219 results about "Transition matrices" patented technology

The present invention relates to the related technical field of natural language inference. Disclosed is a large language model joint inference method based on a knowledge graph-enhanced chain-of-thought prompt, comprising: constructing a local knowledge subgraph; decomposing an original question text into S sub-question texts and concatenating the original question text and the S sub-question texts; inputting a concatenated question text into a graph inference model to obtain a weighted entity distribution; from the weighted entity distribution, extracting first G answer entities having the highest confidence level, using an inference transition matrix to trace an inference process of each answer entity, and generating an inference path from a question entity to the corresponding answer entity; and using the inference path to assist a large language model in predicting an answer to the original question text. By means of the method, the large language model can quickly and accurately find an answer to a question text.

The invention discloses an unmanned aerial vehicle cluster patrol path decision-making method under resource constraint, and relates to the technical field of unmanned aerial vehicle path planning, and the method comprises the steps: carrying out the discretization of an actual to-be-patrolled physical position, and constructing an undirected topological graph; generating steady-state distribution of each patrol node according to topological constraints and importance degrees of the nodes; generating a plurality of transfer matrixes with the same steady-state distribution and different transfer characteristics according to a multi-stage entropy driving random matrix optimization algorithm; initializing the position of a navigator according to the transfer matrix and determining a selected path; according to the reference path of the navigator, the self-adaptive active positioning decision is realized under the positioning constraint to ensure the path tracking effect; according to path selection and tracking of the navigator, the follower and the navigator form a humanoid marshalling cluster through a reward function; and according to the multi-state transfer matrix and the humanoid marshalling, automatically switching to the next transfer matrix when a transfer frequency threshold value is reached, and realizing unmanned aerial vehicle cluster intelligent patrol path decision under resource constraint.

The invention discloses a high-precision continuous tracking method for a strong-maneuvering infrared weak and small target under a space-based detection visual angle, and the method comprises the steps: obtaining the uncertainty measurement of a target at a non-maximum suppression stage of a detection result, and enabling the uncertainty measurement to act on a target state updating and data association stage; therefore, the experience distribution of the detector is fully transmitted to the tracking process, and the tracking accuracy is improved. In order to cope with a complex target maneuvering state, an interactive multi-model technical route is adopted to design a tracking algorithm; in order to reduce the dependence on a prior motion model, a dynamic Markov transfer matrix construction method is designed, and the model transfer probability is updated in a mode of comprehensively modulating historical dynamic information and current static information; in a data association stage, targets with different scales are associated by integrating advantages of IoU and NWD, uncertainty is transmitted to a cost calculation process, and tracks and targets which are indefinitely matched are processed based on scale invariant and energy invariant hypotheses, so that high-precision continuous tracking of the targets is realized.

The invention belongs to the field of unmanned aerial vehicle control, and particularly relates to a complex task-oriented unmanned aerial vehicle modular integrated control platform, which comprises an acquisition module for acquiring and processing information such as a real-time flight state of an unmanned aerial vehicle group, a complex task text, meteorological data and the like; the task analysis module decomposes a complex task into a single subtask set and an incidence matrix, and evaluates the task complexity for resource allocation; the atmospheric analysis module is used for inverting a real-time flight association adjustment graph based on the corrected meteorological data, flight states and the like in combination with a target optimization algorithm and an optimization function taking resource quantity minimization and task completion probability maximization as targets; the record analysis module generates a performance transfer matrix by using a hidden Markov algorithm; and the flight control module responds to the adjustment graph to correct the flight state, and ensures that the task completion probability meets a preset safety threshold. According to the platform, efficient cooperative control and resource optimization allocation of the unmanned aerial vehicle group under complex tasks are realized through modular integration.

The invention discloses a time-frequency analysis method for impact signal positioning based on transient scale extraction transformation, and belongs to the technical field of mechanical vibration signal processing. The method comprises the following steps: collecting a rotating machine fault vibration signal, and reconstructing a signal model through Hilbert transform and a Dirac function; a transition matrix is generated by using a Gaussian window function traversal model, and matching and Fourier transform are carried out in combination with a discretized scale basis function; solving a frequency partial derivative of a transformation result to generate a time redistribution operator, and redefining by a Dirac function to obtain a transient scale extraction operator; based on the sub-time-frequency representation of scale-based rotation discretization, screening optimal matching results of each time center through a maximum kurtosis value, and integrating the optimal matching results into a complete time-frequency representation; and finally, redistributing a time-frequency coefficient by using a transient extraction operator to realize accurate positioning of the impact component. According to the method, the problems of serious impact energy diffusion and insufficient positioning precision in existing time-frequency analysis are solved, and the time-frequency representation readability and the impact positioning reliability are remarkably improved.

The invention discloses a complex network importance node evaluation method based on group interaction. The method comprises the following specific steps: step 1, carrying out community division on a network through a Louvain algorithm; step 2, constructing a Louvain bipartite graph; step 3, obtaining an outgoing transfer matrix and an incoming transfer matrix; step 4, obtaining an extended transfer matrix according to the outgoing transfer matrix and the incoming transfer matrix; 5, expanding the transfer matrix to obtain an enhanced transfer matrix; step 6, calculating the importance score of each node; 7, arranging the nodes in the network in a descending order according to the importance score of each node; and step 8, identifying important nodes of the network through a network disintegration algorithm. According to the method, based on group interaction, the interaction between nodes which are not directly connected is considered, the random walk is expanded to the Louvain bipartite graph, and the concepts of outgoing walk and incoming walk are added; and in combination with a network disintegration algorithm, the key nodes in the network are efficiently and accurately identified, and the robustness and the stability are high.

The invention relates to the technical field of underwater pipeline measurement, in particular to a manifold connection pose measuring device suitable for an underwater limited space and a solving algorithm. The device comprises an angle measuring mechanism and a rope length detecting mechanism, and is fixed on a flange end face of a detected pipeline through a centering mechanism; the angle measuring mechanism is composed of an orthogonal shaft system and a magnetic coupling encoder, and the linear displacement is mapped into an angle signal by combining a sliding rail and a measuring rope extension arm; the rope length detection mechanism winds a stainless steel measuring rope through a friction hub in an anti-corrosion shell, and the number of rotation turns is detected through an encoder so as to calculate the rope length. The method comprises the steps of establishing a measuring rope infinitesimal stress model, calculating a suspension curve based on a parabola theory, constructing an absolute coordinate system and a reference coordinate system, and resolving the relative pose of the two pipelines through pose parameters and a transition matrix. The working load of a diver is reduced through lightweight design and a low-friction shaft system, and high-precision pose measurement is achieved by combining the parabola theory and dynamic coordinate transformation.

The invention discloses a self-adaptive integrated navigation method based on geometric accuracy factors, which belongs to the technical field of underwater navigation and positioning, is used for underwater navigation and positioning, and comprises the following steps: initializing an inertial navigation system and an integrated navigation filter, and setting a state vector and a noise covariance matrix; predicted navigation parameters of the recursive carrier are mechanically arranged through inertial navigation, and the state transition matrix is used for state prediction; and dynamically adjusting an observation noise covariance matrix according to the geometric precision factor value, further calculating a Kalman gain, performing optimal estimation and correction on a prediction state by fusing acoustic observation information, and finally outputting a high-precision carrier position, speed and attitude. According to the method, the statistical characteristics of observation noise are dynamically remodeled by calculating and feeding back geometric precision factor values in real time, so that the Kalman filter has the capabilities of knowing the own geometric situation and adjusting the trust degree of each information source, and the global optimal navigation precision and reliability are realized under any motion track.

A label noise estimation method based on a manifold regularization transfer matrix provided by the present invention pre-trains a first network in a second network, and after distilling a data set, inputs the obtained sub-data set into the second network to obtain the probability of the class to which the data instances in the sub-data set belong and obtain a transfer matrix related to the data instances; further calculates the cross-entropy loss of the second network according to the data instance labels, and combines an association matrix expressing the consistency of the data instances belonging to the same manifold and a penalty matrix of the data instances belonging to different manifolds to calculate the loss function of the second network; adjusts the loss function to reduce the training of the second network to obtain a trained second network, thereby completing the estimation of the class to which the data instances belong. The present invention can reduce the estimation error without affecting the approximation error of the transfer matrix, and experiments prove that the present invention can achieve excellent performance in label noise learning.

The invention relates to a target track association method in a multi-target environment. The method comprises the following steps: firstly, preprocessing a new received trace point; secondly, predicting the next position of each track by using the existing track historical information and adopting a Kalman filtering algorithm, meanwhile, adjusting a state transition matrix and a process noise covariance matrix in real time by considering factors such as ocean current and wind direction in an offshore environment, and adjusting an observation noise covariance matrix according to meteorological information; then comprehensively considering distance, speed difference and motion direction difference to calculate a correlation degree magnitude between a new receiving trace point and each predicted track position; and finally, judging whether the newly received trace point belongs to the existing target track or forms a new target by adopting a threshold judgment method according to the correlation degree value, and updating the state of the track. The method can effectively cope with multi-target intersection, observation loss and clutter interference, improves the stability of a matching result, can realize continuous tracking of a marine target, can adjust parameters according to the environment and target characteristics, and has high adaptability.

Systems and methods for assigning a lane to an object in an environment of an autonomous vehicle are disclosed. The methods include assigning an instantaneous probability to each of a plurality of lanes in the environment based on a current state of the object, generating a transition matrix for each of the plurality of lanes, and identifying the lane in which the object is moving at the current time t based on the instantaneous probability and the transition matrix. The instantaneous probability is a measure of likelihood that the object is in that lane at a current time. The transition matrix encodes one or more probabilities that the object transitioned either into that lane or out of that lane at the current time.

The invention belongs to the technical field of intelligent vehicles, and discloses an autonomous mobile robot multi-target tracking method and system based on a dynamic adaptive motion model. Detecting object information in the environment, and obtaining detection frame data of each frame of laser radar and camera; laser and camera data are projected to the ground to calculate the Euclidean distance so as to realize multi-sensor fusion and different frame data association operation. A corresponding adaptive state transition matrix is set for a previous frame trajectory, and a prediction bounding box and a covariance matrix of the previous frame trajectory in a current frame are calculated by using a Kalman filtering technology. The long-term and short-term memory module stores historical information of a management target and dynamically adjusts a tracking strategy and parameters. According to the invention, the tracking effect of the multi-target tracking algorithm on the autonomous mobile robot is successfully improved, powerful technical support and guarantee are provided for the intelligent robot to realize accurate multi-target tracking and efficient operation in a complex environment, and further development of the intelligent robot technology in practical application is powerfully promoted.

This invention relates to the field of data prediction technology, specifically to a collaborative control method for the opening degree of hydropower station gates based on BeiDou technology. This method constructs state parameters and analyzes the transition of these parameters over historical periods to obtain the transition probability for each state parameter transition. By combining the correlation between meteorological data and opening data, as well as the correlation between historical meteorological data and predicted meteorological data, the transition probabilities are continuously weighted to obtain a second weighted transition probability. The quantitative characteristics of the state transition of the flood discharge channel gate under its predicted state transition are statistically analyzed for the non-flood discharge channel gate, thereby obtaining the upper-level influence weight, obtaining the second state transition matrix of the flood discharge channel gate, and performing state prediction. This embodiment of the invention, by combining the influence of historical meteorological data and further combining the control influence between gates, obtains accurate gate state prediction results.

The invention discloses a bridge cluster multi-agent full-period maintenance decision-making method under deep reinforcement learning, and the method comprises the steps: firstly dividing a bridge into an upper structure, a lower structure and a bridge deck system, and constructing a simulation environment of bridge cluster maintenance; defining the condition and bridge age of each bridge structure in the bridge cluster; defining three intelligent agents, namely agentsup, agentsub and agentdeck, respectively corresponding to the three part structures, and carrying out training and execution of bridge cluster maintenance; defining a state space and an action space of the deep reinforcement learning method; designing a reward function and determining a state transition matrix; constructing a plurality of agent networks based on a deep Q network algorithm, and training an agent neural network; and finally, testing the capability of the intelligent agent in practical application, and displaying a test result to a user. According to the invention, the structure complexity is greatly simplified, and the method is an important basis for practical application of the maintenance framework.

The invention provides a gas concentration detection method, a gas concentration detection device and electronic equipment. The method comprises the following steps: acquiring a spectral signal obtained by detecting to-be-detected gas in a gas cell by a quantum cascade laser under preset sampling parameters; calculating search direction information and search distance information according to the spectral signal and the initial matrix; calculating a transition matrix according to the spectral signal, the search direction information and the search distance information to remove redundant information in the spectral signal; under the condition that a change value between the transition matrix and the initial matrix meets a preset threshold value, determining the transition matrix corresponding to the change value as a target matrix; performing calculation and filtering processing on the target matrix and a preset reference signal to obtain a direct current filtering signal related to the direct current signal; performing signal conversion processing on the direct current filtering signal to obtain a target harmonic signal; and inputting the target harmonic signal into a gas concentration prediction model, and outputting gas concentration information of the to-be-detected gas.

The invention relates to the technical field of attitude estimation, in particular to an attitude estimation method in a magnetic interference environment, which comprises the following steps of: obtaining a conversion relation between an Euler angle and a quaternion; calculating the quaternion at the next sampling moment; respectively solving a first state transition matrix, a first process noise matrix and a first prior covariance according to the first state equation; respectively solving a second state transition matrix, a second process noise matrix and a second prior covariance according to a second state equation; elements in the nb-series rotation matrix are used as observed quantities of state variables in the parameter-series rotation matrix, a corresponding Kalman gain is calculated, and a Jacobian matrix is designed by using the observed quantities; calculating an observation noise covariance matrix by using the Jacobian matrix; updating the Kalman gain by using the observation noise covariance matrix; and updating the state equation and the posterior covariance by using the updated Kalman gain and the observed quantity. The method solves the problem of how to prevent the calculation of the roll angle and the pitch angle from being influenced by magnetic interference when the magnetic interference exists.

The invention provides a river trajectory data protection method based on differential privacy, and belongs to the field of environmental data privacy protection. According to the method, river flow velocity and flow direction data are discretized into a two-dimensional grid, spatial-temporal characteristics are extracted by using a graph convolutional network (GCN), and a Markov transfer matrix is established; and according to the grid access frequency and the spatial density, privacy budget is adaptively allocated through a dual attenuation factor model, and differential privacy protection is realized. In the trajectory generation stage, dynamic privacy budget is combined, noise is injected into direction and time features by adopting an index mechanism and a Laplace mechanism, and a synthetic trajectory conforming to physical constraints is generated; and finally, evaluating and optimizing the track quality by using Savitzky-Golay filtering and multiple indexes (such as Frechet distance, access frequency error and KL divergence). According to the method, the privacy leakage risk is effectively reduced while the space-time continuity of the trajectory is kept, the data privacy and availability are considered, and the method is suitable for hydrological monitoring, ecological analysis and environmental data sharing.

The invention provides a method, device and equipment for promoting retention through interaction scene prediction and a storage medium, and the method comprises the steps: obtaining a current multi-modal interaction data stream between users in an interaction scene, carrying out the preprocessing of noise filtering, framing processing, size normalization, time aggregation and the like, extracting emotion features, and generating a real-time multi-dimensional observation vector sequence. The sequence captures complementarity and time sequence dependence of multi-modal information, and overcomes limitation of single-modal static analysis. The observation vector sequence is input into a pre-trained hidden Markov model, and the model is trained based on historical sequences and defines a hidden state set, an initial probability, a transfer matrix and an emission probability; the optimal emotional state path at the current moment is obtained through Viterbi algorithm reasoning, and probability modeling and dynamic prediction of emotion transfer uncertainty are achieved. The current emotion state is extracted from the path, the mimicry representation of the virtual pet is driven to be displayed on the interactive interface, visual feedback is formed, emotion connection is enhanced, and the user retention rate is increased.

The present application discloses a method for making patrol path decisions of a swarm of unmanned aerial vehicles (UAVs) under resource constraints, which relates to the technical field of UAV path planning. The method comprises: discretizing the actual physical locations to be patrolled to construct an undirected topological graph; generating a steady-state distribution of each patrol node according to the topological constraints and the importance of the nodes; generating a plurality of transfer matrices with the same steady-state distribution but different transfer characteristics according to a multi-stage entropy-driven random matrix optimization algorithm; initializing the position of a navigator and determining the path selected by it according to the transfer matrix; implementing adaptive active positioning decisions under positioning constraints according to the navigator's reference path to ensure path tracking effects; according to the navigator's path selection and tracking, the followers form a humanoid grouping cluster with the navigator through a reward function; according to the multi-state transfer matrix and the humanoid grouping, automatically switching to the next transfer matrix when a transfer number threshold is reached, thereby realizing intelligent patrol path decisions of the UAV swarm under resource constraints.

The invention discloses an electric reactor mechanical vibration diagnosis method, device and equipment and a storage medium, and relates to the technical field of fault diagnosis, and the method comprises the steps: obtaining N window vectors obtained by dividing an electric reactor vibration signal; performing binning according to the amplitude in the window vector to obtain a Markov transfer matrix; generating a Markov transfer field according to the Markov transfer matrix; taking each row of the Markov transfer field as an initial node feature to obtain an initial node feature matrix; calculating a correlation coefficient between every two window vectors according to the N window vectors so as to construct an adjacent matrix; constructing graph structure data according to the initial node feature matrix and the adjacent matrix; inputting the graph structure data into the graph neural network model to obtain a fault classification probability of each window vector; and generating a fault diagnosis conclusion of the whole reactor according to the fault classification probabilities of all window vectors. The method can improve the diagnosis accuracy of the whole reactor.

The invention relates to a river channel sand body random model generation method and device based on hidden Markov model data filling, a medium and equipment. The method comprises the steps that logging data of a target area are collected and arranged; dividing logging data according to a logging gas-bearing interpretation conclusion, and carrying out analytical statistics on the velocity and density of longitudinal and transverse waves in the logging data; initializing an initial state probability, a state transition matrix, and a mean value and a covariance of Gaussian distribution in the hidden Markov model; inputting a three-dimensional observation vector composed of the velocity and density of the longitudinal and transverse waves into the initialized hidden Markov model for iterative training; performing down-sampling on the lithology data, then constructing a state transition probability matrix, and further constructing a lithology sequence conforming to a geological law through simulation; according to the lithologic sequence, calling a hidden Markov model to generate longitudinal wave velocity, transverse wave velocity and density corresponding to the lithologic sequence; and calculating a reflection coefficient of the synthetic stratum, setting a Ricker wavelet dominant frequency, and obtaining synthetic seismic response data through convolution.

The invention provides a Kalman filtering parameter setting method, device and equipment, a medium and a product, and relates to the technical field of digital processing. The method comprises the following steps: acquiring an angular velocity measurement value of the MEMS gyroscope measured at each moment in the previous period; and calculating an autocorrelation coefficient between the angular velocity measurement values, and determining the autocorrelation coefficient as a state transition matrix corresponding to the MEMS gyroscope in the current period. According to the method, the dynamic updating of the state transition matrix can be realized under the working condition that the MEMS gyroscope operates for a long time, the influence caused by temperature drift is effectively counteracted, and finally the purpose of improving the filtering precision is realized.

The present invention aims to provide a target state transfer matrix detection method under partial information loss, comprising the following steps: constructing a target state transfer matrix detection network, the target state transfer matrix detection network comprising a plurality of sequentially connected feature extraction modules; training the target state transfer matrix detection network to obtain trained target state transfer matrix detection network parameters; obtaining a target state observation sequence of length TS, with a number of states SN, as an input matrix, adding a channel dimension to the matrix to make it 1×TS×SN, inputting the matrix into the trained target state transfer matrix detection network, and sequentially processing it through the plurality of feature extraction modules to obtain a final target transfer matrix. The present invention can accurately detect the target's actual motion state transfer matrix, thereby improving the accuracy of filtered predicted track.

This invention discloses a method for recommending points of interest (POIs) based on user spatiotemporal behavior and social information. The method includes constructing a spatiotemporal knowledge graph based on user POI visit sequences and social relationships; learning POI representations in the spatiotemporal knowledge graph and constructing a POI transfer matrix; updating POI features through graph convolution using the POI transfer matrix as weights; calculating a user preference representation based on the user POI visit sequence and POI features; calculating the weights of historically visited POIs based on the spatiotemporal distances between POIs and the distances between POIs and user preferences; inputting the POI sequence into a recurrent neural network and updating a hidden representation using the weights of historically visited POIs; and connecting the hidden representation with the user preference representation, inputting the result into a recommendation model to generate the next POI that matches the user's preferences. This method can effectively model user spatiotemporal behavior, capturing behavioral patterns and user preferences, and making POI recommendations more accurate.

The present invention discloses a method and system for controlling the conductivity of a pure water cooling system. The method includes constructing a conductivity data set; performing adversarial training processing on the conductivity data set to obtain a virtual conductivity sequence; obtaining a conductivity fusion data set; inputting the processed conductivity fusion data set into a cooling system state acquisition model constructed by a non-stationary hidden Markov chain to obtain a conductivity state path and a non-stationary time transition matrix, and the construction process includes adjusting the parameters of the cooling system state acquisition model through a physics-informed neural network to optimize the cooling system state acquisition model; inputting the conductivity state path and the non-stationary time transition matrix into a cooling system state evaluation model to obtain the state of the cooling medium; determining a conductivity control signal for the target pure water cooling system based on the state of the cooling medium, and executing the conductivity control signal. The method provided by the embodiments of the present invention can control the conductivity situation in the pure water cooling system.

The invention provides a task-based dialogue data generation method and device, a medium and electronic equipment, and the method comprises the steps: obtaining a state transition matrix which represents the probability of transferring from any state node of a task-based dialogue to another state node; performing sampling processing on the state transition matrix to obtain a state sequence of a plurality of sampling paths; processing each state sequence by using a large language model and corresponding cue words to generate a plurality of dialogue contents, and scoring each dialogue content to obtain a plurality of dialogue content scores, the dialogue contents being in one-to-one correspondence with the dialogue content scores; and performing multiple iterations on the state transition matrix based on the dialogue content score, and generating task-type dialogue data by adopting the iterated state transition matrix meeting the iteration stop condition, thereby solving the problem of insufficient training caused by lack of high-quality data of the task-type dialogue system.

The invention relates to the technical field of electromagnetism, in particular to a multi-layer slab waveguide mode processing method, device, equipment, medium and program, and the method comprises the steps: constructing a transfer matrix model of a multi-layer slab waveguide; obtaining boundary conditions of the infinite space, and determining a corresponding real number domain characteristic equation and a complex number domain characteristic equation according to the transfer matrix model and the boundary conditions so as to determine a guided mode and a leakage mode of the multilayer slab waveguide in the infinite space; introducing a perfect matching layer to convert a radiation condition of an infinite space into an absorption boundary in a finite computational domain, constructing a finite space characteristic equation according to the thicknesses of the perfect matching layer and the absorption boundary, and positioning a plurality of correction leakage modes according to the finite space characteristic equation to generate a Bereger mode; and generating complete mode distribution according to the guided mode, the leakage mode and the Bereger mode. Therefore, the problems of relatively poor calculation precision, relatively slow calculation speed, limitation of complete mode solving in the multilayer slab waveguide and the like in related technologies are solved.

This invention belongs to the field of electronic digital data processing technology, specifically relating to a low-altitude communication data anomaly detection system and method based on edge intelligence. The system parses protocol fields from the raw bitstream of the low-altitude communication link layer, extracts type identifiers and payload lengths to construct a protocol state machine transition matrix, and utilizes a Long Short-Term Memory (LSTM) network to extract state transition probability sequence features. Geographically adjacent edge nodes are set as micro-federated learning groups. Each node, after training using local features, only uploads network gating weight parameters to its neighboring nodes for weighted aggregation to update its local model. An alarm is triggered when the real-time state transition probability sequence deviates from the normal transition matrix and exceeds a preset topology threshold. This invention can identify protocol state machine logic errors and transition anomalies, reducing the amount of communication data required for collaborative model updates between edge nodes.

The application discloses a method and system for quantitatively analyzing self-insulation resistance shunt effect of a self-powered detector, and the design steps are as follows: a circuit model of the self-powered detector is established according to a working principle of the detector; specific parameters of each element in the circuit are calculated according to geometric structure and physical parameters of the detector; a state space equation in a matrix form is established according to a current generation mechanism of the self-powered detector in a radiation field and the circuit model, and a system state transition matrix of the self-powered detector system is established by solving a matrix index; and influences of geometric dimensions and physical parameters of the detector on the insulation resistance and the shunt effect thereof are analyzed according to the system state transition matrix. The method can quantitatively calculate the shunt effect of the insulation layer resistance of the self-powered detector with different structures and parameters, and can accurately calculate a change of a capacitive current with time, thereby providing guidance for design and application of the detector.

The invention provides a graph neural network training method and device, a medium, equipment and a program product, and the method comprises the steps: obtaining sample graph data, and enabling a plurality of nodes of the sample graph data to comprise a plurality of nodes with noise marks; iteratively training the graph neural network and the matrix estimator based on the sample graph data and the noise marks; in any round of iteration, the sample graph data and the noise marks are input into the graph neural network, so that the graph neural network outputs original prediction marks of all the nodes in the multiple nodes, the original prediction marks are corrected based on the current noise transfer matrix, and corrected prediction marks are obtained; performing parameter adjustment on the graph neural network based on the corrected prediction mark and the noise mark; and after parameter adjustment of the graph neural network is completed, inputting the original prediction mark and the noise mark into a matrix estimator, so that the matrix estimator outputs a noise transfer matrix, and performing parameter adjustment on the matrix estimator based on the noise transfer matrix of the adjacent nodes.