82 results about "Pattern clustering" patented technology

The invention discloses a compressed air energy storage system operation state evaluation method based on principal component clustering analysis. The method comprises the steps that system operation data are collected and preprocessed; performing multi-time scale decomposition and feature extraction on the preprocessed data set; performing nonlinear time-varying adaptive principal component analysis on the multi-time scale feature set, and extracting main features of a system operation state; carrying out clustering analysis on the dimension reduction feature space by adopting a PCA-clustering iterative optimization mechanism; establishing an evaluation model of each functional area of the system based on thermodynamic constraints, and calculating performance index values of the functional areas in combination with the principal component transformation matrix and an operation mode clustering result; dynamically adjusting the weight of each evaluation index; and generating a CAES comprehensive operation state evaluation result. According to the method, the problems of poor PCA adaptability, difficulty in multi-time scale data fusion, low abnormal mode detection sensitivity and the like under the nonlinear time-varying characteristic of the CAES system are solved.

The invention relates to the technical field of data processing, and discloses an anti-oxidation barrier layer performance degradation prediction method and system based on multi-source data. The method comprises the following steps: collecting and preprocessing multivariate data of a barrier layer environment, and constructing three-dimensional tensor data; indexes such as oxygen blocking efficiency and anti-permeability performance are calculated, and performance time sequence data are obtained; extracting multi-dimensional features and fusing the multi-dimensional features through an automatic encoder; applying a hybrid deep learning model to predict performance degradation; analyzing degradation curve characteristics, and executing mode clustering to obtain a risk matrix; and optimizing a maintenance decision scheme based on risk assessment. According to the invention, the hybrid deep learning model is utilized to capture the dependency relationship of time and space dimensions at the same time, and the prediction precision is significantly improved; based on degradation mode identification and risk level evaluation, accurate multi-scene maintenance decision is realized, environmental risk is reduced, and maintenance cost is optimized.

The invention provides a food production information traceability management method and system, and relates to the technical field of food production monitoring. The method comprises the steps of obtaining multiple groups of multi-process production record data of target baked food, performing production process characteristic linkage analysis on the target baked food, and generating a plurality of process joint characteristic matrixes; performing mode clustering based on production process distance perception on the multiple groups of multi-process production record data to generate a plurality of abnormal production mode class clusters; performing process anomaly analysis and back propagation traceability on the to-be-analyzed batch to generate a process anomaly detection result of the to-be-analyzed batch; according to the plurality of production abnormity mode class clusters, mode abnormity tracing is carried out on the to-be-analyzed batch, a production abnormity mode matching result of the to-be-analyzed batch is generated, and a production abnormity tracing analysis result of the to-be-analyzed batch is generated through fusion. According to the invention, the positioning precision of the abnormal source process of the baked food is improved.

The invention discloses a black-box test zero-day vulnerability analysis method and system based on multi-dimensional data, and aims to solve the problems that a traditional black-box test means is weak in unknown vulnerability recognition capability, high in false alarm rate, lack of path modeling and verification mechanisms and the like. The method comprises the following steps: constructing a cross-time window behavior graph by acquiring multi-dimensional heterogeneous information such as network input, system call, log information and abnormal signals; on the basis, potential abnormal paths are identified through structure entropy change and graph structure mutation analysis, path vector representation is constructed by combining graph representation learning and a path embedding method, and path-level risk modeling and mode clustering analysis are achieved; furthermore, vulnerability confirmation is carried out on the suspicious path through multiple verification mechanisms such as attack replay, fuzzy testing and sensitive function combination identification. The system has a multi-module cooperation capability, can realize automatic mining, verification and visual tracing of zero-day vulnerabilities in a source-source-free environment, and has good universality and expansibility.

The invention discloses a credit loan fraud data identification method and system based on artificial intelligence and a graph algorithm, and relates to the technical field of credit loan risk control. User information and behavior data are collected from multiple sources, a relation network graph is constructed after cleaning, dense communities are identified, cross-community intermediary nodes are positioned, community portraits are generated, behavior patterns are quantified, and similar groups are clustered. According to the method, a complex fraud mode is accurately recognized, hidden association is mined through a graph algorithm, the recognition accuracy is improved in combination with community portraits and behavior clustering, the dynamic adaptability is high, real-time feedback and incremental learning ensure that novel fraud is rapidly coped with, and the method is suitable for popularization and application. A high-interpretability report meets compliance requirements, user trust is improved, large-scale data is efficiently processed, modular design adapts to different credit and loan scenes, cost is reduced through automatic decision, the omission ratio is reduced, fraud loss is directly reduced, and the rate of return on investment is high.

The invention relates to the technical field of financial risk management, in particular to a big data-driven financial risk early warning system, which comprises a data detection module, a behavior risk rating module, a dynamic risk monitoring module, a behavior pattern clustering module and a financial risk early warning module. According to the method, the sensitivity and accuracy of risk detection are improved by analyzing small deviation between transaction behaviors and historical data, the dynamic risk monitoring function can realize quick response to abnormal transactions by continuously tracking the fund flow direction and the transaction frequency, and the risk detection accuracy is improved by analyzing the relationship between the fund flow direction and past risk events. According to the method, normal financial activities and potential risk behaviors can be effectively distinguished, an enterprise can take prevention measures before the risk actually occurs, and the clustering analysis of the risk behaviors can help to more accurately position a risk source, so that the measures are taken in a targeted manner, financial resources are optimized, and the risk prevention and control capability and decision-making efficiency are enhanced.

The invention relates to an abnormity alarm method and system for a feed production control system, and the method comprises the following steps: collecting multi-field data related in a feed production process in real time, the multi-field data at least comprising production equipment operation parameters, material characteristic parameters, environmental parameters and process control parameters; preprocessing the collected multi-field data, and fusing to generate a multi-field description feature vector representing the current production state; inputting the multi-field description feature vector into a pre-trained fault prediction model, wherein the fault prediction model respectively calculates the confidence of the fault type prediction result and the confidence of the fault point prediction result; wherein the confidence coefficient is in positive correlation with the distance from the feature vector to a known fault mode clustering center or the distance from the feature vector to a decision boundary; and when the fault prediction result indicates that an abnormal risk exists and the corresponding confidence exceeds a preset threshold, triggering a corresponding alarm signal.

The invention relates to the technical field of parking lot busy degree prediction. The parking lot busy degree prediction method comprises the steps of based on historical parking space number change information, performing feature extraction on the historical parking space number change information through a convolutional neural network (CNN) to obtain local spatial features of parking space changes, performing time sequence modeling on the local spatial features through a recurrent neural network (RNN) to obtain a busy degree prediction result of the parking lot, and obtaining a busy degree prediction result of the parking lot. The method comprises the steps of obtaining long-term trend characteristics of parking space changes, carrying out time sequence mode clustering on historical change information of the number of parking spaces by adopting a hybrid clustering method according to the long-term trend characteristics to obtain a time sequence mode of parking space change rules of a parking lot, and obtaining parking space change rules of the parking lot by utilizing a BallTree multi-stage similarity matching method according to static characteristic information of the parking lot and the time sequence mode. And according to the busy degree information of the similar parking lot, predicting the number of unoccupied parking spaces and the busy degree of the parking lot with the unknown information at the target moment. The method has the effect of predicting the busy degree of the parking lot.

The invention discloses a CKD special disease database construction method and system, and relates to the technical field of database construction, and the method comprises the steps: obtaining and predicating a multi-source heterogeneous atomic fact; constructing and fusing three sets of ontology models; verifying and deducing facts in a layered manner according to a multi-layer priority rule base; calling a constraint completion engine to generate inference facts for missing or conflicting fields; streaming follow-up visit, test and intervention logs into events and triggering graded alarms; an anti-fact intervention scene is simulated for the high-risk patient, and pilot groups are screened; dynamically evaluating and adjusting the rule priority; and based on a causal chain and an event mode, clustering patients and constructing a generality map, and recording a whole-process operation chain. Semantic management is realized through fusion of ontology, anti-fact intervention simulation is performed on high-risk patients by means of multi-layer rule verification, and database semantic consistency, reasoning depth, decision support and traceability are improved through causal atlas driven clustering.

A method of clustering patterns of an integrated circuit includes; providing a pattern image and numeric data, as input data corresponding to a first pattern to a first model, wherein the first model is trained by a plurality of sample images and a plurality of sample values, obtaining a content latent variable using the first model, and grouping a plurality of content latent variables corresponding to a plurality of patterns into a plurality of clusters based on a Euclidean distance, wherein the numeric data represents at least one attribute of the first pattern.

The invention provides a charging and discharging strategy intelligent optimization method and system applied to an energy storage power supply, and the method comprises the steps: carrying out the time sequence segmentation processing of a historical charging and discharging process of the energy storage power supply, employing a sliding time window to traverse historical charging and discharging data, and generating a charging and discharging time period data sequence with a continuous time stamp; performing charging and discharging feature extraction on the charging and discharging time period data sequence to obtain a charging and discharging feature set corresponding to each charging and discharging time period, performing mode clustering analysis based on the charging and discharging feature sets, dividing the charging and discharging time periods with similar feature distribution into a plurality of charging and discharging mode clusters through time sequence clustering, and performing mode clustering analysis on the charging and discharging mode clusters; and carrying out association matching on the charging and discharging mode clusters and power grid load prediction information, carrying out strategy iteration optimization processing on an association matching result through reinforcement learning, and generating a charging and discharging power distribution scheme adapted to different charging and discharging mode clusters. According to the invention, the optimization accuracy and environmental adaptability of the charging and discharging strategy of the energy storage power supply can be improved.

The invention relates to the technical field of electrochemical energy storage systems, and discloses an electrochemical energy storage system battery charging effect evaluation method, which comprises the following steps: acquiring energy storage system operation data and battery charging records, extracting time sequence characteristics, equipment state characteristics and charging parameter characteristics, and calculating the charging effect of an electrochemical energy storage system battery. Constructing a multi-dimensional feature vector and generating an initial charging effect feature library; the evaluation model is dynamically adjusted based on feature library feedback, potential effect features are identified through mode clustering analysis, feature priorities are optimized, and model parameters are updated; and in combination with system configuration information and target model parameters, determining an optimal power compensation effect evaluation result by adopting a hierarchical disassembly and classification statistical method. According to the method, through multi-dimensional feature fusion, dynamic model optimization and refined statistical analysis, the accuracy and adaptability of electricity supplement effect evaluation are remarkably improved, and a scientific basis is provided for efficient operation and maintenance of the electrochemical energy storage system.

The invention discloses an intelligent operation and maintenance management and control method and system based on a digital twinning wind power plant, and relates to the technical field of digital twinning, and the method comprises the steps: obtaining a wind power plant fan time sequence signal, constructing a feature vector, carrying out the Hash mapping, and storing the feature vector into a segmented Hash table; judging an operation mode through a Bloom filter, generating a label triple stream and summarizing abnormal hash keys; counting the Hash value frequency in the time window and marking a high-risk value, and generating a Hash frequency distribution vector; calculating mutual information between nodes, and constructing an adjacent forest through a minimum generation forest; carrying out sampling and low-frequency signal inflection point storage on the sample flow; constructing an exception decision-making tree, and judging exceptional nodes; extracting weighted sub-graphs and dividing the weighted sub-graphs into fault mode clusters; and calculating a fault urgency degree score and generating an operation and maintenance work order. Through a multi-source time sequence signal, Hash mapping, a decision tree and a spectrum division algorithm, wind power plant fault detection, mode recognition and operation and maintenance scheduling are optimized, and the operation efficiency and sustainability are improved.

The invention discloses a plum rain season photovoltaic output prediction method and system based on small sample learning. The method comprises the following steps: constructing a multi-source feature system; clustering and dividing meta-learning tasks based on a meteorological mode; the method comprises the following steps: constructing a TCN-Transform hybrid neural network model, and embedding a learnable meteorological adapter; training a hybrid neural network model by adopting an MAML meta-learning framework, and realizing meta-learning task training of different meteorological models in combination with a physical constraint regularization loss function; model parameters are optimized in three stages through a course learning strategy, and a training set is enhanced by utilizing Mixup time sequence data; and deploying the trained model to carry out output prediction, and outputting a prediction result with a confidence interval. According to the method, high-precision photovoltaic output prediction in a small-sample and high-uncertainty plum rain season scene is realized, and reliable support is provided for power grid dispatching.

The invention provides a log data-oriented system fault mining method, which belongs to the technical field of information, and comprises the following steps: collecting original log data of a system, and preprocessing original system logs, including analysis, key information extraction, vectorization and generation of a structured log event sequence; processing the log event sequence by adopting a two-stage model fusing anomaly detection and mode clustering so as to distinguish accidental anomaly and a real fault mode; and for each candidate fault mode cluster, analyzing a time sequence causal relationship between internal events, and positioning a root cause event according to the causal flow score of the node. The method has the advantages that dependence on artificial experience is reduced through full-process automatic modeling and analysis; according to the method, log analysis, feature extraction, anomaly detection and root cause positioning are all automatically completed by adopting a preset algorithm process, and the detection effect is maintained through self-adjustment of the model, so that the flexibility and sustainability of fault mining are improved.

The invention relates to the technical field of data processing and analysis, in particular to a knowledge graph entity accurate identification relation system for a service system, which comprises the following steps of: analyzing database table data, extracting an attribute change track and generating an attribute evolution sequence to provide a time sequence data basis for subsequent analysis and ensure the traceability of attribute evolution; meanwhile, the adaptability of the system to heterogeneous data is enhanced; clustering and dividing attribute clusters based on an attribute change mode, establishing a cross-cluster association index, revealing a potential association rule between attributes, and supporting rapid classification and dynamic adjustment of attribute relationships in a service scene; dynamic analysis of intra-cluster and cross-cluster attribute influence is realized by using a bidirectional attribute propagation model, and coupling strength between attributes is accurately quantified through iterative calculation and feedback calibration; by constructing a dynamic attribute topological graph and monitoring attribute value changes in real time, association reconstruction is triggered to generate an attribute association group set, dynamic changes of a service system are adapted, and association accuracy is improved.

The invention relates to an ultra-short-term photovoltaic power prediction method, in particular to an ultra-short-term photovoltaic power prediction two-stage GRU optimization method considering main meteorological factors and waveform classification, and aims to improve the photovoltaic power prediction precision and reduce the prediction time complexity. In the first stage, in order to improve the prediction precision and efficiency of a gated loop unit (GRU), an input data optimization method is provided, main meteorological factors based on a factor analysis method (FA) are extracted, similar modes considering photovoltaic power generation power fluctuation characteristics based on a fuzzy C-clustering algorithm (FCM) are clustered, and the prediction precision and efficiency of the GRU are improved. The maximum similarity pattern recognition based on grey correlation degree analysis and cosine similarity is combined; in the second stage, a GRU optimization method based on an improved sparrow search algorithm (ISSA) is provided, structural parameters of the GRU are optimized in the training stage of the GRU, and the prediction precision is further improved.

The invention provides an ultra-short-term wind speed prediction method based on wind speed fluctuation mode clustering division. The ultra-short-term wind speed prediction method comprises the following steps: step 1, collecting historical actually measured wind speed data recorded by a wind field data acquisition and monitoring control system; 2, decomposing the original sequence into a low-frequency sequence and a high-frequency sequence by using discrete wavelet transform, and further decomposing the high-frequency sequence by using improved completely adaptive noise set empirical mode decomposition; 3, calculating wind speed fluctuation intensity and wind speed fluctuation rate characteristics, and quantifying the fluctuation condition of the wind speed data; 4, constructing a self-adaptive wind speed interval division model, extracting wind speed fluctuation characteristics, carrying out wind speed classification engineering, and marking wind speed sections; 5, constructing two prediction basic models by using an improved whale optimization algorithm; and 6, outputting a test result, and verifying the feasibility of the model. According to the prediction method provided by the invention, the accuracy of the wind speed prediction value can be effectively improved, and the reliability of the wind speed prediction value is greatly improved.

The invention relates to the technical field of assisted reproduction health management, and discloses an assisted reproduction management method and system. The method comprises the steps that physiological data of multi-source monitoring equipment is received and subjected to standardization processing, and a multi-dimensional feature matrix is formed through time sequence alignment and feature fusion; identifying a dynamic evolution track of the key physiological mode by utilizing a mode clustering and sliding window technology; performing state deduction on the mode sequence based on the personalized model, and predicting a future physiological state; generating a regulation and control strategy sequence according to the difference between the prediction and the target, and executing the instruction; physiological response data is collected in real time and compared with an expected model, a follow-up strategy is dynamically adjusted, and closed-loop optimization is formed; and finally evaluating path validity and updating model parameters according to complete cycle data. According to the method, continuous accurate prediction and individualized self-adaptive regulation and control of the reproductive physiological state are realized, and the management accuracy and efficiency are improved.

The invention discloses a daily load curve form mode clustering method considering peak-valley shape features, and the method comprises the steps: firstly building a corresponding daily load curve peak-valley shape feature (Peak-Valley Shape, PVS) model on daily load curve data which is subjected to data preprocessing, then building a dynamic time warping distance (DTWpvs) of the daily load peak-valley shape feature, and carrying out the clustering of the daily load curve form mode. The method comprises the following steps of: establishing a target function of minimizing the sum of distances in clusters between data samples in the clusters and the centers of the clusters, then establishing a target function of minimizing the sum of distances in the clusters (Within Cluster Distance Sum, WCDS) between the data samples in the clusters and the centers of the clusters, carrying out clustering division in a daily load curve mode by adopting a K-media clustering algorithm, and finally, determining the optimal clustering number and a final clustering result by using a silhouette Coefficient Index (SCI). According to the method, the prominent problem that the conventional clustering method only performs classification from the overall shape of the daily load curve and does not consider that the load management technology most needs to pay attention to load peak and valley shape characteristics is solved; and compared with the conventional clustering method, the method can more accurately obtain a daily load curve form mode clustering result with more representative peak and valley characteristics.

The application provides a resource scheduling method and system based on campus user behavior analysis, and relates to the technical field of resource management. The method comprises the following steps: collecting target behavior information of a target campus user in a preset period, and analyzing a target behavior time sequence; acquiring an arbitrary time zone and matching arbitrary behavior data; forming a campus user set, and analyzing first behavior information of a first user; if a first mode index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit value, a mode clustering cluster is formed; acquiring a number of user individuals in the mode clustering cluster, and combining the arbitrary behavior data to obtain arbitrary resource demand of the arbitrary time zone; and performing campus resource scheduling processing. The application solves the technical problem that, in the prior art, inaccurate prediction of user demand leads to unreasonable resource allocation, thereby affecting resource scheduling efficiency. By analyzing user behavior mode and determining resource demand, the efficiency of resource scheduling is improved.

The application discloses a fine-grained load segmentation prediction method, and the steps are as follows: based on the daily load curve, dimension reduction indexes are extracted, and a user power consumption mode clustering model is established; a multi-task group load prediction model is constructed; different categories of user daily load curve segmentation is completed; the fluctuation rate, fluctuation standard deviation, fluctuation degree, high energy consumption proportion and low energy consumption proportion indexes of different fluctuation segments are analyzed, and the type of the fluctuation segment is identified; a group prediction result direct correction prediction model is established for the rising and falling trend load fluctuation segment; a cyclic classification correction prediction model is established for the high energy consumption fluctuation, low energy consumption fluctuation, sharp peak fluctuation and oscillation fluctuation segment; and a fine-grained user complete load curve prediction model is constructed. The application is aimed at fine-grained load which is difficult to predict, improves the prediction accuracy, ensures that the power grid can accurately master the fine-grained load curve change situation, matches the power demand situation of the end user at any time, and helps the rapid development of intelligent energy consumption and point-to-point power transaction.

A method includes receiving a set of electrocardiograms (ECG) determined to belong to a given morphologic template indicative of a given type of arrhythmia. Using a location algorithm, a percentage of the ECGs in the set is calculated, that points to a same source location of the given type of arrhythmia. The calculated percentage is compared to a predefined threshold percentage. If the percentage of ECGs is found to exceed the threshold percentage, the source location is reported to a user.

The invention relates to the technical field of titanium alloy smelting analysis, in particular to a titanium alloy smelting effect intelligent analysis method and system, and the method comprises the steps: recording a smelting event of smelting equipment in a preset time period; recording abnormal events of smelting events in each time of smelting in a single parameter and parameter pair combination mode to form an associated parameter chain; performing mode clustering on the associated parameter chain according to a combined single parameter and parameter pair form, and determining a propagation path after clustering; based on the propagation path, performing single event scoring on each batch of abnormal events, and constructing a batch-index incidence matrix; according to the change trend of each key index in the batch-index incidence matrix during multiple times of smelting, obtaining the transfer relation of abnormal events in multiple times of smelting; determining target parameters of each batch on the basis of a passing relation of abnormal events in multiple smelting, and outputting the target parameters; the accuracy of smelting analysis and the efficiency of dynamic perception are realized.

The invention provides a multi-type railway track inspection data mining and state evaluation method based on knowledge embedding and cross attention. The method aims at solving the key technical problems of adaptive feature extraction, high-dimensional spatial pattern clustering, online real-time evaluation and the like of multi-source heterogeneous data. By constructing a technical system fusing domain knowledge embedding, multi-modal feature alignment and dynamic model optimization, full-process intelligentization from data preprocessing, feature extraction to state evaluation is realized, and an efficient and accurate solution is provided for intelligent operation and maintenance of rail transit.

The invention discloses an enterprise data intelligent storage optimization method and system. The method comprises the steps of enterprise data collection, data access mode preliminary screening, data access mode clustering, alternating refinement and enterprise data storage optimization. The invention belongs to the field of data processing, and particularly relates to an enterprise data intelligent storage optimization method and system.According to the scheme, a dispersion popularity membership degree is introduced, a weakening coefficient is added into a target function, historical access influences are attenuated, the weight of burst high-frequency access is reduced, and then misclassification caused by accidental access is reduced; business association driven local self-adaptive approaching clustering is performed on enterprise data, so that a high-benefit storage scheme can be formulated in a unified manner; a common precision objective function is constructed, and bidirectional matching of the mode and enterprise data association degree is ensured through an alternate precision framework; and the enterprise data intelligent storage optimization effect is improved.

The invention relates to a traffic data prediction method of a space-time diagram network based on sustainable learning, which belongs to the technical field of space-time data mining, and is characterized in that the precision, robustness and generalization of a traffic data prediction model are effectively improved based on a representative traffic mode clustering and matching theory modeling space-time data generation process; according to the method, the representative mode of the vehicle flow data is extracted while the space-time characteristics of the vehicle flow data are captured, and a knowledge base is formed, so that the method better adapts to the dynamic change characteristics of traffic modes.

This invention relates to an intelligent deformation discrimination method based on InSAR temporal deformation patterns and building semantic information, comprising: acquiring InSAR temporal monitoring data and building vector data of the target monitoring area; performing temporal deformation pattern clustering on discrete deformation scattering points to determine the deformation pattern category label of each discrete deformation scattering point; identifying discrete deformation scattering points falling within the polygonal area of ​​the building outline as the internal point set of the building, and identifying discrete deformation scattering points falling within the surrounding foundation ring zone as the surrounding foundation point set; extracting a building-level comprehensive feature vector, including basic statistical feature components, temporal pattern distribution features, and internal and external difference features, using a single building as a unit; inputting the building-level comprehensive feature vector into an unsupervised anomaly detection model to filter out anomaly building sets; inputting the features of the anomaly building sets into an anomaly attribution clustering model, and determining the anomaly cause category of each anomaly building based on the clustering results.

This invention discloses a method and system for battery aging assessment of battery swapping cabinets based on charging pattern clustering, belonging to the field of battery testing technology for battery swapping cabinets. The method includes: analyzing battery charging cycles according to the charging cycle of the swapping cabinet to construct multi-dimensional charging features; performing clustering learning based on these features to construct multiple charging pattern clusters; performing health analysis on the battery based on these clusters to obtain battery health status parameters; retrieving real-time charging data and matching the charging pattern clusters with the health status parameters to determine the target charging pattern cluster; and performing battery aging assessment based on the target charging pattern cluster to generate aging assessment results. This invention solves the technical problems of low assessment accuracy and poor real-time performance caused by the diversity of charging patterns in existing battery aging assessment methods. It achieves refined analysis and dynamic matching of battery health status based on charging pattern clustering, improving the accuracy, scenario adaptability, and real-time responsiveness of battery aging assessment results.

The present application provides a method and system for evaluating the moisture permeability of concrete. The method first obtains moisture gradient change data within the concrete and performs moving average processing on the data to generate smoothed moisture diffusion data. Secondly, based on the diffusion data, the frequency offset data caused by humidity influence is measured in the microwave frequency band, and diffusion features are extracted from the offset data using phase locking technology. The diffusion features are then subjected to spatiotemporal correlation processing to identify hotspot patterns. Finally, pattern clustering processing is performed on the hotspot patterns, grouping them into multiple levels and outputting the concrete permeability rating. The technical solution provided by the present application not only ensures real-time and lossless capture of the microscopic dynamics of moisture migration, but also achieves zero-delay analysis of the true permeability dynamics, fundamentally resolving problems such as manual experience misjudgment and offline simulation inaccuracy.