205 results about "Source model" patented technology

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 belongs to the technical field of electric power system information processing, and particularly relates to an electric power information analysis method based on big data, through semantic fusion of multi-source heterogeneous data and dynamic feature mining of a time sequence attention mechanism, in a load prediction scene, compared with a traditional single data source model, the electric power information analysis efficiency is improved. After the meteorological data, the user power consumption behavior data and the power grid operation data are fused, the prediction average error rate is reduced; in an equipment fault early warning scene, through multi-dimensional correlation analysis of vibration signals, oil temperature data and environmental factors, transformer latent faults can be early warned in advance, and the fault identification accuracy is improved; meanwhile, a self-adaptive modeling engine and a closed-loop feedback mechanism enable the system to have a self-evolution capability: when the power grid topology is adjusted or the new energy grid-connected proportion is changed, the model does not need to be manually retrained, and self-adaptive adaptation can be completed in two scheduling cycles through dynamic feature weight adjustment and meta-learner parameter optimization, so that the analysis performance is maintained to be stable.

The invention discloses an electric arc additive manufacturing temperature field and stress field real-time reconstruction method, which comprises the following steps of: 1, constructing a sequential coupling finite element model in which heat conduction analysis and thermoelastic-plastic mechanical analysis are combined on the basis of process parameters of an electric arc additive manufacturing process and three-dimensional geometry of parts, generating a multi-physical field coupling data set among heat flux density, temperature and stress; step 2, constructing and training a neural network model based on a multi-physics field coupling data set, and realizing mapping from heat flux density to temperature and stress; 3, dynamically optimizing heat source model parameters in combination with real-time monitoring data and process parameters in the electric arc additive manufacturing process; and 4, based on the optimized heat source model parameters and the trained neural network model, real-time reconstruction of a temperature field and a stress field in the electric arc additive manufacturing process is achieved. According to the invention, the requirements of rapid sensing and intelligent regulation and control of temperature and stress states on an additive manufacturing site are met.

The invention provides a water environment model coupling data processing method and system, and relates to the technical field of hydrology and water quality monitoring. The method comprises the following steps: determining a soil permeability characteristic descending trend and estimating an uncertainty range of a runoff coefficient; obtaining source model data according to the uncertainty range of the runoff coefficient by using a regional pollution production and convergence model; using the one-dimensional river network model to obtain error information according to the source model data, and outputting prediction data; and determining a prediction deviation mode by comparing the prediction data with the real-time monitoring data, and correcting parameters of all related models in the whole model chain. The method aims at solving the technical problem that the permissible discharge amount set based on a three-model coupling system does not conform to the actual absorption capacity of a water body due to continuous nonlinear deviation of river network model prediction and actually measured water quality data in the three-model coupling system, and accurate analysis of the urban pollution load and water environment quality response relation is achieved. And real-time and self-adaptive adjustment of the permissible emission amount is carried out.

The invention relates to the field of tunnel engineering, in particular to a tunnel multi-physics field coupling simulation and support design method considering construction disturbance, which comprises the following steps of: modeling a disturbance source, collecting disturbance factor information introduced in a tunnel construction process or an external environment, establishing a disturbance source model to represent the spatial position, intensity and evolution characteristics of a disturbance source; constructing a three-dimensional disturbance propagation function; coupling the three-dimensional disturbance propagation function with a multi-physical field model, and introducing disturbance as a source item into a tunnel heat-water-force coupling model; according to the construction method customization mechanism, modeling parameters and solving strategies are adjusted according to the characteristics of different tunnel construction methods, and corresponding disturbance source model parameters, boundary conditions and constitutive relation adjustment coefficients are set according to the different construction methods. The problems that disturbance modeling is rough, a disturbance propagation mechanism is idealized, the disturbance propagation mechanism is disjointed with a multi-physical field model, and a construction method is not included in a disturbance response system are solved.

The invention discloses a stochastic finite fault source model establishment method, which comprises the following steps of S1, determining a geometrical shape of a seismic fault based on regional geological data and seismic monitoring data, and estimating a non-planar fault parameter and a fault plane average sliding amount in combination with historical data and an empirical formula; s2, estimating distribution and sliding strength of concave-convex bodies and obstacles on the fault surface according to historical seismic inversion data, and obtaining the sliding amount of each sub-fault by randomly disturbing the average sliding amount; s3, the discrete fault plane serves as a sub-fault unit, and after an initial fracture point and the average fracture speed are determined, random fracture initial time conforming to normal or power law distribution is generated based on a random number method; s4, calculating the seismic oscillation time history of each sub-fault by adopting a random point source method, superposing contributions, introducing the influence of a shallow velocity structure V30, and generating a three-dimensional seismic oscillation field; and S5, comparing actual strong earthquake record adjustment parameters, and outputting a multi-risk-level earthquake motion parameter evaluation result after iterative optimization. According to the method, by fusing randomness and empirical data, the simulation precision of the seismic source model on the uncertainty of the seismic process is improved, the influence of the potential maximum-magnitude earthquake possibly occurring in the active fault zone in the future can be effectively estimated, the seismic oscillation simulation precision and the calculation efficiency can be improved, and the method is suitable for engineering structure aseismic design and seismic disaster evaluation.

The invention relates to the technical field of language model integration, in particular to a large language model integration method supporting semantic correction. The method comprises the following steps: S1, selecting several large language models, and sorting and preprocessing text data for training and testing; s2, training each source model and an optimization model by using an intelligent fusion language model technology; s3, fusing parameters of each source model by using an intelligent fusion language model technology, selecting model parameters for fusion according to the text data, and adjusting the fused model; s4, evaluating the semantic correction capability of the fused model, and adjusting a fusion strategy and regularization parameters according to an evaluation result; and S5, integrating the trained model into a target system. According to the large language model integration method supporting semantic correction, through an intelligent fusion language model technology, a context sensing and hybrid regularization technology is utilized to train and optimize a model and enhance adaptability, and a FuseLLM fusion technology is adopted to merge all source model parameters.

The invention provides a BIM (Building Information Modeling) full life cycle splitting and cross-model synchronization method and system. The method comprises the steps that BIM model components are coded based on a full life cycle coding rule, private attributes of all engineering stages and component codes of the engineering stages are bound and stored in component extension attributes, and a BIM master model containing multi-stage attribute information is generated; setting a BIM model splitting rule based on a rule engine; the code of each component in the BIM model is analyzed, the codes are compared with screening conditions in the splitting rules according to levels, and component data corresponding to the successfully matched codes are packaged and stored as sub-models; establishing association mapping between the models; and when the source model is modified, the synchronization engine executes synchronous updating of the target model according to the association mapping between the source model and the target model associated with the source model, so that the cross-stage multi-participant cooperation efficiency is improved, and a solid technical support is provided for digital transformation of the construction industry.

The invention discloses an ecological safety early warning evaluation system based on three-generation space coupling and multi-source model fusion. The system comprises an index framework construction module, a weight determination module, an ecological safety level evaluation module, a three-generation space coupling evaluation module and an ecological safety early warning evaluation module. The invention provides an ecological safety early warning evaluation system, which masters the possibility of occurrence of ecological environment problems and spatial and temporal distribution characteristics, and provides a scientific basis for management of governments and environmental protection departments in the region. According to the method, indexes are selected according to historical spatial data and various statistical yearbook, an ecological safety evaluation system is constructed based on a three-generation space theory, three-generation coupling coordination is calculated according to different land utilization functions, and finally an ecological safety early warning area is determined according to the space-time relationship between the two.

The invention relates to the technical field of digital twinning, in particular to a digital twinning drive solid waste real-time matching optimization method and system. The method comprises the following steps: obtaining building solid waste source end data, and carrying out solid waste source end twinning modeling according to the building solid waste source end data to obtain a digital twinning source end model; obtaining building solid waste receiving end data, and carrying out receiving point twinborn modeling according to the building solid waste receiving end data to obtain a digital twinborn receiving end model; performing matching according to the digital twin source end model and the digital twin receiving end model to obtain a solid waste matching model; and performing task splitting fusion scheduling according to the solid waste matching model to obtain solid waste scheduling data. According to the method, the digital twinborn model of the building solid waste source end and the building solid waste receiving end is constructed, fine modeling and dynamic mapping of solid waste attributes, processing capacity and pollution loads are achieved, the environment diffusion risk in the transportation process is effectively reduced, and the feasibility of task splitting and fusion and the resource bearing efficiency are enhanced.

The invention discloses an additive manufacturing surface topography prediction method and system based on multi-source molten pool feature fusion. The method comprises the steps that a visible light image and temperature field data of a molten pool in the laser additive manufacturing process are collected; key molten pool features are extracted according to the collected visible light images and temperature field data; fusing the extracted key molten pool feature data through a grid mapping method to generate a feature matrix; scanning the surface of the formed part to obtain surface topography data, and processing the surface topography data through a grid interpolation segmentation method to generate a label matrix with the same size as the feature matrix; and using a deep learning network based on an adaptive multi-source model, taking the feature matrix as an input, taking the label matrix as an output, carrying out training, and constructing a surface topography prediction model. By means of the scheme, the surface appearance in the laser additive manufacturing process is accurately predicted in real time, and an effective monitoring and predicting means is provided for quality control of additive manufacturing.

Disclosed are example embodiments of systems and methods for virtual try-on of articles of clothing. An example method of virtual try-on of articles of clothing includes selecting a garment from a pre-existing database. The method also includes loading a photo of a source model wearing the selected garment. Additionally, the method includes generating a semantic segmentation of the model image. The method also includes extracting the selected garment from the photo of the model. Additionally, the method includes determining a correspondence between a target model and the source model by performing a feature point detection and description of the target model and the source model, and performing feature matching and correspondence validation. The method also includes performing garment warping and alignment of the extracted garment. Additionally, the method includes overlaying and rendering the garment.

The invention discloses a data model field mapping method and device, a storage medium and a processor. According to the scheme, metadata of a source model and metadata of a target model are obtained; constructing a candidate field mapping set based on the metadata of the source model and the metadata of the target model; traversing each pair of candidate field mappings in the candidate field mapping set, calculating a comprehensive similarity value of each pair of candidate field mappings in the candidate field mapping set, and determining a mapping rule corresponding to each pair of candidate field mappings based on the comprehensive similarity value of each pair of candidate field mappings, and converting each pair of candidate field mapping from the source model to the target model based on the determined mapping rule. Compared with the problems of low efficiency, high error rate and the like of a manual maintenance mode in the prior art for a large number of fields and complex data structures, the method has obvious advantages.

The invention discloses a physical simulation method and device for seismic response certainty of an urban underground rail transit network, and the method comprises the steps: constructing a mixed seismic source model based on the active fault parameters and kinematic parameters of a target region, the seismic source model integrates a low-wavenumber deterministic slip component and a high-wavenumber random slip component on a fault fracture surface to generate a broadband seismic wave field source reflecting the physical process of a seismic source; the constructed seismic source model is used as input, a regional crustal velocity structure model is combined, propagation of seismic waves in a layered geological medium is simulated through a frequency-wavenumber domain method, and a seismic oscillation space-time field is obtained through calculation; and establishing a finite element model of the urban underground rail transit network, applying the seismic oscillation time-space field as non-consistent seismic oscillation input to the finite element model, and solving through dynamic time-history analysis to obtain the dynamic response of the whole underground rail transit network in the earthquake process. According to the invention, a complete physical chain from seismic source fracture to structural response can be reproduced.

The invention discloses a method, a device, equipment, a medium and a product for determining a shot peening forming process scheme, and the method comprises the following steps: constructing a geometric part digital model for a target part, applying a corresponding equivalent heat source model to the geometric part digital model at a shot peening path of a current scheme, and carrying out reverse simulation deformation calculation based on a material shrinkage parameter, obtaining a plate part mathematical model; calculating the weight of each node of the digital model based on the part thickness information and the flatness index value of the flat plate part digital model, and returning to the operation of obtaining the current scheme until all the schemes are processed; and according to the flatness index values, a target shot peening forming process scheme is obtained. Starting from the shape of the target part, reverse calculation is carried out through the equivalent heat source model and the shrinkage parameters, and the digital model of the flat plate part can be generated more accurately. Through the flatness judgment method of the weight of the part thickness information, all the process schemes are sequentially processed, the simulation result can be quantitatively evaluated, and the accuracy and reliability of shot peening forming process scheme selection are improved.

The invention discloses a cross-language named entity recognition method and device based on large interval representation learning and a medium, and the method comprises the steps: obtaining a source language annotated text sequence and a target language unannotated text sequence, and respectively extracting a first span and a second span; and training the source model by using the first span, and generating a pseudo tag corresponding to the second span. And according to the target language span feature and the similarity between the target language span feature and the category center to which the target language span feature belongs, evaluating the false label confidence, and dividing the false label confidence into high confidence and low confidence. And training a target model by using a joint loss function in combination with a source language annotation span and a high-confidence target language pseudo-tag span. And correcting the low-confidence false label to participate in subsequent iterative training of the target model so as to utilize more target language data. The trained target model is used for identifying the named entity in the target language text. The core of the method is to improve the cross-language named entity recognition performance by combining large interval representation learning with pseudo tag screening and dynamic correction.

The invention discloses a generated text detection method and system based on lightweight rewriting conversion and a medium, and the method comprises the steps: carrying out the AI removal conversion of a to-be-detected text through a forward rewriting model, fusing the to-be-detected text and a generated human-like equivalent text, inputting the fused text into a classifier, and outputting a classification result; the training process of the forward rewriting model comprises the following steps: constructing a pairing sample set by utilizing an artificially written text and a machine generated text, and finely tuning the forward rewriting model by minimizing cross entropy loss, the machine generated text is a text which is obtained by generating and filtering redundant samples through at least one large language model in a reverse manner through the large language model; according to the generated text detection method and system and the medium, access to any external, closed source or exclusive large language model API is not needed completely, the cost and delay are reduced, the system architecture and the deployment process are greatly simplified, and the problems that a watermark technology and a similarity regeneration method are limited by a closed source model and are difficult to actually deploy are solved.

A computer-implemented method of performing probabilistic seismic hazard analysis (PSHA) includes receiving a seismic source model, a ground motion model, and a probability distribution, constructing a joint probability distribution, using adaptive importance sampling to obtain an optimal sampling density, computing a PSHA hazard estimate and a hazard deaggregation distribution, and providing the PSHA hazard estimate and the hazard deaggregation to a user. Another computer-implemented method includes estimating a mean and fractile PSHA hazards for each of a series of iterations by drawing a random sample set from a proposal sampling density, evaluating an indicator function for each sample and multiply by an earthquake occurrence rate and a likelihood ratio to produce a weight vector, and estimating a mean hazard from an average of the weight vector.

The invention discloses a machine tool feeding system fault diagnosis method based on multi-level current characteristic distillation. The method comprises the following steps: collecting vibration and current time domain signals and respectively converting the vibration and current time domain signals into two-dimensional time-frequency diagrams; training a source model by using the vibration time-frequency diagram; cloning and freezing a source model, constructing a target model with the same structure, inputting the current time-frequency diagrams into the source model and the target model at the same time, and optimizing the target model through combination of multi-level feature distillation and a multi-target loss function; and finally, fault diagnosis based on the current signal is realized by using the optimized target model. According to the method, source domain data does not need to participate in training, knowledge migration from a vibration mode to a current mode is realized, the problems of weak current signal fault features and scarcity of labeled samples are effectively overcome, and the fault diagnosis precision and cross-working-condition adaptive capacity under the small sample condition are improved.

The invention discloses a dental three-dimensional model local optimization method and system based on multi-modal fusion, and belongs to the field of three-dimensional model modeling. According to the method, a source model (CT model) and a target model (mouth scanning model) are constructed, an initial corresponding relation is established by utilizing manual point selection, after coarse registration is completed, the corresponding position of each point is optimized by adopting fine registration based on triangular surface projection, and finally, a local area in the target model is embedded into the source model, so that unification of structural integrity and local precision is realized.

The invention belongs to the technical field of unmanned driving environment perception, and provides a night semantic segmentation method and system based on passive multi-level collaborative distillation, and the technical scheme is as follows: firstly, initializing a teacher network and a student network based on pre-training model parameters under a normal illumination condition; then, teacher network parameters are fixed, and a teacher network is updated according to student network parameters in a momentum smooth propagation mode; then, based on a prediction result of a pre-training source model on the night image, selecting first K pixel points with the highest confidence coefficient to generate a pseudo tag; and finally, inputting the normal illumination image and the night image into a teacher network and a student network respectively, and realizing multi-level knowledge migration through structure perception level alignment, semantic consistency constraint optimization and frequency domain collaborative fusion. No night annotation data is needed, source domain original data does not need to be accessed, and the data cost and the privacy risk are remarkably reduced.

The invention relates to the technical field of harmonic power flow calculation, in particular to a harmonic power flow calculation method and system of a photovoltaic power distribution system based on scene recursion. The method comprises the steps of generating a plurality of typical operation scenes through a Monte Carlo simulation method based on a probability density function of photovoltaic irradiation intensity and basic load, and constructing a multi-scene sample library; performing clustering processing on the historical operation data and the generated scene sample, and identifying and extracting a plurality of typical operation modes; establishing a harmonic source model for a harmonic source in the power distribution network according to the generated typical operation scene; calculating a time-varying harmonic coupling matrix; and selecting a typical working mode, and calculating a harmonic power flow index of each node of the system under each order of harmonic according to the established harmonic source model and the time-varying harmonic coupling matrix. According to the method, the calculation time delay is remarkably reduced while the analysis precision is ensured, and the method is particularly suitable for a modern power distribution system with high new energy permeability and ubiquitous power electronic equipment.

The invention provides a deep neural network model fingerprint generation and verification method based on decision consistency, and the method comprises the steps: inputting an original sample to a source model, generating a boundary sample through a gradient-based optimization method, carrying out the feature shielding of the boundary sample through a random binary mask matrix, so as to generate a fingerprint sample set, the size of the mask matrix is dynamically adjusted according to the feature complexity of the data set; respectively inputting the fingerprint sample set into a source model and a suspicious model, obtaining output probabilities of boundary samples and fingerprint samples of the two types of models, calculating a probability difference, and respectively calculating feature attribution weight matrixes of the two types of models through regularization linear regression; carrying out binarization processing on the weight matrix according to positive and negative of elements; obtaining binary weight matrixes corresponding to the source model and the suspicious model, and calculating element-by-element decision consistency similarity of the source model and the suspicious model; and when the decision consistency similarity does not exceed a preset threshold, determining the consistency of the two models.

The application provides a high-efficiency expression migration method using base expression space transformation, comprising a preprocessing stage and a facial expression migration stage; the preprocessing stage comprises: obtaining a source model O, the source model O being a base expression model comprising expression meshes under multiple different expressions; performing facial expression reconstruction on the source model O and a target model T to obtain expression description parameters of the two; performing similarity estimation according to the expression description parameters to obtain an expression parameter conversion matrix and a similarity matrix; the facial expression migration stage comprises: inputting a character picture into the base expression model, calculating expression description parameters of a target expression model according to the expression description parameters in the base expression model and the similarity matrix, and completing expression migration.