61 results about "Random field ising model" patented technology

The invention relates to the technical field of power distribution cabinet detection, and discloses an intelligent power distribution cabinet state dynamic monitoring method and system, and the method comprises the following steps: collecting multi-source data generated in the operation process of a power distribution cabinet; preprocessing the multi-source data to generate a standardized data set; a random field model is constructed and used for describing the spatial relevance between units in the power distribution cabinet and the relation between the state of each unit and multi-source data, and model parameters are estimated through the maximum logarithmic posterior probability. An intelligent power distribution simulation model and a multi-source data acquisition technology are adopted, multi-dimensional parameters are acquired in real time through a high-precision sensor, monitoring efficiency and decision accuracy are remarkably improved, data analysis integrity and model sensitivity are ensured through dynamic time modeling and capturing of space and time relevance of the power distribution cabinet, and the power distribution cabinet can be monitored more accurately. And the state distribution visualization and maintenance priority strategy generation module optimizes the maintenance plan, reduces the operation and maintenance cost, and guarantees the stability of the power distribution system.

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

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

The invention provides a large-scale three-dimensional tunnel surrounding rock parameter random field model construction method and system, and relates to the technical field of tunnel surrounding rock modeling, and the method comprises the steps: carrying out the fitting construction of a probability distribution model reflecting surrounding rock parameters; selecting a plurality of surrounding rock parameters as clustering features, quantitatively classifying global geologic structures in tunnel surrounding rocks, and performing global decomposition on a tunnel model into continuous sub-domains containing overlapped buffer areas; for a first sub-domain from any direction of the whole domain of the tunnel model, performing covariance matrix spectral decomposition by adopting a KL decomposition method to generate a first sub-domain random field, and extracting random field values of overlapped regions among the sub-domains as boundary condition data of a recursive generation process; on the basis of the boundary condition data, conditional random fields of subsequent sub-domains are generated layer by layer; and seamlessly splicing the conditional random fields generated by recursion of the sub-fields into a global parameter random field, converting the global parameter random field into probability distribution by adopting a probability mapping method, and performing instruction encapsulation by developing a cross-platform data interface engine to realize a construction process of a parameter random field model.

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

The invention provides a shape function KL expansion random field discretization method considering a slope soil body irregular domain, and belongs to the technical field of soil body parameter random field analysis. Comprising the following steps: establishing a slope numerical model and dividing a discrete grid and a form function grid; establishing a probability distribution model of a soil parameter random field; calculating an element stiffness submatrix ke and an element mass matrix Ee; calculating an autocorrelation matrix rho and a global stiffness matrix B; assembling a global matrix; calculating a characteristic value lambda k, a characteristic function phi k and an expansion term number M; and random field discretization of the slope numerical model is realized. The random field discrete technology provided by the invention is used for efficiently and accurately analyzing the random distribution characteristics of the soil parameters in the rock-soil structure. The discrete random field model can be efficiently constructed in a complex geological structure, the calculation cost is remarkably reduced, the method can be conveniently combined with numerical simulation tools such as a finite element method, and the requirement of actual engineering for efficiency is met while the precision is improved.

The invention discloses a humanistic ancient tree patrol route intelligent recommendation method based on particle swarm optimization. The method comprises the following steps: S1, forming a unified ancient tree patrol data set; s2, constructing an improved Markov random field model according to the ancient tree patrol data set; s3, constructing a multi-target and multi-constraint patrol path optimization model by using the ancient tree patrol data set and the improved Markov random field model, and stipulating a feasible patrol sequence and environmental adaptability constraints among ancient trees; s4, based on the ancient tree patrol data set and prior information of the improved Markov random field model, generating an initial patrol path group through a standard particle swarm optimization algorithm; s5, performing iterative optimization on the initial patrol path group by applying a standard particle swarm optimization algorithm to form an updated patrol path group; and S6, selecting the patrol path with the highest fitness from the updated patrol path group according to a preset patrol path fitness evaluation standard. According to the invention, the overall planning of the patrol path is more scientific and reasonable.

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

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

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

The invention provides a seismic facies classification method and device for seismic data, and the method comprises the steps: dividing a seismic data set in a target work area into K classes, wherein K is equal to the number of seismic facies classes in the target work area; determining initial classification sample data according to the interpretation horizon in the target work area; wherein the initial classification sample data is used as initial data for performing seismic facies classification on the seismic data set; and performing seismic facies classification on the seismic data set according to the initial classification sample data and a pre-generated Markov random field model. According to the method, the actual seismic data in a certain layer are compared trace by trace, and the transverse change of the seismic signal is depicted in detail, so that the plane distribution rule of the seismic anomalous body is obtained.

The present invention discloses a method and device for detecting the horizons of cultivated land soil based on ground penetrating radar and Markov random field. By acquiring the B-SCAN data of cultivated land through ground penetrating radar, preprocessing and selecting horizon seed points are carried out. Based on the undirected graph model and the initial horizon tracking marker field, a Markov random field model is constructed; by integrating the posterior probability energy field of horizon points and the dominant term of horizon envelope characteristics, the optimal horizon points are calculated; finally, the horizon depth value is calculated according to the soil dielectric constant, and whether the thickness of the tillage layer and the effective soil layer meets the standard is evaluated. The present invention has higher accuracy and stability in complex soil environments, can achieve efficient and accurate horizon tracking without relying on large-scale high-quality data, is suitable for the rapid processing of large-scale cultivated land soil data, and meets the requirements of soil layer thickness measurement and evaluation in land consolidation and high-standard farmland construction, providing an innovative technical solution for farmland management and construction.

A medical skin lesion segmentation method based on a multi-scale feature matrix yoke belongs to the technical field of image processing, and comprises the following steps: 1, carrying out preprocessing such as denoising on a skin lesion image, obtaining a plurality of image features by using a gray level co-occurrence matrix method, and constructing a three-dimensional multi-scale image feature matrix; 2, carrying out yoke transformation on the three-dimensional multi-scale characteristic matrix to construct a multi-scale characteristic matrix yoke according with the characteristics of a yoke process; 3, modeling a two-dimensional Markov random field model, and creating an energy function based on a multi-scale feature matrix yoke; and 4, performing post-processing operations such as morphology on the obtained result. According to the method, the features obtained from the gray-level co-occurrence matrix are constructed into the three-dimensional multi-scale feature matrix yoke, and the new Markov random field energy function is constructed on the basis, so that a better segmentation effect can be obtained.

The invention relates to a physical-data-driven sequence type seismic oscillation generation method. The method comprises the following steps: acquiring a historical seismic record; constructing a main earthquake ground motion random field model based on the physical mechanism of the ground motion field; the physical mechanism comprises a seismic source, a propagation path and a local site model; obtaining main earthquake parameters based on historical earthquake records according to the main earthquake ground motion random field model; the main earthquake parameter is used for predicting an unknown main earthquake seismic record according to a main earthquake seismic oscillation random field model to obtain a main earthquake seismic oscillation time history; and constructing an aftershock seismic oscillation generation model based on a conditional generative adversarial network model according to the main seismic oscillation time history to realize prediction of a seismic oscillation field. According to the method, the parameters of the main earthquake are generated based on the earthquake motion field of the physical mechanism, the time history of the main earthquake is obtained, the aftershock prediction model is constructed according to the conditional generative adversarial network, the physical mechanism model is combined with artificial intelligence, the model prediction fitness and accuracy are improved, the aftershock is predicted, the prediction effect is improved, complex calculation is avoided, and the model construction efficiency is improved.

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

The invention provides a knowledge base construction method based on multimode entity automatic extraction, classification and association and a storage medium, and the method comprises the steps: preprocessing text data and image data, extracting a text entity through a bidirectional encoder and a random field model, and obtaining a text semantic relation through a statement analysis algorithm; extracting an image entity and a semantic relationship by using a target detection model and an image description algorithm; text and image entity features are fused, a multi-modal deep learning model is constructed, and an attention mechanism is introduced; classifying the multimode entities, constructing a triple, and constructing a knowledge base based on a classification result and the triple; and performing quality evaluation and optimization on the knowledge base. According to the method, the knowledge base construction efficiency and accuracy are improved through an automation technology, the knowledge base content is enriched, and the classification effect and the knowledge base quality are improved through an attention mechanism.

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

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

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

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

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

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

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

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

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

The invention belongs to the field of crane jib control, and particularly discloses an energy-saving turnover control system for automatic obstacle avoidance of a crane jib, which comprises a data acquisition module, an obstacle recognition module, an obstacle avoidance path design module and a turnover control module. According to the invention, through the Markov random field model, the gradient potential energy, the depth curvature potential energy and the depth variance potential energy are fused, the obstacle is segmented, and the features of the obstacle can be described more comprehensively, so that the segmentation accuracy is improved; a path planning method based on strategy gradient enhancement is used for designing a suspension arm path, the action and state of the suspension arm are continuously updated, explicit definition of an environment rule is not needed, the method is suitable for a dynamic and uncertain environment, long-term rewards are considered, and finding of a globally optimal or nearly optimal path is facilitated.

The present invention discloses a deep learning-based sea ice classification and density inversion method, which relates to the field of remote sensing image processing technology and aims to solve the problems of the existing technology. The method comprises obtaining raw dual-polarization synthetic aperture radar data and preprocessing it; performing superpixel segmentation on the preprocessed data to obtain multiple superpixels; calculating the posterior probability of the superpixel using a conditional random field model to determine the uncertain superpixel unit; using the uncertain superpixel unit as input, outputting the sea ice and seawater boundary lines within the uncertain superpixel unit based on the Ice-WaterNet network model, and combining them to obtain a sea ice classification result map; and performing sea ice density inversion on the sea ice classification result map to obtain a sea ice density inversion result. The present invention improves the inversion accuracy of sea ice classification and density, and can play a more important role in global climate change monitoring, marine environmental protection, polar resource development and utilization, and other aspects.

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

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

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