50 results about "Structure equation" patented technology

The invention relates to the technical field of financial risk prediction, in particular to a financial risk prediction method and device, a storage medium and equipment. The method comprises the following steps: acquiring financial data, and extracting multi-modal features; based on the multi-modal features, generating a causal graph by adopting a constraint-based causal discovery algorithm, and quantifying causal intensity by adopting a structural equation model; adopting the quantized causal graph as a constraint of an anti-fact generative adversarial network, generating an anti-fact scene and analyzing a risk conduction path; training a causal graph neural network model based on the multi-modal features, the causal graph and the risk conduction path; and interpretability analysis and risk monitoring are carried out. According to the technical scheme, financial risk causal association can be accurately constructed, an anti-fact scene clear conduction path can be generated, and through interpretable analysis and monitoring, the risk prediction accuracy and interpretability are improved, financial risks are helped to be prevented and controlled in time, and the financial system stability and the risk response capacity are enhanced.

The invention discloses a network advertisement putting path optimization method based on causal inference, and the method comprises the steps: S1, collecting historical advertisement putting data, and constructing an advertisement putting data set; s2, constructing a causal inference model based on the improved structure equation, and obtaining a causal relationship between the advertisement form and the advertisement effect; s3, designing an advertisement path selection strategy in combination with a causal relationship and a dobby machine algorithm, and obtaining an optimal advertisement form; s4, exploring a new advertisement putting path by using a dobby machine algorithm, and performing advertisement putting; s5, monitoring an advertisement putting process in real time, and dynamically adjusting an advertisement putting path according to a monitoring result; and S6, regularly updating the causal inference model according to the advertisement form, the user behavior and the change of the market environment. According to the method, an efficient and scientific optimization scheme can be provided in network advertisement putting path optimization, and remarkable technical values and economic benefits are brought to practical application.

The invention provides a titanium tetrachloride boiling chlorination process optimization method based on a causal model and electronic equipment, and the method comprises the steps: constructing a generation mechanism between structural equation model expression variables based on the causal relationship between boiling chlorination key process parameters and result variables; the effect of external intervention on the TiCl4 yield and unit cost is simulated through causal inference, and a multi-target optimization model with the minimization of the unit product manufacturing cost and the maximization of the TiCl4 yield as targets is constructed in combination with the structural model and Monte Carlo sampling estimation expectation; and iteratively solving the optimization model by adopting a causal-based non-dominated sorting genetic algorithm, and obtaining a Pareto optimal solution set meeting variable constraint conditions through operations such as causal variable classification, dynamic penalty weighting, non-dominated sorting and sensitive driving disturbance. According to the method, a causal modeling and optimization integrated framework suitable for the boiling chlorination process is constructed, personalized process strategy generation and production operation decision making are supported, and the raw material utilization rate and the process operation economy are improved.

The invention provides a practical training operation intelligent error correction and process traceability system and method, and the method comprises the steps: firstly collecting multi-source data in a practical training process, including a posture track, a tool operation parameter and an environment variable, and constructing an operation state vector through unified timestamp alignment and sliding window feature extraction; a structure equation model is combined with a do operator to establish a causal relationship graph, causal edge weight estimation and confidence interval calculation are completed and are stored as a callable core model, and the system monitors and identifies potential error trends through real-time deviation, positions key intervening variables in a causal chain, and determines the potential error trends in the causal chain. And constructing an anti-fact variable set and setting a reasonable adjustment range and step length. In addition, the system also performs acquisition and comparison verification on data executed by the trainees, realizes traceable evidence storage by adopting hash signature and block chain storage, can discover and correct operation deviation in real time, provides explainable causal traceability and personalized micro prescription prompts, and improves the efficiency, accuracy and responsibility traceability of practical teaching.

The invention discloses an ocean current extraction method and system, and relates to the technical field of data processing, and the method comprises the steps: building causal priori from SWOT satellite observation data based on a set variation assimilation system and a structural equation model; wherein the causal priori comprises a causal path and strength between wind stress forcing and ground rotation adjustment; carrying out iterative generation through a physical constraint diffusion model under the conditions of causal priori and SWOT satellite observation data, and outputting a sea surface flow field; performing multi-level interpretability verification on the causal path and the step of performing iteration generation through the physical constraint diffusion model to obtain a verification result; a verification result is fed back to the structural equation model and the physical constraint diffusion model to form closed-loop optimization, and then the optimized sea surface flow field is obtained. According to the method, iteration is carried out through the physical constraint diffusion model to generate the sea surface flow field, multi-level interpretability verification is carried out, the sea surface flow field can be optimized by utilizing the verification result, and high-resolution ocean current acquisition is realized.

The invention discloses an ocean sound velocity field prediction method and system, and relates to the technical field of data processing, and the method comprises the steps: carrying out the quantitative diagnosis of key driving factors affecting the evolution of an ocean sound velocity field of a target sea area from the ocean environment data, and building a causal network diagram based on the information flow of the key driving factors and a structural equation model, obtaining a core feature set; the ocean sound velocity field sequence data in the core feature set are decomposed into data in a space-time coherent mode through dynamic mode decomposition, and then the data are mapped into low-dimensional space-time features; learning the evolution dynamic state of the ocean sound velocity field according to the low-dimensional spatial-temporal characteristics by using a KAN network, and outputting an ocean sound velocity field prediction result at a future moment; future guide learning is used in the training stage of the KAN network, and real observation data in future set time is used as an auxiliary supervision signal; and using a dynamic feedback mechanism to calibrate the ocean sound velocity field prediction result based on the real-time observation data in the online prediction stage. The accuracy of predicting the ocean sound velocity can be improved.

The invention provides a crop per unit yield prediction method, system and device and a medium, and belongs to the field of agriculture and computer crossing, and the method comprises the following steps: constructing a least square structure equation PLS-SEM model; calculating an initial value of a factor weight w and a factor load i representing a relationship between an observation variable and a latent variable of the initial PLS-SEM model, and calculating a value of a goodness of fit index GOF of the initial PLS-SEM model; performing factor analysis on the initial PLS-SEM model according to the value of the GOF, and removing invalid observation variables, invalid latent variables and invalid paths among the latent variables of the initial PLS-SEM model to obtain a final PLS-SEM model; and inputting the scores of the plurality of latent variables of the final PLS-SEM model into a PSO-LSSVM to obtain a predicted value of the per unit yield of the crops. The method can improve the prediction precision of the per unit yield of crops.

This invention discloses a multi-scale method for identifying and controlling the propagation paths of airworthiness risks for autonomous vessels. The method includes: hierarchically modeling multi-source airworthiness risk factors based on ontology to construct a structured knowledge graph; establishing logical relationships between risk factors using structural equation modeling and converting them into a Bayesian network; dynamically evaluating input vessel operation data and identifying multi-scale airworthiness risk propagation paths and key risk nodes using graph theory topology analysis; and finally, generating a hierarchical control strategy based on the identification results. This invention enables dynamic and probabilistic assessment of the initial and ongoing airworthiness of autonomous vessels, effectively identifying risk propagation mechanisms and key links, and providing support for the safe design, operation, and supervision of autonomous vessels.

The invention discloses a carbon price prediction method and system based on a graph G and a model prediction algorithm, and the method comprises the steps: firstly building a carbon price network, representing the network in the form of the graph G, then introducing a structural equation model to capture key variables of the network, and enabling the structural equation model to be expressed in the form of a matrix, adding additional items into the structural equation model to dynamically and accurately capture the carbon price fluctuation in the complex environment, and finally, constructing a carbon price prediction model by taking the minimum weighted prediction error and policy deviation cost as objective functions, and solving the model by adopting an artificial hummingbird algorithm and adding a chaotic mapping Bernoulli initialized population method. And obtaining the predicted carbon price. According to the carbon price prediction method, the carbon emission price with obvious fluctuation characteristics can be accurately predicted, and the effectiveness of the carbon emission trading market can be realized.

The invention relates to the technical field of soil attribute mapping, in particular to a soil mapping method, system and program combining a convolutional neural network and a structural equation model. According to the method, a causal relationship network between soil attributes and environmental factors is established through a structure equation model, and the causal relationship network is converted into a CNN network topology for guiding neural network structure design and parameter training. By introducing the latent variable constraint and the joint loss function, the prediction precision, the physical consistency and the interpretability of the model are improved. Experimental results show that the method has higher precision and generalization ability in soil attribute space prediction, and is significantly superior to an existing single data driven model.

The invention belongs to the technical field of evaluation of the influence degree of chemical enterprises on the surrounding environment, and particularly relates to an SEM-based chemical enterprise environmental influence risk evaluation method, which comprises the following steps: constructing chemical enterprise environmental influence risk evaluation indexes; variables are set, and a chemical enterprise environment influence risk evaluation value structure equation mechanism model is constructed; evaluating the advantages and disadvantages of the mechanism model; and correcting the mechanism model and evaluating the environmental influence risk of the chemical enterprise by using the mechanism model. When the chemical enterprise environment influence risk is evaluated, the method has the advantages of processing complex causal relationships, analyzing latent variables, comprehensively evaluating the model adaptation degree, combining path analysis and factor analysis, accurately estimating parameters, carrying out statistical verification based on a large amount of data and the like.

The invention discloses a mining regulation and underground space rapid construction method based on system dynamics, and relates to the technical field of mining engineering, and the method comprises the following steps: 1, mining system boundary modeling and key parameter identification; step 2, mining coupling mechanism and multi-loop feedback network modeling; step 3, construction of a mining cooperative dynamical model and development of a structural equation; and 4, performing production dynamic response simulation and production optimization decision making, and giving an evaluation conclusion through multivariate comprehensive judgment. According to the invention, multi-source parameter dynamic modeling including the tunneling subsystem and the coal mining subsystem is established, so that the excavation efficiency and safety control are improved.

The application discloses a multi-system mutual feedback method based on a causal driving progressive reasoning model, and belongs to the technical field of reasoning model application under a multi-system mutual feedback environment. The application solves the problems of poor scene application flexibility and large reasoning result error of a traditional multi-system mutual feedback method based on a reasoning model in the prior art. According to the analyzed scene description and environment analysis, the application identifies observation variables of reasoning system evolution. By introducing latent variables, combining the observation variables, constructing a structural equation model, and establishing the causal relationship between the variables, a neighbor matrix is constructed according to the causal relationship between the variables, the influence of the variables is calculated, the variables are sorted in descending order of influence, and the sorting is used as a reasoning order. According to the reasoning order, gradual reasoning is calculated, and the final dependent variable is analyzed and obtained. The application effectively improves the reasoning result accuracy under the multi-system mutual feedback environment, and can be applied to a complex causal scene between cross-domain multi-systems.

The invention discloses a method and a system for identifying key biological class groups influencing a lake ecosystem based on a sectional structure equation model, relates to the technical field of environmental ecology, and comprehensively investigates the biocenosis diversity and ecological function characteristics of a lake. A nutrition structure of a lake ecosystem is constructed by analyzing the predation relationship among biological groups; the multifunctionality of the lake is evaluated by integrating clustering analysis and a functional threshold method; the method comprises the following steps: constructing a sectional structure equation model based on a nutrition structure relationship of a food web, fitting each path in the model through a mixed effect model, analyzing a path coefficient between nutrition level richness and multifunctionality, and calculating direct and indirect effects of the path coefficient; and finally, identifying the key biological class group which has the greatest influence on the ecological function of the lake. According to the method, the key biological class groups with decisive influence on the ecological function of the lake can be accurately identified, a clear target is provided for ecological protection and restoration, and the method has practical reference significance in making practical restoration management measures.

The present application provides a forest drought death remote sensing evaluation method coupling variable relationship and data learning model, relates to the field of ecological disasters and remote sensing technology. The method firstly constructs a structural equation model based on sample point data, quantifies the direct and indirect relationship between forest drought mortality and key meteorological conditions, forest internal physiological parameters and external greenness characteristics. Subsequently, the random forest regression technology is integrated to predict the selected key variables in space, realize the wide coverage from sample observation to global scale, and finally generate the forest drought mortality in the global range. Compared with the traditional single evaluation method, the present application integrates multiple influence factors and multi-dimensional prediction model, improves the evaluation accuracy and spatial coverage ability of global forest drought mortality, and provides more direct and practical technical support for global forest health monitoring and ecosystem management.

The invention relates to a building life cycle carbon emission prediction method based on causal machine learning, and belongs to the technical field of building energy conservation and emission reduction. According to the method, a core variable of a building design stage is taken as a starting point, and embedded carbon, operation period carbon and demolition stage carbon are uniformly modeled and predicted by constructing a causal graph network and combining a structured causal model and a causal forest algorithm. The method specifically comprises the steps of determining building design initial information; dividing a design influence factor stage; constructing an architectural design causal graph model; converting the causal diagram into a structural equation model; training a causal forest model; and carrying out anti-factual reasoning and design variable sensitivity analysis. According to the method, the complex causal relationship between the design variable and the carbon emission can be identified, accurate prediction and path decomposition of the full-life-cycle carbon emission are realized, and quantitative basis and decision support are provided for low-carbon design in the early stage of design.

The invention belongs to the technical field of water resource attribution and climate change influence evaluation, and particularly discloses a water resource change attribution method and system fused with a physical constraint structure equation, and the method comprises the steps: building a sample matrix related to climate factors, human factors and water resource indexes; the method comprises the following steps: a measurement module maps observation data of climate factors, human factors and water resource indexes into latent variables with clear physical significance; the structure module realizes causal relationship modeling among latent variables; introducing a water balance physical constraint; and performing parameter estimation on the structure equation model based on the sample matrix to obtain a path coefficient, and further determining the attribution contribution rate of the climate factor and the human factor to the water resource change. According to the method, the attribution result can be ensured to conform to the statistical significance and meet the hydrological mechanism, physical unreasonable explanation is avoided, and a scientific basis is provided for drainage basin water resource management and climate change adaptation.

This application discloses a method and system for predicting ocean sound velocity fields, relating to the field of data processing technology. The method includes: quantitatively diagnosing key driving factors affecting the evolution of the ocean sound velocity field in a target sea area from marine environmental data, and constructing a causal network graph based on the information flow and structural equation model of the key driving factors to obtain a core feature set; decomposing the ocean sound velocity field sequence data in the core feature set into spatiotemporally coherent mode data through dynamic mode decomposition, and then mapping it into low-dimensional spatiotemporal features; using a KAN network to learn the evolution dynamics of the ocean sound velocity field based on the low-dimensional spatiotemporal features, and outputting the ocean sound velocity field prediction results for future times; using future-guided learning in the training phase of the KAN network, using real observation data at a future set time as auxiliary supervision signals; and using a dynamic feedback mechanism in the online prediction phase to calibrate the ocean sound velocity field prediction results based on real-time observation data. This application can improve the accuracy of ocean sound velocity prediction.

The invention discloses a security control capability assessment method and system based on a structural equation, and relates to the technical field of network security control. The method comprises the following steps: extracting network security control capability related index variables; a step of constructing a security control capability index system; a modeling and evaluation step based on a structural equation model; and evaluating the management and control capability of the network security system. According to the invention, an explicit variable and hidden variable index system related to the management and control capability of a space security system is provided; providing a structural equation model based on the management and control capability index system of the space security system; the management and control capability assessment system of the space security protection system is realized, the network security protection system is assessed and evaluated, quantifiable network security protection system assessment is realized, and intelligent overall security management and control are supported.

The present invention relates to the technical field of soil property mapping, and in particular to a soil mapping method, system and program that combine a convolutional neural network and a structural equation model. This method establishes a causal relationship network between soil properties and environmental factors through a structural equation model, and transforms this causal structure into the network topology of a CNN to guide the design of the neural network structure and parameter training. By introducing latent variable constraints and a joint loss function, the prediction accuracy, physical consistency and interpretability of the model are improved. Experimental results show that this method has higher accuracy and generalization ability in soil property spatial prediction, significantly superior to existing single data-driven models.

The invention discloses a green plant selection method, system and device and a storage medium, and the technical scheme is characterized in that soil analysis data and plant physiological data corresponding to each candidate plant in a sub-region are acquired; constructing a structural equation model according to the congestion delay indexes, the soil analysis data and the plant physiological data of the sub-regions, and determining significant factors of each candidate plant influenced by traffic according to the structural equation model; calculating the first fitness of each candidate plant according to the congestion delay index of the sub-region and the significant factor of each candidate plant in the region; a plant selection model corresponding to each sub-region is constructed based on a genetic algorithm, the candidate plants are substituted into the plant selection model of each sub-region, target plants corresponding to each sub-region are obtained, and fitness functions of the plant selection models are constructed based on the first fitness, the congestion delay index and the significant factors. According to the method, the plants with high adaptability and high carbon sequestration capability can be selected based on the traffic jam condition.

The invention provides a project contract management method based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: obtaining a sample project contract; performing key feature identification on the sample engineering contract to obtain a plurality of first key features included in the sample engineering contract; presetting a first combination relationship among the plurality of first key features; constructing a structural equation model according to the first combination relationship; obtaining pre-collected historical data; verifying the structural equation model by adopting historical data, and verifying whether the first path coefficient meets preset accuracy or not; if it is determined that a first path coefficient output by the structural equation model meets preset accuracy, the contract to be processed is input to the structural equation model, an output second path coefficient is obtained, and the second path coefficient is a path coefficient corresponding to a second combination relation among a plurality of second key features contained in the contract to be processed. According to the invention, the combination relationship between factors contained in the engineering contract can be quantified.

This application discloses a method, apparatus, and device for auditing vulnerability mechanisms, relating to the field of software security technology. The method includes: extracting vulnerability causal elements and sorting out causal relationships from multi-source evidence associated with vulnerabilities, which is linked to corresponding nodes in a causal graph through globally unique evidence citation identifiers; obtaining a causal graph with vulnerability causal elements as nodes and causal dependencies as edges; extracting observed variables from the multi-source evidence based on the causal graph and constructing a structural equation model based on causal dependencies; solving the structural equation model to obtain the quantitative contribution of each vulnerability causal element to the occurrence of the vulnerability; performing a bidirectional mapping match between the vulnerability causal elements and a pre-set security compliance clause library based on the quantitative contribution to obtain a bidirectional mapping relationship; and integrating multi-source evidence, quantitative contribution, and bidirectional mapping relationship to obtain a structured audit report. This enables complete tracing and accountability for the explanation of vulnerability mechanisms.

The application discloses a building group load prediction method based on causal inference. First, the building group load sequence is acquired and pretreated; the discrete wavelet transform is used to decompose the building load sequence to obtain a plurality of high-frequency components and a low-frequency component; the building load fluctuation characteristics are reconstructed by using the high-frequency components and the low-frequency component; then, the static and dynamic causal diagrams are constructed by taking the building as a node, the building load fluctuation characteristics are coded into latent representations, the building load state structure equation is constructed by using the latent representations, each building load state structure equation is solved by optimization, and the adjacency matrix of the causal diagram is obtained; finally, the load prediction model is constructed, the adjacency matrix of the static causal diagram and the dynamic causal diagram is taken as input, the building group load at a future time step is predicted according to the building group historical load sequence, and the building group load prediction sequence is obtained. The problems that it is difficult to capture the dynamic propagation effect of the load change among the buildings and the modeling of the complex interaction among the buildings is insufficient are solved.

The invention discloses a multi-system mutual feedback method based on a causal-driven progressive reasoning model, and belongs to the technical field of reasoning model application in a multi-system mutual feedback environment. The problems that in the prior art, a traditional multi-system mutual feedback method based on an inference model is poor in scene application flexibility and large in inference result error are solved. The method comprises the following steps: identifying observation variables of inference system evolution according to analyzed scene description and environment analysis; constructing a structural equation model by introducing potential variables and combining observation variables, and establishing a causal relationship between the variables; according to the causal relationship between the variables, constructing an adjacent matrix, calculating to obtain the influence of the variables, sorting according to the sequence of the influence from large to small, and taking the sequence as a reasoning sequence; gradually calculating according to the reasoning sequence, carrying out progressive reasoning, and analyzing to obtain a final dependent variable. The method effectively improves the reasoning result accuracy in a multi-system mutual feedback environment, and can be applied to a cross-domain multi-system complex causal scene.

The invention discloses an activity strategy generation method and device, equipment, a storage medium and a program product. Determining candidate observation variable sample data corresponding to the activity strategy and potential variable sample data corresponding to the candidate observation variable sample data; fitting the structural equation model based on the candidate observation variable sample data and the potential variable sample data to obtain a path coefficient set of the structural equation model; fitting a residual error of the structure equation model through a first machine learning model, and iteratively correcting a path coefficient set of the structure equation model based on a residual error fitting result to obtain a target path coefficient set; determining at least one target observation variable influencing the activity effect in the at least two candidate observation variables based on the target path coefficient set; an activity strategy is generated based on the at least one target observation variable. According to the application, the accuracy and the generation efficiency of the activity strategy can be improved.

This application discloses a method and system for digital transformation adaptability assessment and obstacle diagnosis, relating to the fields of supply chain digital management and industrial intelligence. The method constructs a multi-dimensional assessment index system, based on subjective scoring data and objective quantitative data of enterprises, to obtain high-contradiction indicators for each enterprise and common high-contradiction indicators for the entire supply chain. Simultaneously, it constructs a Bayesian structural equation model to obtain the enterprise's adaptability index, and combines this with an obstacle degree analysis model to identify key obstacle dimensions and common obstacle points in the supply chain, and performs personalized obstacle diagnosis for all enterprises. This method enables comprehensive and accurate digital transformation adaptability assessment and obstacle diagnosis for supply chain enterprises.

The invention discloses a residential building energy consumption prediction method based on a multi-attribute intuition fuzzy decision. The method comprises the following steps: firstly, constructing a residential building model; determining reference attributes based on an expansion plan behavior theory and a structural equation model; then energy consumption behavior preference data in different seasons are collected; the core lies in that a dynamic event chain is cyclically executed in an annual energy consumption simulation process through a Python control script leading EnergyPlus energy consumption simulation engine: according to a current season type, if the current season is a decision season, random sampling and multi-attribute intuitionistic fuzzy decision are carried out to trigger equipment, and if the current season is a transition season, the equipment is selected according to a preset rule; after the equipment is started, the running duration is randomly generated by a survival function, and energy consumption is recorded after simulation is finished; the method has the advantages that through a multi-attribute intuition fuzzy decision and a seasonal mixing strategy, the defects of human behavior cognition uncertainty, multi-attribute tradeoff and one-sided description of a decision mechanism are fundamentally solved, and the accuracy and reliability of residential building energy consumption prediction are remarkably improved.

The application provides a soil salt content dynamic inversion method and device, electronic equipment and storage medium, in the method, the direct and indirect causal relationship between the soil salt content, the environment drought and the crop growth is quantified by introducing a structural equation (SEM) model, which overcomes the limitation that the traditional method only pays attention to the correlation and cannot analyze the coupling effect, provides theoretical support for inversion, filters the input features of the CNN model based on the causal relationship between variables analyzed by the SEM model, realizes high-precision inversion of deep fusion of mechanism and data, significantly improves the soil salt content inversion precision, combines multi-temporal remote sensing observation data and spatial interpolation technology, realizes the leap from static evaluation to dynamic monitoring, and the application can accurately capture the spatiotemporal migration trajectory of the soil salt content and the dynamic response of the crop growth, and provides a reliable technical scheme for targeted regulation and scientific intervention of precision agriculture.

The invention discloses a coal mine production business optimization method based on an industrial knowledge graph, and relates to the field of coal mine production, and the method comprises the steps: constructing a coal mine production knowledge graph according to historical ledger data; extracting prior constraints, and performing causal structure learning to obtain a coal mine production causal diagram; constructing a variable influence structure equation set according to the causal diagram; carrying out anti-fact simulation, calculating key indexes under different intervention behaviors, and taking the intervention behaviors meeting key index thresholds as feasible scheme domains; and performing multi-target optimization on the feasible scheme domain to obtain an optimization scheme set, and writing the scheme conforming to the comprehensive benefit score threshold value as a configuration scheme back to the knowledge graph. The influence of different intervention measures on safety, yield and cost can be evaluated, so that managers can solve the core contradiction between safety and benefit in coal mine production, the optimal solution of production efficiency and cost control is found on the premise that safety is guaranteed, and fine control over coal mine production business risks is facilitated.