some regions due to a lack of observation data, thus improving the accuracy of object flow prediction.

The application provides a causal knowledge graph driven large model cross-knowledge base autonomous retrieval method and system, and relates to the technical field of data processing. The method introduces a causal knowledge graph as a core navigation mechanism for retrieval and reasoning, enabling intelligent retrieval driven by causality in a complex field knowledge environment; by decomposing complex causal analysis tasks into a series of structured and executable cross-knowledge base retrieval subtasks, a fundamental change from passive information retrieval to active causal discovery is achieved; under this mechanism, the application can not only automatically plan a retrieval path according to causal dependency relationships, but also dynamically coordinate and evidence fuse between multi-source heterogeneous data, thereby forming a logically consistent and time-sequentially reasonable causal explanation chain; the application effectively solves the core technical problems of scattered causal evidence, heterogeneous knowledge sources, and incomplete reasoning chain in complex field information analysis, greatly improving the level of intelligence and the level of retrieval explainability.

The invention discloses a decision-making method and device based on a causal knowledge graph, electronic equipment and a medium. The method comprises the steps of obtaining a policy file to be processed; inputting the to-be-processed policy file into a causal knowledge graph, and determining an economic index corresponding to the to-be-processed policy data; wherein the causal knowledge graph is constructed based on a causal association relationship between historical policy documents and historical economic indicators. According to the technical scheme, the causal knowledge graph with the space-time causal reasoning ability is constructed, the causal discovery algorithm and the dynamic updating mechanism are introduced, the causal association relation and the causal mechanism are accurately distinguished, and the chain influence of policy implementation is simulated; meanwhile, based on the causal enhanced data preprocessing and multi-modal data causal alignment technology, the multi-source heterogeneous data processing obstacle is solved, effective integration of policy documents and economic indicators and causal feature extraction are achieved, then effect deduction is carried out on the policy documents to be processed by means of a causal knowledge graph, and the policy document processing efficiency is improved. The long-term influence on the economic indexes is predicted; and early warning is provided.

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 application relates to the technical field of Internet of Things monitoring, and provides an Internet of Things monitoring system and method, wherein a valve position signal, a current signal and a vibration signal are synchronously acquired and features are extracted, the features of the multiple signals are fused by taking a valve position change rate as a weight, and a health feature vector is output by mapping; the health feature vector is embedded into a causal knowledge graph, the causal knowledge graph is reasoned by a graph neural network, and a fault occurrence probability, a residual life and a causal path are output; a component degradation model is integrated in digital twinning, different candidate maintenance strategies are simulated and deduced, a multi-objective coordination is realized by a target optimization algorithm, and the one-dimensionality and the fixed working condition of a maintenance strategy are avoided; after the maintenance strategy is executed, an actual performance track is generated, is compared with a change track of the residual life to obtain a track deviation, parameters of the graph neural network and the component degradation model are adaptively corrected based on the track deviation, long-term stable operation of monitoring is ensured, and the cost of manual operation and maintenance is greatly reduced.

The invention provides an event causal identification method and device based on dynamic relation graph convolution, equipment and a medium. The method comprises the following steps: constructing an encoder to extract overall representation characteristics of each event in an event text; splicing the features of the event pair to obtain a spliced feature, and obtaining a preliminary causal probability value of the event pair through a causal probability preliminary prediction module; based on the constructed dynamic relation graph convolutional network, event pair interaction features are obtained; obtaining explicit causal features of the event based on an explicit causal mining module; utilizing a multi-granularity implicit causal matching mechanism to obtain implicit causal features; and finally, event causal identification is realized through a full-connection network, and the causal relationship and the causal probability value of each event pair in the event text are obtained. According to the method, the interaction relationship between the event pairs can be fully extracted, the causal information is mined and displayed, and the accuracy of event causal identification is improved by utilizing multi-granularity implicit causal knowledge.

The application discloses a water bloom prediction method based on timing causal knowledge guidance, and belongs to the fields of deep learning and environmental monitoring. The method collects multi-source data through water quality monitoring stations and weather stations, extracts a multi-dimensional causal adjacency matrix by using convergent cross-mapping and PCMCI methods, and constructs an encoder composed of parallel variable channels, CCM channels and PCMCI channels. Each channel hard-codes the causal structure to the feature space through a graph convolutional causal coding module, then adaptively adjusts the causal constraint strength through a soft constraint causal attention module, and finally dynamically fuses the channel features through a multi-channel adaptive fusion mechanism, and outputs a prediction value of chlorophyll a concentration through a projection layer. The application significantly improves the mechanism interpretability of the model while ensuring the prediction accuracy, and provides a scientific and effective means for water bloom disaster warning and water environment management.

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 invention relates to the technical field of port engineering facility safety and intelligent operation and maintenance, and discloses a steel berthing member full-life-cycle maintenance decision-making system which firstly integrates multi-source data through a data fusion module to sense the state of the system. The core is that the causal knowledge graph module is used for accurately predicting the consequence of maintenance intervention by constructing a causal network between system variables; meanwhile, the reward reconstruction engine utilizes inverse reinforcement learning to dynamically convert strategic preferences input by human managers into quantitative reward functions. The policy optimization engine then calculates an optimal maintenance policy based on the reward function and the causal model. Finally, the decision interaction module not only presents the optimal suggestion, but also can provide clear and credible decision attribution explanation based on the causal chain. According to the method, the conversion from black box recommendation to white box decision is realized, and the self-adaptability, transparency and man-machine cooperation efficiency of the maintenance decision are remarkably improved.

The application discloses an accident scene reasoning method and device, the method comprises the following steps: extracting a causal relationship mention from historical data and constructing a causal relationship mention dataset; the historical data records the cause event and the result event of the historical accident; the causal relationship mention represents the text containing the causal relationship pair; the causal relationship pair includes the cause event and the result event related to each other; the causal relationship mention in the causal relationship mention dataset is parsed into a causal event; based on the causal event, at least two causal events with commonality are integrated to form a generalized causal event network; and the accident to be analyzed is reasoned based on the generalized causal event network. The accident scene reasoning method constructed by the application can mine valuable causal knowledge from a large number of English accident reports, and form a useful tool capable of predicting future accidents.

The embodiment of the invention relates to the technical field of operation and maintenance, and discloses a causal knowledge graph automatic construction method, device, equipment and medium, the method comprises the following steps: obtaining time sequence data corresponding to a historical time period, the time sequence data comprising a scene identifier, the scene identifier being used for identifying a peak scene and an off-peak scene, and the time sequence data being time sequence data corresponding to different services; performing data feature classification on the time series data to obtain a data type corresponding to the time series data; performing causal mining on the time series data based on a causal mining algorithm corresponding to the data type to obtain at least one causal relationship, and obtaining at least one corresponding causal weight, the causal relationship being a causal relationship between different services; and constructing a causal knowledge graph based on the at least one causal relationship and each corresponding causal weight. Correlation analysis is replaced by time sequence driven causal inference, so that false correlation interference can be eliminated, and the accuracy of the determined causal relationship is improved.

The invention discloses a hydropower station trend analysis and professional report generation system and method based on an intelligent agent and a large language model, and belongs to the technical field of hydropower station intelligent operation and maintenance and data analysis. The system comprises a data perception and execution layer, an agent scheduling and analysis layer, a professional report generation layer and a dynamic causal knowledge base. The method comprises the following steps: analyzing a user instruction through a scheduling agent and scheduling a tool to perform preliminary analysis; the analysis agent queries a dynamic causal knowledge base based on the preliminary anomaly to generate a cross-device causal hypothesis, and autonomously schedules a tool to perform data verification; and finally, synthesizing a structured diagnosis report containing a core diagnosis conclusion, an evidence chain and operation and maintenance suggestions by a professional report generation layer by utilizing a large language model. According to the method, the defect that only isolated data description can be carried out in the prior art is overcome, the crossing from'phenomenon description 'to'disease cause diagnosis' is realized, and the analysis depth and decision support value of the report are remarkably improved.

The invention discloses a bridge report generation method and system based on multi-modal causal and reinforcement learning. The method comprises the following steps: acquiring a disease image and text description, extracting structured disease information from the text description, generating multi-modal feature data, and performing image-text consistency verification; retrieving standard articles and historical cases based on the verified disease information, and positioning disease nodes in the causal knowledge graph and reversely tracing root cause nodes to generate a reasoning chain; fusing the multi-modal feature data, the retrieval result and the reasoning chain, generating an evaluation report draft through a large language model, and performing logic verification; and obtaining an expert correction text, inputting the expert correction text into the reward model, calculating a feedback score, and optimizing a knowledge graph edge weight and a report generation strategy. The invention also provides a system for realizing the method. According to the method, through image-text consistency verification, causal reasoning and reinforcement learning, the report accuracy, interpretability and compliance are effectively improved.

Provided in the embodiments of the present disclosure is a method and device for event extraction based on causal knowledge constraints, which comprises constructing a causal graph of an event text to obtain a causal strength matrix of feature data of the event text; constructing a question template of an event argument according to a type of the event; combining the question template and the event text and encoding, and inputting the encoded sequence into a BERT model to take the hidden state of the last layer as a semantic representation of the input sequence; applying a self-attention weight matrix to weight the semantic representation of the input sequence to obtain a weighted output; comparing the causal strength matrix and the self-attention weight matrix to obtain a causal loss term; and combining the causal loss term to define a loss function to obtain an answer to a question according to the weighted output. Through the processing scheme of the present disclosure, the interpretability of the model is improved.

The application discloses a method and system for causal reasoning and counterfactual question answering based on a large language model and a storage medium. The method comprises the following steps: providing a dynamic causal knowledge graph, which contains causal tuples and state variables and state transformation functions of entity nodes; when receiving a counterfactual reasoning query, extracting an intervention variable, an intervention time point and a target variable, identifying all causal paths from the intervention variable to the target variable, calling a state deduction engine of a large language model to simulate and deduce a state evolution trajectory, generating a counterfactual answer and outputting a causal path explanation and a visualized causal graph; and supporting causal attribution queries and time series prediction queries. Through the combination of the dynamic causal knowledge graph and the state deduction engine of the large language model, the application can effectively perform counterfactual reasoning, causal attribution and time series prediction, and significantly improves the causal reasoning capability and answer accuracy of the question answering system in dynamic change scenarios and complex decision-making requirements.

This invention discloses a method and system for predicting the overload rate of distribution transformers based on multi-source data fusion, relating to the field of load forecasting technology. The method includes the following steps: acquiring transformer operation data for a target area and constructing a knowledge graph; extracting entities and features from the knowledge graph that have causal paths with the target transformer's overload event, generating a feature tensor; embedding the knowledge graph using a graph neural network, and inputting the graph embedding and feature tensor into a time series prediction model to construct a joint prediction network; simulating intervention on the input variables based on causal reasoning methods and evaluating the strength of the impact on the prediction results; outputting the predicted overload rate value of the target transformer for future time periods based on the strength of the simulated intervention, and generating the main causal paths leading to changes in the predicted value. This application achieves accurate and interpretable prediction through multi-source data fusion and a causal knowledge graph.

The invention relates to the technical field of new energy vehicles, and particularly discloses a power battery abnormity monitoring method and system suitable for a new energy vehicle. The power battery abnormity monitoring method suitable for the new energy automobile comprises the following steps: constructing a structural causal model of a power battery system, and fusing expert domain knowledge and historical abnormal cases into a causal knowledge graph; a causal structure learning algorithm based on continuous optimization is adopted, and a causal relationship is automatically found from battery time sequence data; performing multi-level causal reasoning by using an anti-factual reasoning technology, and distinguishing a direct causal relationship and an indirect causal relationship; generating a causal relationship explanation, and mapping the discovered causal relationship to a battery physical mechanism and a fault mode; through an interactive causal exploration interface, an expert is supported to correct and perfect a causal graph. According to the invention, by fusing the data driving capability of the neural network and the logicality of symbol reasoning, the abnormal root cause of the battery is accurately identified, professional explanation is provided, and continuous optimization of causal knowledge of man-machine collaboration is realized.