278 results about "Model set" patented technology

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.

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 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 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 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 software radio unified modeling method and system, and belongs to the field of software radio, and the method comprises the steps: determining modeling objects as platform modeling and waveform modeling; wherein during platform modeling, abstract modeling is performed on each calculation unit, and during waveform modeling, waveform component modeling and waveform application modeling are included; in the waveform component modeling, at least one modeled waveform component runs on a calculation unit, and a plurality of waveform components can be deployed on the calculation unit at the same time; the waveform application modeling comprises the following steps: establishing a connection relation between waveform components, and assembling into waveform application; then executing a modeling process of creating a platform model, creating a waveform model and establishing a platform and waveform connection relationship, and performing modeling detection; establishing a basic model set after modeling detection; the basic model set comprises a platform model subset and a waveform model subset. The modeling efficiency and the standardization degree are improved.

The invention relates to a power grid project basic design system and method based on a general function module. The system comprises a general editing module, a basic primitive modeling module, a parameterized component module, a model integration module and a link reference module. The universal editing module is used for freely adjusting, placing and combining the selected primitives; the basic primitive modeling module is used for providing various basic primitives and completing splicing among the primitives through surface-based arrangement and parameter change; the parameterized component module is used for creating parameterized components in a UI interaction mode; the model integration module is used for importing a public data format through an interface to carry out modeling and design operation; and the link reference module is used for integrating the local file into the current model in the system through the model link reference interface to serve as view reference. Compared with the prior art, the method has the advantages that the technical architecture and functional system design of the design foundation platform is completed under the guidance of the power grid engineering design requirements, and the efficiency is improved.

The invention provides a head and neck cancer image area multi-target classification method and system and a medium, and belongs to the technical field of medical image processing, and the method comprises the steps: obtaining a data set of a complete head and neck cancer CT image; randomly generating a plurality of neural network structure models, performing training and evaluation according to the data set, performing optimization by taking sensitivity and specificity as multiple optimization targets, and generating a Pareto optimal candidate model set; obtaining a weighting coefficient of each candidate model according to the sensitivity, the specificity and the AUC evaluation result of the candidate model; extracting the reliability and uncertainty of the to-be-classified sample, and adjusting the output probability of each candidate model according to the reliability and uncertainty; and taking the weighting coefficient of each candidate model, the adjusted output probability and the prediction reliability as input, and obtaining a classification result, a prediction probability and uncertainty through ER-rule reasoning fusion. According to the method, the robustness of the classification performance of the multi-fusion model is effectively improved.

The invention relates to the crossing field of cloud computing and artificial intelligence technologies, in particular to a tool deployment method, system and device based on a model context protocol, and aims at solving the problem that the integration process of scientific research tools and a large language model (LLM) is complex. A tool description file conforming to a model context protocol specification is automatically generated; in order to meet the rapid and efficient deployment effect of the scientific research tool, a pre-formulated hierarchical construction strategy is adopted, and a container mirror image is generated according to a running environment dependency list in a tool description file, so that the tool construction speed is increased; and meanwhile, on the basis of the security information field and the resource demand list in the tool description file, according to the preset allocation rule, the appropriate operation instance is dynamically allocated, so that the security in the tool deployment process is guaranteed, and the integration and deployment operation efficiency of the tool and the large language model is improved while the labor cost is reduced.

The invention provides a large language model fusion method and system based on gradient approximation. The method comprises the following steps: acquiring a language text data sample; constructing a fine tuning model set and a pre-training model, and defining a difference value between the fine tuning model and the pre-training model as a task vector; the fine tuning model set and the pre-training model are operated in multiple modes, and parameter importance evaluation results of the task vectors are calculated based on gradients in different operation modes; constructing an activation function, and determining a pruning rate in combination with the activation function and a parameter importance evaluation result; pruning and fusion of the fine adjustment model set are completed according to the pruning rate, and a final fine adjustment model is obtained; processing the language text data sample by using a fine tuning model to obtain a corresponding processing result; according to the method, the reliability of a data processing result can be kept while the calculation overhead is remarkably reduced.

The invention discloses a repair material performance prediction and formula optimization method based on a machine learning algorithm, and particularly relates to the crossing field of artificial intelligence and material science, and the method comprises the steps: constructing a structured multi-modal feature library, carrying out the data processing through dual-index and differential noise filtering, constructing an isoproton model set guided by a physical mechanism, and carrying out the optimization of the repair material performance prediction and formula optimization. Comprising three targeted sub-models including a graph neural network, a time sequence convolutional network and a gradient boosting tree, outputs of the sub-models are dynamically fused through a meta-learner, combined prediction of material performance is achieved, a potential formula is actively searched in a high-dimensional solution space through dimension reduction mapping and Bayesian optimization, and the performance of the material is predicted. The method comprises the following steps: performing gradient-guided constraint optimization by using a differentiable physical-data fusion simulator to generate an optimal formula scheme, and finally realizing automatic feedback of new data and autonomous evolution of a model through a triggering rule and a local incremental learning mechanism based on uncertainty and deviation to form a complete self-evolution closed-loop system.

The invention discloses a valve-side dry-type bushing end screen diagnosis and evaluation method, system, medium and equipment, and the method comprises the steps: data collection and preprocessing: obtaining multi-source data of a converter transformer valve-side dry-type bushing through real-time monitoring or historical recording of a sensor; dividing the data set, and dividing the multi-source data into a training set and a test set according to a proportion; building a random forest model, generating training subsets of a plurality of decision trees from the training set by adopting replacement random sampling, randomly selecting a feature subset for each decision tree, performing node splitting based on an information gain ratio, and generating the decision trees in a depth-first mode until a preset maximum depth is reached; performing model integration and diagnosis, adopting a voting mechanism to integrate classification results of all decision trees, and outputting defect types and state evaluation grades, the state evaluation grades being grade II and grade I; and performing dynamic tuning and deployment, performing model parameter optimization by taking a test set macro average F1 score greater than or equal to 0.9 as a threshold value, and performing real-time diagnosis on the optimized model.

The application discloses a three-dimensional model fast retrieval method, equipment and medium, and relates to the computer technical field. The method comprises the following steps: in response to receiving a part of a two-dimensional sketch of a three-dimensional model drawn by a user, performing image segmentation on the part of the two-dimensional sketch to obtain a plurality of sub-images; performing mapping processing on each sub-image to obtain an initial feature corresponding to each sub-image, and performing attention calculation on the initial features corresponding to the plurality of sub-images to obtain a plurality of first key features; fusing the plurality of first key features to obtain a second key feature corresponding to the part of the two-dimensional sketch; based on the second key feature, performing similarity matching on a feature database to obtain a plurality of target features, and searching a three-dimensional model set corresponding to the plurality of target features from a three-dimensional model database. In this way, the target three-dimensional model meeting the design intention of the user can be quickly and accurately retrieved according to the part of the sketch of the model drawn by the user, so that the design efficiency and the user experience are significantly improved.

The embodiment of the invention discloses a question and answer processing method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining a user question input by a user, determining at least two target large models from a candidate large model set, and carrying out the collaborative reply processing of the user question through employing the target large models, and obtaining and displaying a reply result.

The invention provides a large model routing method and device combined with a reward model, and relates to the technical field of artificial intelligence model dynamic routing, and the method comprises the steps: obtaining a question inputted by a user, and determining a candidate model set according to the user authority and a preset priority rule; performing sensitive information judgment on the question through a sensitive detection model, directly returning a preset answer if sensitive information is detected, and otherwise, entering the next step; carrying out reward evaluation on each model in the candidate model set based on a routing function, training the routing function through a knowledge distillation technology, and optimizing a model selection strategy by taking KL divergence as a loss function; and according to an evaluation result of the routing function, dynamically distributing the problem to a target model with the highest reward value for reasoning, and outputting a processing result of the target model. According to the method, the calculation overhead of large model integration can be effectively reduced, the intelligent level of routing decision is improved, and the system resource utilization rate and the response efficiency are remarkably improved.

The invention relates to the field of classification and grading of enterprise data management, in particular to a metadata tag identification method based on multi-Embedding model integration, which comprises the following steps: selecting a plurality of pre-training Embedding models; pre-calculating all label name vector representations in the label library, and constructing a label vector library; receiving database table field metadata to be classified and graded; respectively calculating the cosine similarity of the input metadata and the tag library vector; dynamically adjusting the weight of each model based on a feedback learning mechanism; the weight of the model is updated, after T times of feedback, the weight increment of each model is accumulated, and it is ensured that the sum of the weights of all the models is 1 through a normalization function. By integrating a plurality of pre-training Embedding models, the problem of limitation of a single model in the aspect of field generalization is solved. The weight of the model is dynamically adjusted through a feedback learning mechanism, so that simple judgment of'non-black, namely white 'in a traditional method is avoided, and the accuracy of classification and grading is improved. Meanwhile, the model with higher performance can be replaced at any time, and the expansibility is high.

The application discloses a malicious code model detection method and device and a computer readable medium. Local models generated by respective local model training of each edge side device are obtained to obtain a local model set. Similarities between a single local model in the local model set and other local models except the single local model are determined to obtain a similarity set corresponding to each single local model. According to the similarity set corresponding to each single local model, a local model with a similarity satisfying a preset condition is determined from the local model set as a malicious code model. The application solves the risk diffusion problem caused by the malicious code model by calculating the similarities between the local models and detecting the local model with the similarity satisfying the preset condition as the malicious code model.

The present disclosure provides techniques and solutions for benchmarking process models by evaluating characteristics of the model, such as those reflecting model complexity. Metrics can include the number of elements in a model, the number of roles, and the number of handoffs between roles, as a few examples. Metrics for a model can be compared with reference metrics, such as those calculated from a set of other models, which can be for the same modeled process or different processes. Collections of process models can be evaluated in a similar manner, including for a set of related models that may be expressed at different levels of specificity. Metrics for individual models in the collection can be evaluated and aggregated, and then compared with aggregated metric values of other model collections, for the same or different modeled processes.

The invention relates to methods for predicting at least one target parameter (9, 10) of a vehicle, comprising the steps: S1: Defining a prediction task; S2: Selecting at least one model (11) from a set of given models (11) based on the prediction task; S3: Specifying at least one model input parameter (12); S4: Determining at least one prediction parameter (13) using the at least one selected model (11) based on the at least one given model input parameter (12); and S5: Prediction of at least one target parameter (9, 10) by iteratively updating at least one prediction parameter (13). Furthermore, the invention relates to a computer program product and a vehicle.

The invention relates to a model determination method and apparatus, and an electronic device. The method comprises the steps of determining a bandwidth parameter of a deployment node where a model in a first model set is located; wherein the model guides to generate a query result based on the prompt information; in response to a user query request, inputting a query text corresponding to the user query request into the routing model to obtain a prediction accuracy rate and a prediction cost of the model for the user query request; and determining a target model for processing the user query request from the first model set based on the bandwidth parameter, the prediction accuracy and the prediction cost.

The present application relates to the field of shell-and-tube heat exchanger, in particular to a kind of multi-physical field coupling performance comprehensive simulation evaluation system of shell-and-tube heat exchanger, system includes: analytical modeling module;For integrating obtaining semantic parameterization geometric information library;Flow field geometric model repair and parameterization construction module;For completing the topological reconstruction of initial flow field geometric model and obtaining zero defect parameterization three-dimensional flow field model;Cross-domain grid collaborative generation module;For integrating forming cross-grid model set;Multi-physical field simulation solving and evaluation module;For forming multi-physical field simulation original data set, simulation evaluation is carried out.The present application will flow field geometric model repair and parameterization construction module be converted into three-dimensional voxel grid by voxelization discrete to model, avoid model geometric feature distortion by fairing processing etc., solve the problem that traditional model repair means is single, topological distortion, defect identification is not accurate, guarantee the geometric accuracy of subsequent simulation calculation from source.

The disclosure provides a three-dimensional model retrieval method and system based on single-image cross-modal fusion, which relates to the technical field of three-dimensional model retrieval, comprising: acquiring a to-be-queried image and a multi-view three-dimensional model set; inputting the to-be-queried image and the multi-view three-dimensional model set rendered into a trained single-image cross-modal fusion network to output a corresponding three-dimensional model retrieved; the single-image cross-modal fusion network introduces a data exchange process, gives image domain data to an additional channel of a three-dimensional model domain with a set probability, gives model domain data to an additional channel of an image domain with a set probability, and inputs the image domain network and the three-dimensional model domain network after domain feature alignment respectively into a cross-modal network, fuses information of different modalities, and uses a contrast learning to solve the problem of mining of difficult negative samples of triple loss.

Feature importance is critical to understanding how predictive models produce accurate results, and can change significantly for different models. The present invention is used to achieve a good ranking for stable feature importance. An optimized technique is presented which considers feature importance value variation within different groups of cross-trained models. Feature importance is computed for all group models with this optimized method, and then a best set of models can be selected based on classification error as well as optimized stable feature importance values.

The invention discloses a quick retrieval method and device for a three-dimensional model and a medium, and relates to the technical field of computers. The method comprises the following steps: in response to a received partial two-dimensional sketch of a three-dimensional model drawn by a user, carrying out image segmentation on the partial two-dimensional sketch to obtain a plurality of sub-images; performing mapping processing on each sub-image to obtain an initial feature corresponding to each sub-image, and performing attention calculation on the initial features corresponding to the plurality of sub-images to obtain a plurality of first key features; fusing the plurality of first key features to obtain a second key feature corresponding to a part of the two-dimensional sketch; and based on the second key feature, performing similarity matching on the feature database to obtain a plurality of target features, and searching a three-dimensional model set corresponding to the plurality of target features from the three-dimensional model database. Therefore, the target three-dimensional model conforming to the design intention of the user can be quickly and accurately retrieved according to the model part sketch drawn by the user, so that the design efficiency and the user experience are remarkably improved.

The application discloses an interface-based passenger cabin simulation analysis auxiliary method and tool based on StarCCM+, and the method comprises the following steps: in response to user operation on a user operation interface, the following tasks are performed: reading the user operation interface, determining the input settings of the user for parameters of the user operation interface; calling a model setting module macro file, generating a model setting module macro file with parameters based on simulation analysis functions, model files and calculation parameters; calling StarCCM+ software to run the model setting module macro file with parameters, automatically generating a post-simulation calculation model; calling a model post-processing module macro file, generating a model post-processing module macro file with parameters based on a post-processing auxiliary file; running the model post-processing module macro file with parameters, automatically generating a post-processing output file based on the post-simulation calculation model; and running a report generation program, automatically generating a simulation analysis report based on the post-processing output file. The application can improve the simulation analysis efficiency.

The embodiment of the invention provides a beam tracking method and device, equipment, a medium and a program product. The invention belongs to the technical field of computers. The method comprises the following steps: detecting equipment type information of a tracking object, obtaining motion characteristic parameters, and matching a target model set comprising at least two motion models based on an equipment type; obtaining a model weight and a migration probability at a previous moment, determining a corresponding parameter at a current moment, and adaptively updating the migration probability; when a weight dynamic updating condition is met, the model weight is updated, and computing resources are distributed according to a preset layering strategy; and calculating and predicting the three-dimensional position of the tracked object through multi-model fusion so as to adjust beam parameters for tracking. According to the technical scheme, the method can be adapted to complex motion states of multiple types of targets, the resource utilization rate is optimized and calculated while the beam tracking precision and the real-time performance are guaranteed, and the beam tracking accuracy of a communication and sensing integrated system is effectively improved.

This invention discloses a high-precision ship energy consumption prediction system based on multi-model fusion. It includes a data collection and analysis module for collecting and processing ship energy efficiency data and meteorological data, and performing feature selection on the data using a feature selection method; a single-model algorithm ship energy consumption prediction module for constructing and testing different types of ship energy consumption prediction models, and selecting high-performing models based on the test results to form a ship energy consumption prediction model set; a multi-model fusion ship energy consumption prediction module for fusing the basic models in the ship energy consumption prediction model set using a stacking model fusion method, and optimizing the fused model using Bayesian optimization and adaptive algorithms, and predicting ship energy consumption based on the optimized fused model; and a human-computer interaction module for displaying the analysis, processing, operation process, and analysis results of other modules. This invention constructs a stacking-based ship energy consumption prediction fusion model, improving the prediction accuracy of the ship energy consumption prediction fusion model.