39 results about "Group model" patented technology

A federated learning method is provided, applied to the field of artificial intelligence technologies. According to the method, when obtaining models of different network structures, an aggregation node groups models of a same network structure into a same group, and performs parameter aggregation on models in a same group, to obtain a plurality of aggregation models of different network structures. In addition, for each aggregation model, knowledge distillation training is performed on each aggregation model based on the plurality of originally obtained models, to implement experience transfer between the models of different network structures, so as to integrate knowledge and experience of models of various network structures, combine advantages of parameter aggregation and knowledge distillation in integrating model experience, implement aggregation of the models of different network structures, and ensure prediction precision of a model obtained through aggregation.

Embodiments of the present application provide a model construction system, method, electronic device and storage medium. A model grouping unit is configured to, in response to a model selection instruction for a model database, obtain a main model and a plurality of candidate models corresponding to the main model, combine the main model with each candidate model to obtain at least two model groups, a feature grouping unit is configured to obtain a first model attribute and a first model feature of the main model in each model group, a second model attribute and a second model feature of the candidate model, and group the first model feature and the second model feature according to the first model attribute and the second model attribute to obtain a corresponding feature set, the feature set including a first feature set and a second feature set, and a model construction unit is configured to fuse the first feature set and the second feature set corresponding to each model group to obtain a fused model corresponding to each model group.

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 provides a load group combination regulation capability credibility evaluation method. The method comprises the steps of obtaining multi-dimensional operation data of a user group; the multi-dimensional operation data are analyzed, a load group high-precision model is constructed based on an analysis result, and the load group high-precision model is used for representing dynamic response characteristics of a load group in different scenes; utilizing the load group high-precision model to predict and obtain multi-dimensional load dynamic response characteristics of the user group; and evaluating the overall regulation capability credibility of the load group based on the load dynamic response characteristics, the load declaration value and the actual value to obtain an evaluation result. According to the invention, the comprehensiveness and accuracy of the evaluation result can be improved, and a basis is provided for fine scheduling and decision making of a power grid.

The application discloses a learning resource recommendation method and system based on project field knowledge and user comments, and the method comprises the following steps: collecting learner information, learning resource characteristic information and teacher information, wherein the learner information comprises learner description information and learner interaction information with the learning resource, and the learning resource characteristic information comprises learning resource description information and learning resource characteristic information; finding a teacher with the highest similarity to the learner according to the learner information, and obtaining a matching score of a target learning resource according to the teacher characteristics through a convolutional neural network; establishing a learner short-term preference model and a long-term preference model, and fusing the two models to obtain a learner personal preference model; establishing a learner group preference model, and fusing the learner personal and group models to obtain a learner preference model; and establishing a learning resource characteristic information model and a field knowledge model by using various information characteristics of the learning resource according to the learning resource characteristic information, so that the accuracy of learning resource recommendation is improved.

The invention provides a wind power and photovoltaic field group resource scheduling optimization method and system, and relates to the technical field of energy scheduling, and the method comprises the steps: constructing a three-dimensional field group model according to a collected equipment set which is a set of all equipment in a wind power and photovoltaic field group; based on the three-dimensional field group model, calling a predetermined clustering strategy to perform clustering analysis on the equipment set to obtain a clustering result; a first node index of first equipment is analyzed, a first initial cluster center is determined, and the first equipment refers to any equipment in a first cluster in the clustering result; performing collaborative analysis on the first resource scheduling record of the first initial cluster center to obtain first prediction information; and carrying out resource scheduling optimization on the wind power and photovoltaic field group based on the first prediction information. According to the invention, the technical problem that the scheduling strategy cannot be adaptively adjusted according to the actual scene in the prior art can be solved, and the technical effect of improving the adaptability of new energy scheduling is achieved.

The application discloses a fusion large model intelligent teaching quality evaluation improvement system and relates to the technical field of wisdom education.The application realizes automatic identification of skill response behavior by means of a disturbance group modeling module and a behavior characteristic difference set of students between original questions and candidate comparison questions.System no longer depends on subjective judgment of teachers, but analyzes answer stability of students when facing semantically equivalent and structurally stable questions through quantitative index.When it is detected that the behavior path of students deviates by a high amplitude, the system can immediately determine that there are skill dependence and concept misplacement problems.For example, after answering the disturbance question, the correct rate of the answer decreases, which indicates that there is a strategic answer instead of concept reasoning, and the objectivity and traceability of the teaching quality evaluation are further improved through the knowledge graph of the original question stem.

In some implementations, a model system may receive an indication of the set of models that are associated with a set of data points. Each model in the set of models may have been selected using a grid search. The model system may receive, from a user device, a query associated with a selected data point in the set of data points. The selected data point may be associated with a corresponding model in the set of models. The model system may provide information included in the query to the corresponding model in order to receive a result associated with the selected data point. The model system may transmit, to the user device, the result in response to the query.

Provided are a method and apparatus for managing an object, a device, and a medium. The method comprises: respectively acquiring a plurality of responses of a plurality of objects for a media item, wherein the media item comprises a question, and the plurality of responses are respectively encrypted responses of the plurality of objects for the question; determining at least one response type of the plurality of responses; on the basis of the question and the at least one response type of the plurality of responses, dividing the plurality of objects into at least one group, wherein a group among the at least one group corresponds to a response type among the at least one response type; and on the basis of related data of the objects in the at least one group, determining a sample data set used for updating an object grouping model. In this way, users can be divided into groups without knowing specific information in a user response. Furthermore, related data of users in each group can be used for determining a machine learning model, thereby achieving a desired purpose.

The application discloses a momentum-based hierarchical compromise model federated learning method, comprising the following steps: according to the group model and the global model issued by the corresponding edge node, updating the local momentum, the group momentum and the global momentum in the local device, obtaining the first local momentum, the first group momentum and the first global momentum, and training the local model according to the first local momentum; according to the first group momentum and the first global momentum, aggregating the second group momentum and the second global momentum in the edge node, training the group model according to the second group momentum, and aggregating the third global momentum in the center server according to the second global momentum, training the global model according to the third global momentum, and ending the iteration until the global model obtained in the latest iteration is determined to be converged. The application can improve the learning efficiency of the federated learning method.

This invention discloses an EEG emotion recognition method based on hybrid experts and multi-scale spatiotemporal convolution, specifically relating to the field of emotion recognition technology. The method includes the following steps: Step 1: EEG signal preprocessing, acquiring raw EEG signals, and sequentially performing filtering, artifact removal, resampling, and slicing operations. This invention uses a hybrid expert architecture as its core, combined with a multi-scale spatiotemporal convolutional network to construct an EEG emotion recognition scheme. Through group modeling with a "global leader + group experts," it balances individual difference adaptation with feature extraction completeness, improving robustness across scenarios and achieving accurate and efficient recognition of EEG emotions across subjects. Simultaneously, it considers the model's lightweight nature and real-time performance. This invention can effectively analyze data on the transformation states and probabilistic characteristics of traditional Chinese medicine constitution, facilitating understanding of these transformation states and their probabilistic characteristics. Practical application results are good.

The application provides a pyramid knowledge distillation framework model compression limit analysis method, comprising the following steps: constructing N groups of online deep mutual learning models in a pyramid structure; performing online deep mutual learning on each group of online deep mutual learning models, and recording the parameter quantity and model performance of two models in each group of online deep mutual learning models; wherein, starting from the second group of online deep mutual learning models from bottom to top, while performing online deep mutual learning, the previous group of online deep mutual learning models is accepted for offline knowledge distillation; the potential representation of all models from the first group to the N-1th group is extracted and sent to an adapter to generate teacher importance weight soft labels; the Nth group of online deep mutual learning models is subjected to online deep mutual learning, and the parameter quantity and model performance of the Nth group of models are recorded; and the balance point of the model compression ratio and accuracy is analyzed according to the parameter quantity and model performance of two models in each group of online deep mutual learning models and the parameter quantity and model performance of the Nth group of models.

The invention discloses a packaging box group support optimization method and system based on nonlinear programming, and relates to the technical field of optimization, and the method comprises the steps: obtaining the real-time environment humidity data of a box body and the real-time weight data of the box body; according to the real-time environment humidity data and the real-time weight data, real-time moisture content data corresponding to the box body is obtained through calculation; calling a preset material mechanical property database, performing mapping matching according to the real-time water content data, and extracting corresponding dynamic pressure-bearing threshold data and dynamic friction coefficient data; constructing a nonlinear programming group support model, setting dynamic pressure-bearing threshold data as a stress constraint boundary stacked in the vertical direction, and setting dynamic friction coefficient data as an anti-slip constraint boundary arranged in the horizontal direction; solving and generating grouping scheme data by using a nonlinear programming grouping model on the premise of satisfying a stress constraint boundary and an anti-slip constraint boundary; and outputting the grouping scheme data to an execution terminal.

The invention discloses a discrete agent-based load group modeling and consistency regulation and control method and system, and the method comprises the steps: building a discrete time load group model based on a load group, and enabling the discrete time load group model to comprise a leader and a plurality of followers; determining a system matrix including an adjacent matrix and a leader connection matrix; dividing the followers by using competition relationship representation; obtaining a low-gain state feedback matrix; setting the maximum response time of regulation and control; in the regulation and control process, a complete intermittent control protocol and a partial intermittent control protocol are generated; respectively calculating control tracks of followers under different control protocols and corresponding saturation constraint values; calculating a consistency error between the system states of the leader and the follower at the regulation and control time k; and judging whether the regulation process is ended or not according to the consistency error. According to the method, control paradigm innovation, heterogeneous system compatibility, time-varying demand adaptation, communication overhead optimization, stable performance guarantee and system self-evolution can be realized, and the flexibility, high efficiency and engineering practicability of power load regulation and control are remarkably improved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a semi-asynchronous federal learning method and device based on poisoning attack defense and a storage medium, and the method comprises the steps: in any training round, a server receives a first preset number of local models arriving at first; grouping the local models based on the old degrees of the local models; screening out candidate local models from the local models in each group, and carrying out intra-group model aggregation to obtain a group representative model corresponding to each group; determining an equivalent local gradient of each group of representative models based on each group of representative models, a global model obtained in the previous training round and an equivalent global gradient of the global model, estimating the equivalent global gradient of the training round, determining candidate group representative models and inter-group aggregation weights of the candidate group representative models based on the equivalent local gradient, and executing inter-group aggregation to obtain a candidate group representative model; and determining a global model obtained in the training round, thereby realizing the poisoning attack defense of semi-asynchronous federal learning.

The application relates to the technical field of data processing, in particular to a building group model simulation construction method based on GIS+BIM, which comprises the following steps: according to the moving matching condition between the coincident part and the difference part of the point cloud data between every two monomer buildings, and in combination with the point cloud distribution of the difference part, the comprehensive effectiveness between every two monomer buildings is obtained; the monomer buildings are divided by using the comprehensive effectiveness to obtain each basic building group; according to the distance distribution between the point cloud data of the difference part between every two monomer buildings in the basic building group, the structural degree of the point cloud data of the difference part is analyzed to obtain the basic necessity; the basic building group is divided into each building group; according to each building group in each basic building group, a modeling scheme of a shared basic BIM model is formulated, and GIS is combined to simulate the building group model. The application guarantees the accuracy of model construction and the efficiency of model construction.

The application discloses an adaptive intrusion detection method for an industrial internet, comprising the following steps: step S1: deploying an open set model on a global server and delivering parameters; step S2: training on a local data set by a client; step S3: uploading unknown features by the client, and performing cluster analysis on the unknown features by the global server to generate pseudo labels and corresponding initial class centers; step S4: performing rapid adaptive training based on a meta-learning mechanism by the client to obtain updated client local model parameters; step S5: aggregating group models by an edge server, and generating an updated model by the global server; step S6: iterating until convergence; and step S7: deploying the global model to perform real-time intrusion detection. The application can effectively perceive and adapt to learning new threats, protect data privacy in a distributed environment, break through the limitations of traditional models in a dynamic open environment, and improve the overall security and adaptability of the industrial internet system.

The application discloses a positioning method and device for a target group and a medium, and is suitable for the technical field of data processing. By calling A / B experiments of an experimental group model and a control group model, the experimental group model and the control group model are respectively based on target function triggering users and target function non-triggering users to determine corresponding experimental group probabilities and control group probabilities, and then according to the experimental group probabilities and the control group probabilities, probability values corresponding to respective current users are determined, and current users corresponding to probability values meeting preset conditions are selected from the probability values to realize positioning of the target group. The experimental group model and the control group model based on the division of target function triggering and non-triggering can clearly determine that the positioning of the current target group is based on the target function, the target group positioned based on the target function is more accurate, and resource allocation is performed on the target group determined based on the target function to save resources.

Systems and methods for artificial intelligence (AI) / machine learning (ML) model group validation are discussed herein. A user equipment (UE) receives, from an AI / ML model group management server, an indication that a first AI / ML model is approved for use, and performs a corresponding inference using a group of AI / ML models that includes the first AI / ML model. An AI / ML mode group management server receives, from an AI / ML model network function, a request to approve a first AI / ML model for use, performs first group testing of a group of AI / ML models comprising the first AI / ML model and one or more additional AI / ML models, and sends a corresponding response. An AI / ML model network function sends, to an AI / ML model group management server, a request to approve an AI / ML model for use, the request comprising the AI / ML model, and receives a response to the request that indicates that the AI / ML model is approved for use.

The invention discloses an iterative upgrading method and device for a labeling model, and relates to the technical field of model iterative upgrading. The method comprises the following steps: acquiring multiple groups of model annotation data obtained by annotating to-be-annotated data by an annotation model in multiple annotation correction time periods; determining candidate annotation types corresponding to the to-be-corrected annotation data in each group of model annotation data; according to the candidate annotation types, annotating and revising to-be-corrected annotation data in each group of model annotation data to obtain multiple groups of reference model annotation data, and according to each group of reference model annotation data, training an annotation model to obtain multiple reference annotation models; on the basis of upgrading confirmation operation corresponding to model updating, a reference labeling model corresponding to the upgrading confirmation operation is replaced with a labeling model to be deployed to a production line, and the problems that an existing model iteration upgrading method is lack of automatic closed loop and the accuracy of an iteration model is low are solved; the automatic closed loop of model iteration upgrading is realized, and the model accuracy is improved.

This invention proposes a design method for transient strongly nonlinear scaled-down model tests based on multiple sets of identical scales, belonging to the technical field of transient strongly nonlinear scaled-down model tests. It solves the problems of insufficient accuracy, high extrapolation risk, and weak theoretical support in existing similarity transformation frameworks. The method includes: establishing a similarity transformation equation between model tests and prototype tests based on scaling theory; designing and conducting multiple sets of identical-scale scaled-down model tests for stiffened cylindrical shell structures to obtain dynamic response data; fitting the uncertainty control index and scaling factor based on the multiple sets of model test data; and using the aforementioned similarity transformation equation to transform the model test results to the prototype test results, achieving similarity transformation of transient strongly nonlinear processes. It is mainly used in the field of predicting the uncertainty response of structural systems during transient strongly nonlinear processes.

The present application relates to a kind of unmanned cluster intelligence cooperative behavior modeling method based on riemannian manifold, group manifold and environment manifold are established;Riemannian metric functional on synthetic manifold is constructed, and the equation group that its variation obtains the riemannian metric of synthetic manifold satisfies, realize measurement fusion and generate synthetic manifold;Continuous group model is converted into discrete group model;Optimization solution is carried out to path manifold, and discrete group model is converted into individual motion model.For the intelligent cooperative path planning scene of unmanned cluster in complex local obstacle environment, time-varying riemannian manifold model is established to solve for each individual of cluster, solve the technical problems such as depending on specific central processing unit, depending on large range of environmental information, easily falling into local optimum in the obstacle avoidance path planning of unmanned cluster, realize the decentralized intelligent cooperative optimal motion path planning of unmanned cluster in local obstacle environment, to guide the actual cooperative obstacle avoidance flight trajectory of unmanned cluster.

The application provides a privacy protection-based longitudinal federated joint inference method and system and a storage medium. The method comprises the following steps: a terminal initiates local inference based on a local target feature dataset and inference model parameters to generate intermediate results; the closest classification cluster is determined as a competitive cluster, similarity metrics are calculated and cluster indexes are disclosed; the similarity metrics and the intermediate results are processed through secret sharing to generate share information and exchange with other terminals; the share information is aggregated according to the disclosed cluster indexes to reconstruct the complete similarity metrics and inference output of each group of models on the corresponding cluster; the inference ability score is weighted and fused by using the similarity metrics to obtain an evaluation value, and the evaluation value is mapped to a model output weight through a nonlinear amplification function; finally, the outputs of each group of models are weighted and summed according to the weight to obtain the overall inference result. The application can improve the inference efficiency of the longitudinal federated model under the secret sharing mechanism.

The application provides a personalized federated learning method and system based on adaptive clustering layering, comprising: performing weighted average processing on the gradients of all clients of a parameter server, adjusting global model parameters by using the calculated average gradient; calculating the similarity between clients according to the gradients uploaded by all clients in the last round, clustering and grouping all clients according to the calculation result, and generating an in-group personalized weight vector; the parameter server sends the latest global model parameters to all group servers, and the group servers iteratively perform in-group personalized federated learning training to upload the obtained latest in-group model parameters to the parameter server; and the parameter server performs weighted average aggregation on the latest in-group model parameters sent by all client groups received to obtain a new global model. The application achieves the technical effect of greatly improving the personalized performance of the client local model without impairing the global generalization capability.

The invention discloses a multi-agent dynamic defense game method and system based on federal reinforcement learning, and relates to the technical field of information security. The method comprises the following steps: modeling a distributed network defense scene into a multi-agent-based partially observable Markov environment, defining a seven-tuple environment model comprising an agent set, a global state space, a local observation space, an action space, a state transfer function, an observation function and a reward function, and designing a layered mixed reward function; and constructing a hierarchical collaborative defense architecture based on federal reinforcement learning, and executing a closed-loop online dynamic defense process based on the defense architecture. Distributed training and real-time decision are executed through the local agent layer, intra-group model encryption aggregation is performed through the edge layer, and global meta-strategy generation and dynamic role allocation are completed through the central layer. According to the architecture, communication overhead is reduced, single-point failure is avoided, original data privacy of each node is effectively protected, and efficient adaptive strategy learning and dynamic game collaboration can be realized.

The application provides a model material optimization method and system for comprehensive quantitative evaluation of strength and deformation indexes, and the method comprises the following steps: obtaining two types of samples and performing uniaxial compression experiments on the two types of samples, the model material samples comprising multiple groups of model material samples; obtaining a strength response deviation of the model material samples based on uniaxial compression test results of the two types of samples and similarity theory; obtaining stress-strain curves of corresponding samples based on the uniaxial compression test results of the two types of samples, and then determining multiple characteristic points, the characteristic points comprising a peak stress point and multiple deformation characteristic points; obtaining a deformation index deviation of the model material samples based on the compressive strength of each characteristic point and the slope of a linear fitting curve between any two characteristic points by using the compressive strength of each characteristic point; obtaining a comprehensive deviation of each group of model material samples based on the strength response deviation and the deformation index deviation, and selecting a group of model material samples corresponding to the minimum comprehensive deviation as optimal model material for building a physical similar model.

A computer-implemented method includes receiving data and while using a process that promotes exploration during training, training a new set of model parameters using the received data. The new set of model parameters is used to form a collection of sets of model parameters. Data is separately applied to each set of model parameters in the collection to identify sets of model parameters that perform similarly on the set of data. The sets of model parameters that perform similarly on the data are grouped together in a group of sets of model parameters and test data is applied to groups of sets of model parameters to obtain an uncertainty measure for each group. A group with the lowest uncertainty measure is selected and outputs produced by the sets of model parameters in the selected group are used to generate an output value for the test data.

A method of using a pre-configured AI / ML (artificial intelligence / machine learning)-based group model ID assignment in a wireless mobile communication system including a base station (e.g., gNB) and a mobile station (e.g., UE). If the AI / ML model is applied to the radio access network, the signaling of the model ID information exchange may be severely congested based on different model execution environments with different models. Thus, a model operation may be established between the network and the UE by assigning the group model ID.

The invention discloses a machine learning model recommendation method and device based on user requirements. The method comprises the following steps: receiving a use scene, training data and service requirements of a machine learning model input by a user; querying a model scene knowledge graph based on the use scene to obtain at least one machine learning model corresponding to the use scene; screening a target machine learning model from the at least one machine learning model according to the characteristics and business requirements of the training data; according to the characteristics of the training data and the classification of the target machine learning model, generating multiple groups of model parameter combinations for the target machine learning model, and displaying the model parameter combinations to a user; receiving a model parameter combination selected by the user from the multiple groups of model parameter combinations; and based on the training data and the selected model parameter combination, obtaining a trained target machine learning model for the target machine learning model. According to the invention, the machine learning model meeting the user demand can be efficiently generated for the user.

The invention discloses a carrier-based aircraft take-off performance evaluation method and system based on digital twin enabling, belongs to the technical field of performance evaluation, and aims to solve the problems that a traditional method is insufficient in full-working-condition coverage, low in multi-parameter coupling evaluation precision and poor in real-time performance. The core process of the method comprises the following steps: constructing an influence parameter space containing conventional and extreme working conditions, and generating a sampling parameter group through layered guided sampling; collecting data and constructing a health monitoring data set by relying on the simulation platform; the measuring point parameters are converted into mechanism parameters through a mechanism model of the engine core component; clustering and dividing typical clustering groups, dynamically matching weights, training a time sequence deep learning network, and constructing a clustering type reference performance digital twin model library; and during actual takeoff, a target cluster group model is matched to generate a predicted value, and performance grading is completed through residual analysis and multi-dimensional index calculation. According to the method, high-precision and real-time evaluation of the take-off performance of the shipboard aircraft under all working conditions is realized, and the evaluation suitability and the decision support reliability are remarkably improved.