439 results about "Model set" patented technology

The invention relates to the technical field of numerical control machine tools, in particular to a five-axis machining center real-time thermal error compensation system based on digital twinning and a medium. Firstly, a data acquisition unit is used for acquiring physical actual measurement data in real time; then, the digital twin processing unit constructs a model set used for representing the thermal dynamic behavior of the five-axis machining center, and the model set is composed of a plurality of virtual thermal model members; thirdly, fusing physical measured data into the model set through a data assimilation algorithm to dynamically correct the state of each model member and predict the thermal error of the machine tool; the prospective compensation decision-making unit receives the thermal error prediction result output by the digital twinning processing unit and generates a prospective compensation instruction; and finally, the compensation execution unit issues the prospective compensation instruction to a numerical control system of the five-axis machining center for real-time adjustment. The control precision of real-time thermal error compensation of the five-axis machining center can be improved.

The invention relates to the technical field of electrical design and intelligent optimization calculation, and discloses a capacitor structure design optimization method and system and a storage medium. The method comprises the following steps: carrying out modeling processing on capacitor structure parameters, and dividing a parameter space to obtain an initial model set; obtaining a multi-physical field simulation model according to the geometric model and the material attributes; obtaining performance indexes such as capacitance value, heat distribution and stress based on the simulation model; setting a target function and constraint conditions, and operating an optimization algorithm to obtain an optimal solution set; performing feedback control processing on an optimization result, and analyzing a convergence path to obtain a structure parameter; according to the invention, the execution efficiency of capacitor structure design optimization is improved, and the consistency and stability of the optimization process and the performance prediction result are improved.

The invention discloses a multi-fingered dexterous hand grabbing posture generation method and system based on CVAE and a Ball Query algorithm, and belongs to the technical field of robot grabbing control. The method comprises the following steps: (1) a data sampling step; (2) a data preprocessing step: carrying out standardization processing on the collected data, generating enhanced point cloud data and constructing a training data set; (3) a model training step: through a multi-scale feature extraction module, combining global semantics and local geometric features extracted by a Ball Query algorithm, generating a grabbing attitude by using a conditional variation auto-encoder, and optimizing model parameters through reconstruction loss and KL divergence; and (4) real-time deployment: integrating the trained model to a physical platform, screening candidate grabbing postures based on parallel collision detection, and realizing real-time grabbing control in combination with inverse kinematics verification. The problem that a traditional method is insufficient in generalization ability in complex object grabbing is effectively solved, and self-adaptive grabbing of unknown objects is achieved while grabbing stability is guaranteed.

The invention discloses an interactive multi-model underwater maneuvering target tracking method and system based on a pure azimuth second-order EKF. The method comprises the following steps: establishing a discrete state space model of a pure azimuth target tracking system; performing second-order linearization on the pure azimuth measurement model; calculating mixed input of a sub-filter corresponding to each model in the model set of the interactive multi-model algorithm; estimating a target state through parallel filtering of the azimuth-pure second-order EKF sub-filter corresponding to each model in the model set; updating the probability of each model in the model set; and combining the estimation results of all the sub-filters to obtain a final estimation result of the target state. According to the method, the target tracking precision can be improved, the problem of highly nonlinear measurement of the UUV on a target detection and tracking system through a passive sonar is effectively solved, good real-time performance is achieved, and real-time tracking of the UUV on the motion state of the underwater maneuvering target is achieved through adaptive matching of the real motion of the target through the interactive multi-model algorithm.

The invention relates generally to the logistics modeling and prediction field, and more specifically to a new and useful prediction model determination method in the logistics modeling and prediction field. A method for prediction model determination can include: determining a set of models, training each model, determining package transit data, evaluating the set of models, selecting a model from the set of models, predicting package transit data using the selected model, and / or any other suitable element.

The invention discloses a building collision detection method based on BIM cooperative multi-agent reinforcement learning, and belongs to the technical field of building engineering. The method comprises the following steps: firstly, acquiring geometric data and pipeline distribution information from a preset building information model, and determining model block granularity through analysis to obtain a sub-model set; then, a multi-agent system is adopted to distribute monitoring responsibilities, edge geometrical shape data and physical connection point locations are extracted, potential conflict areas with overlapped boundaries are judged, and a collision probability distribution diagram is generated; exchanging real-time data by setting an information synchronization period between intelligent agents to obtain local conflict distribution details, introducing real-time change data to train the intelligent agents by adopting a reinforcement learning algorithm, and updating a monitoring priority and a cooperative action sequence; and if the conflict points which are not solved still exist, local collision detection is carried out by adopting a distributed computing framework, and finally, efficient and accurate building information model collision detection is realized by adaptively adjusting sub-model division and task allocation rules.

The invention relates to a multi-model-question-based group consensus large model illusion reduction method, which comprises the following steps of: screening a Top-N model from a candidate model set according to a multi-dimensional comprehensive scoring result, and executing full-combination bidirectional knowledge distillation on the Top-N model to obtain an initial model group, loading a plurality of domain knowledge bases for each model in the initial model group to carry out domain self-adaptive fine tuning, and constructing to obtain a group model set; giving a user question, triggering a plurality of fine-tuned field expert models in the group model set to perform parallel reasoning to generate an initial answer, performing iterative optimization by constructing a question set, generating a question instruction and updating the answer, and calculating the similarity of group answers by adopting a mixed kernel function in the iterative optimization process to obtain a group answer set; and when the similarity and the stability reach preset threshold values at the same time or reach the maximum number of iterations, stopping iteration and outputting a result. Compared with the prior art, the method has the advantages of high answering accuracy, high field adaptability and the like.

The invention discloses an uncertainty quantification method for satellite temperature data, and the method comprises the steps: training a plurality of deep learning models which are the same in structure and different in parameter initialization, so as to obtain prediction results of the plurality of models for the same input data; according to the prediction results of the multiple models, a calibration data set is constructed, and the calibration data set comprises an experience quantile and a prediction quantile; training a calibration model according to the calibration data set, and mapping a predicted quantile in the calibration data set to an experience quantile; inputting the initial quantile level value into a calibration model to obtain a calibrated quantile level value, and obtaining a prediction vector corresponding to the calibrated quantile level according to a prediction value of the deep learning model; and evaluating the calibrated uncertainty interval quality according to the predicted vector corresponding to the quantile level after calibration and the predicted vector corresponding to the initial quantile level. The method is based on a model integration method and is combined with the characteristics of a quantile calibration method to form a high-quality uncertainty calibration method.

A method of processing a compound prompt includes decomposing the compound prompt into a plan having multiple steps, and associating a domain descriptor with each of several specialized machine learning models. For each step of the plan, a relevance score for each specialized model is assigned by semantic comparison between its domain descriptor and the step. A subset of the models are selected based on relevance score and used to produce a step output. The outputs of all steps are assembled into a syntactically and semantically coherent final output via an integration module utilizing a large language model.

The invention discloses a particle mass transfer characteristic prediction method and system based on a machine learning algorithm, and relates to the technical field of particle movement in a multiphase flow system. The method comprises the following steps: constructing a bidirectional coupling numerical model, simulating a particle stirring process of a stirring tank by using the bidirectional coupling numerical model, and analyzing particle mass transfer characteristics and motion characteristics; constructing a machine learning model set, determining a neural network model, training the neural network model, and predicting the behavior of particles in the stirring tank by using the trained neural network to obtain a predicted value of the mass transfer coefficient of the stirring tank; and carrying out combined analysis on the analysis result of the interaction force between the particles and the fluid and the predicted value of the mass transfer coefficient of the stirring tank to obtain an inter-phase mass transfer rule in the stirring tank. The problems that the strong nonlinearity of the stirring tank is difficult to analyze, the mixing efficiency in the solid-liquid suspension process is low, the real-time performance based on dynamic model regulation and control is poor, and industrialization cannot be completely adapted are solved.

A method for establishing and generating contextual links between data from a plurality of data sources is described. The method includes receiving data and decomposing the received data into a decomposed data set; parsing and analyzing the decomposed data set based on a set of attribute analyzers to associate one or more attributes to the decomposed data set; determining an intent of data from the decomposed data set; generating a semantic graph of the decomposed data set based on the intent of data to evaluate data relatability between the decomposed data set; generating atomic knowledge units (AMUs) based on the parsed decomposed data set and the semantic graph; analyzing the AMUs corresponding to the received data by applying trained machine learning models to generate links between the AMUs and processing the generated links by a model ensemble to establish contextual links between data.

The invention discloses a climate mode pre-estimation downscaling correction method based on generative deep learning, and the method comprises the steps: recognizing the global climate mode hydro meteorological variable pre-estimation deviation through an unsupervised generative adversarial network, continuously reducing the adversarial loss through the adversarial training of a generator and a discriminator, and improving the accuracy of the adversarial training. Therefore, the trained generative deep learning network has the capability of processing a complex non-linear relationship so as to achieve the comprehensive optimum of downscaling and deviation correction. The method can be used for correcting the estimated average deviation of a multi-mode variable (rainfall, temperature and the like) set and improving the resolution ratio of the multi-mode variable set. The embodiment of the invention shows that the method can effectively estimate and downscale a multi-model set, and has a better downscaling effect than common quantile mapping and a convolutional neural network.

Techniques for model evaluation and selection are provided. A plurality of models trained to generate predictions at each of a plurality of intervals is received, and a plurality of model ensembles, each specifying one or more of the plurality of models for each of the plurality of intervals, is generated. A test data set is received, where the test data set includes values for at least a first interval of the plurality of intervals and does not include values for at least a second interval of the plurality of intervals. A first model ensemble, of the plurality of model ensembles, is selected based on processing the test data set using each of the plurality of model ensembles.

The invention discloses an efficient optimization selection and model adaptation method and system based on LoRA and MoE technologies, and the method comprises the steps: firstly, constructing a LoRA module pool for various models and vertical field data sets according to different field models and data set features, so as to rapidly screen and call adaptation models in similar tasks; secondly, based on downstream task description, hidden layer features and confusion, performing coarse-grained LoRA selection from a LoRA module pool; and then, by using the performance characteristics and the single LoRA weight distance, further screening a fine-grained LoRA module from the LoRA modules selected from the coarse-grained LoRA modules based on diversity. And finally, activating the selected LoRA module by adopting a Top-k strategy based on the MoE architecture, and finally determining the LoRA module which is most adaptive to the downstream task in combination with performance feedback after integration with the basic model. According to the method, a large number of LoRA modules can be effectively constructed, the module most adaptive to the downstream task is selected, and the accuracy of the model in processing tasks such as mathematical reasoning is remarkably improved.

The invention relates to the technical field of image processing, and discloses a house quality detection method and system based on a live-action three-dimensional model. The method comprises the following steps: converting an OSGB format live-action three-dimensional building model into a body coordinate system and carrying out quality evaluation, carrying out semantic segmentation on a standardized model to obtain a component geographic entity set, establishing an independent local coordinate system of each component to form a single three-dimensional model set, generating a multi-view projection feature image set based on a normal vector distribution planning view angle, and carrying out multi-view projection on the single three-dimensional model set. And detecting defects by adopting a 3D-YOLO-BuildingDefect algorithm, and carrying out inverse transformation to obtain three-dimensional space defect distribution and a quality grade evaluation result. The technical problems that a traditional two-dimensional detection method is insufficient in spatial positioning precision, incomplete in detection coverage rate and insufficient in geometric information utilization are solved, and the spatial positioning accuracy of house quality detection and the comprehensiveness of defect recognition are improved.

There are provided methods, systems, and non-transitory storage mediums for performing a meta-prediction of time series by using a set of forecasting models each associated with a forecasting theme. Time series data is received, and a set of forecast signals is generated. At least one signal and feature processing model generates a set of features. A meta-learner having been trained on historical time series data generates, based on the time series data and the set of features, a set of weights for the set of forecasting models. A meta-prediction is generated by using the set of features and forecast signals. Implementations may use combinations of endogenous and exogenous data, latent space transformations and generate interpretations and explanations for the meta-prediction.

The invention discloses a maneuvering target tracking method based on model adaptation, which combines Bayesian online change point detection and a model selection method, and is characterized in that the Bayesian online change point detection detects change points of generated parameters in sequence data in an online mode, so that the change of a target motion state can be perceived in real time; according to the model selection method, the motion model matched with the target motion state can be selected in the model set according to the change of the target motion state; specifically, the change of the motion state of a target is detected in real time through a Bayesian online change point detection technology, when a change point is detected, a model selection mechanism is triggered, a proper motion model is selected according to the current motion state of the target, and parameters of a tracking filter are updated, so that accurate tracking of the maneuvering target is realized. The method not only can adapt to the change of the motion state of the target, but also can make full use of information in historical data, and improves the robustness and accuracy of a tracking algorithm.

A method, computer system, and a computer program product are provided. A first data sample is received via a computer. The first data sample is compared to a collection of models to select one of the models that is determined as a best match for the first data sample. The comparing includes (A) the computer comparing metrics of data summarization for the first data sample to metrics of data summarization of the models and (B) the computer comparing a neural network metric for the first data sample to respective neural network metrics for the models.

The invention discloses a dynamic scheduling reasoning method based on a hybrid expert model and related equipment, and the method comprises the steps: determining a to-be-reasoned hybrid expert model which comprises a plurality of expert sub-models; performing nested weight quantization processing on the plurality of expert sub-models to obtain a quantized sub-model set; in response to an inference task, performing routing activation processing on the quantized sub-model set to obtain an activated sub-model set; performing dynamic bit width selection processing on the activation sub-model set according to the reasoning task to obtain an initial sub-model set; performing bit width sensing reordering processing on the initial sub-model set to obtain a target sub-model queue; and performing execution processing on the reasoning task according to the target sub-model queue to obtain a reasoning result. The embodiment of the invention can improve the efficiency of model reasoning, and can be widely applied to the technical field of artificial intelligence.

The invention relates to the field of city planning, and discloses a city spatial evolution prediction system fusing multi-modal data, and the system comprises a data preprocessing and multi-modal knowledge graph construction module which is used for configuring a knowledge graph ontology architecture and preprocessing multi-source city data; establishing a multi-modal knowledge graph based on the preprocessed multi-source city data and the knowledge graph ontology architecture; the model setting module is used for configuring a multi-modal representation learning model; the data integration module is used for a multi-modal representation learning model and performing deep integration on multi-modal data in a vector space to obtain vector representation with remote sensing and streetscape semantic information; and the knowledge reasoning and predicting module is used for performing knowledge reasoning on the missing part in the multi-modal knowledge graph based on the vector representation so as to predict the urban spatial evolution event. The urban spatial evolution event prediction can be realized, and the problem that the remote sensing image and the streetscape image are difficult to be deeply fused is effectively solved.

The invention discloses an industrial field knowledge question answering method and device, equipment, a storage medium and a product, and relates to the technical field of industrial manufacturing, and the method comprises the steps: carrying out the key information extraction of a question input by a user, and carrying out the matching of an extraction result with a thinking chain cue word template, and obtaining prompt information; the prompt information is input into the large model for answer prediction, and a prediction result is obtained; key prediction information in the prediction result is extracted, a meta-model set is called based on the key prediction information for prediction, a question and answer result output by the meta-model set is obtained, and the meta-model set comprises meta-models obtained by disassembling an industrial mechanism model and an optimization algorithm. The answer prediction is performed based on the large model, and then the optimization prediction is performed based on the meta-model set to obtain the question and answer result, so that compared with an existing mode of performing question and answer only depending on the large model, the method can meet the requirements of complex professional questions in the industrial field, realize refined question and answer processing, and ensure the accuracy and specialty of question and answer.

The invention provides a heat supply digital twin modeling method and system based on a U3D engine and a medium. The method comprises the steps that a historical static data set and a historical dynamic data set are obtained for preprocessing, a historical static optimized data set and a historical dynamic optimized data set are obtained, a U3D engine is combined with a preset parameterized component library to conduct heat supply digital twinning model construction, initialization is conducted based on the historical static data set, and a heat supply digital twinning model is obtained. Obtaining an initial heat supply digital twinborn model, generating an LOD model set with different precisions through an LOD rendering method, inputting the historical dynamic optimization data set into the initial heat supply digital twinborn model for processing, obtaining a simulation data set and equipment operation state evaluation data, and evaluating the qualified state of the model through threshold comparison; according to the method, data security fusion is realized through the block chain, the hydraulic and thermal coupling model is constructed by using the U3D engine, and predictive maintenance and multi-objective optimization are realized through an intelligent algorithm, so that intelligent construction of the heat supply word twinborn model is realized.

The invention discloses an ore body three-dimensional modeling method and device, and relates to the technical field of three-dimensional modeling. The method includes the following steps that geometric feature parameters of an ore body to be monitored are obtained, a three-dimensional boundary model is constructed, and the surface is divided into a plurality of equal-size grids; collecting point cloud data of the topographic surface of the ore body, mapping the point cloud data into a grid, analyzing the point cloud data through different modeling methods, generating a plurality of three-dimensional ore body structure models, and preferably forming a model set; coupling and analyzing the structural complexity, and screening out an information comparison grid; calculating accumulated differences between the point cloud surface features and the model features, and selecting the model with the minimum accumulated difference as a target ore body three-dimensional model; in combination with real-time mining position information, a construction influence range is determined as a monitoring area, the local structure of the target ore body model is dynamically updated by obtaining vibration information and area point cloud data of the monitoring area, the targets of real-time monitoring and dynamic management of the ore body are achieved, and mining safety and efficiency are improved.

Described herein is a computer implemented method for correcting for clock drift of a system clock in a signal sampling device comprising the system clock and configured to sample a signal in real time, the method comprising: obtaining data relating to an environmental parameter of an environment of the signal sampling device; matching the data relating to the environmental parameter to an environmental scenario; selecting, from a model set, a model tagged with the matched environmental scenario; and correcting for clock drift of the system clock using the selected model. Also described herein is a method for preparing a model set for clock drift correction, a sampling device, and a computer implemented method for correcting for clock drift of the system clocks of an array of signal sampling devices.

The invention discloses a construction method of a high-entropy alloy mechanical property prediction model, which comprises the following steps: constructing a high-entropy alloy model set, namely defining proportional distribution of high-entropy alloy components, determining component structures, and enabling one group of component structures to correspond to one high-entropy alloy model; performing force field parameter setting stable configuration on the high-entropy alloy model; simulating and acquiring mechanical characteristics of the high-entropy alloy model through a stretching process; obtaining a multi-scale feature data set; the multiple scales comprise environment features, reference features and analog calculation features; performing feature screening on the multi-scale feature data set to obtain a sample data set; defining a plurality of regression machine learning models; and training and verifying the regression machine learning model by adopting the sample data set, selecting an optimal regression machine learning model, and constructing a mechanical property prediction model. According to the technical scheme, the limitation of a traditional scheme can be broken through, the calculation efficiency and the prediction credibility are improved, the new material research and development period is remarkably shortened, and the experiment cost is reduced.

The invention relates to the technical field of oil-gas exploration, in particular to a micro-amplitude structure seismic exploration detection method and system based on pre-stack depth migration, and the method comprises the steps: generating an equivalent speed model set, calculating speed uncertainty data, probabilistically detecting a micro-amplitude structure, and fusing and displaying a result. Compared with the prior art that an absolutely correct speed model is blindly pursued, but the influence of model errors on tiny structure recognition cannot be overcome finally, the method has the advantages that the speed model errors are converted into valuable detection signals from interference needing to be minimized; by actively generating multiple sets of global equivalent speed models and analyzing the uncertainty of the speed models, the most unstable areas in the modeling process become direct evidences for indicating the existence of the micro-amplitude structure, normal form transfer from error elimination to error utilization is realized, and the detection capability of the micro-amplitude structure is remarkably improved.

The invention provides a time sequence prediction method and apparatus. The method comprises the steps of obtaining historical data of a to-be-predicted index; according to the historical data length of the to-be-predicted index, a target model subset is selected from a preset model set, and the input length corresponding to the target model subset is smaller than or equal to the historical data length of the to-be-predicted index; calculating a prediction error of each time sequence small model in the target model subset by using the offline data of the to-be-predicted index, and taking the time sequence small model with the minimum prediction error as a target model; and generating a prediction result according to the historical data of the to-be-predicted index by using the target model. According to the method, the preset model set covering the time sequence small models of various input lengths is set, prediction of the to-be-predicted indexes of various historical data lengths can be achieved, the limitation that a traditional time sequence small model only supports a single input length is broken through, and the application scene of the time sequence small model is greatly expanded.

The invention provides a model cooperative processing method and device, electronic equipment and a computer storage medium, and relates to the technical fields of artificial intelligence, natural language processing, computer vision and the like. According to the specific implementation scheme, to-be-processed information in an agricultural scene is acquired; sending the to-be-processed information and the decision information cue word to the large model to obtain small model information and decision parameter information output by the large model; based on the small model information, determining a target small model set, and sending the decision parameter information to related target small models in the target small model set; sending the to-be-processed information to the target small model set; receiving a small model processing result set output by the target small model set; and obtaining a processing result of the to-be-processed information based on the small model processing result set, the to-be-processed information, the small model information, the decision parameter information and the large model.

The invention relates to the technical field of industrial detection, and provides a steel ladle air brick defect detection method and system based on image recognition, and the method comprises the steps: carrying out the preprocessing of a target steel ladle air brick image shot by an industrial camera, including edge feature extraction, cutting and enhancement, and obtaining a preprocessed image set; for the block corresponding to each preprocessed image, acquiring a multi-angle image set with different resolutions shot by a multi-angle sensor; inputting the multi-angle images into a defect feature extraction network to generate a feature image set, and integrating to obtain an integrated feature image; generating defect positioning and type information based on the integrated feature map and the defect identification model set; and finally, combining the initial image, the model set and the defect information to generate a defect detection result. According to the method, the defect detection precision is improved through multi-angle image fusion and model collaborative verification. According to the invention, the accuracy and reliability of steel ladle air brick defect detection can be improved, and the accuracy of defect positioning and classification is enhanced.

The invention discloses a power distribution load prediction method and system, and relates to the technical field of graph calculation, and the method comprises the following steps: obtaining load data and auxiliary features of a user, and constructing a load portrait; according to the load portrait, selecting a model subset from a pre-training model library, migrating the selected model, and outputting an initial load prediction result; constructing a load association graph according to the spatial adjacency and behavior similarity between the users, and spreading load characteristics in the load association graph; regulating and controlling the model of the target user according to the propagated load characteristics in combination with an initial load prediction result; obtaining a user load data distribution change after regulation and control, and identifying a behavior mutation; through multi-model integration, individual fine tuning, load association graph construction, incremental learning and drift detection, the problems of low precision, poor dynamic adaptability and slow response to sudden change in traditional power distribution load prediction are effectively solved.