41 results about "Random field ising model" patented technology

The invention discloses a landslide risk assessment method based on an extreme rainfall and geology coupling model, and relates to the technical field of geological disasters. Comprising the following steps: S1, constructing a three-dimensional probability density field of a fracture network and a non-Gaussian random field model of a permeability coefficient tensor; s2, setting a physical kernel layer according to the non-Gaussian random field model, setting a data driving layer through space-time Transform coding, and constructing a graph attention network model; s3, generating an adversarial network through physical information, constructing extreme rainfall coupling data, and updating the non-Gaussian permeability coefficient random field model according to the graph attention network model; and S4, acquiring an entropy generation rate according to the mechanical field data, the seepage field data and the temperature field data, and determining a risk level. Physical interpretability grading early warning of landslide risks is realized, and meanwhile, risk space distribution can be visually displayed through a sliding surface probability cloud picture, so that accurate decision support is provided for disaster prevention and control.

The invention belongs to the field of cultural heritage digital protection, and discloses an ancient building three-dimensional modeling method based on three-dimensional laser scanning, which comprises the steps of extracting feature points of a point cloud data set and texture image data, and performing registration in combination with a flight log of an unmanned aerial vehicle; performing image restoration and feature extraction on the texture image data and the point cloud-image registration result through a convolutional neural network-probability Markov random field (CNN-PMRF) model; performing geometric feature extraction on the point cloud data set, fusing the texture image feature vector to obtain a geometric-texture joint feature vector, and optimizing a rough mesh model generated based on the point cloud data set; mapping the repaired texture image data to the optimized grid model to obtain a preliminary three-dimensional grid model; and processing the preliminary model parameters through a gradient boosting decision tree (GBDT) model to obtain a correction value, and adjusting the preliminary three-dimensional grid model based on the correction value to obtain an optimal three-dimensional model. The precision of three-dimensional modeling of the ancient building can be improved.

The invention relates to the technical field of intelligent breeding, and discloses a beef cattle identification method based on multi-scale segmentation optimization and multi-modal data fusion, which comprises the following steps: acquiring beef cattle multi-modal image data, carrying out time-space synchronization and fusion to construct a fusion image, carrying out preprocessing of illumination invariant transformation and multi-scale pyramid construction, and carrying out multi-scale segmentation optimization and multi-modal data fusion on the fusion image; generating an enhanced image, inputting the enhanced image into a depth-guided attention segmentation network to extract double-branch foreground features, generating an initial segmentation probability graph, optimizing a segmentation mask in combination with a conditional random field model and a motion consistency constraint, finally extracting multi-dimensional features from the mask, inputting the multi-dimensional features into a multi-classification support vector machine to perform individual classification reasoning, and obtaining a final segmentation result. And obtaining a beef cattle individual identification result. Therefore, the foreground and background segmentation method applied to the intelligent breeding scene for beef cattle individual recognition is provided, the beef cattle individual recognition precision is improved, and meanwhile the management requirements of commercial breeding for high precision, high stability and multi-scene adaptability are met.

The invention relates to the technical field of sleep quality evaluation, in particular to a sleep monitoring optimization system based on artificial intelligence. The system comprises the steps of collecting sleep monitoring data of a user at different collection moments, extracting dominant frequency components in snore audio data through spectrum envelope analysis, extracting audio primitives based on the dominant frequency components, inputting the audio primitives into a snore classification model, outputting a snore category corresponding to the snore audio data of the user, and outputting the snore category corresponding to the snore audio data of the user. Carrying out Bayesian inversion analysis on the brain wave data to obtain a posterior sample of random field model parameters, executing reliability analysis based on the posterior sample to calculate a posterior failure probability, obtaining a first sleep quality index of the user based on the posterior failure probability, obtaining a second sleep quality index of the user based on vital sign data analysis, and sending the second sleep quality index to the user; and obtaining a user sleep quality evaluation result based on the snore type, the user first sleep quality index and the user second sleep quality index. The accuracy and efficiency of user sleep quality evaluation can be improved.

The invention relates to an artificial intelligence image segmentation processing method and device, equipment and a medium. The method comprises the following steps: acquiring pixel intensity distribution of an input image and extracting local features by using a convolutional neural network to generate a pixel intensity change feature map; on the basis of the feature map, boundary area probability distribution is calculated by using a conditional random field model, and a zigzag edge is smoothed by using a graph cut algorithm to generate a continuous segmentation boundary; splicing the continuous segmentation boundary and an input image, inputting the spliced continuous segmentation boundary and the input image into a Transform enhanced U-Net network, balancing edge alignment loss and region overlapping precision loss through a dynamic weighted loss function, and generating an optimized segmentation mask; and performing threshold binarization processing on the optimized segmentation mask, removing isolated noisy points in combination with morphological closed operation, and generating a segmentation image matched with the physical defect form. By adopting the method, the continuity of segmentation boundaries and the matching precision of defect forms can be improved, and the problems of edge sawteeth and noise interference in traditional segmentation are solved.

The invention provides a single photon and visible light image fusion method and system based on a multi-scale Markov random field model, and belongs to the technical field of multi-modal image fusion. In the long-distance target ranging and imaging process, a multi-sensor fusion method is used, the high resolution advantage of a visible light intensity image is utilized, the problems that a single-photon laser radar is small in point cloud density and low in image resolution are effectively solved, and the sensing capacity of the single-photon laser radar for scene target information is effectively enhanced; by using the fusion method based on the multi-scale Markov random field model, the structural consistency and the anti-interference capability are enhanced, global structural deviation or local overfitting under a single scale is effectively avoided, and the method is suitable for image fusion under multi-modal and complex scenes.

The invention discloses a method and a device for predicting gas-water two-phase productivity of a fractured horizontal well. The method comprises the following steps: establishing a target block heterogeneous permeation Gaussian random field model and a target well reservoir geologic model; establishing a corresponding coarse scale grid, a fine scale grid and a dual control volume grid based on the target well reservoir geologic model; determining a dual basis function for mutual mapping of the coarse-scale grid and the fine-scale grid according to the coarse-scale grid, the fine-scale grid and the dual control volume grid; discretizing a control equation corresponding to the coarse-scale grid, and calculating pressure in cracks and a matrix on the coarse grid according to the heterogeneous permeation Gaussian random field model of the target block; according to the dual basis function, the pressure in the cracks and the matrix on the coarse grid is mapped to the fine-scale grid; and determining the gas-water two-phase productivity of the target well according to the cracks on the fine-scale grids and the pressure in the matrix.

This application pertains to the field of address recognition technology. It provides a method, apparatus, device, and storage medium for Chinese address recognition. The method includes: acquiring user-annotated query text; matching the query text with administrative addresses in a Chinese address map; when an administrative submap in the Chinese address map matches the query text, using the matching submap as the target submap; injecting the target submap into the query text to form a sentence tree; preprocessing the sentence tree and inputting it into a pre-built K-BERT model for encoding to obtain a semantic information matrix; inputting the semantic information matrix into a Bi-LSTM deep model to obtain a label score sequence; and using a CRF (Conditional Random Field) model to construct constraint relationships between labels, generating Chinese address recognition results. This provides the model with rich prior information, reduces model learning complexity, and accelerates model convergence.

The invention belongs to the technical field of anti-seepage curtains of red-bed landfills, and discloses an optimal design method for a vertical anti-seepage curtain of an irregular landfill in a red-bed region, which adopts a drilling, geological radar and X-ray diffraction combined technology in the exploration and data acquisition stage to clearly distinguish hydrophilic expansive mudstone and high-permeability sandstone, and the optimal design method for the vertical anti-seepage curtain of the irregular landfill in the red-bed region is provided for the vertical anti-seepage curtain of the irregular landfill in the red-bed region. A space coupling model of the pile body and the red rock stratum is established by means of three-dimensional laser scanning, and the lithologic boundary of the dual seepage system is defined; in the model construction stage, parameter distribution is analyzed through a Markov random field model, regular updating is conducted in combination with a Kalman filtering algorithm, and dynamic changes such as sandstone fracture expansion caused by pile settlement can be adapted; a modified bentonite and nanoscale montmorillonite composite material is used in a sandstone area, construction is conducted through a high-pressure jet grouting technology, the permeability coefficient is set to be that the insertion depth extends to the complete bed rock by 2-2.5 m, and the problem of local leakage caused by the fact that the seepage-proofing design is not matched with the actual conditions of a red layer is solved.

The application discloses a method and a device for monitoring effluent orthophosphate concentration and resisting analyzer deviation, and relates to the technical field of sewage treatment. In the method, the monitoring device firstly constructs a state space vector according to operation parameters in a sewage phosphorus removal process, and then constructs a dynamic Markov random field model by taking a true value of effluent orthophosphate concentration as a hidden state variable and the state space vector as an observation variable. After predicting a prior probability distribution based on the model and a historical sequence, when the measurement value of the analyzer is lower than a precision threshold value, the prior probability distribution and the observation value are fused by using a Kalman filtering algorithm to obtain a calibrated concentration value and output the calibrated concentration value to a control system to guide reagent adjustment. In this way, the accuracy and reliability of detection of the effluent orthophosphate concentration are improved when the orthophosphate concentration in the effluent water sample is extremely low.

In order to explore the effectiveness of the functional data analysis method in the hyperspectral image processing, the application proposes a classification method combining the Gaussian regression mixture model and the MRF hyperspectral function data; first, the polynomial regression is used to fit the hyperspectral image pixel spectrum curve, so as to express the pixel spectrum information in the form of function; then, the neighborhood relationship is introduced to establish the Markov random field model, and the neighborhood Gaussian regression mixture model is established in combination with the Gaussian regression mixture model; finally, according to the maximum posterior probability criterion, the final hyperspectral image classification result is obtained. Since the spatial-spectral information of the hyperspectral image is fully combined, the algorithm has high-precision classification result, and effectively improves the classification performance of the hyperspectral image.

This invention discloses an environmental anomaly broadcasting method and system based on semantic analysis and knowledge graph, belonging to the field of environmental anomaly detection technology. Key technical points include: acquiring the current inspection record text and performing semantic analysis to obtain text keywords; determining the nodes corresponding to the text keywords in a preset knowledge graph based on a conditional random field (CRF) model; training the CRF model according to a preset constraint matrix; the types of nodes in the knowledge graph include enterprises, emission outlets, processes, pollutants, and sensitive targets; obtaining anomaly information corresponding to the current inspection record text based on the association relationship between the nodes corresponding to the text keywords and nodes of each type in the knowledge graph; and broadcasting the anomaly information. This invention improves the accuracy of node positioning and generates more accurate anomaly information by constructing a constraint matrix to clarify the matching rules between text and nodes and training the CRF model accordingly.

The application relates to the field of artificial intelligence and discloses a target recognition method and system based on deep learning, which comprises the following steps: acquiring visible light and infrared images of the same scene, generating illumination invariance features through an adversarial training network; modeling the feature sequence by using a space-time joint network to generate an initial recognition result; performing space-time verification on the initial recognition results of continuous multiple frames by using a Markov random field model to generate a calibrated recognition result; and performing online model calibration on the space-time joint network based on the correction deviation between the initial recognition result and the calibrated recognition result. The application also provides a recognition system for executing the method. Through the synergistic mechanism of multi-modal feature decoupling, space-time joint modeling and verification, and online feedback calibration, the application effectively improves the all-weather adaptability, recognition accuracy and trajectory continuity of the system in complex scenes such as illumination changes and target occlusions.

This application relates to the field of relational network analysis in artificial intelligence, specifically to a user differentiation method, apparatus, device, and medium based on content and network features, comprising: acquiring a social network graph; acquiring node features of each node based on the social network graph; inputting the node features into a Markov random field model to obtain a first classification result of the node; extracting content features from the content information; inputting the content features into a trained content classification model to obtain a second classification result of the content features; and determining the user type of the node based on the first classification result and the second classification result. This application combines the different characteristics of content features and network features, utilizing more comprehensive user information to detect whether users on social network platforms are spam accounts, making it less likely for malicious users to bypass the detection.

The application provides a coal mine main fan frequency converter speed regulation method based on random wind speed field prediction. First, wind measuring points are arranged in underground stoping working faces, tunneling working faces and air shafts. According to various data monitored by the wind measuring points, information prediction is carried out, and a graph neural network is established to calculate air supply. According to the real-time air volume calculated by the graph neural network, the relationship between the control frequency of the main fan frequency converter and the real-time air volume is obtained, and the frequency converter control frequency is calculated. The beneficial effect is that the present application takes the random field as the theoretical basis, takes each key ventilation detection in the underground as the vertex of the random field, takes the ventilation detection result as the attribute of the vertex, establishes an underground ventilation control random field model, then establishes a field data prediction model to predict the future information of the wind field, thereby guiding the ventilation regulation of the main fan and effectively improving the response speed of the ventilation control.

The application relates to a recommendation method based on social network user behavior information, which comprises the following steps: obtaining user behavior data and obtaining user activity holding location preference and holding time preference; constructing a preference similar network by using the obtained user preference, and then fusing a user online social relationship network to obtain a plurality of non-overlapping community structures reflecting the social connection and preference similarity between users; calculating the value of each hidden point representing the user's decision on a project by using a hybrid pairwise Markov random field model; calculating all node states of each project, and then selecting a recommendation list by sorting. The application aims to recommend the optimal activity holding location and holding time for an activity organizer, so as to maximize the number of participants in the activity and meet the decision planning needs of the activity organizer.

The invention discloses an environmental anomaly broadcasting method and system based on semantic analysis and a knowledge graph, and relates to the technical field of environmental anomaly detection.The technical scheme is characterized by comprising the steps that a current inspection record text is obtained and subjected to semantic analysis, and text keywords are obtained; determining a node corresponding to the text keyword in a preset knowledge graph according to a conditional random field model; the conditional random field model is obtained by training according to a preset constraint matrix; the types of nodes in the knowledge graph comprise enterprises, discharge ports, processes, pollutants and sensitive targets; obtaining abnormal information corresponding to the current inspection record text according to the association relationship between the node corresponding to the text keyword and each type of node in the knowledge graph; according to the method, the matching rule between the text and the node is defined by constructing the constraint matrix, and the conditional random field model is trained according to the matching rule, so that the accuracy of node positioning is improved, and more accurate abnormal information is generated.

The invention relates to the technical field of radar data processing, in particular to an environment sensing method for constructing a grid map based on a navigation radar, which comprises the following steps: acquiring maritime radar original echo data; dividing the environment area into a grid map; mapping to a grid rectangular coordinate system, and distributing an initial occupancy probability; radar and electronic chart data are fused, the grid occupancy probability is updated, and time sequence optimal estimation is carried out; carrying out space correlation optimization, and carrying out space-time compensation on the electronic chart area; outputting a binary grid map; compared with the prior art, the radar scanning data is directly subjected to independent grid probability updating, so that the continuity of a real physical environment cannot be reflected; according to the scheme, a Markov random field model is introduced, a grid map is modeled into an undirected graph network, radar split targets are effectively aggregated by defining an eight-connection neighborhood system and a Pots energy function, discretization misjudgment is eliminated, the obstacle boundary is smooth and continuous, and physical rationality and navigation safety are improved.

A computer-implemented method (100) for system optimization using distributed quantum computing performed by a network node The optimization problem can be represented as a factorizable Markov random field, MRF, model. The method comprises partitioning (S101) a graph structure of the MRF model into two or more partitions based on a cost function of the optimization problem. The method comprises mapping (S105) the optimization problem onto a plurality of trainable quantum circuits, each trainable quantum circuit corresponding to a partition of the two or more partitions. The method comprises initiating training (S107) each of the trainable quantum circuits on a separate quantum processing unit of the distributed quantum computing device. Further disclosed are a related network node, quantum computing device, computer program, and computer program product.

The application belongs to the field of digital protection of cultural heritage, and discloses a three-dimensional modeling method for ancient buildings based on three-dimensional laser scanning, which comprises the following steps: extracting feature points of point cloud data sets and texture image data and combining with unmanned aerial vehicle flight logs for registration; performing image restoration and feature extraction on the texture image data and point cloud-image registration results through a convolutional neural network-probabilistic Markov random field (CNN-PMRF) model; performing geometric feature extraction on the point cloud data sets and fusing texture image feature vectors to obtain geometric-texture joint feature vectors, and optimizing a rough grid model generated based on the point cloud data sets; mapping the restored texture image data to the optimized grid model to obtain a preliminary three-dimensional grid model; processing preliminary model parameters through a gradient boosting decision tree (GBDT) model to obtain a correction value, and adjusting the preliminary three-dimensional grid model based on the correction value to obtain an optimal three-dimensional model. The application can improve the accuracy of three-dimensional modeling of ancient buildings.

The application provides a game role behavior control method and device and electronic equipment; wherein the method comprises: obtaining current state data of a target game; inputting the current state data into a pre-trained machine learning model to obtain a first output result; wherein the first output result comprises probabilities corresponding to a plurality of preset behavior operations; obtaining a specified number of historical output results of the machine learning model; inputting the first output result and the historical output result into a pre-trained conditional random field model to obtain a target behavior operation. In this way, the machine learning model and the conditional random field model are combined, the machine learning model and the conditional random field model can both establish a relationship between a state and a behavior operation, the conditional random field model can also establish a time sequence relationship between behavior operations, the intelligent degree of the game AI can be high, and meanwhile, the model structure is simple and easy to converge, and has strong applicability.

The invention relates to the technical field of health management and digital asset interaction, and discloses an online and offline linked intelligent calorie exchange system, in which an online and offline linked intelligent calorie exchange method comprises the following steps: acquiring a multi-source sensor data stream of group sports participants, and generating a spatio-temporal data matrix; using a conditional random field model to fuse individual mode recognition results, and outputting a corrected motion mode tag sequence; calculating a calorie consumption value of each participant based on the corrected motion mode label sequence, and generating a calorie integral result; obtaining a social relation graph of the group exercise participants, and generating a social network topological graph; member data of different trust levels are integrated based on Bayesian inference, and calorie calculation parameters are dynamically adjusted. According to the invention, the credibility of the whole transaction ecology is improved, and a high-quality value voucher is provided for offline commodity exchange.

The present invention discloses a seismic probability analysis method for corroded natural gas pipelines that considers the random spatial correlation of soil parameters. The method comprises establishing a random field model of soil along the pipeline axis; establishing a seismic response model for the corroded natural gas pipeline based on the random field model; performing a probability analysis on the seismic response model of the corroded natural gas pipeline to obtain a probability density function and a cumulative density function; and calculating the failure probability of the corroded natural gas pipeline. The present invention provides a seismic probability analysis method for corroded natural gas pipelines that considers the random spatial correlation of soil parameters to address the inaccuracy of seismic probability analysis for buried corroded natural gas pipelines in the prior art. The method analyzes the seismic damage probability of corroded pipelines while accounting for the uncertainty of soil properties, thereby improving the accuracy of seismic probability analysis.

The present disclosure provides a large three-dimensional tunnel surrounding rock parameter random field model construction method and system, relates to the tunnel surrounding rock modeling technical field, and includes: fitting and constructing a probability distribution model reflecting surrounding rock parameters; selecting multiple surrounding rock parameters as clustering features, quantitatively classifying the global geological structure in the tunnel surrounding rock, and decomposing the global tunnel model into continuous subdomains containing overlapping buffer zones; for the first subdomain started in any direction of the global tunnel model, the KL decomposition method is used for covariance matrix spectral decomposition to generate the first subdomain random field, and the random field value of the overlapping area between the subdomains is extracted as the boundary condition data of the recursive generation process; based on the boundary condition data, the conditional random field of the subsequent subdomain is generated layer by layer; the conditional random fields of each subdomain recursively generated are seamlessly spliced into the global parameter random field, the probability mapping method is used to convert the probability distribution, the cross-platform data interface engine is developed to encapsulate instructions, and the construction process of the parameter random field model is realized.

The invention belongs to the technical field of preparation of rock samples, and particularly discloses a preparation method of a rock sample containing space correlation random joints based on 3D printing, and the preparation method comprises the following steps: manufacturing a sample outer mold and a joint steel insertion strip according to the specification of the rock sample; the method comprises the following steps: acquiring spatial distribution parameters of random joints in a rock mass through geological survey, and generating a spatial correlation random joint group by adopting a random field model according to the acquired spatial distribution parameters of the random joints; a three-dimensional cover plate model is established according to the generated space correlation random joint group, cover plate holes used for installing joint steel insertion strips are formed in the three-dimensional cover plate model, and then a 3D printer is used for printing to obtain a 3D printing cover plate; and loading the prepared cement mortar into the assembled sample outer mold, covering with a 3D printing cover plate, inserting the joint steel insertion strip coated with the release agent into a cover plate hole, pulling out the joint steel insertion strip after the cement mortar is cured, and demolding and curing the sample to obtain the rock-like sample.

The invention discloses an expressway base layer global moisture content detection method based on a three-dimensional ground penetrating radar, which comprises the following steps: constructing a three-dimensional multiphase random medium electromagnetic simulation model by considering aggregate grading and a pore structure; based on the model, simulating the propagation process of radar waves in a base layer under different moisture content conditions to obtain simulated radar reflection wave data; the A-scan waveform is converted into an A-scan waveform; extracting a reflected wave mean value, a standard deviation and a peak value coefficient, so as to establish a reflected wave intensity-dielectric constant-moisture content three-variable regression model; based on a line tracking theory, inversing an actually measured dielectric constant through actually measured reflected wave two-way travel time and horizon thickness; calculating actually measured moisture content data by utilizing the actually measured dielectric constant obtained by inversion; and constructing a complete random field model representing the spatial variability of the moisture content, and carrying out constraint and calibration on the random field model by taking the actually measured moisture content as a sample point through a Kriging interpolation method, so as to generate a base-layer global moisture content visual distribution diagram.

A large-size structural plane first-order and second-order fluctuation grading sampling measurement method belongs to the technical field of geotechnical engineering, and comprises the following steps: measuring the length of a structural plane along a shearing direction, determining a frequency demarcation point of first-order and second-order fluctuation components according to an empirical formula, and determining a sampling interval of the first-order fluctuation components, performing sparse measurement on the large-size structural surface; the method comprises the following steps: arranging a plurality of small-size measurement areas on a structural plane, obtaining a two-dimensional contour line or a three-dimensional structural plane morphology, extracting a second-order fluctuation component through frequency domain filtering, calculating a fluctuation angle statistical characteristic, evaluating a measurement error based on a confidence interval, and adaptively determining the measurement number of small-size structural planes; and establishing a random field model of the second-order fluctuating component, generating the second-order fluctuating component with the same size as the large-size structural plane, and superposing the second-order fluctuating component with the actually measured first-order fluctuating component to obtain a structural plane digital model. On the premise of guaranteeing the measurement precision, the number of measurement points and the measurement workload are reduced, and the applicability of large-size structural plane measurement engineering is improved.

The application discloses a kind of narrow river detection methods suitable for spaceborne wide swath interferometric radar altimeter image, comprising: reading into spaceborne wide swath interferometric radar altimeter image;It is enhanced river linear feature by Gaussian difference preprocessing to suppress background;Curvature structure perception detector is constructed, curvature response map is calculated based on Hessian matrix eigenvalue, and feature fusion enhancement is carried out in conjunction with multi-direction structure consistency score;The binary image obtained by adaptive threshold segmentation based on local statistics is used as region label by carrying out adaptive threshold segmentation to enhanced feature map, maximum value is extracted in the region corresponding to enhanced feature map, seed point set is formed, and adaptive region growth based on queue priority is executed, to generate initial river center line;Markov random field model is introduced, global structure optimization and topological connectivity correction are carried out using graph cut algorithm, to obtain optimized river center line;Direction and radiation characteristic constraint is applied again, morphological dilation is carried out, and finally complete river mask is generated.

The invention discloses a space-based infrared dim and small target detection and calculation integrated detection method based on a vector signal, and aims to overcome the bottleneck of low timeliness and large resource consumption of a traditional imaging-caching-preprocessing-detection link, skip an image caching and preprocessing link and directly take a DN value vector signal read by a detector row as input. Wherein two-dimensional or higher-dimensional features of a target are recovered from a one-dimensional vector signal through a network based on CNN and BERT mechanisms and by means of a Markov random field model; target and background clutter features are decoupled by using a network based on a self-supervised U-Net structure, and target features are selectively enhanced in combination with a multi-scale detection mechanism to complete detection; a network is lightened through a multi-teacher knowledge distillation architecture, and pruning and quantification are combined to obtain a lightweight detection model suitable for an on-satellite resource limited environment. According to the invention, integration of detection and calculation is realized, and timeliness and resource efficiency of space-based infrared weak and small target detection are significantly improved.

The embodiment of the application belongs to the technical field of data processing, and relates to a thread running state classification method and device, computer equipment and a storage medium. In addition, the application also relates to blockchain technology, and the classification result of a user can be stored in a blockchain. The application performs data interception on a stack in a sample thread through a preset hook technology and labels type information, does not need to label all data one by one, greatly reduces the time of data labeling under the premise of ensuring labeling accuracy, effectively improves the efficiency of data labeling, converts labeled stack data with type information into a vector after type labeling is completed, obtains training data used for training a model, and trains a conditional random field model according to the training data. After the model training is completed, the trained conditional random field model can be called to automatically classify the obtained threads, and the efficiency of classifying thread running states is greatly improved.