298 results about "Noise estimation" patented technology

The invention discloses a weak light image enhancement method fusing noise adaptive diffusion and illumination perception, and the method comprises the steps: firstly designing a reflection-illumination decomposition module RID based on a Retinex theory, and extracting a reflectivity component and an illumination component of an input weak light image; then designing an ADRD (adaptive diffusion reflection denoising) module, performing denoising enhancement on the reflectivity component, and outputting an enhanced reflectivity image; introducing a noise estimation network, and dynamically adjusting the de-noising amplitude of the diffusion model according to the noise intensity of the region in the reflectivity graph; designing an illumination perception enhancement module IEM, fusing an attention mechanism and a local enhancement block, enhancing the illumination image, and outputting an enhanced illumination component; and building a complete neural network framework, carrying out joint training on the provided module, finally testing the stored neural network model, and outputting an enhanced image. According to the method, the problems of detail loss, noise residue and uneven illumination of the enhanced image in the prior art are solved.

According to the VLA-based body robot SLAM method and device and the storage medium, a VLA large model is introduced on the basis of multi-modal fusion SLAM of traditional point cloud geometry, vision and the like, perception is improved from a geometric layer to semantic concept alignment, and the SLAM is more accurate. A VLA large model is used for carrying out dynamic prediction updating on dynamic interference filtering, key frame screening, factor graph relation construction, noise estimation, loopback detection and the like, the real-time requirement is met in the modes of incremental optimization and the like, and the dislocation problem of geometric constraints is corrected through global semantic constraints. The stability of the robot SLAM in extreme scenes such as excessive environmental dynamic interference, loud sensor noise and environmental degradation is improved, and the constructed hierarchical situation map can meet the requirement of a high-order navigation task while the geometric accuracy is met, so that the robot SLAM can be deployed to carriers such as a body-equipped intelligent carrier for subsequent application.

The invention discloses a combined navigation method and system of an unmanned surface vehicle. The method comprises the following steps: forming a GNSS (Global Navigation Satellite System) / INS (Inertial Navigation System) integrated navigation system by using a GNSS (Global Navigation Satellite System) and a strapdown inertial navigation system (INS), and establishing a mathematical model of a GNSS / INS integrated navigation system filter; the mathematical model comprises a state equation and a measurement equation; establishing a mathematical model of the influence of the GNSS auxiliary information on the GNSS positioning precision so as to preliminarily adjust the measurement noise in the measurement equation; through an improved Sage-Husa adaptive filtering algorithm, adaptive estimation is carried out on the preliminarily adjusted measurement noise, and a measurement noise estimation final value is obtained; and according to the motion characteristics of the unmanned surface vehicle, adding motion constraint conditions to the measurement equation. The GNSS auxiliary information mathematical model based on multivariate function fitting is established, the influence of the external environment on the positioning precision is objectively reflected, the measurement noise in the filter is dynamically adjusted, and the positioning precision of the integrated navigation system under the interference condition is remarkably improved.

The invention belongs to the field of medical image processing and radiotherapy quality control, particularly relates to a gamma distribution diagram calculation method based on a diffusion model, and aims to solve the problem that the traditional radiotherapy quality guarantee efficiency is low. The method includes deriving a field flux profile image from a radiotherapy planning system. A reverse process noise estimation network is improved based on a conditional diffusion model, a field flux distribution diagram image is taken as conditional input, field flux distribution diagram information is extracted layer by layer at an encoder part, information fusion with noise path coding is carried out at different coding scales, diffusion noise is predicted by adopting multi-scale fusion Unet, and the prediction precision is improved. And constructing to obtain a gamma distribution diagram generation model. A dual-path residual block is adopted as a basic module of an encoder and a decoder of the multi-scale fusion Unet, a moving window jump connection module is adopted to integrate global and local features of different stages, and the moving window jump connection module introduces spatial offset through a moving window mechanism.

The invention relates to the technical field of inertial navigation and sensor fusion, in particular to an IMU (inertial measurement unit) attitude estimation and error correction method based on a state space physical information neural network, which comprises the following steps: acquiring original data of an IMU and preprocessing; constructing a state space model, and designing a state transition physical information neural network based on the state space model; training the state transition physical information neural network based on the preprocessed original data, optimizing network parameters through a joint loss function in the training process, and obtaining the trained state transition physical information neural network; and collecting real-time data streams of the IMU, inputting the real-time data streams into the trained state transition physical information neural network, and outputting the corrected pose, position and speed. According to the method, physical constraints and adaptive noise estimation are fused, so that the attitude estimation precision and the error correction capability in a dynamic complex environment are remarkably improved.

The invention discloses an adaptive edge detection iterative denoising point cloud reconstruction method and system. A regularization parameter and a kernel bandwidth are automatically set through point cloud normalization and local covariance noise estimation; an implicit curved surface is fitted based on a parameterized Gaussian field, and initial curved surface construction without a normal direction is realized. Edge detection is carried out by utilizing Voronoi covariance measurement, and the edge detection is continuously mapped into a projection weight, so that feature details of the point cloud are reserved in an acute angle region, and smooth denoising is realized in a flat region. The regularization intensity is dynamically adjusted through residual trend analysis to enhance detail representation, and a triangular mesh is extracted and output in combination with octree discretization and contour surface extraction. The method has unsupervised adaptivity, has outstanding performance in the aspects of edge fidelity, noise robustness and complex structure adaptability, can effectively process point cloud data with high noise, missing normal direction or irregular structure, and is suitable for the fields of engineering survey, reverse modeling, cultural relic digitization and the like.

The invention relates to the technical field of cable force detection, in particular to a bridge inhaul cable fundamental frequency identification method, device and equipment, a storage medium and a product, vibration acceleration data of a bridge inhaul cable structure to be monitored in the duration time is converted into a power spectrum data set, a noise floor is calculated through the power spectrum data set, the noise estimation precision is improved, and the noise estimation accuracy is improved. Energy peak value screening is carried out on the power spectrum data, part of energy peak value data is screened out, a frequency-energy peak value array is obtained, energy evaluation and scoring are carried out on the frequency-energy peak value array and a predetermined candidate fundamental frequency through a preset fundamental frequency scoring model, and the energy evaluation and scoring precision of the candidate frequency is improved; finally, the actual fundamental frequency of the to-be-detected inhaul cable is determined through the score value of the candidate fundamental frequency, manual screening is not needed, the identification efficiency is improved, and meanwhile high-precision identification of the fundamental frequency of the inhaul cable is achieved.

The invention provides an inertia / satellite / vision adaptive integrated navigation method and system. The method comprises the following steps: carrying out inertia measurement and navigation calculation to obtain inertia data; calculating satellite navigation observed quantity according to the satellite navigation data and the inertial data, and constructing a satellite observation model; calculating visual navigation observed quantity according to the visual navigation data and the inertial data, and constructing a visual observation model; aiming at a satellite and a visual observation model, respectively adopting an innovation-based adaptive covariance estimation method to obtain satellite and visual observation noise covariance updated values; constructing a satellite and visual navigation health degree, and calculating a satellite and visual fusion weight according to the satellite and visual navigation health degree; controlling updating of satellite and visual navigation observed quantity according to the satellite and visual fusion weight; and calculating a weighted equivalent observation matrix and a noise covariance, and carrying out filtering estimation. According to the method, an adaptive noise estimation and sensor health degree evaluation mechanism is introduced, dynamic weighted fusion of multi-sensor data is realized, and the robustness and precision of a navigation system in complex environments such as satellite signal lock losing and visual feature missing are improved.

The invention discloses a semantic constraint adversarial sample generation method and system. According to the method, firstly, a confrontation sample generation task based on a natural language instruction is constructed, and parameters are initialized; then deploying a proxy model and a diffusion model for double-branch noise estimation; by judging instruction complexity, mask guidance is selectively adopted to realize natural constraints of spatial differentiation; by constructing a residual-guided antagonistic DDIM sampler and combining an adaptive optimization iterative algorithm, the calculation complexity is reduced, and the attack mobility is enhanced at the same time; and aiming at a three-dimensional generation requirement, a three-dimensional Gaussian sputtering rendering model is further integrated, and geometric consistency is ensured through multi-view gradient averaging. According to the method, the problems of inaccurate semantic control, weak migration aggressiveness, poor three-dimensional generation consistency and the like in the prior art are effectively solved, the attack success rate and the visual naturalness are remarkably improved on multiple target models, and an efficient and reliable red team test tool is provided for security evaluation and alignment of a multi-modal large model.

The invention provides a non-uniform haze degraded image restoration method and a related device, and belongs to the technical field of image processing. The method comprises the following steps: estimating noise randomly sampled from standard normal distribution by using a trained noise estimator to obtain estimated noise, and removing the estimated noise from the noise randomly sampled from the standard normal distribution to obtain a noisy image; constructing a visual state space mixed scale expansion convolution module, and constructing a conditional diffusion U-shaped denoising model based on the visual state space mixed scale expansion convolution module; and based on the guide image, estimating and denoising the noisy image by using a conditional diffusion U-shaped denoising model in an iterative calculation mode to obtain a restored non-uniform haze degraded image. According to the method, the problem that the restoration sharpness degree of the degraded image is poor when the haze concentration change range is large or the non-uniform change is severe is solved.

The invention provides a robot action generation method and a robot control system, and the method comprises the steps: obtaining multi-modal observation data at a current moment; the modal weight and the initial noise trajectory of each modal are acquired; and according to the multi-modal observation data, the modal weight of each modal and the noise estimation model corresponding to each modal, performing iterative exploration on the initial noise trajectory according to a time inverse sequence, and generating an action trajectory sequence of the robot. According to the method, noise estimation of the pre-trained single-mode diffusion strategy can be combined during reasoning, and information of different modes can be efficiently fused, so that on the premise of avoiding complexity of multi-mode data collection and joint training, multi-mode strategy fusion is realized, and meanwhile, the multi-mode data collection and joint training efficiency is improved. And the flexibility, the real-time adaptability, the robustness and the expandability of the action generation process are enhanced. Moreover, by avoiding multi-modal joint training, the training cost and the computing resource demand are greatly reduced.

The invention discloses an image generation model training method and device and an image generation method and device, and the training method comprises the steps: obtaining a training data set, and carrying out the training of a generated image generation model; the training process comprises the following steps: respectively carrying out pixel feature extraction and semantic feature extraction on an original image; carrying out image feature extraction on the target image, and carrying out noise processing on the extracted image features to obtain noise features; performing noise estimation and de-noising processing on the noise features based on the pixel features of the original image, the semantic features of the original image and the guidance of the text description, and performing image restoration on the result features obtained by the de-noising processing to obtain a generated image; and updating parameters of pixel feature extraction, semantic feature extraction, noise estimation and de-noising processing based on a comparison result of the generated image and the target image, so that the generated image is closer to the target image. By applying the method and the device, the image generation model suitable for various scenes can be provided, and the high-quality image meeting user requirements can be generated.

The invention relates to a fixed parameter optimization cubature Kalman filtering tracking method for a high-speed high-maneuvering target, belongs to the technical field of signal processing and target tracking, and aims to solve the problem of insufficient tracking performance caused by difficulty in parameter tuning and isolation of an improved mechanism when an existing method is used for coexistence of model mismatch, noise time variation and outlier interference. According to the scheme, a framework integrating off-line multi-parameter collaborative optimization and on-line multi-mechanism adaptive filtering is constructed; in the off-line stage, an optimal combination of key parameters such as covariance adjustment factors is determined through a grid search system; in the online stage, the combination is loaded, and a complete filtering process including innovation feedback type dynamic covariance adjustment, sliding window type noise estimation and outlier suppression and trace-related adaptive regularization is executed, so that an enhanced tracking method with active pre-judgment and closed-loop learning capabilities is formed. The method is mainly used for carrying out high-precision and high-robustness real-time state estimation on the high-speed high-maneuvering target.

A distributed ultra-wide band (UWB) radar system and methods for operating the same are disclosed. The distribute radar system uses a plurality of separate UWB radios or nodes that do not use a centralized clock or source of time. However, the distributed UWB system operates to provide radar-like functionality and fine-grain sensing capabilities through synchronization based on line-of-sight (LOS) signal processing and noise estimations. Synchronized channel impulse responses (CIRs) can be processed for general object detection and tracking, gesture recognition, or even micro-motions such as monitoring vitals

The invention relates to an underwater electromagnetic detection noise suppression method based on an NARX neural network, and the method comprises the steps: collecting first magnetic field data through a first vector magnetic sensor, and collecting second magnetic field data through a second vector magnetic sensor; training a sea wave noise prediction model based on the first magnetic field data and the second magnetic field data, and repeatedly and synchronously intercepting the first magnetic field data and the second magnetic field data in a preset time range through a sliding window, inputting the intercepted first magnetic field data and the intercepted second magnetic field data into the sea wave noise prediction model for prediction to obtain a corresponding sea wave noise prediction value; and performing differential processing on the first magnetic field data in each sliding window and the sea wave noise prediction value in the corresponding preset time range, and splicing differential results to obtain secondary field information in the first magnetic field data. According to the invention, the accuracy of noise estimation is improved, and the background interference in the signal can be better stripped.

The invention provides a high-throughput Raman spectrum-oriented identification method, and belongs to the technical field of Raman spectrum data processing. According to the method, the number of principal components is dynamically determined through the adaptive feature contribution rate and the noise estimation algorithm, flexible compression for different spectral complexity is achieved, and the operation efficiency in large-batch data processing is remarkably improved; on this basis, a lightweight convolutional neural network model introducing a channel attention mechanism is constructed to enhance the response ability to a key Raman peak position and suppress background interference; and meanwhile, an auxiliary loss function based on inter-spectrum cosine similarity constraint is introduced in the training process, the intra-class consistency and the inter-class separation degree are improved, and a visual feedback mechanism is combined to optimize the region of interest of the model on a discrimination section. Compared with a traditional Raman spectrum classification method, the method does not depend on artificial feature extraction and preset dimension parameters, has the advantages of being high in discrimination, good in interpretation, wide in adaptability and the like, and can achieve efficient and accurate classification of complex Raman spectrums.

According to an embodiment, an information processing device includes one or more hardware processors configured to: generate a plurality of exogenous noise estimation values corresponding to a plurality of variables for each of one or more pieces of record data, based on a pre-update model being a structural causal model representing a causal relationship of the plurality of variables; determine whether a causal relationship of the plurality of variables represented by the one or more pieces of record data is different from the causal relationship represented by the pre-update model, based on independence between any two or more variables in the plurality of exogenous noise estimation values with respect to each of the one or more pieces of record data; and generate a post-update model being the structural causal model based on the one or more pieces of record data when determining that the causal relationships are different.

The invention discloses a gating image low-illumination enhancement method based on an improved RRDnet network, and the method comprises the steps: carrying out the processing of a collected low-illumination gating image through employing an RGRRDnet model, and obtaining an enhanced image. In RGRRDnet, firstly, an image is divided into a reflection component, a noise component and an illumination component by using a residual decomposition network; secondly, locally adjusting an illumination component by adopting a two-dimensional adaptive Gamma correction method, and improving the problem of uneven illumination of a gated image; meanwhile, the reflection component generated by the decomposition network and the reflection component obtained through calculation are fused through an adaptive weighted fusion method, and the influence of noise estimation errors is effectively reduced; and finally, introducing a detail enhancement module, and enhancing the edge and texture information of the image by using DEConv convolution operation. Experimental results show that the method is superior to a current mainstream low-illumination enhancement algorithm in the aspects of objective indexes and subjective vision on a gated image data set.

The invention relates to a dynamic light beam shaping system and method based on a spatial light modulator. The system comprises a laser light source module, a beam expanding collimation light path, a light beam modulator, a focusing optical assembly, a detection and feedback module and a control and optimization module. According to the method, the uniformity of the output flat-topped beam can be corrected by virtue of a random parallel gradient descent (SPGD) algorithm and combining a Zernike polynomial as a control variable. Meanwhile, a composite performance index comprehensively considering energy distribution and shape features is constructed, the correction process of the flat-topped beam is accelerated by adopting a mode of gradually improving Zernike polynomial orders in multiple stages, the convergence trend of the performance index is used as a judgment basis of stage switching, stage independent variable dimension expansion is implemented, and the correction precision of the flat-topped beam is improved. And the convergence speed is obviously improved. Besides, adaptive selection of disturbance amplitude and learning rate parameters in the SPGD algorithm is realized by using noise estimation and a local linearity index, and the robustness of the system to noise and environmental disturbance is enhanced.

Methods, systems, and devices for wireless communications are described. In some examples, a user equipment (UE) may estimate phase noise using a phase noise tracking reference signal (PTRS). A network entity may transmit a PTRS waveform to the UE including a single pilot tone with a boosted transmission power that is surrounded by zero-amplitude tones based on a capability of the UE. The network entity may transmit control signaling indicating that the PTRS waveform includes the single pilot tone. Additionally, the network entity may indicate a size of the PTRS waveform, a location of the pilot tone relative to the zero-amplitude tones, and locations of the pilot tone and the zero-amplitude tones within a wireless channel. The UE may select a phase noise estimation algorithm based on the capability of the UE and the control signaling and may estimate the phase noise in accordance with the selected algorithm.

The invention discloses an inland river ship ferry whole ship equipment health monitoring and early warning system based on the Internet of Things, and relates to the technical field of ship equipment monitoring. A dynamic dual-threshold coupling mechanism is adopted, and the method comprises the steps that a noise estimation module combines a navigation state and a historical working condition library to generate a fundamental frequency floating range vector and a harmonic ratio threshold, and the problem of signal distortion caused by vibration fundamental frequency drift is solved; the collaborative analysis module constructs a three-dimensional incidence matrix of temperature gradient, envelope energy and current distortion rate, expands a harmonic ratio threshold into a dynamic window, and realizes multi-parameter synchronous out-of-limit judgment; and the health scoring module quantifies the equipment degradation degree through dynamic regular comparison of a waveform envelope line and a historical curve. And when the incidence matrix is in a continuous five-period super-dynamic window, outputting a micro-fault feature code, and mapping the micro-fault feature code to an equipment topology library in combination with the health score to generate an operation instruction. The fault recognition rate under the variable working conditions of the ship is improved, and predictive maintenance of early faults such as bearing abrasion and electric overload is supported.

The invention discloses a joint blind denoising method and system based on self-heuristic learning and Bayesian reasoning, belongs to the field of computational imaging, and solves the problems that in the prior art, the mixed noise modeling capability is insufficient, the performance is degraded under the condition of low signal-to-noise ratio, the combination of uncertainty quantization and regularization is lacked, and the generalization capability is limited due to data dependence. Comprising the following steps: collecting an original image and preprocessing; generating a noise data pair; an enhanced residual attention U-Net model is constructed; a noise estimation sub-network is adopted to extract noise features, the noise features are fused with original image features, and the model is trained; adopting the trained model to carry out multiple times of forward propagation on the same input image to obtain multiple groups of denoising results; calculating a mean value and a standard deviation to obtain a de-noising prediction and uncertainty heat map; and training the trained model again based on the uncertainty heat map, optimizing network parameters, and obtaining a final denoising prediction result and uncertainty estimation thereof. The method is suitable for complex noise distribution processing scenes.

The invention discloses a sound signal processing method and device, equipment and a storage medium, and belongs to the technical field of audio processing. According to the invention, sound signal noise reduction with noise suppression and target signal reservation is realized. The method comprises the following steps: after acquiring a sound signal collected in a running state of mechanical equipment, firstly performing time-frequency analysis on the sound signal; then, a noise determination threshold is automatically determined based on the logarithmic magnitude spectrum of the sound signal, and noise estimation is performed based on the determined noise determination threshold. According to the scheme, a completely data-driven parameter selection mechanism is realized, and manual parameter or threshold setting is not needed, so that the automation degree is improved, the unreliability of manual parameter or threshold setting is avoided, and the accuracy and robustness of noise estimation are enhanced. In addition, the noise-reduced sound signal does not comprise noise components, so that the accuracy and reliability of subsequent operation state recognition and fault diagnosis of the mechanical equipment are ensured.

The invention relates to the technical field of acoustic signal processing, and discloses a sound source positioning method and system, and the method comprises the steps: collecting sound through a multi-microphone array, aligning data based on a synchronization mechanism, and obtaining an initial time domain signal; executing transformation and filtering to generate a spectrogram; separating interference based on noise estimation, and extracting independent source frequency domain components; calculating a time difference in combination with a synchronization mechanism, and determining a preliminary orientation; the moving direction is analyzed, the track is smoothed, and continuous track data are obtained; constructing a velocity vector to generate a Doppler compensation coefficient, and executing phase calibration to obtain a calibration signal; and performing inverse transformation on the reconstructed signal, and calculating a generalized cross-correlation peak value to determine a final position. The method can achieve the precise tracking and positioning of a dynamic sound source, effectively eliminates the Doppler effect and environment noise interference, and remarkably improves the positioning precision.

The invention discloses a magnetocardiogram P-wave detection method based on wavelet analysis and a local noise self-adaptive threshold, which is characterized in that accurate and robust detection of a P wave is realized by searching on a characteristic scale which can highlight the P wave, a self-adaptive threshold confirmation mechanism based on local noise estimation is introduced, and a self-adaptive threshold confirmation mechanism is established for a time domain search window of each cardiac cycle. According to the method, the internal noise level is dynamically evaluated, and an estimated value capable of accurately reflecting the local noise condition of the current heart beat can be obtained by carrying out statistical analysis on wavelet coefficients in a characteristic scale in an area where P waves are most likely to appear.

The invention discloses a molded case circuit breaker fault prediction and alarm method based on artificial intelligence, and the method comprises the following steps: S1, collecting current, voltage, temperature and contact resistance signals, constructing multi-channel time sequence observation data, and generating a fusion observation vector; s2, inputting the fusion observation vector to a noise estimation sub-network, and generating a dynamic covariance parameter; s3, inputting the fusion observation vector, the dynamic covariance parameter and a previous state estimation value into a KalmanNet structure, and outputting a current state estimation value; s4, a physical prior regularization module is introduced in the training stage, a constraint loss function is constructed, and network parameters are jointly optimized; s5, executing drift detection in an operation stage, and extracting historical window data to perform incremental updating when conditions are met; s6, pruning and quantifying the trained KalmanNet structure, and generating a lightweight model; and S7, deploying to a monitoring system, and predicting the state in real time for alarm judgment. According to the invention, the accuracy and deployment efficiency of circuit breaker fault prediction are improved.

The invention provides a single photon array image data processing method and system based on time correlation, and relates to the technical field of image processing.The method comprises the steps that a photon event sequence with a timestamp and position information is obtained through a detector array, a four-dimensional space-time tensor is constructed, and space-time data is obtained through normalization and noise estimation; performing time sequence analysis on each spatial position and neighborhood in the spatio-temporal data to extract time sequence features, separating target features from the time sequence features, removing noise features and generating a time confidence map; inputting the time confidence map and the spatio-temporal data into a variational optimization model for joint optimization, and dynamically updating a time weight field and a spatial support domain in optimization according to the confidence map to obtain an initial reconstructed image; and finally, inputting the initial reconstructed image and the time confidence map into a neural network, and outputting a final image through modeling and residual path restoration. According to the invention, the signal-to-noise ratio and dynamic scene adaptability of single photon imaging under extremely low illumination are improved.

Transformer neural network based decoder for decoding Quantum Error Correction Codes (QECC), comprising, an input layer, a plurality of decoding layers, and an output layer. The input layer is adapted to receive initial noise estimation computed by a noise estimator for noise injected to syndrome bits of codewords encoded using QECC and transmitted over transmission channel(s) subject to interference, and create embeddings for the syndrome bits. The decoding layers adapted to compute an estimated logical operator matrix of each codeword, each comprises a self-attention layer constructed according to a mask indicative of a relation between the embeddings derived from a parity-check matrix of the error correction code. The plurality of decoding layers are trained using a combined loss function directed to minimize LER, BER, and error rate of the noise estimator. The output layer is adapted to produce a vector representing predicted soft error of the codeword's logical operator matrix.

The invention discloses a Bluetooth earphone call intelligent noise reduction method based on cloud cooperation, and the method comprises the following steps: S1, obtaining a call voice signal and an environment state parameter, carrying out the preprocessing, and constructing a voice spectrum sequence and an environment feature sequence; s2, performing noise estimation and suppression processing on the speech spectrum sequence by using a DCCRN model to obtain a spectrum feature sequence; s3, constructing a cooperative processing sequence based on the environment feature sequence and the spectrum feature sequence; s4, using a Conv-TasNet model to execute speech enhancement on the co-processing sequence, and generating a target spectrum sequence; s5, performing phase reconstruction and inverse frequency spectrum transformation based on the target frequency spectrum sequence to generate a target voice signal; and S6, constructing a loss function according to the target voice signal, and updating the Conv-TasNet model. According to the method, the DCCRN model and the like are fused, and the method has the advantages of high noise reduction precision, high environment adaptability and sustainable optimization.

The invention relates to a spatio-temporal data rule extraction method based on spatio-temporal Fourier expert mixing, belongs to the technical field of urban spatio-temporal data processing, solves the problem that global stability characteristics and local disturbance characteristics driven by real physical rules are difficult to effectively describe in the prior art, and comprises the steps that S1, a spatio-temporal data acquisition module acquires historical data information; s2, establishing a space-time Fourier expert hybrid network, and carrying out expert mixing to obtain mixed features; s3, using adaptive group normalization as a conditional fusion module to obtain fusion features; s4, establishing a space-time Fourier attention mechanism module to obtain output features; s5, establishing a diffusion model for performing back diffusion on the noisy data in combination with the noise estimation network to obtain predicted denoised data, and performing training to obtain a trained diffusion model; and S6, performing sampling to obtain spatio-temporal data, inputting the spatio-temporal data into the trained diffusion model, and obtaining an extracted causal law for urban traffic flow prediction.