205 results about "Model network" patented technology

A natural gas pipeline multi-working-condition fault diagnosis method and system based on Bayesian adversarial attack and single-source domain transfer, relating to the technical field of mechanical fault detection and diagnosis. The core of the method is using the transfer learning technology to solve the problem of insufficient generalization ability of existing deep reasoning models when processing pipeline fault diagnosis tasks under different working conditions. The method mainly comprises the following steps: constructing an attack sample generator on the basis of a Bayesian network, wherein the attack sample generator is used for generating, by adding delicately designed tiny disturbance into an input sample, an attack sample that can cause an reasoning model to make an incorrect decision, so as to mine and analyze a defect of the reasoning model; constructing a domain discriminator on the basis of the Bayesian network, wherein the domain discriminator is used for assist in generating a high-concealment attack sample by means of adversarial learning between the domain discriminator and the generator, that is, there is almost no visible difference between the high-concealment attack sample and an original sample; and constructing a classifier on the basis of the Bayesian network, and by expanding the distance between the attack sample and an original decision boundary of the reasoning model, constraining the posterior distribution of network parameters of the reasoning model to be adjusted towards a higher score of the attack sample, thereby enhancing the adaptability and robustness of the model when facing disturbance in different domains. By means of the steps, the present invention effectively solves the problem of missing reporting and false reporting risk improvement caused by poor generalization ability of traditional deep learning models under different working conditions.

The invention provides a geophysical gravity and magnetic anomaly source model construction and rapid forward and reverse modeling method, and relates to the technical field of intelligent three-dimensional geological modeling and simulation. According to geological information of a research area, source body modeling parameters of a gravity and magnetic anomalous field are set for the research area, and a three-dimensional model matrix M capable of describing a plurality of underground anomalous bodies is obtained; constructing a fast forward modeling network, establishing nonlinear mapping from the three-dimensional model matrix to the simulated abnormal data through the fast forward modeling network, and calculating forward modeling response of the three-dimensional model matrix; and constructing an inversion network based on a concurrent module CFTBlock and combining a CNN and a Transform, and establishing nonlinear mapping from the gravity and magnetic abnormal data to a three-dimensional model matrix. The method has the advantages of fast and accurate forward modeling, high-resolution inversion and the like, and is suitable for better interpretation of actually measured gravity and magnetic data.

The invention relates to the technical field of geophysical exploration, in particular to a multichannel deep learning magnetotelluric inversion method based on physical information constraint. The method comprises the following steps: generating a synthetic data set containing a geoelectric model and forward modeling response thereof, and adding a noise simulation actual observation condition; constructing a hybrid network architecture combining Transform and U-Net, taking apparent resistivity and impedance phase as dual-channel input, extracting global features by using an encoder, gradually recovering spatial resolution through a decoder, and outputting an underground resistivity model; network training adopts a composite loss function fusing model loss and data loss, and an inversion process is constrained by introducing a magnetotelluric forward modeling physical rule, so that a result is ensured to fit observation data and conform to a physical mechanism; after training is completed, preprocessed actual measurement data are input into the model, and a resistivity image can be directly obtained. The method is used for geological structure identification and reservoir interpretation, and the inversion precision and reliability are effectively improved.

The invention discloses a remote sensing image semantic segmentation method based on geometric perception diffusion guidance, and is applied to the technical field of remote sensing image semantic segmentation. Comprising a training stage and a testing stage, in the training stage, original remote sensing images, nDSM corresponding to each original remote sensing image and real semantic segmentation images are selected to form a training sample set, and a segmentation everything model based on geometric perception diffusion guidance is constructed and trained; comprising an enhanced visual converter encoder, a diffusion prompt module, a segmented everything image prompt encoder, a segmented everything image mask decoder and a prompt level supervision strategy. In the test stage, various channel components of a to-be-detected remote sensing image are input into the trained model, and the model network outputs a remote sensing image semantic segmentation prediction map corresponding to an original remote sensing image. According to the method, multi-modal remote sensing data can be effectively fused, a multi-scale space structure is captured, and full-automatic semantic segmentation is realized, so that the segmentation efficiency and accuracy are remarkably improved.

The invention discloses an OCT (Optical Coherence Tomography) retina image denoising method based on a high-frequency enhanced diffusion model, which is characterized in that a double-branch diffusion model network constructed based on frequency perception Fourier transform attention (FFTA) is used for separating different frequency domains, enhancing specific frequency domain features and fusing the specific frequency domain features into a spatial domain feature map to realize stronger frequency domain perception and processing capability; the invention relates to a time step T coding method for a module of frequency domain attention. The time step T of the diffusion model is used as a parameter to be coded into a frequency domain attention module to participate in self-attention matrix calculation, so that frequency domain feature processing is aligned with the iteration step number of the diffusion model, and different frequency domain information is pointedly processed at different time steps T; the frequency selective hopping mechanism uses pooling operation to obtain a high / low frequency characteristic pattern, so that the network has adaptive frequency domain retention capability for different local parts.

The invention discloses an echocardiogram video classification method, system and terminal, and the method comprises the steps: constructing a classification model network which comprises a feature extraction module, a feature enhancement module and a feature aggregation module; obtaining an echocardiogram video, obtaining a plurality of standard section views according to the echocardiogram video, performing interpolation processing and feature extraction on the plurality of standard section views through a feature extraction module, and outputting a plurality of video features; inputting the plurality of video features into a feature enhancement module for aggregation enhancement of spatial features and time sequence features, and outputting a plurality of enhanced features; and inputting the plurality of enhanced features into a feature aggregation module for frame-level feature weighted fusion to obtain a plurality of key frame features, selecting related features from the plurality of key frame features, obtaining fusion features according to the related features, and classifying the fusion features to obtain a classification result of the echocardiogram video. According to the method, the classification accuracy of the echocardiogram videos is effectively improved.

A method comprises receiving a request to predict a deployment configuration for at least one application, analyzing code of the at least one application to identify one or more additional applications on which the at least one application will depend, identifying a plurality of network paths between the at least one application and the one or more additional applications, and using one or more machine learning algorithms to predict execution times for the at least one application over the plurality of network paths. The predicted execution times for the at least one application over the plurality of network paths are inputted to a network graph model. The network graph model predicts the deployment configuration for the at least one application based at least in part on the predicted execution times, wherein the deployment configuration comprises a subset of the plurality of network paths.

The invention belongs to the technical field of image processing, and particularly relates to an image tampering detection method fusing noise residual errors and compression artifacts and a program product. According to the scheme, noise residual features of compression artifact features of an original image are extracted through an error level analysis technology and an airspace rich model, and then an image tampering detection model with quality adaptability is constructed by combining the two types of features. The network model firstly extracts tampering features from image compression features and steganography noise dimensions through a convolutional layer in an ELA branch and an SRM branch, and then performs multi-scale feature coding through a lightweight MobileNetV2 network; feature interaction enhancement is realized in combination with an SECA attention mechanism; and finally, generating a pixel-level binary mask representing the tampered area through a feature fusion strategy. According to the scheme, the compression characteristic and the noise characteristic of the image can be fully utilized, and the detection precision of the model on the low-quality image and the robustness in a multi-quality scene are improved.

The invention discloses a dexterous mechanical arm control method based on uncertainty perception fused with long and short term reward strategy gradient, which comprises the following steps: acquiring mechanical arm state information in real time, and preprocessing to obtain a unified state vector; according to the state vector, obtaining a prediction mean value and prediction uncertainty of a next state through a forward model network; according to the prediction uncertainty, dynamically generating a long and short-term reward fusion weight through an attention network; according to the fusion weight, fusing the long-term reward strategy gradient and the short-term reward strategy gradient, and updating strategy network parameters; in a strategy network updating process, according to a forward model prediction error and a real state error, shielding a short-term reward through a reliability judgment module when the error exceeds a threshold value; and according to the action instruction output by the updated strategy network, the mechanical arm is driven to execute motion. According to the method, the control precision, the convergence speed and the motion smoothness of the mechanical arm in a complex dynamic environment can be improved.

The invention provides a fault diagnosis method and system for few-sample incremental equipment in an open set environment. The method comprises the following steps: pre-training a basic model comprising a feature extractor and a cosine similarity classifier based on a basic vibration sample; training a complementary model based on the enhanced sample and the pseudo-increment sample; the complementary model comprises a feature extractor added with a CBAM module and a square Euclidean distance classifier; inputting a basic vibration sample into the basic model and the complementary model at the same time, and fusing the dual-model output probability; a trained dual-model network is obtained through minimizing a loss function; inputting real incremental data into the trained dual-model network, freezing basic model parameters, and finely adjusting the last two convolutional layers and the classifier of the complementary model; and fusing the fine-tuned dual-model output probabilities to generate a final fault classification result. According to the method, intelligent fault diagnosis under the condition of continuously introducing a new type of data set can be realized, the applicable condition is more practical, the robustness is high, and the accuracy is high.

The embodiment of the invention provides a large model parameter adjustment method based on cloud edge collaboration and related equipment, and belongs to the technical field of network security. The method comprises the following steps: acquiring a general basic large model, a network security knowledge matrix and cloud sample data in a network security scene, and constructing an initial low-rank matrix; inputting the cloud sample data into the basic large model, and performing data mapping processing on the cloud sample data based on the original parameter matrix and the initial low-rank matrix to obtain cloud target data; adjusting the initial low-rank matrix based on the cloud sample data and the cloud target data to obtain a target low-rank matrix; and integrating the target low-rank matrix and the basic large model into a teacher model, and sending the teacher model to edge side equipment, so that the edge side equipment determines a target large model for completing cloud edge collaborative parameter adjustment in a network security scene according to the teacher model. According to the method, the knowledge accuracy and the parameter adjustment efficiency of the target large model can be balanced under the condition that specific domain knowledge is introduced.

The invention relates to the technical field of oil and gas reservoir development and geological modeling, and discloses a multi-scale factor constraint-based tectonic network fracture modeling method, which comprises the following steps of: synthesizing a Riemannian metric tensor field on the basis of earthquake, logging and geomechanics data, and defining non-Euclidean distance cost of a fracture expanded in an anisotropic medium; initial seed points are screened according to the elastic strain energy density, and initial growth potential energy in a limited range is distributed; solving the eikonal equation by using an anisotropic fast marching algorithm to carry out wavefront competitive growth, and dividing a grid region into generalized Voronoi units; identifying a wavefront contact interface, and extracting gradient features to judge a fusion or truncation type so as to establish fracture topological connection; and finally, tracking a geodesic line path along an anti-gradient direction to generate a three-dimensional discrete fracture network. According to the method, macro and micro constraints are unified through Riemannian geometry, clear physical significance is given to the fracture by utilizing an energy mechanism, and automatic and accurate construction of the complex fracture network topology structure is realized.

The invention provides a time series data enhancement method and system for point cloud polar voxel mask modeling, and belongs to the field of deep learning, and the method comprises the steps: S1, employing positioning information to assist point cloud space scanning and sampling, and constructing a basic unlabeled data set; s2, spatial data information complementary increase is carried out through differentiated continuous inter-frame point clouds; s3, improving the unit sampling balance degree through polar coordinate voxelization sampling; and S4, carrying out generative pre-training through the voxel mask modeling network, and improving the generalization perception capability of the neural network on the basic point cloud voxels on the premise of avoiding introduction of complex point cloud manual annotation. According to the method, under the condition that complex manual annotation is not introduced, the generalization perception capability driven by limited sample point cloud data is improved.

The invention discloses a method for generating a high-precision dynamic digital human, which belongs to the field of computer vision and comprises the following steps of: extracting skeleton motion and frame-level potential codes from a multi-view video, driving a coarse model network to generate a three-dimensional grid, and realizing attitude alignment by combining double quaternion skin and embedded deformation; a vertex three-dimensional corresponding relation is obtained through 2D point tracking and a depth map, and grid alignment precision is optimized; on the basis, animatable Gaussian textures are trained, and texture detail modeling is achieved; a physical solver is further introduced, the physical response of cloth is solved according to the bone posture and the material type, and die penetration and distortion are eliminated; meanwhile, modeling is carried out on texture offset by adopting a space-time Transform, so that the dynamic consistency is improved; and finally, high-fidelity image rendering is completed through analytical sputtering, and a dynamic digital human which is rich in details, stable and controllable is generated.

The invention relates to a laryngoscope image classification method based on multi-scale cross-axis attention collaborative optimization, and the method comprises the steps: carrying out the preprocessing of a to-be-classified laryngoscope image, inputting the to-be-classified laryngoscope image after the preprocessing into a trained classification model based on multi-scale cross-axis attention collaborative optimization, and obtaining a classification result. The classification model sequentially comprises a feature extraction module, a feature coupling module, an average pooling module and a probability conversion module which are serially arranged from input to output. The feature extraction module comprises a first feature extraction unit and a second feature extraction unit which are parallel, the first feature extraction unit comprises an encoder and a decoder which are serial, and the second feature extraction unit is of an OfficientNet-B0 network structure. The encoder is of a ResNet50 network structure, and the decoder is of a multi-scale cross-axis attention network structure. According to the method, the parallel multi-model network is adopted for laryngoscope image feature extraction, the feature representation capability is high, and the problems of over-fitting and weak generalization capability cannot be caused.

The invention discloses an environmental noise classification method based on adaptive joint parameter space optimization, and the method comprises the steps: collecting a plurality of noise signals, enabling each type of signals to correspond to a specific environmental noise type, and constructing a data set; defining a joint parameter space comprising a plurality of optimization variables, wherein the joint parameter space comprises a data enhancement parameter subspace, a model network parameter subspace and a model training hyper-parameter subspace; according to training data characteristics, environmental noise classification task complexity and model deployment constraint, adaptively calculating each parameter range space; and constructing an objective function, and searching a multi-parameter optimal collaborative combination by using Bayesian optimization. According to the method, a joint parameter space is constructed, and Bayesian optimization is utilized to adaptively search a multi-parameter optimal collaborative combination of a data enhancement parameter, a model network parameter and a training hyper-parameter in a multi-model training process, so that synchronous dynamic optimization of data enhancement, a model structure and model training is realized; and finally, the performance of the neural network model in environmental noise classification is improved.

Techniques for calculating or determining risk scores for certain natural disasters perils based on machine learning model outputs are discussed herein. For example, a machine learning model may weight each of the pixels of a map in accordance with the set of weights associated with a structure, to calculate a risk score for a particular natural disaster peril associated with that structure. A plurality of risk selections may be provided to a user computing device for selection by a user, with those risk selections being associated with that risk score. Advantageously, the computing system facilitates the interaction of datasets with different measurement parameters in a machine learning model. In normalizing datasets before providing the datasets to input nodes of a machine learning model, a computing system may efficiently provide hazard and vulnerability outputs of the machine learning model.

The invention discloses an artificial intelligence model optimization method based on a brain-like artificial neural network, and the method comprises the steps: inputting a task data set into an artificial intelligence model, carrying out the forward propagation, and discriminating a corresponding dormancy neuron or an activation neuron of the artificial intelligence model in a process of executing an artificial intelligence task; a neuron dormancy matrix or activation matrix is generated as a mask matrix of the artificial intelligence model network weight, and a forward propagation path of the artificial intelligence model is reconstructed, so that dormancy neurons do not participate in the training and testing process of the artificial intelligence model network structure; or only enabling the activated neurons to participate in the training and testing process of the artificial intelligence model network structure; and loading the reconstructed artificial intelligence model at the computing device to execute the artificial intelligence task. According to the method, the working mode that only 0.5%-2.5% of neurons of the human brain are activated and most neurons are in a dormant state is effectively simulated, the calculation cost of the model is greatly reduced while the calculation performance of the model is not reduced, and the calculation efficiency of the model is improved.

A system includes one or more processors and memory. The memory stores instructions for execution by the one or more processors, including instructions for: obtaining a configuration request for a communications network; configuring a network of models (e.g., oscillators or oscillators'settings) into an initial configuration representing the configuration request for the communications network; reading out a final configuration of the network of models, the final configuration representing a solution to the configuration request for the communications network; and providing information over the communications network according to the configuration request.

The present invention relates to an intelligent sorting device reconstruction method based on a diffusion model. The technical features thereof lie in: inputting into a latent diffusion model a reference image from an object observation viewpoint, target viewpoint images, a viewpoint difference value and text features; adding noise to a plurality of target viewpoint images, and then performing transformation to obtain a joint feature; performing local interpolation to obtain features at different levels from a specific camera viewpoint; fusing the features into a latent diffusion model network by means of a mip-attention module, using the latent diffusion model network to perform denoising, and performing reconstruction by means of a neural implicit surface; and adding a normal-line function to a signed distance function, and optimizing the neural implicit surface by adding high-frequency information. In the present invention, spatial feature information is extracted and constructed, a diffusion process is guided, and a surface is then continuously optimized, so that a more refined surface is reconstructed, thereby realizing a three-dimensional reconstruction function for high-quality industrial devices; and the present invention has the characteristics of high efficiency, fast speed, high convenience, etc.

The invention relates to the technical field of artificial intelligence, in particular to a production scene-oriented multi-modal large model system, terminal equipment and a storage medium. The system comprises a data acquisition and analysis module used for acquiring multi-modal data; the teacher model module is used for configuring and constructing a heterogeneous multi-teacher model network and generating a lightweight multi-modal sub-network according to resource constraints of target terminal equipment, and the student model comprises a shared perception coding layer, a plurality of modal specific channels and a plurality of task decision heads; a distillation training module for training a student model according to a mixed distillation loss function, and a deployment optimization module for obtaining hardware configuration information of a target terminal, generating an optimal student model adapted to the target terminal according to the hardware configuration information and completing a deployment test; the terminal equipment has the comprehensive judgment capability close to that of an artificial expert, can quickly respond to problems and tasks, and solves the problem of timeliness.

Techniques for building and maintaining model webs are described. In some examples, a model web is built by selecting models for the model web from one or more available model types based on at least one or more of availability, tensor information, and compute type, instantiating synapses between the selected models to form the model web and updating information regarding availability of the selected models of the model web to indicate being in use.

The invention relates to a performance adjustment method and device of a large language model, equipment and a storage medium. The method comprises the steps that a first service sample is processed based on a large language model to obtain a first reference result, the large language model comprises N network layers with the same function, and M1 network layers are pruned from the large language model based on weight factors to obtain a first intermediate model; the network layer has a weight factor which is used for representing the contribution degree of the network layer in executing the text processing task; processing the first business sample based on the first intermediate model to obtain a first prediction result; performing quantitative comparison based on the first reference result and the first prediction result to obtain performance loss of the first intermediate model; and when the performance loss of the first intermediate model is within the threshold range corresponding to the loss threshold, the first intermediate model is used as the business model, so that the text reasoning performance of the business model can be improved.

The application discloses an adaptive modulation and coding method, a network device, a network element and a storage medium. The method comprises the following steps: when it is determined that base stations in a jurisdictional area satisfy a trigger condition of a smart AMC algorithm based on federated learning, the network device groups the base stations based on a similarity algorithm of base station feature information; a federated learning model network element corresponding to each group of base stations is determined; and the federated learning model network element is triggered to execute a life cycle process, and the life cycle process is used to obtain a smart AMC algorithm model, and all base stations in the same group share one smart AMC algorithm model. The embodiment can collect rich data resources of different devices, improve model accuracy, generalization and other performances; the multiple base stations in the federated learning model network element simultaneously perform model training, thereby saving the time for constructing the model; and the global model of the federated training suitable for the base station group is obtained by using a base station grouping rule to perform inference and prediction, thereby saving computing power and obtaining performance gain brought by the smart algorithm.

This invention discloses a method for constructing a digital twin model for smart water conservancy based on artificial intelligence, relating to the field of smart water conservancy technology. The method includes: establishing a project twin model based on smart water conservancy, performing related project analysis, and obtaining associatable equipment; establishing a twin model network and obtaining the response conditions and content of each node; and constructing a response analysis model based on the response content of real-time nodes. This invention addresses the problem in existing methods for constructing digital twin models for smart water conservancy that, when multiple types of water conservancy data exist and a certain type of water conservancy data exhibits abnormal changes, it is impossible to construct a targeted, real-time digital twin model for water conservancy equipment with significant data fluctuations. This results in an inability to effectively monitor abnormal equipment in water conservancy projects.

The invention provides a multiphase dielectric material microstructure three-dimensional fracture whole process simulation method based on space-time sequence prediction. The method comprises the following steps: S1, acquiring sample data; s2, constructing and training a deep learning model network; and S3, model verification: inputting historical surface crack information of the composite material into the trained generative network to obtain a subsequent fracture damage process of the composite material, applying Wasserstein distance quantification, comparing forms between fracture surfaces, and judging whether the performance of the model is good or bad. According to the method, the fracture surface in the entity can be predicted according to the historical apparent cracks of the composite material under the condition that component distribution information of the composite material is not needed; a network model is trained completely from the perspective of observation data, and it can be theoretically achieved that a prediction result is almost consistent with a result observed in an experiment; the calculation efficiency is high, and the calculation duration can be shortened from weeks to seconds; pixel-level modeling can be realized; the fracture process in the material can be predicted according to the apparent cracks of the material.

The invention relates to the technical field of communication, and discloses a reinforcement learning-based cross-space resource autonomous configuration method, which comprises the following steps of: performing joint modeling on network resources and physical resources by using a unified heterogeneous graph, and expressing a cross-space resource comprehensive configuration problem as a random and time-varying mixed integer nonlinear programming problem in a rolling time domain; introducing reinforcement learning to convert the nonlinear programming problem into a constrained Markov decision process; a resource configuration language instruction output by the policy network is mapped into a specific network domain and physical domain control instruction through a domain specific compiler, the specific network domain and physical domain control instruction is transactionally issued and executed, and an execution receipt is collected and fed back to the policy network to form closed-loop learning; according to the method, the engineering feasibility and the theoretical interpretability are unified. By means of a resource configuration language and triple masks, strategy output naturally falls in a compilable and rollback instruction subspace, and invalid exploration and configuration conflicts are remarkably reduced.

The invention discloses an autonomous traffic signal control subarea division method and device, a medium and a product, and relates to the field of traffic signal control, and the method comprises the steps: constructing traffic signal control agent models of different sizes of a regional road network based on a deep Q network, and constructing a multi-intersection cooperation model network; dividing the multi-intersection collaborative model network into a plurality of signal control units, and determining different signal control unit combinations; constructing an optimization model by taking the minimum road network maximum queuing length of the credit control unit combination as a target and taking time complexity and space complexity constraints of the credit control unit combination as constraint conditions; and according to the optimization model, determining an optimal signal control unit combination by adopting a genetic algorithm, and carrying out traffic signal control sub-region division according to the optimal signal control unit combination. According to the invention, the traffic signal control sub-areas can be accurately divided, so that the accuracy and the control effect of traffic signal control are improved.

The application provides a digital twin architecture of a network, a network session processing method and device, the method comprising: a data acquisition and control entity configured to acquire characteristic data of a physical network corresponding to a virtual network; a core entity connected to the data acquisition and control entity, configured to construct a network-related model corresponding to the physical network according to the characteristic data acquired by the data acquisition and control entity, the network-related model being configured to perform convergent processing on a network session event; and a user entity connected to the core entity, configured to visually display the network based on the network-related model. In the embodiment of the application, the digital twin architecture comprehensively uses perception, calculation, modeling, simulation and other technologies, realizes virtual-real mapping and interaction, can fully train and efficiently simulate more intelligent applications with high error cost, reduces the risk generated when a new technology is verified in a physical space, and reduces the possibility of errors occurring when the new technology is deployed in a real environment.

This application provides a method and electronic device for network topology repair of a 3D model. The method includes: constructing a first mapping information containing mesh faces and corresponding halves based on 3D model mesh data; determining a second mapping information containing each vertex and its corresponding half based on this; then combining the first two to determine the twin relationship information of each half; next, identifying non-manifold vertices based on the three types of information and counting their sector counts; and finally, completing the repair of non-manifold vertices based on the sector count and the second mapping information. By constructing multi-layer mapping information, a complete topology data system is built. Each step supports parallel processing. It accurately identifies non-manifold vertices based on topological features and achieves targeted repair based on the sector count. While ensuring repair accuracy, it significantly improves the efficiency of mesh topology repair and provides stable topology data support for subsequent mesh processing.