48 results about "Causal reasoning" patented technology

The invention relates to a system (100) for generating real-time causal reasoning insights in real time. The system (100) comprises a global causal graph creation module (101), a natural language query processing module (102), an information extraction module (103), a query-centric subgraph generation module (104), and an adaptive causal reasoning engine (105). The queries from users are processed to identify relevant causal relationships in the global causal graph. The adaptive causal reasoning engine (105) refines the insights iteratively based on user feedback, improving accuracy. The system (100) converts technical insights into structured narratives. A visualization module presents causal relationships through graphs and charts. The feedback mechanism allows users to correct errors and adjust outputs, facilitating user-driven data analysis and causal reasoning, delivering actionable insights for a variety of applications.

This invention discloses a production line modeling and real-time data-driven quality deviation prediction method for process inspection, comprising: employing a forward causal reasoning mechanism to calculate the transfer function step by step along the path based on the overall causal relationship layer, obtaining the expected value and deviation probability prediction of the target process quality index; periodically adaptively optimizing the parameters of the causal relationship layer model based on the cause node list and historical data loop, using machine learning algorithms to enhance parameter accuracy, and determining the optimized parameter set; updating the digital model structure by optimizing the parameter set, incorporating enhanced causal relationships during subsequent real-time data acquisition, and obtaining a more accurate transfer function representation; re-performing causal reasoning and deviation prediction based on the accurate transfer function representation, judging the overall production line quality status, and obtaining the final deviation control basis.

The application relates to an excitation system fault recording and event record analysis and diagnosis method and system, belonging to the field of excitation systems. The method comprises collecting recording files and event sequence records of the excitation system; performing multi-domain feature extraction based on the recording files to obtain a multi-domain feature tensor; performing space-time causal structure learning based on the multi-domain feature tensor and the event sequence records to output a causal adjacency matrix, a causal diagram and a time delay matrix; performing double-channel interpretable fault classification based on the multi-domain feature tensor, the causal diagram and an event time tag list E in the event sequence records to output a fault type label M and an attention space-time heat map; performing counterfactual causal tracing to obtain a root cause variable set and a causal propagation path, and outputting a diagnosis report. The application realizes intelligent diagnosis of the excitation system with signal analysis capability, causal reasoning capability and diagnosis interpretability.

The application is suitable for the technical field of artificial intelligence and medical health, and provides a postpartum depression intelligent screening and early intervention system and method, which comprises a whole life cycle management module for managing continuous data flow and state transition; a physical entity layer for collecting physiological data of puerpera, mother-infant behavior interaction data and environmental semantic data; a digital twin layer for constructing a dynamic virtual mapping model, the model comprising a causal graph model based on a structural causal model and a time sequence evolution mechanism; an application service layer for generating and pushing a risk early warning, an attribution analysis and a self-adaptive intervention scheme based on causal reasoning in stages; through causal reasoning instead of correlation analysis, the early warning accuracy is improved, the digital twin layer constructs a puerpera-baby binary group dynamic mapping based on a structural causal model, and through a directed acyclic graph to quantify the causal relationship between variables and combine Monte Carlo tree search to deduce the future risk probability, compared with a traditional scale, high-risk events such as self-harm thoughts can be early warned.

The application discloses a fault root cause positioning method, device, equipment and readable storage medium, the method comprises determining a plurality of source abnormal characteristics; acquire the field knowledge graph; retrieve analysis basis from the field knowledge graph; utilize the preliminary screening layer, combine the analysis basis to carry out root cause tracing, generate root cause reasoning process and reasoning complexity score; when the reasoning complexity score is lower than the complexity threshold, the conclusion generation layer is utilized to generate the root cause analysis report; when the reasoning complexity score is not lower than the complexity threshold, the deep reasoning layer is called to carry out deep causal reasoning, generate reasoning train of thought and root cause propagation path; the conclusion generation layer is utilized, and the root cause analysis report is generated based on the reasoning train of thought and the root cause propagation path. It can be seen that the application can improve the reasoning efficiency and the fault root cause positioning rate through the hierarchical reasoning architecture and the field knowledge graph, clearly present the reasoning train of thought of different difficulty faults, and improve the credibility and verifiability of various fault root cause positioning conclusions.

This invention discloses a method and system for coal mine safety risk assessment based on causal subgraph enhancement and LLM dynamic completion. The method includes: 1. Acquiring textual data in the field of coal mine safety and constructing a knowledge graph; 2. Extracting entities based on user queries and selecting initial triples in the knowledge graph through semantic relevance scores; 3. Expanding reachable triples using breadth-first search to construct an initial causal subgraph; 4. Performing causal reasoning and dynamic completion on the subgraph using a Large Language Model (LLM) to generate an enhanced complete causal subgraph; 5. Finally, generating an interpretable coal mine safety risk assessment report using LLM. This invention aims to solve the problems of missing causal logic and knowledge illusion in existing coal mine risk assessments by improving the accuracy of risk assessment through causal subgraph enhancement technology.

This invention provides a method for injecting industrial knowledge based on retrieval enhancement, belonging to the field of industrial knowledge technology. This invention establishes a time-series data flow matrix by collecting multi-source heterogeneous data, constructs a time-series causal knowledge graph using Granger causality tests, establishes an industrial knowledge document library with a hybrid index structure, performs time-series-aware query expansion on the query input, performs a hybrid retrieval of dense vectors and sparse inverted indexes and cross-encodes and reorders the data, associates the refined documents with the time-series causal knowledge graph to extract event evolution paths and fuses them to generate a time-series enhanced knowledge representation, inputs it into a time-series knowledge enhancement model to generate answer text containing fault analysis and prediction suggestions, injects it into an industrial decision support system after quality assessment, and stores feedback data for continuous model optimization. This solves the technical problem of industrial knowledge retrieval being disconnected from real-time temporal status, resulting in a lack of time-series causal reasoning ability in the generated answers.

This invention provides a method for safety alignment assessment of large industrial models, belonging to the technical field of large industrial models. This invention collects multi-dimensional parameter time-series data of industrial systems and establishes a physical constraint rule base. It combines Gaussian process regression and Bayesian optimization to search for a dynamic safety boundary point set, establishes a structural causal model, performs do-of-fact calculus and counterfactual reasoning to extract causal inference chains, and inputs the boundary robustness index and causal inference chains into a spiral progressive network structure safety boundary alignment model to output an alignment score. Through temporal continuity analysis, alignment spikes are detected, and a reverse alignment correction process is initiated to adjust the physical constraint weight coefficients. This solves the technical problem of unstable alignment assessment in large industrial models due to the lack of physical mechanism constraints and causal reasoning capabilities during safety boundary identification.

To address the problems existing in the prior art, this invention provides a method and system for causal analysis of power system safety events. The system executes the steps of the method, which includes: Step 1: Based on the identified system hazard information, a hierarchical and progressive retrieval strategy is employed to dynamically generate a query sequence adapted to the system hazard information, thereby achieving hierarchical derivation of system safety constraints. Step 2: LLMs are guided to perform deep and systematic causal reasoning on power system safety events, thereby systematically identifying comprehensive causes ranging from physical component failures to organizational decision-making deficiencies. Step 3: A feedback verification method combining counterfactual reasoning and logical consistency verification is used to double-verify the intermediate results and the final comprehensive causes output in Step 2. This invention systematically improves the accuracy, reliability, and structured output capability of large language models in complex causal mining during power system safety event causal analysis.

This invention relates to a causal consistency long-chain reasoning method based on structured semantic parsing, comprising a semantic structured representation module for decomposing complex tasks into structured semantic units with causal relationships; a causal consistency reasoning module, which mainly constructs a multi-stage causal reasoning graph to logically model and divide the task execution path into stages; and a path evaluation and error correction module, which performs confidence evaluation and logical verification of intermediate states during the reasoning process. This invention constructs a causal consistency long-chain reasoning mechanism based on structured semantic parsing, achieving interpretability of reasoning steps, verifiability of process logic, and error-correcting capability of the reasoning path through structured modeling of the reasoning process.

The application discloses an industrial defect detection method based on causal feature enhancement, relates to the technical field of industrial visual detection, and constructs a structural causal model of industrial defect formation and obtains a causal diagram; collects an industrial component surface image and performs pretreatment to obtain an input image; the input image is input into a backbone network of a target detection network to extract multi-scale backbone features; a causal attention map is calculated according to causal variables, i.e., environmental variables and image gradient information; the backbone features are subjected to causal feature enhancement based on the causal attention map to obtain causal enhanced features; the causal enhanced features are input into a neck network and a detection head of the target detection network, and a defect bounding box, a defect category and a confidence are output. Through the introduction of the causal reasoning and feature enhancement mechanism, the application realizes high-precision and high-robustness industrial defect detection.

This invention discloses a large-model-driven method and system for constructing a building knowledge graph. It generates a terminology feature library by differentially annotating unstructured building document data with semantics; based on the terminology feature library, it detects cross-document conflicts to generate a set of conflicting knowledge points; and constructs a building knowledge graph through cross-source semantic difference quantification and difference-oriented knowledge fusion using a large language model. It identifies knowledge backlog nodes and marks weak knowledge areas through topological structure analysis, and injects graph knowledge vectors in a targeted manner to generate a knowledge-enhanced control model. Based on the knowledge-enhanced control model, it executes bidirectional causal reasoning of the HVAC system to generate a decision reasoning chain, and outputs interpretable control decisions after violation of aggregation patterns identification and weight reduction processing. It generates behavioral deviation values ​​based on the comparison between equipment behavior data and the deviation of the decision reasoning chain, and triggers adaptive reconstruction of the building knowledge graph through hierarchical over-limit identification, achieving continuous accumulation of building knowledge and steady improvement in the quality of HVAC control decisions.

A method and system for managing a device knowledge base based on a knowledge graph, relating to the field of big data resource services, is disclosed. The method includes: preprocessing and cross-validating multimodal data within the device knowledge base to obtain structured knowledge units; constructing a device knowledge graph based on these structured knowledge units; responding to user-input queries, recalling structured facts corresponding to the query, and retrieving unstructured document evidence from the multimodal data; constructing a contextual knowledge set as a fact closure based on the structured facts and unstructured document evidence; constructing an explicit causal reasoning chain based on preset causal rules and the fact closure corresponding to the device knowledge base; and constructing controlled prompt words by combining the query, the fact closure, and the causal reasoning chain, and inputting the controlled prompt words into a large language model to generate the query answer. Implementing this application can improve the accuracy of knowledge retrieval services.

The application discloses an AI robot dialogue understanding method based on causal reasoning, comprising the following steps: obtaining user dialogue text, and splitting semantic roles, event elements, emotional expressions and key sentences into semantic microparticles; establishing a semantic charge conservation constraint in a semantic microparticle set, and adaptively adjusting microparticle charges; generating causal bias change information for the semantic microparticles, and updating the moving trend of the microparticles in the semantic space; constructing a semantic microparticle density field, identifying a semantic area with a density exceeding a threshold, and determining the semantic meaning corresponding to the area as the user intent of the current dialogue; and generating a robot action instruction or a natural language reply matched with the user intent and the moving trend of the semantic microparticles in the area. The application realizes fine-grained semantic tracking and stable robot response generation in multi-round dialogue by splitting dialogue text into semantic microparticles and applying a semantic charge conservation and causal bias driving mechanism.

To address the problems existing in the prior art, this invention proposes a multi-agent collaborative accident causal chain mining method, specifically including the following steps: decomposing the received task into an accident cause identification subtask and a causal chain identification subtask. Specifically, the cause analysis agent and the counterfactual reasoning agent collaboratively execute the accident cause identification subtask, while the causal chain reasoning agent independently executes the causal chain identification subtask, using the identified accident causes as input for causal reasoning to reconstruct the causal chain. In detail: the cause analysis agent parses the input task text to identify the accident causes contained within, and uses the identification results as input for the causal chain identification subtask; the counterfactual reasoning agent evaluates the necessity and sufficiency of the direct causes obtained by the cause analysis agent based on the accident case text. This invention, through a multi-agent collaborative mechanism, effectively enhances the ability to extract task-related information, thereby reducing the probability of misjudging accident causes.

The wisdom heating full-dimensional perception and decision assistance system and method based on a large model of the present application comprise the following steps: constructing a multi-modal heterogeneous data perception and preprocessing network; performing semantic alignment and unified representation of multi-modal features, extracting feature vectors of heterogeneous data through respective modal dedicated encoders; performing retrieval enhancement generation based on space-time constraints, retrieving matching disposal plans and mechanism knowledge in the pre-constructed heating field knowledge base and historical case base according to the fusion context vector corresponding to the current working condition; performing causal reasoning and decision generation based on thought chains, comprehensively analyzing the fusion context vector and the enhanced prompt context by using a large-scale pre-trained language model; and performing decision closed-loop optimization based on human feedback. The present application realizes the continuous accumulation of knowledge assets; and the special cold start strategy and online evolution mechanism ensure that the system can be quickly put into operation and produce actual benefits in old pipe networks or newly built areas with missing data.

This application discloses an event evolution reasoning and prediction method based on cognitive-driven intelligent generation. First, it utilizes a domain-wide language model to extract expert knowledge points, analysis processes, analytical perspectives, and logical reasoning from event research reports, constructing an interactive thought chain. It then extracts causal reasoning and constructs a causal reasoning network structure. Cognitive logical knowledge is integrated with relevant facts of the event to be predicted and embedded into a prompt template to construct a prompt model. This allows the domain-wide language model to generate event evolution reasoning and prediction results based on expert analysis dimensions and processes. Finally, conflict detection is performed on event elements through closed-loop evidence chain analysis, and credible conclusions are selected to obtain credible prediction conclusions. By constructing prompt templates to guide the large model through cognitive logical learning and combining multi-level credible verification and screening, the technical problem of excessive prediction errors caused by illusions generated by the large model is solved, improving the accuracy and credibility of event evolution prediction.

This invention discloses an iterative task execution method and system based on dynamic feedback and causal fault tolerance, belonging to the field of artificial intelligence and data analysis technology. By integrating multimodal perception, dynamic feedback, and causal reasoning, it significantly improves the success rate and robustness of complex data analysis tasks, avoids decomposition bias caused by information fragmentation, quantifies task complexity through graph neural networks to achieve adaptive task decomposition, and combines a dynamic feedback mechanism to correct the task structure in real time during execution, supporting the insertion, merging, and order adjustment of subtasks. A causal fault tolerance strategy based on historical failure trajectories is introduced, which can predict high-risk paths and automatically embed defensive operations to block error propagation. The entire execution trajectory is stored in a memory bank for continuous optimization of the model and strategy, forming a closed-loop learning capability.

This application relates to the fields of power technology and artificial intelligence technology. It discloses a method, apparatus, and equipment for evaluating temporary power supply systems based on a causal reasoning model. The method includes: inputting the current fusion features of the current temporary power supply system into a trained causal reasoning model; generating the current risk level, current abnormal parameter information, and current causal chain path of the current temporary power supply system through the trained causal reasoning model; obtaining the handling suggestions corresponding to the current risk level; obtaining the deviation value between the environmental parameters of the current temporary power supply system and the standard environmental parameters; when the deviation value is greater than a preset value, multiplying a preset current threshold by a reduction coefficient to generate a reduced current threshold; and writing the current risk level, current abnormal parameter information, current causal chain path, reduced current threshold, and handling suggestions into a preset evaluation template to generate an evaluation report for the current temporary power supply system. This application is beneficial for improving the efficiency of obtaining evaluation reports for temporary power supply systems.

The application discloses an industrial software performance optimization method and system based on causal reasoning, and relates to the field of industrial software optimization; the method comprises the following steps: predefining an intervention parameter set and an operation environment parameter set of each to-be-optimized parameter; extracting N causal observation events from historical operation logs of the industrial software; constructing a causal event knowledge base based on the N causal observation events; constructing a to-be-completed causal event; wherein the to-be-completed causal event comprises a to-be-optimized parameter of a current system and a target value thereof; extracting K intervention configurations of a to-be-completed causal event candidate in the causal event knowledge base; and obtaining a recommended intervention configuration of the to-be-optimized parameter based on the K intervention configurations; the application generates a recommended intervention configuration that is adapted to a current operation environment, inherits historical effective events, is adapted to the current operation environment, and significantly improves the performance optimization level of the industrial software on the current system.

The application discloses a kind of social governance risk element discovery method and system based on knowledge guide counterfactual reasoning, belong to artificial intelligence and public governance cross technical field, wherein method includes: based on historical case information construction knowledge graph, using semantic encoder extracts semantic features from historical case information, using graph neural network embedding in the node in knowledge graph, obtain knowledge characteristics;In the concept cluster level of knowledge graph, semantic level counterfactual intervention is executed, and fact fusion and counterfactual fusion are carried out;By the difference between fact fusion feature and counterfactual fusion feature, the fact fusion feature is corrected, and the cause-effect enhanced feature is obtained;Cause-effect enhanced feature is input into multi-label classification head, and risk element list is predicted.The application effectively improves the logical rigor, explainability and generalization ability of risk element identification by deeply integrating structured governance knowledge and causal reasoning without a large number of labeled causal labels.

The application discloses a kind of multi-modal big model's video human-like causal inference ability's evaluation method and system, belong to computer vision and artificial intelligence technical field.The present application is to solve the problem that existing evaluation system is difficult to capture human causal consensus in depth, by selecting causal scene and multilevel causal task for evaluation, generate the video dataset composed of synthetic video containing basic setting and interference setting and real video, construct causal problem based on the causal structure corresponding to video, and use video dataset and causal problem to test the inference of the model to be evaluated, finally obtain human-like causal inference evaluation result.The present application can be applied to the field such as automatic driving, medical treatment and justice, which has high requirement for inference fidelity, to realize comprehensive and accurate evaluation of causal inference ability of multi-modal big model.

This invention provides a time-constrained optimization method for flight ground support events based on causal reasoning, comprising the following steps: Step 1, construction of a hierarchical analysis system and data standardization processing; Step 2, generation of civil aviation prior constraint set and causal feasible region matrix; Step 3, causal structure learning using the constraint-based NOTEARS-MCP algorithm; Step 4, partitioning of heterogeneous intervals of influencing factors and generation of effective intervention sets; Step 5, quantification and intensity ranking of entropy balance weighted causal effects; Step 6, Markov decision process modeling and space compression of the support process; Step 7, construction of a causal dual-constraint initial behavioral strategy set; Step 8, solving for the global optimal strategy using the path integral control algorithm; Step 9, robustness verification of the optimal strategy under perturbation; Step 10, output and mapping of time control requirements for flight ground support events. This invention effectively reduces the risk of flight departure delays and helps airports achieve refined and intelligent management of support processes.

This invention discloses a smart home control method, device, equipment, and medium based on causal inference. The method includes: acquiring user behavior data, environmental data, and user profiles; determining user behavior deviation characteristics based on the behavior data, environmental data, and preset historical behavior data; determining user behavior deviation vectors based on the user behavior deviation characteristics, user profiles, and environmental data; inputting the user behavior deviation vectors into a preset causal inference model, performing causal reasoning on the user behavior deviation vectors through the preset causal inference model to determine the root cause of the user behavior deviation; determining smart home control commands based on the root cause of the user behavior deviation, and controlling the corresponding smart home devices according to the smart home control commands. This achieves smarter, more user-centric, and automated control of smart home devices, improving user experience and bringing energy-saving benefits.

This application proposes an interpretable financial anomaly detection method based on causal reasoning and contrastive learning, belonging to the field of anomaly detection technology. This method calculates the Pearson correlation coefficient matrix based on normal transaction samples and constructs a causal directed acyclic graph (DAG). Then, a clustering algorithm is used to identify various business patterns of normal transactions. Using this as an anchor point, a deep neural network model is trained in conjunction with the feature constraints of the DAG, allowing the model to learn feature representations that conform to business logic and are causally consistent. Subsequently, the trained model outputs raw anomaly scores for the transactions to be detected. For anomaly transactions exceeding a threshold, interpretable intervention features are selected to generate counterfactual transaction samples and predict counterfactual anomaly scores. The change in scores is calculated to evaluate the intervention effect. Combined with causal path analysis, natural language causal explanations and priority actionable suggestions are generated. This method not only solves the "black box" defect of deep learning models but also overcomes the problem of existing methods only outputting anomaly scores without practical improvement guidance.

An interpretable solution generation method based on causal reasoning graphs and large language models is proposed, characterized by: Step 1: generating solution tasks according to requirements; Step 2: introducing a causal model to more accurately characterize the decision-making environment; Step 3: adding causally identifiable optimal interventions to generate solutions. This application proposes an interpretable solution generation method based on causal reasoning graphs and large language models. This method combines the structured causal reasoning capabilities of causal reasoning graphs with the natural language generation capabilities of large language models. Reasoning graphs, with events as nodes and relationships between events as edges, can describe the evolutionary patterns of dynamic processes. To support causal reasoning, this application further introduces causal structures to construct causal reasoning graphs.

The application discloses a large model causal reasoning method and system based on a structural causal model, which comprises the following steps: automatically discovering the causal relationship between variables based on user input content and outputting a causal diagram; encoding the causal diagram and converting it into a form available for a large model; increasing causal attention bias on the basis of a standard model Transformer, so that tokens on a path with a causal relationship obtain a higher attention weight addition and non-causal correlation paths are inhibited; receiving an intervention question query input by a user during the reasoning process and performing intervention reasoning; outputting the reasoning result of the large model to the user in a natural language; and based on the modified large model reasoning result fed back by the user, the large model is retrained or fine-tuned for continuous optimization. The application automatically learns the causal relationship from data, does not depend on manual definition, can perform intervention reasoning, visually outputs the causal relationship, and then guides the reasoning process of the large model, thereby enhancing the causal reasoning capability of the large language model.

This invention discloses a method and system for causal and counterfactual reasoning in the field of alloys, comprising: acquiring and parsing target documents in the field of alloys, establishing entity-hyperedge associations; performing aliasing, unit standardization, and conflict resolution on entities and hyperedges to form a consistent evidence knowledge structure, and establishing entity-hyperedge association indexes and hyperedge retrieval indexes; retrieving matching hyperedges in the evidence knowledge structure according to the query statement to form a candidate evidence set, and performing bidirectional expansion and redundancy control based on entity-hyperedge associations to obtain an evidence subgraph; classifying the query statement according to keywords and semantics to construct a constrained causal graph; outputting causal reasoning conclusions and their evidence chains for the target causal effects represented by the causal graph; and generating counterfactual comparison conclusions when the query statement is a counterfactual query, providing traceable evidence containing hyperedge identifiers. This effectively reduces the generation of illusions and improves the quality and verifiability of responses.

The present application belongs to the technical field of hydrological forecasting, and in particular to a physical constraint basin hydrological real-time forecasting method based on semantic causal reasoning. In view of the semantic gap of multi-source heterogeneous data and the missing problem of physical mechanism existing in the prior art, the following scheme is proposed: first, a knowledge graph within a basin is constructed based on water conservancy text data; second, a semantic causal reasoning is performed by using a large language model combined with the knowledge graph to dynamically identify key disaster-causing factors and generate an input feature set; then, a semantic constraint prediction network is constructed, which realizes the spatio-temporal aggregation of upstream station features through a knowledge graph attention mechanism, and modifies the forget gate by introducing a rainfall attenuation coefficient and adds a water balance constraint term in the loss function to explicitly inject the hydrological physical law into the neural network; finally, the model is trained by using historical data and features are completed and dynamically optimized in the real-time data stream combined with the knowledge graph to output the water level prediction value at the future time.